RoboCup 2009 Publications

From RoboCup Wiki
Revision as of 09:15, 7 February 2012 by Asad (talk | contribs) (Created page with "{| id="qstable" border="1" ! width="20%" | Author ! width="30%" | Title ! width="5%" | Year ! width="30%" | Journal/Proceedings ! width="10%" | Reftype ! width="5%" | DOI/URL |- ...")

(diff) ← Older revision | Latest revision (diff) | Newer revision → (diff)
Jump to: navigation, search
Author Title Year Journal/Proceedings Reftype DOI/URL
Ashkan Radmand, E.N. & Goodarzi, M.

Integrated Genetic Algorithmic and Fuzzy Logic Approach for Decision Making of Police Force Agents in Rescue Simulation Environment

2010 RoboCup 2009: Robot Soccer World Cup XIII, pp. 288-295 inproceedings


Abstract: The major task of police force agents in rescue simulation environment is to connect the isolated parts of the city. To achieve this goal, the best blocked roads should be chosen to clear. This selection is based on some issues such as number of burning buildings and victims existing in the mentioned parts. A linear combination of these factors is essential to determine a priority for each road. In this paper we propose an integrated Genetic Algorithm (GA) and Fuzzy Logic approach to optimize the combination statement. The parameters are learned via GA for some training maps. Then, because of differences between test and train maps, the agent should decide which parameters to choose according to the new map. The agents’ decision is based on similarity measures between characteristics of maps using Fuzzy Logic. After utilizing this method, the simulation score increased between 2% and 7% in 20 test maps.
Dirk Holz, G.K.K. & Rome, E.

Robust and Computationally Efficient Navigation in Domestic Environments

2010 RoboCup 2009: Robot Soccer World Cup XIII, pp. 104-115 inproceedings


Abstract: Presented in this paper is a complete system for robust autonomous navigation in cluttered and dynamic environments. It consists of computationally efficient approaches to the problems of simultaneous localization and mapping, path planning, and motion control, all based on a memory-efficient environment representation. These components have been implemented and integrated with additional components for human-robot interaction and object manipulation on a mobile manipulation platform for service robot applications. The resulting system performed very successfully in the 2008 RoboCup@Home competition.
Dorer, K.

Modeling Human Decision Making Using Extended Behavior Networks

2010 RoboCup 2009: Robot Soccer World Cup XIII, pp. 81-91 inproceedings


Abstract: In their famous work on prospect theory Kahneman and Tversky have presented a couple of examples where human decision making deviates from rational decision making as defined by decision theory. This paper describes the use of extended behavior networks to model human decision making in the sense of prospect theory. We show that the experimental findings of non-rational decision making described by Kahneman and Tversky can be reproduced using a slight variation of extended behavior networks.
Evan Wong, W.L. & Chen, X.

Connecting the Real World with the Virtual World - Controlling AIBO through Second Life

2010 RoboCup 2009: Robot Soccer World Cup XIII, pp. 402-413 inproceedings


Abstract: The main aim of this project is to develop middleware so that the Second Life online virtual space (virtual world) can be used to simulate and control the movements of a Sony AIBO robot (real world) in a wireless environment. This paper details the design of an immersive teleoperation system, and the rationale behind the design. The prototype proves that the concept of teleoperation with greater sense of immersion is achievable and can lead to future work in application domains such as smart home and immersive remote operating machinery in the industry such as mining.
Fares Alnajar, H.N. & Visser, A.

Coordinated Action in a Heterogeneous Rescue Team

2010 RoboCup 2009: Robot Soccer World Cup XIII, pp. 1-10 inproceedings


Abstract: In this paper we describe a new approach to make use of a heterogeneous robot team for the RoboCup Rescue League Virtual Robot competition. We will demonstrate coordinated action between a flying and a ground robot. The flying robot is used for fast exploration and allows the operator to find the places where victims are present in the environment. Due to the fast aggregation of the location error in the flying robot no precise location of the victim is known. It is the task of the ground robot to autonomously go the point of interest and to get an accurate location of the victim, which can be used by human rescue workers to save the victim. The benefit of this approach is demonstrated in a small number of experiments. By integrating the abilities of the two robots the team’s performance is improved.
Frederico Santos, Luís Almeida, L.S.L.J.L.A. & Cunha, M.B.

Communicating among Robots in the RoboCup Middle-Size League

2010 RoboCup 2009: Robot Soccer World Cup XIII, pp. 320-331 inproceedings


Abstract: The RoboCup Middle-Size League robotic soccer competitions pose a real cooperation problem for teams of mobile autonomous robots. In the current state-of-practice cooperation is essential to overcome the opponent team and thus a wireless communication protocol and associated middleware are now fundamental components in the multi-robots system architecture. Nevertheless, the wireless communication has relatively low reliability and limited bandwidth. Since it is shared by both teams, it is a fundamental resource that must be used parsimoniously. Curiously, to the best of our knowledge, no previous study on the effective use of the wireless medium in actual game situations was done. In this paper we show how current teams use the wireless medium and we propose a set of best practices towards a more efficient utilization. Then, we present a communication protocol and middleware that follow such best practices and have been successfully used by one particular MSL team in the past four years.
Harald Altinger, Stefan J. Galler, S.M.-K.G.S.F.W. & Zangl, H.

Concept Evaluation of a Reflex Inspired Ball Handling Device for Autonomous Soccer Robots

2010 RoboCup 2009: Robot Soccer World Cup XIII, pp. 11-22 inproceedings


Abstract: This paper presents a concept evaluation for a passive ball handling device for autonomous robots that enables the robot to ”feel” the ball. A combination of a capacitive and a pressure sensor delivers accurate information of the ball position and movement within the ball handling device - even without touching it. Inspired by the human reflex the sensor values are evaluated to implement a low-level based control loop. This should enable the robot to make minor movement corrections to the overall path calculated by the high-level control system.
Havoutis, I. & Ramamoorthy, S.

Motion Synthesis through Randomized Exploration on Submanifolds of Configuration Space

2010 RoboCup 2009: Robot Soccer World Cup XIII, pp. 92-103 inproceedings


Abstract: Motion synthesis for humanoid robot behaviours is made difficult by the combination of task space, joint space and kinodynamic constraints that define realisability. Solving these problems by general purpose methods such as sampling based motion planning has involved significant computational complexity, and has also required specialised heuristics to handle constraints. In this paper we propose an approach to incorporate specifications and constraints as a bias in the exploration process of such planning algorithms. We present a general approach to solving this problem wherein a subspace, of the configuration space and consisting of poses involved in a specific task, is identified in the form of a nonlinear manifold, which is in turn used to focus the exploration of a sampling based motion planning algorithm. This allows us to solve the motion planning problem so that we synthesize previously unseen paths for novel goals in a way that is strongly biased by known good or feasible paths, e.g., from human demonstration. We demonstrate this result with a simulated humanoid robot performing a number of bipedal tasks.
Heikow Bülow, A.B. & Feyzabadi, S.

Creating Photo Maps with an Aerial Vehicle in USARsim

2010 RoboCup 2009: Robot Soccer World Cup XIII, pp. 35-45 inproceedings


Abstract: Photo maps, i.e., 2D grids that provide a large scale bird’s eye view of the environment, are of interest for many application scenarios but especially for safety and security missions. We present a very efficient and robust algorithm for this task, which only uses registration between consecutive images, i.e., it does not require any localization. The algorithm is benchmarked in USARsim, where the video stream of a down-looking camera of an aerial vehicle, namely a blimb, is used to generate a large scale photo map.
Huimin Lu, Hui Zhang, S.Y. & Zheng, Z.

A Novel Camera Parameters Auto-adjusting Method Based on Image Entropy

2010 RoboCup 2009: Robot Soccer World Cup XIII, pp. 192-203 inproceedings


Abstract: How to make vision system work robustly under dynamic light conditions is still a challenging research focus in robot vision community. In this paper, a novel camera parameters auto-adjusting method based on image entropy is proposed. Firstly image entropy is defined and its relationship with camera parameters is verified by experiments. Then how to optimize the camera parameters based on image entropy is proposed to make robot vision adaptive to the different light conditions. The algorithm is tested using the omnidirectional vision system in indoor RoboCup Middle Size League environment and outdoor RoboCup-like environment, and the results show that our method is effective and color constancy to some extent can be achieved.
J. Martínez-Gómez, J.A. Gámez, I.G.-V. & Matellán, V.

Using Genetic Algorithms for Real-Time Object Detection

2010 RoboCup 2009: Robot Soccer World Cup XIII, pp. 215-227 inproceedings


Abstract: This article presents a new approach to mobile robot vision based on genetic algorithms. The major contribution of this proposal is the real-time adaptation of genetic algorithms, which are generally used offline. In order to achieve this goal, the execution time must be as short as possible. The scope of this system is the Standard Platform category of the RoboCup soccer competition. The system developed detects and estimates distance and orientation to key elements on a football field, such as the ball and goals. Different experiments have been carried out within an official RoboCup environment.
J. Ruiz-del-Solar, M. Mascaró, M.C.F.B.R.R. & Verschae, R.

Analyzing the Human-Robot Interaction Abilities of a General-Purpose Social Robot in Different Naturalistic Environments

2010 RoboCup 2009: Robot Soccer World Cup XIII, pp. 308-319 inproceedings


Abstract: The main goal of this article is to report and analyze the applicability of a general-purpose social robot, developed in the context of the RoboCup @Home league, in three different naturalistic environments: (i) home, (ii) school classroom, and (iii) public space settings. The evaluation of the robot’s performance relies on its degree of social acceptance, and its abilities to express emotions and to interact with humans using human-like codes. The reported experiments show that the robot has a large acceptance from expert and non-expert human users, and that it is able to successfully interact with humans using human-like interaction mechanisms, such as speech and visual cues (particularly face information). It is remarkable that the robot can even teach children in a real classroom.
Jann Poppinga, A.B. & Pathak, K.

A Characterization of 3D Sensors for Response Robots

2010 RoboCup 2009: Robot Soccer World Cup XIII, pp. 264-275 inproceedings


Abstract: Sensors that measure range information not only in a single plane are becoming more and more important for mobile robots, especially for applications in unstructured environments like response missions where 3D perception and 3D mapping is of interest. Three such sensors are characterized here, namely a Hokuyo URG-04LX laser scanner actuated with a servo in a pitching motion, a Videre STOC stereo camera and a Swissranger SR-3000. The three devices serve as prototypical examples of the according technologies, i.e., 3D laser scanners, stereo vision and time-of-flight cameras.
Johannes Strom, G.S. & Chown, E.

Omnidirectional Walking Using ZMP and Preview Control for the NAO Humanoid Robot

2010 RoboCup 2009: Robot Soccer World Cup XIII, pp. 378-389 inproceedings


Abstract: Fast-paced dynamic environments like robot soccer require highly responsive and dynamic locomotion. We present an implementation of an omnidirectional ZMP-based walk engine for the Nao robot. Using a simple inverted pendulum model, a preview controller generates dynamically balanced center of mass trajectories. To enable path planning, we introduce a system of global and egocentric coordinate frames to define step placement. These coordinate frames allow translation of the CoM trajectory, given by the preview controller, into leg actions. Walk direction can be changed quickly to suit a dynamic environment by adjusting the future step pattern.
João Silva, Nuno Lau, J.R.J.L.A. & Neves, A.J.R.

Sensor and Information Fusion Applied to a Robotic Soccer Team

2010 RoboCup 2009: Robot Soccer World Cup XIII, pp. 366-377 inproceedings


Abstract: This paper is focused on the sensor and information fusion techniques used by a robotic soccer team. Due to the fact that the sensor information is affected by noise, and taking into account the multi-agent environment, these techniques can significantly improve the accuracy of the robot world model. One of the most important elements of the world model is the robot self-localisation. Here, the team localisation algorithm is presented focusing on the integration of visual and compass information. To improve the ball position and velocity reliability, two different techniques have been developed. A study of the visual sensor noise is presented and, according to this analysis, the resulting noise variation depending on the distance is used to define a Kalman filter for ball position. Moreover, linear regression is used for velocity estimation purposes, both for the ball and the robot. This implementation of linear regression has an adaptive buffer size so that, on hard deviations from the path (detected using the Kalman filter), the regression converges more quickly. A team cooperation method based on sharing of the ball position is presented. Besides the ball, obstacle detection and identification is also an important challenge for cooperation purposes. Detecting the obstacles is ceasing to be enough and identifying which obstacles are team mates and opponents is becoming a need. An approach for this identification is presented, considering the visual information, the known characteristics of the team robots and shared localisation among team members. The same idea of distance dependent noise, studied before, is used to improve this identification. Some of the described work, already implemented before RoboCup2008, improved the team performance, allowing it to achieve the 1st place in the Portuguese robotics open Robótica2008 and in the RoboCup2008 world championship.
Kalyanakrishnan, S. & Stone, P.

Learning Complementary Multiagent Behaviors: A Case Study

2010 RoboCup 2009: Robot Soccer World Cup XIII, pp. 153-165 inproceedings


Abstract: As machine learning is applied to increasingly complex tasks, it is likely that the diverse challenges encountered can only be addressed by combining the strengths of different learning algorithms. We examine this aspect of learning through a case study grounded in the robot soccer context. The task we consider is Keepaway, a popular benchmark for multiagent reinforcement learning from the simulation soccer domain. Whereas previous successful results in Keepaway have limited learning to an isolated, infrequent decision that amounts to a turn-taking behavior (passing), we expand the agents’ learning capability to include a much more ubiquitous action (moving without the ball, or getting open), such that at any given time, multiple agents are executing learned behaviors simultaneously. We introduce a policy search method for learning “GetOpen” to complement the temporal difference learning approach employed for learning “Pass”. Empirical results indicate that the learned GetOpen policy matches the best hand-coded policy for this task, and outperforms the best policy found when Pass is learned. We demonstrate that Pass and GetOpen can be learned simultaneously to realize tightly-coupled soccer team behavior.
Kouki Shimada, Y.T. & Asada, M.

Efficient Behavior Learning by Utilizing Estimated State Value of Self and Teammates

2010 RoboCup 2009: Robot Soccer World Cup XIII, pp. 355-365 inproceedings


Abstract: Reinforcement learning applications to real robots in multi-agent dynamic environments are limited because of huge exploration space and enormously long learning time. One of the typical examples is a case of RoboCup competitions since other agents and their behavior easily cause state and action space explosion.
This paper presents a method that utilizes state value functions of macro actions to explore appropriate behavior efficiently in a multi-agent environment by which the learning agent can acquire cooperative behavior with its teammates and competitive ones against its opponents.
The key ideas are as follows. First, the agent learns a few macro actions and the state value functions based on reinforcement learning beforehand. Second, an appropriate initial controller for learning cooperative behavior is generated based on the state value functions. The initial controller utilizes the state values of the macro actions so that the learner tends to select a good macro action and not select useless ones. By combination of the ideas and a two-layer hierarchical system, the proposed method shows better performance during the learning than conventional methods.
This paper shows a case study of 4 (defense team) on 5 (offense team) game task, and the learning agent (a passer of the offense team) successfully acquired the teamwork plays (pass and shoot) within shorter learning time.
Kyrylov, V. & Hou, E.

Pareto-Optimal Collaborative Defensive Player Positioning in Simulated Soccer

2010 RoboCup 2009: Robot Soccer World Cup XIII, pp. 179-191 inproceedings


Abstract: The ability by the simulated soccer player to make rational decisions about moving without ball is a critical factor of success. In this study the focus is placed on the defensive situation, when the ball is controlled by the opponent team in 2D simulated soccer. Methods for finding good defensive positions by the robotic soccer players have been investigated by some RoboCup scholars. Although soccer teams using these methods have proved to be reasonably good, the collaboration issue in defense has been overlooked. In this paper, we demonstrate that collaboration in defense yields better results. In doing so, we treat optimal defensive positioning as a multi-criteria assignment problem and propose a systematic approach for solving it. Besides achieving better performance, this makes it possible to gracefully balance the costs and rewards involved in defensive positioning.
Luis Paulo Reis, Rodrigo A.M. Braga, M.S. & Moreira, A.P.

IntellWheels MMI: A Flexible Interface for an Intelligent Wheelchair

2010 RoboCup 2009: Robot Soccer World Cup XIII, pp. 296-307 inproceedings


Abstract: With the rising concern about the needs of people with physical disabilities and with the aging of the population there is a major concern of creating electronic devices that may improve the life of the physically handicapped and elderly person. One of these new solutions passes through the adaptation of electric wheelchairs in order to give them environmental perception, more intelligent capabilities and more adequate Human – Machine Interaction. This paper focuses in the development of a user-friendly multimodal interface, which is integrated in the Intellwheels project. This simple multimodal human-robot interface developed allows the connection of several input modules, enabling the wheelchair control through flexible input sequences of distinct types of inputs (voice, facial expressions, head movements, keyboard and, joystick). The system created is capable of storing user defined associations, of input’s sequences and corresponding output commands. The tests performed have proved the system efficiency and the capabilities of this multimodal interface.
Malmir, M. & Shiry, S.

Object Recognition with Statistically Independent Features: A Model Inspired by the Primate Visual Cortex

2010 RoboCup 2009: Robot Soccer World Cup XIII, pp. 204-214 inproceedings


Abstract: Human can perform object recognition with high accuracy under a variety of object rotations and translations. The structure and function of the visual cortex has inspired many models for invariant object recognition. In this paper, we propose a hierarchical model for object recognition based on the two well-known properties of the visual cortex neurons: invariant responses to stimulus transformations and redundancy reduction. We used the trace learning rule to provide the neurons in the model with invariant responses to object transformations. In hierarchical neural networks, neighboring neurons are tuned to similar features because their receptive fields in the image overlap. This similarity results in a form of redundancy in neuronal responses. We used a variant of divisive normalization mechanism to increase the efficiency of responses of neurons in the model. Results of experiments demonstrate the high recognition rates of the proposed model.
Masaru Okaya, S.Y. & Takahashi, T.

A Hybrid Agent Simulation System of Rescue Simulation and USARSim Simulations from Going to Fire-Escape Doors to Evacuation to Shelters

2010 RoboCup 2009: Robot Soccer World Cup XIII, pp. 414-424 inproceedings


Abstract: Disaster & rescue simulations handle complex social issues, the macro level modeling of which is difficult. Agent-based social simulation provides a platform to simulate such social issues. It is ideal that the simulations cover various evacuation patterns and the results are used to make effective plans against disasters. This requires that the behaviors of a numbers of heterogeneous agents are simulated at urban size areas in hostile environments. Representing all buildings of the area by 3D model requires a large amount of computer resources and computing the behaviors of a number of agents takes a lot of computation time. These make it difficult to simulate rescue behaviors at disasters in real scale.
We propose a hybrid agent simulation system that switches systems that is suitable for situations during simulations. A hybrid system of two simulations with different time and space resolution makes it possible to simulate urban size human behaviors and indoor movements with less computational resources than doing by one system. This paper presents protocols that connect two systems that are used in RoboCup Rescue Simulation League, Rescue Agent Simulation and USARSim. The prototype system provides a simulation of people’s evacuation from going to fire-escape doors to moving to shelters.
Mauricio Correa, Javier Ruiz-del-Solar, R.V.J.L.-F. & Castillo, N.

Real-Time Hand Gesture Recognition for Human Robot Interaction

2010 RoboCup 2009: Robot Soccer World Cup XIII, pp. 46-57 inproceedings


Abstract: In this article a hand gesture recognition system that allows interacting with a service robot, in dynamic environments and in real-time, is proposed. The system detects hands and static gestures using cascade of boosted classifiers, and recognize dynamic gestures by computing temporal statistics of the hand’s positions and velocities, and classifying these features using a Bayes classifier. The main novelty of the proposed approach is the use of context information to adapt continuously the skin model used in the detection of hand candidates, to restrict the image’s regions that need to be analyzed, and to cut down the number of scales that need to be considered in the hand-searching and gesture-recognition processes. The system performance is validated in real video sequences. In average the system recognized static gestures in 70% of the cases, dynamic gestures in 75% of them, and it runs at a variable speed of 5-10 frames per second.
Michael de Denus, J.A. & Baltes, J.

Heuristic Formation Control in Multi-robot Systems Using Local Communication and Limited Identification

2010 RoboCup 2009: Robot Soccer World Cup XIII, pp. 437-448 inproceedings


Abstract: Groups of individuals often use formations as a means of providing orderly movement while distributing members in a manner that is advantageous to the group’s activities. A particular formation may offer a defensive advantage over moving individually, for example, exposing only some of the agents to the proximity of enemies, or might increase group abilities by allowing individuals to limit perceptual focus to one small part of the environment. Formations are used throughout the natural world and in many organized human groups, and are equally valuable to multi-robot systems. Most formation control in multi-robot systems is extremely limited compared to the formations we see in nature: formations are precisely defined, and mechanisms for forming and maintaining formations often require unique labels for individuals and broadcast communication. In this paper, we explore a method for creating heuristic formations - where agents create an overall formation, but forgiveness exists for small variations in form - using only local rules for creating formations and allowing only local communication. Our approach defines relative positions in terms of a probability given the position of one’s nearest neighbor, and improves on prior work by assuming that all agents do not begin knowing the unique labels of others in the group. The approach also assumes heterogeneity in sensing, in that agents may not be able to perceive the unique labels of others, and thus may require assistance from those who can. This assumptions make formations robust to the failure of individual agents, and allow previously unknown agents to join an existing formation. An evaluation of this approach is illustrated using Player/Stage, a commonly accepted simulation package for multi-robot systems, for controlled experimentation.
Nima Shafii, Siavash Aslani, O.M.N. & Shiry, S.

Evolution of Biped Walking Using Truncated Fourier Series and Particle Swarm Optimization

2010 RoboCup 2009: Robot Soccer World Cup XIII, pp. 344-354 inproceedings


Abstract: Controlling a biped robot with a high degree of freedom to achieve stable and straight movement patterns is a complex problem. With growing computational power of computer hardware, high resolution real time simulation of such robot models has become more and more applicable. This paper presents a novel approach to generate bipedal gait for humanoid locomotion. This approach is based on modified Truncated Fourier Series (TFS) for generating angular trajectories. It is also the first time that Particle Swarm Optimization (PSO) is used to find the best angular trajectory and optimize TFS. This method has been implemented on Simulated NAO robot in Robocup 3D soccer simulation environment (rcssserver3d). To overcome inherent noise of the simulator we applied a Resampling algorithm which could lead the robustness in nondeterministic environments. Experimental results show that PSO optimizes TFS faster and better than GA to generate straighter and faster humanoid locomotion.
Pellenz, J. & Paulus, D.

Stable Mapping Using a Hyper Particle Filter

2010 RoboCup 2009: Robot Soccer World Cup XIII, pp. 252-263 inproceedings


Abstract: Often Particle Filters are used to solve the SLAM (Simultaneous Localization and Mapping) problem in robotics: The particles represent the possible poses of the robot, and their weight is determined by checking if the sensor readings are consistent with the so far acquired map. Mostly a single map is maintained during the exploration, and only with Rao-Blackwellized Particle Filters each particle carries its own map.
In this contribution, we propose a Hyper Particle Filter (HPF) – a Particle Filter of Particle Filters – for solving the SLAM problem in unstructured environments. Each particle of the HPF contains a standard Particle Filter (with a map and a set particles, that model the belief of the robot pose in this particular map). To measure the weight of a particle in the HPF, we developed two map quality measures that can be calculated automatically and do not rely on a ground truth map: The first map quality measure determines the contrast of the occupancy map. If the map has a high contrast, it is likely that the pose of the robot was always determined correctly before the map was updated, which finally leads to an overall consistent map. The second map quality measure determines the distribution of the orientation of wall pixels calculated by the Sobel operator. Using the model of a rectangular overall structure, slight but systematic errors in the map can be detected. Using the two measures, broken maps can automatically be detected. The corresponding particle is then more likely to be replaced by a particle with a better map within the HPF.
We implemented the approach on our robot “Robbie 12”, which will be used in the RoboCup Rescue league in 2009. We tested the HPF using the log files from last years RoboCup Rescue autonomy final, and with new data of a larger building. The quality of the generated maps outperformed our last years (league’s best) maps. With the data acquired in the larger structure, Robbie was able to close loops in the map. Due to a highly efficient implementation, the algorithm still runs online during the autonomous exploration.
Quinlan, M.J. & Middleton, R.H.

Multiple Model Kalman Filters: A Localization Technique for RoboCup Soccer

2010 RoboCup 2009: Robot Soccer World Cup XIII, pp. 276-287 inproceedings


Abstract: In the Standard Platform League (SPL) there are substantial sensor limitations due to the rapid motion of the camera, the limited field of view of the camera, and the limited number of unique landmarks. These limitations place high demands on the performance and robustness of localization algorithms. Most of the localization algorithms implemented in RoboCup fall broadly into the class of particle based filters or Kalman type filters including Extended and Unscented variants. Particle Filters are explicitly multi-modal and therefore deal readily with ambiguous sensor data. In this paper, we discuss multiple-model Kalman filters that also are explicitly multi-modal. Motivated by the RoboCup SPL, we show how they can be used despite the highly multi-modal nature of sensed data and give a brief comparison with a particle filter based approach to localization.
Rob Janssen, J. d.B. & van de Molengraft, R.

Real-Time Ball Tracking in a Semi-automated Foosball Table

2010 RoboCup 2009: Robot Soccer World Cup XIII, pp. 128-139 inproceedings


Abstract: In this article a method is proposed for ball tracking using 100 Hz computer vision in a semi-automated foosball table. In this application the behavior of the ball is highly dynamic with speeds up to 10 m/s and frequent bounces occur against the sides of the table and the puppets. Moreover, in the overhead camera view of the field the ball is often fully or partially occluded and there are other objects present that resemble the ball. The table is semi-automated to enable single user game play. This article shows that it is possible to perform fast and robust ball tracking by combining efficient image processing algorithms with a priori knowledge of the stationary environment and position information of the automated rods.
Rodrigo A.M. Braga, P.M. & Reis, L.P.

Development of a Realistic Simulator for Robotic Intelligent Wheelchairs in a Hospital Environment

2010 RoboCup 2009: Robot Soccer World Cup XIII, pp. 23-34 inproceedings


Abstract: Nowadays one can witness the increase of the world population carrying some kind of physical disability, affecting locomotion. With the objective of responding to numerous mobility problems, various intelligent wheelchair related projects have been created in the last years. The development of an Intelligent Wheelchair requires a lot of testing due to the complexity of the algorithms used and the obligation of achieving a failproof final product. This paper describes the some need for an Intelligent-Wheelchair specific simulator as well as the requirements of such a simulator. The simulator implementation, based on “Ciber-Mouse” simulator, is also described with emphasis on analyzing the limitations concerning intelligent wheelchair simulation using this adapted simulator. The changes applied on the existing software and the difficulties of robotic simulation development are described in detail. Experimental results are also presented showing that not only the simulator reveals flexible simulation capabilities but, also, enabled to validate the algorithms implemented in the physical intelligent wheelchair controlling agent.
Ryota Nakanishi, Junya Maeno, K.M. & Naruse, T.

An Approximate Computation of the Dominant Region Diagram for the Real-Time Analysis of Group Behaviors

2010 RoboCup 2009: Robot Soccer World Cup XIII, pp. 228-239 inproceedings


Abstract: This paper describes a method for a real-time calculation of a dominant region diagram (simply, a dominant region). The dominant region is proposed to analyze the features of group behaviors. It draws spheres of influence and is used to analyze a teamwork in the team sports such as soccer and handball. In RoboCup Soccer, particularly in small size league(SSL), the dominant region takes an important role to analyze the current situation in the game, and it is useful for evaluating the suitability of the current strategy. Another advantage of its real-time calculation is that it makes possible to predict a success or failure of passing. To let it work in a real environment, a real-time calculation of the dominant region is necessary. However, it takes 10 to 40 seconds to calculate the dominant region of the SSL’s field by using the algorithm proposed in [3]. Therefore, this paper proposes a real-time calculation algorithm of the dominant region. The proposing algorithm compute an approximate dominant region. The basic idea is (1) to make a reachable polygonal region for each time t 1, t 2, ... , t n , and (2) to synthesize it incrementally. Experimental result shows that this algorithm achieves about 1/1000 times shorter in computation time and 90% or more approximate accuracy compared with the algorithm proposed in [3]. Moreover, this technique can predict the success or failure of passing in 95% accuracy.
Santos, J. & Lima, P.

Multi-robot Cooperative Object Localization
Decentralized Bayesian Approach

2010 RoboCup 2009: Robot Soccer World Cup XIII, pp. 332-343 inproceedings


Abstract: We introduce a multi-robot/sensor cooperative object detection and tracking method based on a decentralized Bayesian approach which uses particle filters to avoid simplifying assumptions about the object motion and the sensors’ observation models. Our method is composed of a local filter and a team filter. The local filter receives a reduced dimension representation of its teammates’ sample belief about the object location, i.e., the parameters of a Gaussian Mixture Model (GMM) approximating the other sensors’ particles, and mixes the particles representing its own belief about the object location with particles sampling the received GMM. All particles are weighted by the local observation model and the best ones are re-sampled for the next local iteration. The team filter receives GMM representations of the object in the world frame, from the sensor teammates, and fuses them all performing Covariance Intersection among GMM components. The local estimate is used when the sensor sees the object, to improve its estimate from the teammates’ estimates. The team estimate is used when the sensor does not see the object alone. To prevent the fusion of incorrect estimates, the disagreement between estimates is measured by a divergence measure for GMMs. Results of the method application to real RoboCup MSL robots are presented.
Shivaram Kalyanakrishnan, Todd Hester, M.Q.Y.B. & Stone, P.

Three Humanoid Soccer Platforms: Comparison and Synthesis

2010 RoboCup 2009: Robot Soccer World Cup XIII, pp. 140-152 inproceedings


Abstract: In this article, we provide an overview of three humanoid soccer platforms currently in use at RoboCup: 3D simulation, the humanoid Standard Platform League (SPL), and the Webots-based simulator released with the SPL. Although these platforms trace different historical roots, today they share the same robot model, the Aldebaran Nao. Consequently, they face a similar set of challenges, primary among which is the need to develop reliable and robust bipedal locomotion. In this paper, we compare and contrast these platforms, drawing on the experiences of our team, UT Austin Villa, in developing agents for each of them. We identify specific roles for these three platforms in advancing the overarching goals of RoboCup.
Stefan Czarnetzki, S.K. & Klagges, D.

Combining Key Frame Based Motion Design with Controlled Movement Execution

2010 RoboCup 2009: Robot Soccer World Cup XIII, pp. 58-68 inproceedings


Abstract: This article presents a novel approach for motion pattern generation for humanoid robots combining the intuitive specification via key frames and the robustness of a ZMP stability controller. Especially the execution of motions interacting with the robot’s environment tends to result in very different stability behavior depending on the exact moment, position and force of interaction, thus providing problems for the classical replay of prerecorded motions. The proposed method is applied to several test cases including the design of kicking motions for humanoid soccer robots and evaluated in real world experiments which clearly show the benefit of the approach.
Stefan Czarnetzki, S.K. & Urbann, O.

Applying Dynamic Walking Control for Biped Robots

2010 RoboCup 2009: Robot Soccer World Cup XIII, pp. 69-80 inproceedings


Abstract: This article presents the application of a novel observer-based control system to achieve reactive motion generation for dynamic biped walking. The proposed approach combines a feedback controller with an online generated feet pattern to assure a stable gait. Experiments in a simulated environment as well as on real robots clearly demonstrate the robustness of the control system. The presented algorithms enable the robot not only to walk dynamically stable but also to cope with major internal disturbances like flaws of the robots internal model and external disturbances like uneven or unstable ground or collisions with objects or other robots.
Stefan Jacobs, Alexander Ferrein, S.S.D.B. & Lakemeyer, G.

Robust Collision Avoidance in Unknown Domestic Environments

2010 RoboCup 2009: Robot Soccer World Cup XIII, pp. 116-127 inproceedings


Abstract: Service robots operating in domestic indoor environments must be endowed with a safe collision avoidance and navigation method that is reactive enough to avoid contacts with the furniture of the apartment and humans that suddenly appear in front of the robot. Moreover, the method should be local, i.e. should not need a predefined map of the environment. In this paper we describe a navigation and collision avoidance method which is all of that: safe, fast, and local. Based on a geometric grid representation which is derived from the laser range finder of our domestic robot, a path to the next target point is found by employing A*. The obstacles which are used in the local map of the robot are extended depending on the speed the robot travels at. We compute a triangular area in front of the robot which is guaranteed to be free of obstacles. This triangle serves as the space of feasible solutions when searching for the next drive commands. With this triangle, we are able to decouple the path search from the search for drive commands, which tremendously decreases the complexity. We used the proposed method for several years in RoboCup@Home where it was a key factor to our success in the competitions.
Stefan Zickler, Tim Laue, O.B.M.W. & Veloso, M.

SSL-Vision: The Shared Vision System for the RoboCup Small Size League

2010 RoboCup 2009: Robot Soccer World Cup XIII, pp. 425-436 inproceedings


Abstract: The current RoboCup Small Size League rules allow every team to set up their own global vision system as a primary sensor. This option, which is used by all participating teams, bears several organizational limitations and thus impairs the league’s progress. Additionally, most teams have converged on very similar solutions, and have produced only few significant research results to this global vision problem over the last years. Hence the responsible committees decided to migrate to a shared vision system (including also sharing the vision hardware) for all teams by 2010. This system – named SSL-Vision – is currently developed by volunteers from participating teams. In this paper, we describe the current state of SSL-Vision, i.e. its software architecture as well as the approaches used for image processing and camera calibration, together with the intended process for its introduction and its use beyond the scope of the Small Size League.
Thomas Wisspeintner, Tijn van der Zan, L.I. & Schiffer, S.

RoboCup@Home: Results in Benchmarking Domestic Service Robots

2010 RoboCup 2009: Robot Soccer World Cup XIII, pp. 390-401 inproceedings


Abstract: Benchmarking robotic technologies is of utmost importance for actual deployment of robotic applications in industrial and every-day environments, therefore many efforts have recently focused on this problem. Among the many different ways of benchmarking robotic systems, scientific competitions are recognized as one of the most effective ways of rapid development of scientific progress in a field. The RoboCup@Home league targets the development and deployment of autonomous service and assistive robot technology, being essential for future personal domestic applications, and offers an important approach to benchmarking domestic and service robots.
In this paper we present the new methodology for benchmarking DSR adopted in RoboCup@Home, that includes the definition of multiple benchmarks (tests) and of performance metrics based on the relationships between key abilities required to the robots and the tests. We also discuss the results of our benchmarking approach over the past years and provide an outlook on short- and mid-term goals of Home and of DSR in general.
Tim Niemüller, A.F. & Lakemeyer, G.

A Lua-based Behavior Engine for Controlling the Humanoid Robot Nao

2010 RoboCup 2009: Robot Soccer World Cup XIII, pp. 240-251 inproceedings


Abstract: The high-level decision making process of an autonomous robot can be seen as an hierarchically organised entity, where strategical decisions are made on the topmost layer, while the bottom layer serves as driver for the hardware. In between is a layer with monitoring and reporting functionality. In this paper we propose a behaviour engine for this middle layer which, based on formalism of hybrid state machines (HSMs), bridges the gap between high-level strategic decision making and low-level actuator control. The behaviour engine has to execute and monitor behaviours and reports status information back to the higher level. To be able to call the behaviours or skills hierarchically, we extend the model of HSMs with dependencies and sub-skills. These Skill-HSMs are implemented in the lightweight but expressive Lua scripting language which is well-suited to implement the behaviour engine on our target platform, the humanoid robot Nao.
Vadim Kyrylov, M.C. & Ng, H.

Rollover as a Gait in Legged Autonomous Robots: A Systems Analysis

2010 RoboCup 2009: Robot Soccer World Cup XIII, pp. 166-178 inproceedings


Abstract: Rollover has been normally regarded as an undesirable way of legged robot locomotion. In spite of this, we are looking for the improved robot movement by combining the rollover with regular gaits. By considering gaits on the macro level, we identify the conditions when adding rollover may result in a faster movement of a legged robot. Our method is generic because the number of legs does not matter; we are taking into account only the features and constraints shared by all legged robots. As the outcome of this study, we propose a mathematical model for estimating the efficiency of using rollover as additional gait. This model is illustrated by evaluating the speed gain achieved in 4-legged Sony Aibo ERS-7 robot if it is equipped with a rollover skill. While having in our implementation the same linear speed as walking, rollover in some situations eliminates the need to make turns, thus saving time for the robot to change its pose.
Özkucur, N.E. & Akın, H.L.

Cooperative Multi-robot Map Merging Using Fast-SLAM

2010 RoboCup 2009: Robot Soccer World Cup XIII, pp. 449-460 inproceedings


Abstract: Multi-robot map merging is an essential task for cooperative robot navigation. In the realistic case, the robots do not know the initial positions of the others and this adds extra challenges to the problem. Some approaches search transformation parameters using the local maps and some approaches assume the robots will observe each other and use robot to robot observations. This work extends a previous work which is based on EKF-SLAM to the Fast-SLAM algorithm. The robots can observe each other and non-unique landmarks using visual sensors and merge maps by propagating uncertainty. Another contribution is the calibration of noise parameters with supervised data using the Evolutionary Strategies method. The developed algorithms are tested in both simulated and real robot experiments and the improvements and applicability of the developed methods are shown with the results.