Robot League

League Overview

Objective

The RoboCupRescue Robot League is an international league of teams with one objective: Develop and demonstrate advanced robotic capabilities for emergency responders using annual competitions to evaluate, and teaching camps to disseminate, best-in-class robotic solutions.

Approach

The league hosts annual competitions to 1) increase awareness of the challenges involved in deploying robots for emergency response applications such as urban search and rescue and bomb disposal, 2) provide objective performance evaluations of mobile robots operating in complex yet repeatable environments, and 3) promote collaboration between researchers. Robot teams demonstrate their capabilities in mobility, sensory perception, localization and mapping, mobile manipulation, practical operator interfaces, and assistive autonomous behaviors to improve remote operator performance and/or robot survivability while searching for simulated victims in a maze of terrains and challenges. Winning teams must reliably perform 7-10 missions of 20-30 minutes each from various start points to find the most victims. As robots continue to demonstrate successes against the obstacles posed in the arenas, the level of difficulty will continually be increased so the arenas provide a stepping-stone from the laboratory to the real world. Meanwhile, the annual competitions provide direct comparison of robotic approaches, objective performance evaluations, and a public proving ground for capable robotic systems that will ultimately be used to save lives.

Competition Vision

When disaster happens, minimize risk to search and rescue personnel while increasing victim survival rates by fielding teams of collaborative mobile robots which enable human rescuers to quickly locate and extract victims. Specific robotic capabilities encouraged in the competition include the following: 


• Negotiate compromised and collapsed structures
• Locate victims and ascertain their conditions
• Produce practical sensor maps of the environment
• Establish communications with victims
• Deliver fluids, nourishment, medicines
• Emplace sensors to identify/monitor hazards
• Mark or identify best paths to victims
• Provide structural shoring for responders

These tasks are encouraged through challenges posed in the arena, specific mission tasks, and/or the performance metric. Demonstrations of other enabling robotic capabilities are always welcome.

Search Scenario

A building has partially collapsed due to earthquake. The Incident Commander in charge of rescue operations at the disaster site, fearing secondary collapses from aftershocks, has asked for teams of robots to immediately search the interior of the building for victims. The mission for the robots and their operators is to find victims, determine their situation, state, and location, and then report back their findings in a map of the building with associated victim data. The section near the building entrance appears relatively intact while the interior of the structure exhibits increasing degrees of collapse. Robots must negotiate and map the lightly damaged areas prior to encountering more challenging obstacles and rubble. The robots are considered expendable in case of difficulty.

Field Description

The RoboCupRescue arenas constructed to host these competitions consist of emerging standard test methods for emergency response robots developed by the U.S. National Institute of Standards and Technology through the ASTM International Committee on Homeland Security Applications; Operational Equipment; Robots (E54.08.01). They are repeatable test method apparatuses that anybody can build and practice. The competition field is divided into color-coded arenas that form a continuum of challenges with increasing levels of difficulty for robots and operators and highlight certain robotic capabilities:

• Simulated Victims: Simulated victims with several signs of life such as form, motion, head, sound and CO2 are distributed throughout the arenas requiring directional viewing through access holes at different elevations.

• Yellow Arena: For robots capable of fully autonomous navigation and victim identification, this arena consists of random mazes of hallways and rooms with continuous 15° pitch and roll ramp flooring.

• Orange Arena: For robots capable of autonomous or remote teleoperative navigation and victim identification, this arena consists of moderate terrains with crossing 15° pitch and roll ramps and structured obstacles such as stairs, inclined planes, and others.

• Red Arena: For robots capable of autonomous or remote teleoperative navigation and victim identification, this arena consists of complex stepfield terrains requiring advanced robot mobility.

• Blue Arena: For robots capable of mobile manipulation on complex terrains to place simple block or bottle payloads carried in from the start or picked up within the arenas.

• Black/Yellow Arena (RADIO DROP-OUT ZONE): For robots capable of autonomous navigation with reasonable mobility to operate on complex terrains.

• Black Arena (Vehicle Collapse Scenario): For robots capable of searching a simulated vehicle collapse scenario accessible on each side from the RED ARENA and the ORANGE ARENA.
• Aerial Arena (< 2 KG, VTOL sUAS): For small unmanned aerial systems under 2 kg with vertical take-off and landing capabilities that can perform station-keeping, obstacle avoidance, and line following tasks with varying degrees of autonomy.

A detailed description of fields can be download from here. Detailed Field Description

Organization

• Trustees
  • Adam Jacoff, National Institute of Standards and Technology, USA (Trustee/League Chair 2010-2013)
  • Satoshi Tadokoro, Tohoku University, Japan (Trustee Emeritus)

• Executive Committee
  • Johannes Pellenz, University of Koblenz-Landau, Germany (Exec 2010-2013)
  • Tetsuya Kimura, Nagaoka Univ. of Technology, Japan (Exec 2011-2014)
  • Ehsan Mihankhah, K.N. Toosi University of Technology, Iran (Exec 2012-2015)
  • Jackrit Suthakorn, Mahidol University, Thailand (Exec 2011-2014)
  • Andreas Birk, International University Bremen, Germany (Exec Emeritus)

• Technical Committee
  • Gerald Steinbauer, Austria (TC 2012-2015)
  • Jafar Chegini,Iran (TC 2011-2014)
  • Sören Schwertfeger, Germany (TC 2011-2014)

• Organizing Committee
  • Dr. Gabriel Delgado Lopes, Netherlands (Local Chair 2013)
  • Ann Marie Virts, National Institute of Standards and Technology, USA (OC Chair 2011-2013)
  • Raymond Sheh, University of New South Wales (OC 2011-2013)
  • Amir H. Soltanzadeh Iran (OC 2013-2015)

Rules

RoboCup Rescue Complete Rule Book

• NEW 2013 Rules

2012 Additions

• QR codes (2012)

This year, we will attach QR codes (see http://en.wikipedia.org/wiki/QR_code) all over the arena. These will be used in a similar way to the way in which they were used in the German Open, see http://wiki.ssrrsummerschool.org/doku.php?id=robocup2012:qrcodes for examples of QR code placements as they appeared in the German Open.

QR codes are a measure of machine vision capabilities and coverage. There will be high resolution QR codes placed alongside victims, in similar locations as the existing hazardous materials labels and tumbling-E charts. There will also be large QR codes placed around the arena (around 70-100 or so) that robots will be expected to identify as they move around the arena. Both autonomous and teleoperated robots may score based on QR codes but QR code detection and identification must be performed autonomously.

It is NOT permitted for the operator to point the camera at a QR code and then push a button or execute a command (or point a camera phone at the screen!) to identify the code. Software, running either on the robot or on the OCU, must identify the code autonomously, decode it, display it in a window that is visible to the referee (a console window with the bottom few lines visible is acceptable) and save it to a file without operator intervention. Note that, of course, given that cameras usually have a limited field of view, it is acceptable for the operator to direct the camera at a QR code to ensure that it can be seen and (for this year at least) if necessary zoom the camera in.

A single QR code will be associated with each victim (along with the existing artifacts - tumbling E charts, hazmat labels and so-on). At first, the QR code will be approximately 50 x 50 mm to 70 x 70 mm in size, consist of 21 x 21 logical pixels encoded in UTF-8 with error correction level L. An example of such a code may be obtained from https://chart.googleapis.com/chart?cht=qr&chs=300x300&chld=L%7C0&choe=UTF-8&chl=VictimRoboCupMexicoCity2012 . They may become harder as the competition progresses. Points will be awarded for the robot observing, recognizing and decoding the code associated with the victim just as points are awarded for the Tumbling E charts and hazardous materials labels.

Sets of QR codes will be placed in semi-random locations around the arena to encourage teams to more fully explore the environment. These codes, which we call "landmarks", will be approximately 150 x 150 mm to 200 x 200 mm in size but otherwise the same as the QR codes above. They may be placed anywhere in the arena. This includes high or low on the walls, on the ground, on stepfields and on the ceiling when underneath the raised floors. Points will be awarded depending on the number of landmark codes observed, recognized and decoded (coverage). It is possible that smaller QR codes may also appear in the arena and be worth extra points. Note that it is NOT necessary to get co-located with a landmark to score it - any robot may score any landmark to which it has line of sight however the operator must demonstrate to the referee that the robot has clearly observed, recognized and decoded the QR code. A well localized QR code will be worth roughly 10% of the score of a well localized victim.

So please make sure that your robot can not only transmit the video images, but is also able to interpret the QR codes. This is important for both, autonomous and teleop robots.

If you have an existing image processing pipeline in Java or C++, it is very easy to use the ZXing library to add QR code detecting to your existing infrastructure. See http://wiki.ssrrsummerschool.org/doku.php?id=robocup2012:qrcodes for some examples to get you started.

Additions 2011

• A radio drop-out zone with crossing pitch/roll ramp flooring to encourage mobile robots to demonstrate autonomous navigation capabilities in complex terrains.
• Payload delivery to encourage mobile manipulators using inverse kinematics to perform automatic payload grasping, tool changing, object retrieval, and precision placement tasks on complex terrains. Three items can be carried as payloads from the start, additional items can be grasped in the arena.
• Two-way communications tests to establish victim identification by a remote operator (and judge) using randomly spoken numbers played as audio files within victim boxes.

Qualification Process

The RoboCupRescue Robot League encourages participation by interested organizations from around the world, but limits participation to one team per organization. Regional open competitions are hosted around the world to provide essential practice deployment experience for teams and to support qualification of teams for the World Championship competition each year. The World Championship includes a maximum of 5 teams from each regional open competition, which are typically the three awardees and up to two more teams based on the previous year’s awards, Best-In-Class demonstrations in the current year, and other considerations noted below.

RoboCupRescue Robot League regional open competitions are hosted in Japan, Germany, Iran, Thailand, Mexico, and we are actively trying (but need help from locals) to establish regional open competitions in other areas as well. All teams should use regional open competitions to:

• Practice your deployment strategies,

• Familiarize yourselves with the arenas and rules, and

• Demonstrate your capabilities to the Technical Committee.

Unfortunately, due to the close scheduling of the regional open competitions and the World Championship each year, the qualification process can't be completely sequential because teams sometimes have trouble making it to the World Championship on short notice. So the Technical Committee qualifies an initial set of teams each year for the World Championship based on performance in the previous year’s competition and their updated team description papers. Teams that win a 1st, 2nd, or 3rd place award at any regional open competition and submit a team description paper are qualified for the World Championship competition in that year and the following year.

The Technical Committee usually keeps a few slots open in the World Championship competition to include additional capable teams that emerge from the regional open competitions each year. When there is no regional open competition in the region of the World Championship, the technical committee typically qualifies proportionally more teams from the local region, while encouraging them to try to participate in other regional open competitions as well. At large qualifications may also be granted for teams in regions without a regional open competition. Although it is clear that the best route to participate in a World Championship competition is to perform well in a regional open competition and write a good team description paper. You will find the lessons learned from both are well worth the effort.

Each year the Technical Committee looks at the following criteria to qualify teams for the World Championship:

• Your TDP which describes improvements to your robot based on lessons learned from the previous year’s competitions that produced a semi-final round appearance in the World Championship, a Best-In-Class award in the World Championship, or a Place award in a regional open.

• Your TDP describes a particularly interesting or innovative approach that the Technical Committee considers likely to perform well at the World Championship competition even without previous experience at a regional open competition, especially when there is not yet a regional open competition nearby to you. This is especially possible if you can demonstrate your capabilities convincingly within representative arena apparatuses through video of the robot performing any or all of the requisite capabilities:
• advanced mobility (traversing random stepfields or confined space cubes)
• navigation (wall following, centering between obstacles or constrictions)
• localization and mapping (2D/3D maps, SLAM on non-flat-flooring i.e. pitch/roll ramps, low-profile stepfields)
• directed perception (visual acuity for near/far/dark/light, sensor probing into voids, sometimes with reaching)
• victim identification (fusion of the various sensory signals to improve confidence and reduce errors)
• autonomy (assistive features, bounded intervals, or fully autonomous performance of any or all of the above)
• effective operator interfaces

Finally, some qualifications for the World Championship may be granted by the Technical Committee to include particular countries in the league, encourage technologies that the league should be investigating, or to support other league outreach efforts.

Teams

Congratulations on being accepted to the RoboCup 2013 Competition. Looking forward to seeing you all in Eindhoven.

RoboCup 2013 Information

Location: Eindhoven, The Netherlands

• Dates: June 24 - 30, 2013

Important Dates:

• January 25, 2013:
  • Submit Team Participation Formto rescue.robot.league@el.nist.gov

• February 15, 2013:
  • Submit Team Description Paperto rescue.robot.league@el.nist.gov

• March 15, 2013:
  • Announcement of First Round Qualified Teams

RoboCup 2012 Scores

RoboCup Rescue 2012 Placements

	Team Name	Country
1st Place	MRL	Iran
2nd Place	Hector Darmstadt	Germany
3rd Place	Stabilize	Thailand
3rd Place	YRA	Iran

Best of Class 2012

	Team Name	Country
Best in Autonomy	Hector Darmstadt	Germany
Best in Manipulation	DML	Iran
Best in Mobility	Stabilize	Thailand
Commendation of Innovation	Hector Darmstadt	Germany

RoboCup Champions

Year	1st Place Team	2nd Place Team	3rd Place Team	Media
2011	iRAP_Judy, Thailand	MRL, Iran	STABILIZE, Thailand
2010	iRAP_Pro, Thailand	BART LAB Rescue, Thailand	Success, Thailand (Tied for Second)
2009	xxxxx	xxxxx	xxxxxx	video

Year	Best in Autonomy	Best in Manipulation	Best in Mobility	Media
2011	CASualty, Australia	YRA, Iran	iRAP_Judy, Thailand
2010	CASualty, Australia	PELICAN, Japan	CASualty, Australia
2009	xxxxx	xxxxx	xxxxxx	video

Other Information

2011 Assembly Guide for RoboCup Elements

Publications

Summary of RoboCupRescue Robot League June 2010, Singapore