RoboCup 2001 Publications

From RoboCup Wiki
Jump to: navigation, search
Author Title Year Journal/Proceedings Reftype DOI/URL
Adorni, G., Bolognini, L., Cagnoni, S. & Mordonini, M.

Stereo Obstacle Detection Method for a Hybrid Omni-Directional/Pin-Hole Vision System


2002 RoboCup 2001: Robot Soccer World Cup V, pp. 113-144 inproceedings

DOI URL

Abstract: This paper describes an application of a vision system based on the use of both an omnidirectional vision sensor and a standard CCD camera. Such a hybrid sensor permits implementation of peripheral/foveal vision strategies, that can be very useful for navigation tasks. This paper focuses particularly on the use of the device as a stereo vision system to locate obstacles in a semi-structured environment through a perspective removal algorithm.
Akín, H.L., Topalov, A. & Kaynak, O.

Cerberus 2001 Team Description


2002 RoboCup 2001: Robot Soccer World Cup V, pp. 689-692 inproceedings

DOI URL

Abstract: Cerberus is one of the four new teams in the RoboCup Tournament, Legged Robot Category. The team is a joint effort of Boğaziçi University (Turkey) and Technical University of Sofia, Branch Plovdiv (Bulgaria). We have divided the robot software design into six major tasks, and worked on those tasks in parallel. The tasks were locomotion, localization, vision, behavior control, learning and communication. With limited time in our hands, our aims were a clear object oriented design, readable behavior architecture, and maximum code reuse.
Arai, T., Fukase, T., Ueda, R., Kobayashi, Y. & Kawabe, T.

The Team Description of ARAIBO


2002 RoboCup 2001: Robot Soccer World Cup V, pp. 77-123 inproceedings

DOI URL

Abstract: This paper describes a localization method and a navigation method for Sony Legged Robot League. They solve the problems caused by the robot’s limited abilities (CPU power, sensor ability, control ability). These methods are implemented in the soccer program for the RoboCup 2001.
Arnold, A., Flentge, F., Schneider, C., Schwandtner, G., Uthmann, T. & Wache, M.

Team Description Mainz Rolling Brains 2001


2002 RoboCup 2001: Robot Soccer World Cup V, pp. 201-224 inproceedings

DOI URL

Abstract: The Mainz Rolling Brains 2001 team is based on our last year’s team. Our modular design as described in [1] has proved to be efficient and flexible. Thus the team could easily be adopted to the soccerserver’s new features and some of the weak spots of our team could be eliminated.
Azari, D., Burns, J., Deshmukh, K., Fox, D., Grimes, D., Kwok, C., Pitkanen, R., Shon, A. & Tressel, P.

Team Description: UW Huskies-01


2002 RoboCup 2001: Robot Soccer World Cup V, pp. 11-30 inproceedings

DOI URL

Abstract: This paper provides an overview of the robot control system of the UW Huskies, our entry in the RoboCup-2001 Sony AIBO legged robot league. Our development team consisted of one faculty member (D. Fox, team leader), one technical support staff (R. Pitkanen), one undergraduate student (J.K. Burns), and six graduate students. Since this was our first participation in RoboCup, we relied on the implementation of well-established techniques for robot control. These techniques include a layered control system, particle filters for robot localization, and efficient computer vision techniques for object recognition.
Bach, J. & Gollin, M.

Self-Localisation Revisited


2002 RoboCup 2001: Robot Soccer World Cup V, pp. 251-256 inproceedings

DOI URL

Abstract: We discuss different approaches of self-localisation in the Simulation League. We found that the properties of the soccer server’s quantization function tend to produce artifacts with the common approaches, which we try to deal with using a new method: We simulate the player’s position, and dynamically correct this estimate with a gradient descent function by the minimal amount necessary to make it consistent with the perceived flag positions (where we allow for error margins according to the quantization function). It can be shown that self-localisation using the new method is not only relatively exact (between 6.6% and 35% smaller average error than the ’Nearest Flag’ algorithm) but also yields much more consistency than the other approaches....
Baltes, J.

Yue-Fei: Object Orientation and Id Without Additional Markers


2002 RoboCup 2001: Robot Soccer World Cup V, pp. 87-101 inproceedings

DOI URL

Abstract: This paper describes a novel approach to detecting orientation and identity of robots using a global vision system. Instead of additional markers, the shape of the robot is used to determine an orientation using a general Hough transform. In addition the movement history as well as the command history are used to calculate the quadrant of the orientation. The identity of the robot is determined by correlating the motion of the robot with the command history. An empirical evaluation shows that the performance of the new video server is at least as good as that of a traditional approach using additional coloured markers.
Baltes, J.

Efficient Image Processing for Increased Resolution and Color Correctness of CMOS Image Sensors


2002 RoboCup 2001: Robot Soccer World Cup V, pp. 165-171 inproceedings

DOI URL

Abstract: This paper describes fast demosaicing methods to quadruple the resolution of a CMOS camera. The resulting increase in accuracy in camera calibration and object detection is important for local vision robots, especially those that use computer vision as their only source of information about the state of the world. The paper describes two methods for demosaicing: interpolation and variance demosaicing. A comparison of three sample views is shown to demonstrate the increased resolution and the difference between the interpolation and variance demosaicing methods. Both demosaicing methods work well. Variance demosaicing performs better around edges in the image, but is computationally more expensive.
Baltes, J.

4 Stooges


2002 RoboCup 2001: Robot Soccer World Cup V, pp. 1-5 inproceedings

DOI URL

Abstract: The 4 Stooges are a small sized RoboCupteam, which grew out of the All Botz, a team which competed previously at RoboCup-99 and RoboCup-00. One of the main differences is that the 4 Stooges are a team of fully autonomous robots. All sensors, actuators, and power supply (CMOS camera, and battery) as well as all processing is housed on the robot itself.
Baltes, J. & Park, Y.

Comparison of Several Machine Learning Techniques in Pursuit-Evasion Games


2002 RoboCup 2001: Robot Soccer World Cup V, pp. 15-41 inproceedings

DOI URL

Abstract: This paper describes the results of an empirical evaluation comparing the performance of five different algorithms in a pursuit and evasion game. The pursuit and evasion game was played using two robots. The task of the pursuer was to catch the other robot (the evader). The algorithms tested were a random player, the optimal player, a genetic algorithm learner, a k-nearest neighbor learner, and a reinforcement learner. The k-nearest neighbor learner performed best overall, but a closer analysis of the results showed that the genetic algorithm suffered from an exploration-exploitation problem.
Benosman, R., Bras, F., Bach, F., Boulay, S., Cahn, E., Come, S., Cordurié, G., Annick, J.M., Loic, L., Potereau, C., Richard, F., Sath, S., Vasseur, X. & Vincent, P.

ROBOSIX UPMC-CFA: RoboCup Team Description


2002 RoboCup 2001: Robot Soccer World Cup V, pp. 353-390 inproceedings

DOI URL

Abstract: This paper describes the Robosix team of the University Pierre and Marie Curie. The team is composed of five robots built inside the institute based on an omnidirectional motion system associated to a catadioptric sensor developped by the Laboratory of Instruments and System. The team started developping the robots during the year 1999 in prevision to participate to the RoboCup 2001, the team is partially composed by member of the French middle size team that participated to RoboCup98 in Paris. The robots computational system is based on a pc card with a celeron 633Mhz running under a light version of Linux. The localization system relies on an assocation of multiagent panoramic vision system developped inside the LIS lab.
Benosman, R., Douret, J. & Devars, J.

A Simple and Accurate Camera Calibration for the F180 RoboCup League


2002 RoboCup 2001: Robot Soccer World Cup V, pp. 171-189 inproceedings

DOI URL

Abstract: Camera calibration is a very important issue in computer vision each time extracting metrics from images is needed. The F180 camera league offers an interesting problem to solve. Camera calibration is needed to locate robots on the field with a very high precision. This paper presents a method specially created to easely calibrate a camera for the F180 league. The method is easy to use and implement, even for people not familiar with computer vision. It gives very acurate and efficient results.
Bianchi, R.A. & Reali-Costa, A.H.

Implementing Computer Vision Algorithms in Hardware: An FPGA/VHDL-Based Vision System for a Mobile Robot


2002 RoboCup 2001: Robot Soccer World Cup V, pp. 167-220 inproceedings

DOI URL

Abstract: A time critical process in a real-time mobile robot application such as RoboCup is the determination of the robot position in the game field. Aiming at low-cost and efficiency, this paper proposes the use of field-programmable gate array device (FPGA) in the vision system of a robotic team. We describe the translation of well-known computer vision algorithms to VHDL and detail the design of a working prototype that includes image acquisition and processing. The CV algorithms used in the system includes thresholding, edge detection and chain-code segmentation. Finally, we present results showing that an FPGA device provides hardware speed to user applications, delivering real-time speeds for image segmentation at an affordable cost. An efficiency comparison is made among the hardware-implemented and a software-implemented (C language) system using the same algorithms.
Birk, A., Coradeschi, S. & Tadokoro, S.

The Tournament Results of the Different Leagues of RoboCup-2001


2002 RoboCup 2001: Robot Soccer World Cup V, pp. 47-60 inproceedings

DOI URL

Abstract: A complete overview of all results from the RoboCup 2001 tournaments in the different leagues is given here. In most leagues, the competition consisted of two parts. In the first part, teams were placed in groups were they played round robin games. After this, the teams were ranked in their groups. Based on the ranking, a second part with elimination rounds took place to determine the places.
de Boer, R., Kok, J. & Groen, F.

UvA Trilearn 2001 Team Description


2002 RoboCup 2001: Robot Soccer World Cup V, pp. 5-14 inproceedings

DOI URL

Abstract: This paper describes the main features of the UvA Trilearn 2001 soccer simulation team. UvA Trilearn 2001 is a new team that participated for the first time in 2001. It has been built from scratch and does not contain any code copied from other RoboCup teams. Topics that will be discussed include our architecture, world model and synchronisation method. On a higher level we will talk about an optimal scoring policy and about our fast-play strategy which makes use of heterogeneous players. UvA Trilearn 2001 finished 5th in the German Open 2001 and reached 4th place at the RoboCup 2001 World Cup.
Bonarini, A., Invernizzi, G., Marchese, F., Matteucci, M., Restelli, M. & Sorrenti, D.

Fun2Mas: The Milan Robocup Team


2002 RoboCup 2001: Robot Soccer World Cup V, pp. 123-125 inproceedings

DOI URL

Abstract: We present Fun2maS, the Milan Robocup Team. In its implementation we have faced many aspects: hardware (electronics, mechanics), sensors (omnidirectional vision), behaviors (fuzzy behaviors management and composition), multi-agent coordination (strategy and tactics), and adaptation of the team behavior. We could fully exploit the characteristics of all the components thanks to the modular design approach we have adopted. All the modules have also been designed to be used in generic applications, and we have already adopted most of them for surveillance, mapping, guidance, and document delivery tasks.
Bonarini, A., Matteucci, M. & Restelli, M.

A Framework for Robust Sensing in Multi-Agent Systems


2002 RoboCup 2001: Robot Soccer World Cup V, pp. 329-351 inproceedings

DOI URL

Abstract: We present the framework we have adopted to implement robust sensing in the Milan Robocup F-2000 Team. The main issue concerns the definition of symbolic models both for the single agent and for the whole multi-agent system. Information about physical objects is collected by intelligent sensors and anchored to symbolic concepts. These are used both to control the robots through a behavior-based system, and to improve the global knowledge about the environment.
Bras, F., Benosman, R., Anglade, A., Latidine, S., Martino, O., Lagardere, A., Boun, A., Testa, A. & Cordurié, G.

RoboCup 2001 (F180) Team Description: RoboSix UPMC-CFA (France)


2002 RoboCup 2001: Robot Soccer World Cup V, pp. 57-85 inproceedings

DOI URL

Abstract: This paper describes the team RoboSix UPMC-CFA that participated to the German open 2001 and RoboCup 2001 in the F180-league. We will present the mechanical and electrical design of the robots. We will then introduce the vision choices explaining the colometric and geometric calibrations stages. Finally we will explain the implemented behaviour and the path planning associated to it.
Bredenfeld, A., Becanovic, V., Christaller, T., Günther, H., Indiveri, G., Kobialka, H.-U., Plöger, P.-G. & Schöll, P.

GMD-Robots


2002 RoboCup 2001: Robot Soccer World Cup V, pp. 31-57 inproceedings

DOI URL

Abstract: The overall research goal of our RoboCup middle-size league team is to increase both, the controlled speed of mobile robots acting as a team in dynamic environments and the speed of the development process for robot control systems. Therefore, we started in 1998 to develop a proprietary fast robot platform and in parallel the development of an integrated design environment.
Browne, K., McCune, J., Trost, A., Evans, D. & Brogan, D.

Behavior Combination and Swarm Programming


2002 RoboCup 2001: Robot Soccer World Cup V, pp. 85-97 inproceedings

DOI URL

Abstract: The RoboCup Simulator League provides an excellent platform for research on swarm computing. Our research focuses on group behaviors emerge from collections of actors making decisions based on local information. Our RoboCup simulator team is designed around an architecture for experimenting with behavioral primitives defined over groups and mechanisms for combining those behaviors.
Browning, B., Bowling, M., Bruce, J., Balasubramanian, R. & Veloso, M.

CM-Dragons'01 - Vision-Based Motion Tracking and Heteregenous Robots


2002 RoboCup 2001: Robot Soccer World Cup V, pp. 135 inproceedings

DOI URL

Abstract: At Carnegie Mellon, we have developed several small-size robot teams that have helped us to investigate a variety of aspects of the small-size RoboCup competition. The CM-Dragons’01 is our new team complete with new hardware and sensing and behavior-processing algorithms. Although still in the development phase, a number of modules have been developed that we feel can contribute to the RoboCup community. In this paper, we briefly describe our vision and tracking modules, the new robot hardware and our new communications modules. Our primary interest is on presenting our advances in modeling and prediction using an Extended Kalman-Bucy Filter (EKBF) that tracks the ten robots and the ball through vision. We identify that Kalman-Bucy filters are susceptible to white noise caused by misidentifications. Within CM-Dragons’01, we developed a new approach, Improbability Filtering, that addresses this problem in a computationally efficient yet principled manner.
Bruce, J., Lenser, S. & Veloso, M.

Fast Parametric Transitions for Smooth Quadrupedal Motion


2002 RoboCup 2001: Robot Soccer World Cup V, pp. 13-20 inproceedings

DOI URL

Abstract: This paper describes a motion system for a quadruped robot that performs smooth transitions over requested body trajectories. It extends the generality of path based approaches by introducing geometric primitives that guarantee smoothness while decreasing (and in some cases entirely removing) constraints on when and what types of parameter transitions can be made. The overall motion system for the autonomous Sony legged robot that served as our test-bed is also described. This motion system served as a component in our entry in the RoboCup-2000 world robotic soccer championship, in which we placed third, losing only a single game.
This research was sponsored by Grants Nos. DABT63-99-1-0013, F30602-98-2-0135 and F30602-97-2-0250. The information in this publication does not necessarily reflect the position of the funding agencies and no official endorsement should be inferred.
Brunn, R., Düffert, U., Jüngel, M., Laue, T., Lötzsch, M., Petters, S., Risler, M., Röfer, T., Spiess, K. & Sztybryc, A.

GermanTeam 2001


2002 RoboCup 2001: Robot Soccer World Cup V, pp. 215-250 inproceedings

DOI URL

Abstract: The GermanTeam is the successor of the Humboldt Heroes who already participated in the Sony Legged Robot League competitions in 1999 and 2000. Because of the strong interest of other German universities, in March 2001, the GermanTeam was founded. It consists of students and researchers of five universities: Humboldt-Universität zu Berlin, Universität Bremen, Technische Universität Darmstadt, Universität Dortmund, and Freie Universität Berlin. However, for the system presented in this document, the Humbold Heroes only had reinforcements from Bremen and Darmstadt. The two other universities will actively participate with the beginning of the winter semester.
Buck, S., Beetz, M. & Schmitt, T.

Planning and Executing Joint Navigation Tasks in Autonomous Robot Soccer


2002 RoboCup 2001: Robot Soccer World Cup V, pp. 112-122 inproceedings

DOI URL

Abstract: In this paper we propose a hybrid navigation planning and execution system for performing joint navigation tasks in autonomous robot soccer. The proposed system consists of three components: an artificial neural network controller, a library of software tools for planning and plan merging, and a decision module that selects the appropriate planning and execution methods in a situation-specific way. The system learns by experimentation predictive models for the performance of different navigation planning methods. The decision module uses the learned predictive models to select the most promising planning method for the given navigation task.
In extensive experiments using a realistic and accurate robot simulator that has learned the dynamic model of the real robots we show that our navigation system is capable to (1) generate fast and smooth navigation trajectories and (2) outperform the state of the art planning methods.
Buhler, P. & Vidal, J.M.

Biter: A Platform for the Teaching and Research of Multiagent Systems’ Design Using RoboCup


2002 RoboCup 2001: Robot Soccer World Cup V, pp. 209-241 inproceedings

DOI URL

Abstract: We introduce Biter, a platform for the teaching and research of multiagent systems’ design. Biter implements a client for the RoboCup simulator. It provides users with the basic functionality needed to start designing sophisticated RoboCup teams. Some of its features include a world model with absolute coordinates, a graphical debugging tool, a set of utility functions, and a Generic Agent Architecture (GAA) with some basic behaviors such as “dribble ball to goal” and “dash to ball”. The GAA incorporates an elegant object-oriented design meant to handle the type of activities typical for an agent in a multiagent system. These activities include reactive responses, long-term behaviors, and conversations with other agents. We also discuss our initial experiences using Biter as a pedagogical tool for teaching multiagent systems’ design.
Buttinger, S., Diedrich, M., Hennig, L., Hoenemann, A., Huegelmeyer, P., Nie, A., Pegam, A., Rogowski, C., Rollinger, C., Steffens, T. & Teiken, W.

Dirty Dozen Team and Coach Description, The


2002 RoboCup 2001: Robot Soccer World Cup V, pp. 43-52 inproceedings

DOI URL

Abstract: The Dirty Dozen team consists of the player agents and an online coach. The players’ low-level-skills and world-model are based on the publicly available code of the CMU-99 team [1]. The team behavior is specified using a new strategy formalization language (SFL), an extension of the standard coach language. This allows to modify the behavior easily and makes the whole team coachable, even for online coaches developed by different teams. We introduce the main concepts of SFL and one possible system with modules that interprete and run the SFL specifications. We also give an outline of the online coach.
Cai, Y., Chen, J., Yao, J. & Li, S.

Global Planning from Local Eyeshot: An Implementation of Observation-Based Plan Coordination in RoboCup Simulation Games


2002 RoboCup 2001: Robot Soccer World Cup V, pp. 27-70 inproceedings

DOI URL

Abstract: This paper presents a method of implementing distributed planning in partial-observable, low communication bandwidth environments such as RoboCup simulation games, namely, the method of global planning from local perspective. By concentrating planning on comprehending and maximizing global utility, the method solved the problem that individual effort might diverge against team performance even in cooperative agent groups. The homogeny of the agent decision architecture and the internal goal helps to create privities among agents, thus make the method applicable. This paper also introduces the application of this method in the defense system of Tsinghuaolus, the champion of RoboCup 2001 Robot Soccer World Cup Simulation League.
Carpenter, P., Riley, P., Kaminka, G., Veloso, M., Thayer, I. & Wang, R.

ChaMeleons-01 Team Description


2002 RoboCup 2001: Robot Soccer World Cup V, pp. 53-61 inproceedings

DOI URL

Abstract: The following paper describes the ChaMeleons-01 Robocup 2001 simulation league team. Development was concentrated in two main areas: the design and implementation of an action-selection architecture and the development of the online coach. The architecture was designed in such a way to support the integration of advice from an external agent. Currently, the only external agent the ChaMeleons-01 support is an online coach offering advice using the standard coach language. The online coach offers advice in the form of passing rules, marking assignments, and formation information.
Casper, J., Micire, M., Hyams, J. & Murphy, R.

A Case Study of How Mobile Robot Competitions Promote Future Research


2002 RoboCup 2001: Robot Soccer World Cup V, pp. 131-154 inproceedings

DOI URL

Abstract: The purpose of mobile robot competitions is to push the field of research and inspire future work. Our involvement in the Urban Search and Rescue event of the 2000 AAAI Mobile Robot Competition allowed us the opportunity to test our Urban Search and Rescue robot team in a standardized testbed. The result was ideas for future enhancements and research work. This article presents our experience as a case study on how mobile robot competitions promote research.
Castelpietra, C., Guidotti, A., L. Iocchi, D.N. & Rosati, R.

Design and Implementation of Cognitive Soccer Robots


2002 RoboCup 2001: Robot Soccer World Cup V, pp. 101-108 inproceedings

DOI URL

Abstract: One of the major challenges in the design of robots that can act autonomously in unstructured, dynamic and unpredictable environments is the ability to achieve desired goals by executing complex high-level plans, while promptly reacting to unpredicted situations and adjusting the behavior based on new knowledge acquired through the sensors during task execution. Several years of research have focussed on the software architecture by exploiting the sense-plan-act (or deliberative) approach [9], the behavior-based (or reactive) one [1], as well as hybrid architectures [3] which combine advantages of both reactivity and deliberation. However, for an effective application of hybrid approaches a crucial role is played by the organization of information among the layers, which is heavily influenced both by the features of the robotic platform and by the problem at hand.
Chang, M.M., Browning, B. & Wyeth, G.F.

ViperRoos: Developing a Low Cost Local Vision Team for the Small Size League


2002 RoboCup 2001: Robot Soccer World Cup V, pp. 9-42 inproceedings

DOI URL

Abstract: The development of cheap robot platforms with on-board vision remains one of the key challenges that robot builders have yet to surmount. In this paper we describe the prototype development of a low cost (
Chang, M.M. & Wyeth, G.F.

ViperRoos 2001


2002 RoboCup 2001: Robot Soccer World Cup V, pp. 135-163 inproceedings

DOI URL

Abstract: The ViperRoos are a team of three autonomous local vision robots that were developed to play robot soccer. The team participated for the second time at the RoboCup 2001. This paper describes the on-board intelligent and the simulator implemented to aid the team development. The paper concludes with future direction of the ViperRoos.
Chen, S., Siu, M., Vogelgesang, T., Yik, T.F., Hengst, B., Pham, S.B. & Sammut, C.

The UNSW RoboCup 2001 Sony Legged Robot League Team


2002 RoboCup 2001: Robot Soccer World Cup V, pp. 41-70 inproceedings

DOI URL

Abstract: In 2001, the UNSW United team in the Sony legged robot league successfully defended its title. While the main effort in last year’s competition was to develop sound low-level skills, this year’s team focussed primarily on experimenting with new behaviours. An important part of the team’s preparation was playing practice matches in which the behaviour of the robots could be studied under actual game-play conditions. In this paper, we describe the evolution of the software from previous years and the new skills displayed by the robots.
Chitta, S., Sacks, W., Ostrowski, J., Das, A. & Mishra, P.

The University of Pennsylvania RoboCup Legged Soccer Team


2002 RoboCup 2001: Robot Soccer World Cup V, pp. 317-327 inproceedings

DOI URL

Abstract: This paper describes the University of Pennsylvania’s RoboCup 2001 Legged League team, called the UPennalizers. This year’s team was very successful in both the main competition, placing third out of sixteen teams, and the RoboCup Technical Challenges, where we placed second. Much of this success can be credited to our being able to build on a strong foundation, in both software architecture and low-level, fast locomotion, developed last year. We also were one of only two teams to utilize sound communication between robots, which gave a significant advantage in resolving conflicts between team members.
Ciesielski, V., Mawhinney, D. & Wilson, P.

Genetic Programming for Robot Soccer


2002 RoboCup 2001: Robot Soccer World Cup V, pp. 37-55 inproceedings

DOI URL

Abstract: RoboCup is a complex simulated environment in which a team of players must cooperate to overcome their opposition in a game of soccer. This paper describes three experiments in the use of genetic programming to develop teams for RoboCup. The experiments used different combinations of low level and high level functions. The teams generated in experiment 2 were clearly better than the teams in experiment 1, and reached the level of ‘school boy soccer’ where the players follow the ball and try to kick it. The teams generated in experiment 3 were quite good, however they were not as good as the teams evolved in experiment 2. The results suggest that genetic programming could be used to develop viable teams for the competition, however, much more work is needed on the higher level functions, fitness measures and fitness evaluation.
Clarke, K., Dempster, S., Falcao, I., Jones, B., Rudolph, D., Blair, A., McCarthy, C., Walter, D. & Barnes, N.

RoboMutts++


2002 RoboCup 2001: Robot Soccer World Cup V, pp. 713-716 inproceedings

DOI URL

Abstract: The University of Melbourne’s RoboMutts++ team competed in the Sony Legged League at RoboCup for the second consecutive year in 2001. This paper describes the areas of research and development focused on in 2001. The software system developed evolved from the system implemented by the RoboMutts team in 2000. In order to direct development effort effectively, the 2000 system was evaluated and limitations were identified. The areas of development were: motion, system architecture, localisation and behaviours. For motion, a variable parameterised walk, and numerous kicks were developed. The system architecture was remodelled to remove multiple concurrent threads, and to facilitate easy integration of various behaviours. Localisation development included one beacon position determination. A number of attacking behaviours were developed for use in differing scenarios, as well as a defensive goalie behaviour.
Costa, P., Sousa, A., Marques, P., Costa, P., Gaio, S. & Moreira, A.

5dpo Team Description


2002 RoboCup 2001: Robot Soccer World Cup V, pp. 31-78 inproceedings

DOI URL

Abstract: The 5dpo team presented a solid set of innovative solutions. The overall workings of the team are presented. Mechanical and electronic solutions are explained and closed loop working is discussed. Main innovative features include I-R communications link and circular bar code for robot tracking. Low level control now presents a dynamics prediction layer for enhanced motion control. Team strategy is also new and a multi-layered high level reasoning system based on state charts allows for cooperative game play.
Demura, K., Tachi, N., Maekawa, T. & Ueno, T.

KENSEI-Chan: Design of a Humanoid for Running


2002 RoboCup 2001: Robot Soccer World Cup V, pp. 283-315 inproceedings

DOI URL

Abstract: This paper presents the design of the humanoid robot KENSEI-chan for RoboCup Humanoid League. Many humanoids have been developed, but no humanoids have a capability of running. Because running needs huge torque, shock tolerance, and weight reduction. KENSEI-chan was designed with these things. KENSEI-chan is planed to have 12 degrees of freedom (DOFs) in two legs, 4 DOFs in two arms, 2 DOFs in the neck, and 1 DOFs in the trunk. Totally KENSEI-chan has 19 DOFs. 2DOFs in the knees and the ankles are Rotary Elastic Joints, which provide shock tolerance and force control.
Dietl, M., Gutmann, J.-S. & Nebel, B.

CS Freiburg: Global View by Cooperative Sensing


2002 RoboCup 2001: Robot Soccer World Cup V, pp. 21-31 inproceedings

DOI URL

Abstract: Global vision systems as found in the small size league are prohibited in the middle size league. This paper presents methods for creating a global view of the world by cooperative sensing of a team of robots. We develop a multi-object tracking algorithm based on Kalman filtering and a single-object tracking method involving a combination of Kalman filtering and Markov localization for outlier detection. We apply these methods for robots participating in the middle-size league and compare them to a simple averaging method. Results including situations from real competition games are presented.
This work has been partially supported by Deutsche Forschungsgemeinschaft (DFG), by Medien- und Filmgesellschaft Baden- Württemberg mbH (MFG), and by SICK AG.
New address: Sony Corporation, Digital Creatures Laboratory, Tokyo 141-0001, Japan.
Drücker, C., Hübner, S., Visser, U. & Weland, H.-G.

"As Time Goes By" - Using Time Series Based Decision Tree Induction to Analyze the Behaviour of Opponent Players


2002 RoboCup 2001: Robot Soccer World Cup V, pp. 325-330 inproceedings

DOI URL

Abstract: With the more sophisticated abilities of teams within the simulation league, high level online functions become more and more attractive. Last year we proposed an approach to recognize the opponents strategy and developed the online coach accordingly. The coach was able to detect their strategy and then passed this information together with appropriate countermeasures to his team. However, this approach gives only information about the entire team and is not able to detect significant situations (e.g. double pass, standard situations). In this paper we describe a new decision tree induction for continous valued time series, used to analyze the behaviour of opponent players.
Esaki, T., Sakushima, T., Asai, Y. & Ito, N.

Team Description of NITStones 2001


2002 RoboCup 2001: Robot Soccer World Cup V, pp. 1-9 inproceedings

DOI URL

Abstract: In this paper, we describe the feature of the NITStones2001 team participated in the RoboCup 2001 simulation league. In a Multi-Agent System, it is important that an agent cooperate with the others appropriately. We consider the cooperative activity of an agent as action by a group of the agent who aims at achievement of the common goal, and construct the cooperative agent and the dynamic grouping agent model.
Figueras, A., Colomer, J., Fossen, T.I. & de la Rosa, J.L.

Supervision of Robot Control


2002 RoboCup 2001: Robot Soccer World Cup V, pp. 239-289 inproceedings

DOI URL

Abstract: This work shows how to supervise a set of controllers designed by different specification to be applied at requested constrained trajectory for the autonomous mobile robot. In this paper are explained part of the control structure from local controllers to the agent level, the communication between the high supervisor and the local controller are detailed. Several controllers are designed in order to minimize different cost functions. Non-linear behavior of the robot force to work off-line to model all possible controllers, the on-line process concludes the optimal controller to realize a requested task. This work is applied over the soccer robots in the RogiTeam [1].
Frank, I., Tanaka-Ishii, K., Matsubara, H. & Osawa, E.

Walkie-Talkie MIKE


2002 RoboCup 2001: Robot Soccer World Cup V, pp. 191-207 inproceedings

DOI URL

Abstract: We address the problem of information flow in disaster relief scenarios by presenting an architecture for generating natural language dialogues between large numbers of agents. This architecture is the first step towards real-time support systems for relief workers and their controllers. Our work demonstrates how techniques from the Mike commentary system for RoboCup soccer can be carried over to the domain of RoboCup Rescue. Thanks to this background, the initial product of our research is a system that explains a RoboCup Rescue simulation not to the agents in the domain themselves but to a watching audience. This “commentary” is produced by recreating the actual dialogues most likely be occurring in the domain: walkie-talkie conversations.
Fukase, T., Yokoi, M., Kobayashi, Y., Ueda, R., Yuasa, H. & Arai, T.

Quadruped Robot Navigation Considering the Observational Cost


2002 RoboCup 2001: Robot Soccer World Cup V, pp. 251-280 inproceedings

DOI URL

Abstract: In this paper, we present a new method to decide the optimal robot’s motion with a quadruped robot of Sony Legged Robots League. The method keeps the “observational cost” as small as possible. The task we cope with is navigation. The robot can reach the destination rapidly and robustly with this method in spite of under the unfavorable conditions such as restricted sensor ability, limited CPU power, and inaccurate locomotion. Finally the efficiency of our method is verified by experiments.
Gu, D. & Hu, H.

Evolving Fuzzy Logic Controllers for Sony Legged Robots


2002 RoboCup 2001: Robot Soccer World Cup V, pp. 5-11 inproceedings

DOI URL

Abstract: This paper presents an evolutionary approach to learning a fuzzy logic controller(FLC) employed for reactive behaviour control of Sony legged robots. The learning scheme is divided into two stages. The first stage is a structure learning in which the rule base of FLC is generated by a backup updating learning. The second stage is a parameter learning in which the parameters of membership functions of fuzzy sets are learned by a genetic algorithm (GA). Simulation results are provided to show the effectiveness of the proposed learning scheme.
Habibi, J., Nouri, A. & Ahmadi, M.

An Approach to Multi-Agent Communication Used in RobocupRescue


2002 RoboCup 2001: Robot Soccer World Cup V, pp. 295-300 inproceedings

DOI URL

Abstract: This paper describes our strategies used in the RobocupRescue simulation contest in seattle 2001[3]. we first introduce our powerful communication manager for multi-agent systems which is specially designed to work in difficult, let’s say ”Hard-zone”, environment where number of communicated messages are drastically limited and also sensory noises and limited information about the environment are major problems. Also some hints are provided for developing multi-agent systems. Then we introduce our approach for solving some NP-Complete problems faced in the system.
Haker, M., Meyer, A., Polani, D. & Martinetz, T.

A Method for Incorporation of New Evidence to Improve World State Estimation


2002 RoboCup 2001: Robot Soccer World Cup V, pp. 243-282 inproceedings

DOI URL

Abstract: We describe an approach to incorporate new evidence into an existing world model. The method, Evidence-based World state Estimation, has been used in the RoboCup soccer simulation scenario to obtain a high precision estimate for player and ball position.
Hengst, B., Ibbotson, D., Pham, S.B. & Sammut, C.

Omnidirectional Locomotion for Quadruped Robots


2002 RoboCup 2001: Robot Soccer World Cup V, pp. 73-94 inproceedings

DOI URL

Abstract: Competing at the RoboCup 2000 Sony legged robot league, the UNSW team won both the challenge competition and all their soccer matches, emerging the outright winners for this league against eleven other international teams. The main advantage that the UNSW team had was speed. A major contributor to the speed was a novel omnidirectional locomotion method developed for the quadruped Sony ERS-110 robot used in the competition. It is believed to be the fastest walk style known for this type of robot. In this paper we describe the parameterised omnidirectional walk in detail. The walk also made a positive contribution to other robot tasks such as ball tracking and localisation while playing soccer. The authors believe that this omnidirectional locomotion could be applied more generally in other legged robots.
Hibino, S., Kodama, Y., Nagasaka, Y., Takahashi, T., Murakami, K. & Naruse, T.

Owaribito - A Team Description


2002 RoboCup 2001: Robot Soccer World Cup V, pp. 1-4 inproceedings

DOI URL

Abstract: In this paper, we describe image processing method for highspeed robot ID recognition with black and white markers, path generation algorithm which controls left and right wheel velocity independently, strategy and communication software with error correcting code (ECC).
Hu, H., Gu, D., Golubovic, D., Li, B. & Liu, Z.

Essex Rovers 2001 Team Description


2002 RoboCup 2001: Robot Soccer World Cup V, pp. 1-29 inproceedings

DOI URL

Abstract: This article introduces our research efforts to build the Essex Rovers’01 robot soccer team participated in the RoboCup-2001 competition. A modular design for implementing a behavior-based hierarchy is introduced, which consists of three modules such as Perception module, Cognition module and Action module. This architecture is used for the team to achieve intelligent actions in real time. The implementation aspect of these three modules are briefly described.
Hu, H., Kostiadis, K., Hunter, M. & Kalyviotis, N.

Essex Wizards 2001 Team Description


2002 RoboCup 2001: Robot Soccer World Cup V, pp. 511-514 inproceedings

DOI URL

Abstract: This article presents an overview of the Essex Wizards 2001 team participated in the RoboCup 2001 simulator league. Four major issues have been addressed, namely a generalized approach to position selection, strategic planning and encoded communication, reinforcement learning (RL) and Kanerva-based generalization, as well as the agent architecture and agent behaviours.
Hugel, V., Stasse, O., Bonnin, P. & Blazevic, P.

French LRP Team's Description


2002 RoboCup 2001: Robot Soccer World Cup V, pp. 167-204 inproceedings

DOI URL

Abstract: This paper deals with the developments of the French team in RoboCup 2002 Sony legged league. For this event, Sony provided new quadruped robots that were able to compute and move faster, and to see further. The robots got improved skills in locomotion and vision. Compared to last year, soccer games were more lively with a lot of goals scored. Our team focused on designing a localization procedure while walking by taking into account significant and reliable information from the vision system.
v. Hundelshausen, F., Behnke, S. & Rojas, R.

An Omnidirectional Vision System That Finds and Tracks Color Edges and Blobs


2002 RoboCup 2001: Robot Soccer World Cup V, pp. 31-49 inproceedings

DOI URL

Abstract: We describe the omnidirectional local vision system developed for the FU-Fighters, a RoboCup F180 league soccer team. A small video camera mounted vertically on top of the robots looks at a concave parabolic mirror placed above the camera that reflects the field around. The image is sent via a radio link to an external PC for processing.
Our computer vision system can find the ball and detect other robots as obstacles. The walls of the field are also recognized and are used to determine the initial position of the robot. In order to be able to process the video stream at full frame rate the movement of all objects is tracked, including the walls of the field. The key idea of our approach is to predict the location of color edges in the next frame and to search for such color transitions along lines that are perpendicular to the edge.
Hunter, M. & Hu, H.

A Generalised Approach to Position Selection for Simulated Soccer Agents


2002 RoboCup 2001: Robot Soccer World Cup V, pp. 179-205 inproceedings

DOI URL

Abstract: Position selection is a key task that must be carried out by a soccer-playing agent, but is often overlooked in favour of the more active tasks such as ball control. This paper examines the position selection implemented by the Essex Wizards team in the RoboCup Simulator league in recent competitions. The initial approach using task specific behaviours is firstly reviewed. The new approach is then addressed based on modular decomposition for flexibility. Implementation results are given to show the applicability.
Indiveri, G.

On the Motion Control of a Nonholonomic Soccer Playing Robot


2002 RoboCup 2001: Robot Soccer World Cup V, pp. 1-6 inproceedings

DOI URL

Abstract: A nonlinear control law to steer the unicycle model to a static or dynamic target pose is presented. If the target is static the control signals are smooth in their arguments and the solution guarantees exponential convergence of the distance and orientation errors to zero. The major advantages of the proposed approach are that there is no need for path planning and, in principle, there is no need for global self-localization either.
Iocchi, L., Baldassari, D., Cappelli, F., Farinelli, A., Grisetti, G., Maathuis, F. & Nardi, D.

S.P.Q.R. Wheeled Team


2002 RoboCup 2001: Robot Soccer World Cup V, pp. 7-30 inproceedings

DOI URL

Abstract: This paper presents the design and implementation issues that have been addressed for the realization of the S.P.Q.R. Wheeled team of soccer robots. The team is formed by “senior” soccer robots that have participated to previous RoboCup competitions as well as by new robots developed for completing the team. By exploiting our previous experience in designing and developing soccer robots, we have developed innovative techniques for vision, localization, planning and coordination.
Isekenmeier, G., Nebel, B. & Weigel, T.

Evaluation of the Performance of CS Freiburg 1999 and CS Freiburg 2000


2002 RoboCup 2001: Robot Soccer World Cup V, pp. 7-40 inproceedings

DOI URL

Abstract: One of the questions one may ask when following research in robotic soccer is whether there is a measurable progress over the years in the robotic leagues. While everybody who has followed the games from 1997 to 2000 would agree that the robotic soccer players in the F2000 league have improved their playing skills, there is no hard evidence to justify this opinion. We tried to identify a number of criteria that measure the ability to play robotic soccer and analyzed all the games CS Freiburg played at RoboCup 1999 and 2000. As it turns out, for almost all criteria, there is a statistically significant increase for CS Freiburg and the opponent teams demonstrating that the level of play has indeed increased from 1999 to 2000.
This work has been partially supported by Deutsche Forschungsgemeinschaft as part of DFG project Ne 623/3-1.
Jamzad, M., Chitsaz, H., Foroughnassirai, A., Ghorbani, R., Kazemi, M., Mirrokni, V. & Sadjad, B.

Basic Requirements for a Teamwork in Middle Size RoboCup


2002 RoboCup 2001: Robot Soccer World Cup V, pp. 621-626 inproceedings

DOI URL

Abstract: In this paper we describe some mechanical, hardware and software aspects of our robots specially used in teamwork. The pneumatic design of the gripers and kicker enables the robot to make a good control of ball when dribbling and also passing the ball in short and long distances. The teamwork software enables our robots to perform a cooperative behavior by dividing the field to three major regions and assigning each robot a role such as defender, forward and middle in these three regions. The server can order the robots to change their role when needed and make them return to their original state after a short time.
Jamzad, M., Sadjad, B., Mirrokni, V., Kazemi, M., Chitsaz, H., Heydarnoori, A., Hajiaghai, M. & Chiniforooshan, E.

A Fast Vision System for Middle Size Robots in RoboCup


2002 RoboCup 2001: Robot Soccer World Cup V, pp. 159-203 inproceedings

DOI URL

Abstract: A mobile robot should be able to analyze what it is seeing in real time rate and decide accordingly. Fast and reliable analysis of image data is one of the key points in soccer robot performance. In this paper we suggest a very fast method for object finding which uses the concept of perspective view. In our method, we introduce a set of jump points in perspective on which we search for objects. An object is estimated by a rectangle surrounding it. A vector based calculation is introduced to find the distance and angle of a robot from objects in the field. In addition we present a new color model which takes its components from different color models. The proposed method can detect all objects in each frame and their distance and angle in one scan on the jump points in that frame. This process takes about 1/50 of a second. Our vision system uses a commercially available frame grabber and is implemented only in software. It has shown a very good performance in RoboCup competitions.
Johansson, S.J. & Saffiotti, A.

Using the Electric Field Approach in the RoboCup Domain


2002 RoboCup 2001: Robot Soccer World Cup V, pp. 117-138 inproceedings

DOI URL

Abstract: In autonomous robotics, so-called artificial potential fields are often used to plan and control the motion of a physical robot. In this paper, we propose to use an artificial electric field to address the problem or real time action selection in embodied, autonomous agents. We attach positive and negative electric charges to the relevant objects in the agent’s domain, and use the resulting electric field to estimate the heuristic value of a given configuration. This value is used to select the action that results in the best configuration. This allows us to consider in the same framework both navigation and manipulation actions. We apply the electric field approach in the RoboCup domain, and present results drawn from our experience in the Sony legged robots league.
de Jong, F., Caarls, J., Bartelds, R. & Jonker, P.P.

A Two-Tiered Approach to Self- Localization


2002 RoboCup 2001: Robot Soccer World Cup V, pp. 57-77 inproceedings

DOI URL

Abstract: This paper describes a two-tiered approach to the self-localization problem for soccer playing robots using generic off-the-shelf color cameras. The solution consists of two layers; the top layer is a global search assuming zero knowledge, and the bottom layer is a local search, assuming a relatively good estimation of the position and orientation of the robot. The global search generally yields multiple candidate positions and orientations, which can be tracked, and assigned a confidence level using the local search and/or historic information.
Kiat, N.B., Ming, Q.Y., Hock, T.B., Yee, Y.S. & Koh, S.

LuckyStar II - Team Description Paper


2002 RoboCup 2001: Robot Soccer World Cup V, pp. 95-116 inproceedings

DOI URL

Abstract: Our first robotic soccer team, LuckyStar, competed in Stockholm 1999 and was lucky enough to win third place. From that experience, we found that our team weaknesses were due to lack of vision reliability, smooth robot movement control, shooting capability and team cooperation. We decided to concentrate on areas with the most immediate impact on the game, i.e. vision, robot movement control and shooting mechanism.
Kraetzschmar, G., Utz, H., Sablatnög, S., Enderle, S. & Palm, G.

Miro - Middleware for Cooperative Robotics


2002 RoboCup 2001: Robot Soccer World Cup V, pp. 95-110 inproceedings

DOI URL

Abstract: Developing software for mobile robot applications is a tedious and error-prone task. We suggest the use of object-oriented middleware to remedy the problem. After identifying crucial design goals, we present Miro, an object-oriented middleware for robots meeting the design goals. We discuss its implementation and demonstrate Miro’s role in the implementation of applications on different kinds of robots.
Kuwata, Y. & Shinjoh, A.

Building User Models for RoboCup-Rescue Visualization


2002 RoboCup 2001: Robot Soccer World Cup V, pp. 111-116 inproceedings

DOI URL

Abstract: Information visualization is one of the most important fields in RoboCup-Rescue research. As requirements for visualization vary by users and by their purpose of viewer use, we introduce a mechanism called user model. User models hold the requirements of typical users. They are used for the selection and customization of information, controls of viewer, and so on. We implemented the mechanism with five user models in RoboCup-Rescue 2D Viewer.
Lafrenz, R., Becht, M., Buchheim, T., Burger, P., Hetzel, G., Kindermann, G., Schanz, M., Schulé, M. & Levi, P.

CoPS-Team Description


2002 RoboCup 2001: Robot Soccer World Cup V, pp. 23-61 inproceedings

DOI URL

Abstract: The control software of the robot soccer team CoPS is designed as a multi-agent-system. The basis for a cooperation between the robots is a suitable environment model based on uncertain sensory data and communication.
Lau, N. & Reis, L.P.

FC Portugal 2001 Team Description: Flexible Teamwork and Configurable Strategy


2002 RoboCup 2001: Robot Soccer World Cup V, pp. 1-10 inproceedings

DOI URL

Abstract: FC Portugal is a cooperation project between the Universities of Aveiro and Porto in Portugal. FC Portugal 2001 is our second step towards the creation of a flexible RoboSoccer team, with tactical changing abilities, that may be coached at any level, before and during the games, by human or automatic coaches. Although having the best goal average in the competition (scoring 150 goals in 13 games), the team was not able to score against the good defenses of Tsinghuaeolus and Brainstomers and finished third in RoboCup 2001.
We would like to thank the financial support from IEETA/University of Aveiro, LIACC and FEUP/University of Porto and ICEP.
Lenser, S., Bruce, J. & Veloso, M.

A Modular Hierarchical Behavior-Based Architecture


2002 RoboCup 2001: Robot Soccer World Cup V, pp. 79-99 inproceedings

DOI URL

Abstract: This paper describes a highly modular hierarchical behavior-based control system for robots. Key features of the architecture include: easy addition/removal of behaviors, easy addition of specialized behaviors, easy to program hierarchical structure, and ability to execute non-conflicting behaviors in parallel. The architecture uses a unique reward based combinator to arbitrate amongst competing behaviors such as to maximize reward. This behavior system was successfully used in our Sony Legged League entry in RoboCup 2000 where we came in third losing only a single game.
This research was sponsored by Grants Nos. DABT63-99-1-0013, F30602-98-2-0135 and F30602-97-2-0250. The information in this publication does not necessarily reflect the position of the funding agencies and no official endorsement should be inferred.
Li, X., Zhang, Z., Jiang, L. & Chen, X.

Wright Eagle 2001 - Sony Legged Robot Team


2002 RoboCup 2001: Robot Soccer World Cup V, pp. 7-29 inproceedings

DOI URL

Abstract: This paper introduces team Wright Eagle - the only Chinese team in Sony legged robot league of RoboCup. The architecture and four main modules will be described.
Lima, P., Custódio, L., Damas, B., Lopes, M., Marques, C., Toscano, L. & Ventura, R.

ISocRob 2001 Team Description


2002 RoboCup 2001: Robot Soccer World Cup V, pp. 33-45 inproceedings

DOI URL

Abstract: This paper describes the ISocRob team current status, new features demonstrated in RoboCup 2001, and the project long term scientific goals. An evolution of the team prior software architecture, full demonstration of multi-sensor navigation during games, a new goalkeeper and field robots endowed with dribble capability are new features that will be briefly described.
Manzuri, M.T., Chitsaz, H.R., Ghorbani, R., Karimian, P., Mirazi, A., Motamed, M., Mottaghi, R. & Sabzmeydani, P.

Sharif CESR Small Size Robocup Team


2002 RoboCup 2001: Robot Soccer World Cup V, pp. 145-177 inproceedings

DOI URL

Abstract: Robotic soccer is a challenging research area, which involves multiple agents that need to collaborate in an adversarial environment to achieve specific objectives. Here we describe the Sharif CESR small robot team, which was participated in Robocup 2001 small size league in Seattle, USA. This paper explains the overall architecture of our robotic soccer system. Figure 1 shows a picture of our soccer robots.
Marques, C.F. & Lima, P.U.

Multi-Sensor Navigation for Soccer Robots


2002 RoboCup 2001: Robot Soccer World Cup V, pp. 167-188 inproceedings

DOI URL

Abstract: This work introduces a method for robot navigation in structured indoors environments, based on the information of multiple sensors. Guidance control is based on odometry, reset at some time instants by a vision-based self-localization algorithm introduced in previous work. Sonar data is used to avoid and go around obstacles. Results from the application of the complete navigation system to a real robot moving on a RoboCup soccer field are presented.
Matsuoka, T., Araoka, M., Hasegawa, T., Mohri, A., Yamamoto, M., Kiriki, T., Ushimi, N., Sugimoto, T., Inoue, J. & Yamaguchi, Y.

Localization and Obstacles Detection Using Omni-Directional Vertical Stereo Vision


2002 RoboCup 2001: Robot Soccer World Cup V, pp. 101-114 inproceedings

DOI URL

Abstract: This paper describes an omni-directional vertical stereo vision system for an autonomous mobile robot. The system is composed of two omni-directional cameras and enables both the localization with wide range of view and the obstacles detection by 3D measurement of arbitrary direction. The system architecture and an experimental result are shown.
Matsuoka, T., Yamamoto, M., Ushimi, N., Inoue, J., Sugimoto, T., Araoka, M., Kiriki, T., Yamaguchi, Y., Hasegawa, T. & Mohri, A.

Fusion


2002 RoboCup 2001: Robot Soccer World Cup V, pp. 109-122 inproceedings

DOI URL

Abstract: This paper introduces team ”Fusion” and its soccer robots for RoboCup-2001. The team is organized by Kyushu University, Fukuoka University, Hitachi Information & Control Systems Inc. considering technical requirements of RoboCup F2000 league. The soccer robots have been originally designed and made for the league. It is first attempt to join RoboCup for the robots and the team.
Menegatti, E., Nori, F., Pagello, E., Pellizzari, C. & Spagnoli, D.

Designing an Omnidirectional Vision System for a Goalkeeper Robot


2002 RoboCup 2001: Robot Soccer World Cup V, pp. 193-213 inproceedings

DOI URL

Abstract: The aim of this paper is to provide a guideline for the design of an omnidirectional vision system for the Robocup domain. We report the design steps undertaken, with a detailed description of the design of an omnidirectional mirror with a custom profile. In the second part, we present the software written to exploit the properties of the designed mirror. The application for which the vision system is designed is the Middle-Size Robocup Championship. The task performed by the vision system is to localise the robot and to locate the ball and other robots in the field of play. Several practical tricks and suggestions are provided.
Merke, A. & Riedmiller, M.

Karlsruhe Brainstormers - A Reinforcement Learning Approach to Robotic Soccer


2002 RoboCup 2001: Robot Soccer World Cup V, pp. 17-36 inproceedings

DOI URL

Abstract: Our long-term goal is to build teams of agents where the decision making is based completely on Reinforcement Learning (RL) methods. It requires an appropriate modelling of the learning task and the paper describes how robotic soccer can be seen as a multi-agent Markov Decision Process (MMDP). It discusses how optimality of behaviours of agents can be defined and what difficulties one encounters in developing concrete algorithms which are supposed to reach such optimal agent/team policies. We also give an overview of already incorporated algorithms in our ’Karlsruhe Brainstormers’ simulator league team and report some results on learning of offensive team behaviour.
Miene, A. & Visser, U.

Interpretation of Spatio-Temporal Relations in Real-Time and Dynamic Environments


2002 RoboCup 2001: Robot Soccer World Cup V, pp. 291-318 inproceedings

DOI URL

Abstract: With the more sophisticated abilities of teams within the simulation league high level online functions become more and more attractive. Last year we proposed an approach to recognize the opponents strategy and developed the online coach accordingly. However, this approach gives only information about the entire team and is not able to detect significant situations (e.g. double pass, standard situations). In this paper we describe a new method which describes spatio-temporal relations between objects. This approach is able to track the objects and therefore the relations between them online so that we are able to interpret situations over time during the game. This enables us to detect the above mentioned situations. We can implement this in the online coach in order to enrich our team with high level functions. This new method is domain independent.
Mitsunaga, N. & Asada, M.

Visual Attention Control by Sensor Space Segmentation for a Small Quadruped Robot Based on Information Criterion


2002 RoboCup 2001: Robot Soccer World Cup V, pp. 281-300 inproceedings

DOI URL

Abstract: Since the vision sensors bring a huge amount of data, visual attention is one of the most important issues for a mobile robot to accomplish a given task in complicated environments. This paper proposes a method of sensor space segmentation for visual attention control that enables efficient observation by taking the time for observation into account. The efficiency is considered from a viewpoint of not geometrical reconstruction but unique action selection based on information criterion regardless of localization uncertainty. The method is applied to four legged robot that tries to shoot a ball into the goal. To build a decision tree, a training data set is given by the designer, and a kind of off-line learning is performed on the given data set. The visual attention control in the method and the future work are discussed.
Mitsunaga, N., Nagai, Y., Ishida, T., Izumi, T. & Asada, M.

BabyTigers 2001: Osaka Legged Robot Team


2002 RoboCup 2001: Robot Soccer World Cup V, pp. 71-120 inproceedings

DOI URL

Abstract: We have developed all kinds of motions such as walking, standing-up, and kicking towards Seattle. From a human designer’s point of view, it is easier to write strategies based on the geometric, global position data but seems less attractive. Then, we are attacking learning issues such as action selection [1] [2], observation strategy without 3D-reconstruction.
Morimoto, T., Kono, K. & Takeuchi, I.

YabAI The First Rescue Simulation League Champion


2002 RoboCup 2001: Robot Soccer World Cup V, pp. 75-99 inproceedings

DOI URL

Abstract: RoboCupRescue project aims to simulate large urban disasters. In order to minimize damage resulting from disasters, various rescue agents try to accomplish their missions in the disaster space in the simulation system. Ability of an individual agent, however, is utterly insufficient. Agents need to cooperate with other same and different types utilizing as little communication as possible under stringently limited visual sensory information. Our YabAI team, however, successfully implemented effective cooperations under this limitation.
Morishita, T., Shimora, H., Hiratsuka, K., Kubo, T., Hiroshima, K., Funakami, R., Nishino, J., Odaka, T. & Ogura, H.

Zeng01 Team Description: Formation Decision Method Using Game Theory


2002 RoboCup 2001: Robot Soccer World Cup V, pp. 61-83 inproceedings

DOI URL

Abstract: The combined team, Zeng01, have players developed by several subject of investigation. We have analyzed better player combination based on game theory. We look up the formation property through changing a opposite team strategy on every games. Comparing formation property on every games, we decide own team formation.
Murray, J., Obst, O. & Stolzenburg, F.

RoboLog Koblenz 2001


2002 RoboCup 2001: Robot Soccer World Cup V, pp. 267-290 inproceedings

DOI URL

Abstract: Outline. A formalism for the specification of multiagent systems should be expressive enough to model not only the behavior of one single agent, but also the collaboration among several agents and the influences caused by external events. For this, state machines [4] seem to provide an adequate means. Therefore, the approach of the team RoboLog Koblenz 2001 employs techniques from software engineering and artificial intelligence research by using UML statecharts and implementing them systematically with logic and deduction in Prolog [3].
This research is partially supported by the grants Fu 263/6-1 and Fu 263/8-1 from the German research foundation DFG.
Nair, R., Ito, T., Tambe, M. & Marsella, S.

Task Allocation in the RoboCup Rescue Simulation Domain: A Short Note


2002 RoboCup 2001: Robot Soccer World Cup V, pp. 1-22 inproceedings

DOI URL

Abstract: We consider the problem of disaster mitigation in the RoboCup Rescue Simulation Environment [3] to be a task allocation problem where the tasks arrive dynamically and can change in intensity. These tasks can be performed by ambulance teams, fire brigades and police forces with the help of an ambulance center, a fire station and a police office. However the agents don’t get automatically notified of the tasks as soon as they arrive and hence it is necessary for the agents to explore the simulated world to discover new tasks and to notify other agents of these.
Nakayama, K. & Takeuchi, I.

Team YowAI-2001 Description


2002 RoboCup 2001: Robot Soccer World Cup V, pp. 1-5 inproceedings

DOI URL

Abstract: The team YowAI-2001 inherits the low-level individual skill and the world modeling technique of YowAI-2000 developed by Takashi Suzuki and improved by Sinnosuke Asahara. Its objective is “cooperation by short shouts” instead of co-operation by communicating large amount of non human-like messages among agents.
Nardi, D., Bonifaci, V., Castelpietra, C., Iorio, U.D., A. Guidotti, L.I., Salerno, M. & Zonfrilli, F.

S.P.Q.R. Legged Team


2002 RoboCup 2001: Robot Soccer World Cup V, pp. 717-720 inproceedings

DOI URL

Abstract: The SPQR (Soccer Player Quadruped Robots, but also Senatus PopolusQue Romanus) team participated for the second time to Sony Legged League in RoboCup 2001. This work is a team description where it will be highlighted what the team development effort focused on: the realization of a motion module, the realization of a vision module and the improvement of the plans which characterize the different robot roles.
Nazemi, E., Rahmani, M. & Radjabalipour, B.

3T Architecture for the SBCe Simulator Team


2002 RoboCup 2001: Robot Soccer World Cup V, pp. 117-157 inproceedings

DOI URL

Abstract: In this paper we briefly describe the process of action control used by the agents of the SBCe Simulator team. It is based on 3T Architecture, which helps to coordinate planful activities with real-time behavior for dealing with dynamic environments.
Our main goal in this project was to achieve some features of teamwork in the multi-agent system of simulated RoboSoccer such as Combination Play and Dynamic Positioning. To achieve this, SBCe used some real soccer rules and knowledge. SBCe’s low level structure is based on the CMUnited-99.
Noda, I., Takahashi, T., Morita, S., Koto, T. & Tadokoro, S.

Language Design for Rescue Agents


2002 RoboCup 2001: Robot Soccer World Cup V, pp. 125-166 inproceedings

DOI URL

Abstract: We are proposing a model of communication and a specification of language for civilian agents in RoboCup Rescue Simulation. Robust information systems are critical infrastructure for rescue in huge disasters. The main issue of the information system in the rescue domain is that the most of information sources are civilians who may report incomplete information. Proposed model and specification is designed to reflect natural features of human communication behaviors. The model is also designed in order to provide for researchers to implement new design of information devices in the simulation flexibly. Using the model and specification, we can evaluate information systems and behaviors of rescue specialist agents.
Nooraei, B.B., Rahbar, N.S. & Aladini, O.

Helli-Respina 2001 Team Description Paper


2002 RoboCup 2001: Robot Soccer World Cup V, pp. 519-521 inproceedings

DOI URL

Abstract: One of the most important problems for development of intelligent agents is adaptation to the environment. In this paper we briefly describe Helli-Respina soccer simulator team that uses a new self-adaptive method named Dynamic Multi-Behavior Assessment (DMBA). By using built-in behavior manager named dynamic behavior transformer method lets the agent can choose the best algorithms to decide during the game. This system always tries to choose a set of available algorithms to get the best result against each opponent. The main objective in this research is how to choose a set of algorithms dynamically to get the best result against an opponent.
Obst, O.

Specifying Rational Agents with Statecharts and Utility Functions


2002 RoboCup 2001: Robot Soccer World Cup V, pp. 173-182 inproceedings

DOI URL

Abstract: To aid the development of the robotic soccer simulation league team RoboLog-2000, a method for the specification of multi-agent teams by statecharts has been introduced. The results in the last years competitions showed that though the team was competitive, it did not behave adaptive in unknown situations. The design of adaptive agents with this method is possible, but not in a straightforward manner. The purpose of this paper is to extend the approach by a more adaptive action selection mechanism and to facilitate a more explicit representation of goals of an agent.
This research is supported by the grant Fu 263/6-1 from the German research foundation DFG.
Oda, K., Ohashi, T., Kouno, S., Gohara, K., Hayashi, T., Kato, T., Katsumi, Y. & Ishimura, T.

ASURA: Kyushu United Team in the Four Legged Robot League


2002 RoboCup 2001: Robot Soccer World Cup V, pp. 21-41 inproceedings

DOI URL

Abstract: This paper presents our approach to the Sony Four Logged Robot League of RoboCup 2001. The components of our system consist of strategy, vision, localization, behaviors and walking module. We introduce several techniques for these modules: The image based cooperation, TSL color space for robust color classification, accurate localization through observing the nearest marker and enhanced parameterized walk. We also develop two powerful tools, the color classification tool which allows us to extract accurate thresholds fast, and the forth interpreting language environment which provides interactive access for the robot control.
Padgham, L., Thangarajah, J., Poutakidis, D. & Fernando, C.

Team Description for RMIT-on-Fire: Robocup Rescue Simulation Team 2001


2002 RoboCup 2001: Robot Soccer World Cup V, pp. 189-246 inproceedings

DOI URL

Abstract: This team description paper outlines the reasons that RMIT Compter Science considers RoboCupRescue a valuable domain for ongoing research, and describes the preliminary architecture which has been developed as an infrastructure for ongoing work in the area of building BDI (Belief Desire Intention) intelligent agents and multi-agent cooperating teams.
Pagello, E., Bert, M., Barbon, M., Menegatti, E., Moroni, C., c. Pellizzari, Spagnoli, D. & Zaffalon, S.

Artisti Veneti: An Heterogeneous Robot Team for the 2001 Middle-Size League


2002 RoboCup 2001: Robot Soccer World Cup V, pp. 139-170 inproceedings

DOI URL

Abstract: We illustrate our new team Artisti Veneti a new entry in the Middle-size league from The University of Padua (Italy). The team is composed of heterogeneous robots that use only vision as perception system. The vision systems have been designed separately for each robot. Our players are coordinated in the frame of ADE (Artisti Veneti’s Development Environment), a multi-thread distributed real-time Environment working under Linux OS. Cooperative abilities, like exchanging a ball, can be achieved through the use of efficient collision avoidance algorithms using roles swapping triggered using an enhanced reactivity approach.
Pham, S.B., Hengst, B., Ibbotson, D. & Sammut, C.

Stochastic Gradient Descent Localisation in Quadruped Robots


2002 RoboCup 2001: Robot Soccer World Cup V, pp. 83-105 inproceedings

DOI URL

Abstract: Competing at the RoboCup 2000 Sony legged robot league, the UNSW team convincingly won all their matches. One of the advantages of the team was a new localisation algorithm that is very fast and can tolerate noisy input from the environment as well as unexpected collisions with other objects. This paper describes the algorithm in detail.
Prokopenko, M., Wang, P. & Howard, T.

Cyberoos'2001: "Deep Behaviour Projection" Agent Architecture


2002 RoboCup 2001: Robot Soccer World Cup V, pp. 127-155 inproceedings

DOI URL

Abstract: The RoboCup Simulation League presents developers with a variety of challenges. Arguably, the following list includes the most critical topics:
- distributed client/server system running on a network;
- concurrent communication with a medium-sized (25) number of agents;
- fragmented, localised and imprecise (noisy and latent) information about the environment (field);
- heterogeneous sensory data (visual, auditory, kinetic);
- asynchronous perception-action activity;
- limited range of basic commands/effectors (turn, kick, dash,...);
- limited window of opportunity to perform an action;
- autonomous decision-making under constraints enforced by teamwork (collaboration) and opponent (competition);
- conflicts between reactivity and deliberation;
- no centralised controllers (no global vision, etc.);
- evolving standards, rules and parameters of the Simulation.
Reis, L.P. & Lau, N.

COACH UNILANG - A Standard Language for Coaching a (Robo) Soccer Team


2002 RoboCup 2001: Robot Soccer World Cup V, pp. 251-265 inproceedings

DOI URL

Abstract: This document introduces COACH UNILANG, a standard language for coaching (Robo)Soccer teams. This language was developed with two main objectives: to coach FC Portugal 2001 team and as a proposal to be used in Fukuoka 2002 RoboCup coach competition. This language enables high-level and low-level coaching through coach instructions. High-level coaching includes changing tactics, formations used in each situation and changing player behavior. Low-level coaching includes defining formations, situations, player behavior and positioning with high detail. The language also enables the coach (functioning like an assistant coach) to send opponent modeling information and game statistical information to the players.
Ribeiro, F., Machado, C., Sampaio, S. & Martins, B.

MINHO Robot Football Team for 2001


2002 RoboCup 2001: Robot Soccer World Cup V, pp. 225-250 inproceedings

DOI URL

Abstract: This paper describes an autonomous robot football team. The work is being carried out since 1998. It describes the hardware used by the robots, the sensory system and interfaces, as well as the game strategy. Data acquisition for the perception level is carried out by the vision system, and the image processing system is described. Two cameras are used requiring sensorial fusion. With this architecture, an attempted is made to make the autonomous robots more real world intelligent. These robots have a kicker with controlled power, which allows passing the ball to a teammate with controlled distance and direction.
Riley, P. & Veloso, M.

Recognizing Probabilistic Opponent Movement Models


2002 RoboCup 2001: Robot Soccer World Cup V, pp. 205-245 inproceedings

DOI URL

Abstract: In multiagent adversarial domains, team agents should adapt to the environment and opponent. We introduce a model representation as part of a planning process for a simulated soccer domain. The planning is centralized, but the plans are executed in a multi-agent environment, with teammate and opponent agents. Further, we present a recognition algorithm where the model which most closely matches the behavior of the opponents can be selected from few observations of the opponent. Empirical results are presented to verify that important information is maintained through the abstraction the models provide.
Rojas, R., Behnke, S., Liers, A. & Knipping, L.

FU-Fighters 2001 (Global Vision)


2002 RoboCup 2001: Robot Soccer World Cup V, pp. 247-294 inproceedings

DOI URL

Abstract: Our F180 team, the FU-Fighters, participated for the third time at the RoboCup competition. This year we used a heterogeneous team, consisting of improved differential drive robots and new omnidirectional robots. We designed new electronics and added prediction and path planning to the behavior control. Our team won fourth place in the SmallSize league competition.
Rojas, R., von Hundelshausen, F., Behnke, S. & Frötschl, B.

FU-Fighters Omni 2001 (Local Vision)


2002 RoboCup 2001: Robot Soccer World Cup V, pp. 43-59 inproceedings

DOI URL

Abstract: Currently, the Small Size League is the only RoboCup competition that permits the use of external sensing systems. Most teams use a color camera that is mounted above the field to determine the positions of the robots and the ball. Since this simplified setup is not compatible with the idea of autonomous robots, we decided to build a second F180 team for the World Championships 2001 in Seattle, consisting of (only) three robots using local omnidirectional vision, the “FU-Fighters Omni”.
de la Rosa, J.L., Innocenti, B., Montaner, M., Figueras, A., Muñoz, I. & Ramon, J.A.

Rogi Team Description


2002 RoboCup 2001: Robot Soccer World Cup V, pp. 301-338 inproceedings

DOI URL

Abstract: This paper resumes the main features introduced to RoGi team for RoboCup 2001.
Saffiotti, A., Björklund, A., Johansson, S. & Wasik, Z.

Team Sweden


2002 RoboCup 2001: Robot Soccer World Cup V, pp. 725-729 inproceedings

DOI URL

Abstract: “Team Sweden” is the Swedish national team that entered the Sony legged robot league at the RoboCup2001 competition. The work was distributed over three universities in Sweden. This nationwide character has made the project organization particularly demanding, but has resulted in a rewarding cooperation experience, both scientific and human. The Team identity is as follows: Team Leader: Alessandro Saffiotti (asaffio@aass.oru.se) Team Members: include the authors, plus: R. Johansson (Örebro); P. Davidsson, D. Erman, and J. Kronqvist (Blekinge); J. Carstensen, P. Eklund, P. Larsson, and K. Prorok (Umeå). Sponsors: Swedish KK foundation, Qualisys AB, Örebro University, Umeå University, and the Blekinge Institute of Technology. Team home page: http://www.aass.oru.se/Living/RoboCup/.
Sakushima, T., Esaki, T., Asai, Y., Ito, N. & Wada, K.

A Design of Agents for the Disaster Simulator on RoboCup-Rescue


2002 RoboCup 2001: Robot Soccer World Cup V, pp. 205-236 inproceedings

DOI URL

Abstract: In a Multi-Agent System, it is important that an agent cooperate with the others appropriately. In our rescue agent team “NITRescue”, each agent acts in cooperation with other kind of agent by using limited communication facility. Therefore they aim at coping with complicated disaster circumstances of Rescue simulator.
Schmitt, T., Buck, S. & Beetz, M.

AGILO RoboCuppers 2001: Utility- and Plan-Based Action Selection Based on Probabilistically Estimated Game Situations


2002 RoboCup 2001: Robot Soccer World Cup V, pp. 11-19 inproceedings

DOI URL

Abstract: This paper describes the AGILO RoboCuppers 1 the RoboCup team of the image understanding group (FG B V) at the Technische Universität München. With a team of four Pioneer I robots, all equipped with CCD camera and a single board computer, we’ve participated in all international middle size league tournaments from 1998 until 2001. We use a modular approach of concurrent subprograms for image processing, self localization, object tracking, action selection, path planning and basic robot control. A fast feature extraction process provides the data necessary for the on-board scene interpretation. All robot observations are fused into a single environmental model, which forms the basis for action selection, path planning and low-level robot control.
The name is derived from the Agilolfinger, which were the first Bavarian ruling dynasty in the 8th century, with Tassilo as its most famous representative.
Schmitt, T., Hanek, R., Buck, S. & Beetz, M.

Cooperative Probabilistic State Estimation for Vision-Based Autonomous Soccer Robots


2002 RoboCup 2001: Robot Soccer World Cup V, pp. 63-133 inproceedings

DOI URL

Abstract: With the services that autonomous robots are to provide becoming more demanding, the states that the robots have to estimate become more complex. In this paper, we develop and analyze a probabilistic, vision-based state estimation method for individual, autonomous robots. This method enables a team of mobile robots to estimate their joint positions in a known environment and track the positions of autonomously moving objects. The state estimators of different robots cooperate to increase the accuracy and reliability of the estimation process. This cooperation between the robots enables them to track temporarily occluded objects and to faster recover their position after they have lost track of it. The method is empirically validated based on experiments with a team of physical robots.
Sear, J.A. & Ford, R.W.

RoboBase: An Extensible Framework Supporting Immediate Remote Access to Logfiles


2002 RoboCup 2001: Robot Soccer World Cup V, pp. 92-101 inproceedings

DOI URL

Abstract: This paper describes RoboBase, a system that provides immediate access to entire libraries of RoboCup logfiles. A centralised database stores the logfiles allowing them to be viewed remotely. Instead of downloading a 2MB uncompressed logfile, the match is transferred and displayed in real-time.
The system has been designed specifically to perform well in low bandwidth situations by using a domain specific compression method. Dynamic frame-rates are also employed, providing uninterrupted viewing in fluctuating network conditions.
The system conforms to an Object Oriented methodology and is implemented in Java allowing extension of the software by the user.
Sekimori, D., Mori, N., Ieda, J., Matsui, W., Miyake, O., Usui, T., Tanaka, Y., Kim, D.P., Maeda, T., Sugimoto, H., Fujimoto, R., Enomoto, M., Masutani, Y. & Miyazaki, F.

Team Description of the Team OMNI, The


2002 RoboCup 2001: Robot Soccer World Cup V, pp. 599-602 inproceedings

DOI URL

Abstract: The Team OMNI has developed a robot system with omnidirectional vision and omni-directional mobility according to the rule of the RoboCup Small Size League. This paper describes the hardware configuration, software configuration, and simulator of this robot system.
The RoboCup 2001 competition participants
Sekimori, D., Usui, T., Masutani, Y. & Miyazaki, F.

High-Speed Obstacle Avoidance and Self-Localization for Mobile Robots Based on Omni-Directional Imaging of Floor Region


2002 RoboCup 2001: Robot Soccer World Cup V, pp. 79-118 inproceedings

DOI URL

Abstract: In this paper, we propose a method of obstacle avoidance and a method of self-localization based on floor region provided by omnidirectional imaging. With our methods, omni-directional imaging is used not for recognition of the three-dimensional environment but for detecting obstacles and landmarks in a wide area at high speed. Several experiments with a real robot according to the rules of the RoboCup Small-Size League was demonstrated, and proved the effectiveness of these methods.
Spaan, M., Wiering, M., Bartelds, R., Donkervoort, R., Jonker, P. & Groen, F.

Clockwork Orange: The Dutch RoboSoccer Team


2002 RoboCup 2001: Robot Soccer World Cup V, pp. 71-111 inproceedings

DOI URL

Abstract: The Dutch RoboSoccer Team, called “Clockwork Orange”1 is a Dutch research project in which 3 universities participate: the University of Amsterdam, the Delft University of Technology, and University Utrecht. In this research project we study multi agent systems in general and multi robot systems in particular, as we participate in the RoboCup middle-size league. Due to severe hardware problems Utrecht University could sadly not contribute to the team this year.
Stancliff, S., Balasubramanian, R., Balch, T., Emery, R., Sikorski, K. & Stroupe, A.

CMU Hammerheads 2001 Team Description


2002 RoboCup 2001: Robot Soccer World Cup V, pp. 43-56 inproceedings

DOI URL

Abstract: The CMU MultiRobot Lab focuses on the study of team behavior in dynamic and uncertain environments. In order to further this research, we have developed an inexpensive autonomous robot platform, the Minnow. The CMU Hammerhead robot soccer team competes in the middle-size RoboCup competition using four of these Minnow robots.
Stone, P.

ATTUnited-2001: Using Heterogeneous Players


2002 RoboCup 2001: Robot Soccer World Cup V, pp. 59-125 inproceedings

DOI URL

Abstract: ATTUnited-2001 is a successor of the CMUnited teams: CMUnited-97, CMUnited-98, CMUnited-99, and ATT-CMUnited-2000. It is built mainly upon CMUnited-99 [4]. It also incorporates the team action architecture from ATT-CMUnited-2000 [3], but not the dynamic planning of set-plays capability [2]. The main research focus of ATTUnited-2001 is the affect of heterogeneous players in the RoboCup simulator [1].
Stone, P. & Sutton, R.S.

Keepaway Soccer: A Machine Learning Test Bed


2002 RoboCup 2001: Robot Soccer World Cup V, pp. 207-237 inproceedings

DOI URL

Abstract: RoboCup simulated soccer presents many challenges to machine learning (ML) methods, including a large state space, hidden and uncertain state, multiple agents, and long and variable delays in the effects of actions. While there have been many successful ML applications to portions of the robotic soccer task, it appears to be still beyond the capabilities of modern machine learning techniques to enable a team of 11 agents to successfully learn the full robotic soccer task from sensors to actuators. Because the successful applications to portions of the task have been embedded in different teams and have often addressed different sub-tasks, they have been difficult to compare. We put forth keepaway soccer as a domain suitable for directly comparing different machine learning approaches to robotic soccer. It is complex enough that it can’t be solved trivially, yet simple enough that complete machine learning approaches are feasible. In keepaway, one team, “the keepers,” tries to keep control of the ball for as long as possible despite the efforts of “the takers.” The keepers learn individually when to hold the ball and when to pass to a teammate, while the takers learn when to charge the ball-holder and when to cover possible passing lanes. We fully specify the domain and summarize some initial, successful learning results.
Sud, D., Cayouette, F., Hua, G.J. & Cooperstock, J.

McGill Reddogs


2002 RoboCup 2001: Robot Soccer World Cup V, pp. 31-94 inproceedings

DOI URL

Abstract: For the Robocup 2001 competition, the McGill Reddogs team moved from a monolithic architecture to a distributed one and created a flexible motion module. The Monte Carlo localization and custom script interpreter for behaviors were also replaced by simpler algorithms.
Suzuki, K., Tanaka, N. & Yamamoto, M.

11monkeys3 Team Description


2002 RoboCup 2001: Robot Soccer World Cup V, pp. 119-166 inproceedings

DOI URL

Abstract: For these three years, we have been trying to build an accurate world model for the agent to select a best/better behavior. This required a lot of resources of the system, though it is still impossible to get the exact world model. So we stood back to the point: Why are we trying to get an accurate world model. It is only because we believed that an accurate world model would help the agent determine the best/better behavior to win the soccer game. If the agent could select best/better behavior with less information, our requirement is fulfilled. So, this year we have worked to build a world model that has minimum but enough for the agent to determine its behavior.
Takahashi, T., Tadokoro, S., Ohta, M. & Ito, N.

Agent Based Approach in Disaster Rescue Simulation - From Test-Bed of Multiagent System to Practical Application


2002 RoboCup 2001: Robot Soccer World Cup V, pp. 63-74 inproceedings

DOI URL

Abstract: We apply multi-agent approach to search and rescue in a large-scale domain. The simulator is designed to simulate various domain specific simulation and human behaviors. Kobe-Awaji earthquake data is used as disaster scenarios and a prototype system was made open at RoboCup 2000. A rescue team composed of heterogeneous agents, - fire brigades, ambulances, and polices -, takes active part in the disastrous situation where about 100 civilian agents move autonomously. By comparing with rescue operations of two teams, we showed that the search and rescue in disasters can be used as a test-bed for multi-agent systems. The comparing experiments made clear that rescue task is not well defined in spite of its practical importance, and planning based on multi-perspectives on disaster losses is necessary. It points that the rescue problem is not only a test-bed for multi-agent system but also for laboratory work for practical system.
Takahashi, Y., Ikenoue, S., Inui, S., Hikita, K., Katoh, Y. & Asada, M.

Osaka University "Trackies 2001


2002 RoboCup 2001: Robot Soccer World Cup V, pp. 61-81 inproceedings

DOI URL

Abstract: This is the team description of Osaka University “Trackies” for RoboCup2001. The hardware and software architecture are presented.
Takahashi, Y., Tamura, T. & Asada, M.

Strategy Learning for a Team in Adversary Environments


2002 RoboCup 2001: Robot Soccer World Cup V, pp. 155-191 inproceedings

DOI URL

Abstract: Team strategy acquisition is one of the most important issues of multiagent systems, especially in an adversary environment. RoboCup has been providing such an environment for AI and robotics researchers. A deliberative approach to the team strategy acquisition seems useless in such a dynamic and hostile environment. This paper presents a learning method to acquire team strategy from a viewpoint of coach who can change a combination of players each of which has a fixed policy. Assuming that the opponent has the same choice for the team strategy but keeps the fixed strategy during one match, the coach estimates the opponent team strategy (player’s combination) based on game progress (obtained and lost goals) and notification of the opponent strategy just after each match. The trade-off between exploration and exploitation is handled by considering how correct the expectation in each mode is. A case of 2 to 2 match was simulated and the final result (a class of the strongest combinations) was applied to RoboCup-2000 competition.
Thomas, J., Yoshimura, K. & Peel, A.

Roobots


2002 RoboCup 2001: Robot Soccer World Cup V, pp. 155-166 inproceedings

DOI URL

Abstract: This paper describes the Roobots small league RoboCup team from the University of Melbourne which competed in Robocup 2001, Seattle. The highlights from our team included an omnidirectional drive mechanism, an integrated dribbling and kicking mechanism, a robust vision system and communications system and a BDI agent oriented stategy module.
Tu, K.-Y.

Design and Implementation of a Soccer Robot with Modularized Control Circuits


2002 RoboCup 2001: Robot Soccer World Cup V, pp. 1-15 inproceedings

DOI URL

Abstract: RoboCup is designed to evaluate various theories, algorithms, and architectures for new challenges of Artificial Intelligent (AI) research. New challenges will import new functions into a soccer robot. Thus, a soccer robot with modularized control circuits is proposed to conveniently add new functions for further challenges. At present, the designed soccer robot, based on circuit function, has five modules: processor module, radio communication module, input/output module, supersonic module and extensible module. Five modules are together connected via Industry Architecture Standard bus (ISA bus) in extensible module. In addition, the motion planning of a soccer robot for kicking the ball is formularized to shoot goal. Experiment is also included.
Uchibe, E., Yanase, M. & Asada, M.

Evolutionary Behavior Selection with Activation/Termination Constraints


2002 RoboCup 2001: Robot Soccer World Cup V, pp. 51-71 inproceedings

DOI URL

Abstract: In order to obtain the feasible solution in the realistic learning time, a layer architecture is often introduced. This paper proposes a behavior selection mechanism with activation/termination constraints. In our method, each behavior has three components: policy, activation constraints, and termination constraints. A policy is a function mapping the sensor information to motor commands. Activation constraints reduce the number of situations where corresponding policy is executable, and termination constraints contribute to extract meaningful behavior sequences, each of which can be regarded as one action regardless of its duration. We apply the genetic algorithm to obtain the switching function to select the appropriate behavior according to the situation. As an example, a simplified soccer game is given to show the validity of the proposed method. Simulation results and real robots experiments are shown, and a discussion is given.
Ushimi, N., Yamamoto, M., Inoue, J., Sugimoto, T., Araoka, M., Matsuoka, T., Kiriki, T., Yamaguchi, Y., Hasegawa, T. & Mohri, A.

On-Line Navigation of Mobile Robot Among Moving Obstacles Using Ultrasonic Sensors


2002 RoboCup 2001: Robot Soccer World Cup V, pp. 121-154 inproceedings

DOI URL

Abstract: This paper proposes a realistic on-line navigation method of the mobile robot in dynamical environment where multiple obstacles are always changing their velocities. Considering characteristics of actual sensor system, a method to estimate the velocity of moving obstacles is presented. The estimated velocity and measured distance from the nearest obstacle are used to plan a velocity of mobile robot based on a new idea of Collision Possibility Cone(CPC). Then an on-line navigation method is proposed by using CPC and feasible velocity space of mobile robot. Simulational examples show an effectiveness of the new navigation.
Uther, W., Lenser, S., Bruce, J., Hock, M. & Veloso, M.

CM-Pack'01: Fast Legged Robot Walking, Robust Localization, and Team Behaviors


2002 RoboCup 2001: Robot Soccer World Cup V, pp. 1-26 inproceedings

DOI URL

Abstract: CM-Pack’01 came in second place at RoboCup-2001 in the Sony Legged League. This is our fourth year competiting in this league. We used a simplified architecture this year. Our vision, localization, and behaviors ran synchronously with the camera input while our motions remained an asynchronous process. We focused on reducing latency and increasing timeliness and completeness of environment modelling for this year. We used more structured software engineering this year than in previous years and found this very useful[4].
Utz, H., Mayer, G., Maschke, D., Neubeck, A., Schaeffer, P., Baer, P., Baetge, I., Fischer, J., Holzer, R., Lauer, M., Reisser, A., Sterk, F., Palm, G. & Kraetzschmar, G.

The Ulm Sparrows 2001


2002 RoboCup 2001: Robot Soccer World Cup V, pp. 391-419 inproceedings

DOI URL

Abstract: The Ulm Sparrows team is a student-oriented, interdisciplinary research effort at the University of Ulm. The team is active in both the simulation and the middle-size league, but simulation efforts are targeted towards supporting the middle-size league robot team. We competed in the RoboCup World Championships in Paris (1998) [5] and Stockholm (1999, quarterfinals) [7], the European RoboCup Championships in Amsterdam (2000, semifinals) [4], plus a number of national events in Germany. For time and budget constraints, we could not participate in Melbourne in 2000.
Wang, H., Wang, H., Wang, C. & Soh, W.Y.C.

Cooperation-Based Behavior Design


2002 RoboCup 2001: Robot Soccer World Cup V, pp. 237-289 inproceedings

DOI URL

Abstract: Robot soccer explores such a research topic that multiple agents work together in a Real-time, Cooperative and Adversarial (RCA) environment to achieve specific objectives. It requires that each agent can not only deal with situations individually, but also present cooperation with its teammates. In this paper, we describe a robot architecture, which addresses ”scaling cooperation” among robots, and meanwhile allows each robot to make decisions independently in real-time case. The architecture is based on “ideal cooperation” principle and implemented for Small Robot League in RoboCup. Experimental results prove its effectiveness and reveal several primary characteristics of behaviors in robot soccer.
Wang, H., Wang, H., Wang, C. & Soh, W.Y.C.

Multi-Platform Soccer Robot Development System


2002 RoboCup 2001: Robot Soccer World Cup V, pp. 1-7 inproceedings

DOI URL

Abstract: Robot soccer is a challenging research domain, which involves multiple agents (physical robots or ”softbots”) to work together in a dynamic, noisy, cooperative and adversarial environment to achieve specific objectives. The paper focuses on the design and implementation of an effective system for developing a small-size physical soccer team for the competition of RoboCup. There are three goals preset in our research, that is, robust individual behaviors, controllable cooperation and behavioral learning. The system is therefore required to collect data in real-time situations and repeat experiments accurately, which are found difficult to be achieved in pure physical or simulated case. A distinct feature of our system is that it is a close combination of three functional parts: physical test platform, simulation platform and measurement platform, which support each other to overcome many defects inherent in traditional physical system or simulation system.
Weigel, T., Kleiner, A., Diesch, F., Dietl, M., Gutmann, J.-S., Nebel, B., Stiegeler, P. & Szerbakowski, B.

CS Freiburg 2001


2002 RoboCup 2001: Robot Soccer World Cup V, pp. 107-129 inproceedings

DOI URL

Abstract: The CS Freiburg team has become F2000 champion the third time in the history of RoboCup. The success of our team can probably be attributed to its robust sensor interpretation and its team play. In this paper, we will focus on new developments in our vision system, in our path planner, and in the cooperation component.
This work has been partially supported by Deutsche Forschungsgemeinschaft (DFG), by Medien- und Filmgesellschaft Baden-Württemberg mbH (MFG), by SICK AG and Sony Corporation
Wyeth, G., Ball, D., Cusack, D. & Ratnapala, A.

UQ RoboRoos: Achieving Power and Agility in a Small Size Robot


2002 RoboCup 2001: Robot Soccer World Cup V, pp. 99-133 inproceedings

DOI URL

Abstract: The UQ RoboRoos have been developed to participate in the RoboCup robot soccer small size league over several years. RoboCup 2001 saw a focus on the mechanical design of the RoboRoos, with the introduction of an omni-directional drive system and a high power kicker. The change in mechanical design had implications for the rest of the system particularly navigation and multi-robot planning. In addition, the overhead vision system was upgraded to improve reliability and robustness.
Wyeth, G., Venz, M., Mayfield, H., Akiyama, J. & Heathwood, R.

UQ CrocaRoos: An Initial Entry to the Simulation League


2002 RoboCup 2001: Robot Soccer World Cup V, pp. 45-76 inproceedings

DOI URL

Abstract: The UQ CrocaRoos entered the RoboCup Simulation League for the first time in 2001. The team demonstrated many of the basic functions required to play the simulated game: vision, action and multi-agent planning. The design of the team extends many of the concepts developed for the real robot leagues. This paper describes the fundamental architecture of the team, and the principles for developing the team in the future.
Yamasaki, F., Endo, K., Asada, M. & Kitano, H.

A Control Method for Humanoid Biped Walking with Limited Torque


2002 RoboCup 2001: Robot Soccer World Cup V, pp. 1-4 inproceedings

DOI URL

Abstract: This paper presents an energy-efficient biped walking method that has been implemented in a low-cost humanoid platform, PINO, for various research purposes. For biped walking robots with low torque actuators, a control method that enables biped walking with low torque is one of the most important problems. While many humanoids use high-performance motor systems to attain stable walking, such motor systems tend to be very expensive. Motors that are affordable for many researchers have only limited torque and accuracy. Development of a method that allows biped walking using low-cost components would have a major impact on the research community as well as industry. From the view point of high energy-efficiency, many researchers have studied a simple planar walker without any control torque. Their walking motions, however, are decided by the relationship between a gravity potential effect and structural parameters of their robots. Thus, there is no control of walking behaviors such as speed and dynamic change in step size. In this paper, we propose a control method using the moment of inertia of the swing leg at the hip joint, and confirm that a robot controlled by this method can change its walking speed when the moment of inertia of the swing leg at the hip joint is changed without changing the step length. Finally, we apply this control method to the PINO model with torso in computational simulations, and confirm that the method enables stable walking with limited torque.
Yao, J., Chen, J., Cai, Y. & Li, S.

Architecture of TsinghuAeolus


2002 RoboCup 2001: Robot Soccer World Cup V, pp. 103-129 inproceedings

DOI URL

Abstract: RoboCup Simulation Server provides a wonderful challenge for all the participants. This paper explains key technology implemented by Tsinghuaeolus RoboCup team played in RoboCup environment, including basic adversarial skills, which is developed by using Dynamic Programming in combination with heuristic search algorithm, and reactive strategy architecture. Tsinghuaeolus was the winner of RoboCup2001.
Yoshida, K., Tsuzaki, R., Kougo, J., Okabe, T., Kurihara, N., Sakai, D., Hayashi, R. & Fujii, H.

Team Description Eigen


2002 RoboCup 2001: Robot Soccer World Cup V, pp. 1-43 inproceedings

DOI URL

Abstract: EIGEN participates in RoboCup at World Meeting for the first time. Our team provides three robots of the same type and one goalkeeper robot. Our aim is to realize a cooperative team play among robots as well as high performance of robot relating to image processing, decision making of behaviors, and motion control. As a first step, we realized a motion control for a field-player robot by the Fuzzy control method and cooperative behaviors by a wireless LAN.
Yuen, A.

Lazarus Team Description


2002 RoboCup 2001: Robot Soccer World Cup V, pp. 301-338 inproceedings

DOI URL

Abstract: This paper describes the Lazarus team that participated in the RoboCup Simulation League in 2001. It is characterized by tight formation of players during play. The purpose is to provide data for training the coach in recognizing team formations using neural networks.