Disaster rescue is one of the most serious social issues which involves very large numbers of heterogeneous agents in a hostile environment. The main goal of the RoboCup Rescue project is to promote research and development in this socially significant domain at various levels involving multi-agent team work coordination, physical robotic agents for search and rescue, information infrastructures, personal digital assistants, a standard simulator and decision support systems, evaluation benchmarks for rescue strategies and robotic systems that are all integrated into a comprehensive systems in future.
Two projects and leagues, Simulation League and Real Robot League, are currently in use. The goal is that integration of these activities will create the digitally-empowered international rescue brigades in the future.
The RoboCupRescue -Simulation League- is an international testbed for the simulation of software agents and robots performing Urban Search And Rescue (USAR) missions. The main purpose of the RoboCupRescue Simulation Project is to provide emergency decision support through the integration of disaster information, prediction, planning, and human interface. Heterogeneous intelligent agents conduct search and rescue activities in this virtual disaster world. This problem introduces researchers to advanced and interdisciplinary research themes. In AI/Robotics research, for example, behaviour strategy (e.g. multi-agent planning, realtime/anytime planning, heterogeneity of agents, robust planning, mixed-initiative planning) is a challenging problem.
June 1999: Version 0 simulator is open to public.
August 2001: 1st competition for research evaluation starts.
2003: Version 1 simulator with more realistic simulation and agent behaviour with PDA interface.
2005: Version 2 simulator partially in practical level as a decision support system.
2020: Realization of the RoboCup Rescue concept with digitally empowered rescue brigades.
2050: Autonomous robot rescue agent team saves human lives
More than 30 teams from all around the world (Portugal, Iran, Denmark...).
May 1998 |
Hiroaki Kitano and Satoshi Tadokoro meet at ICRA98 in Leuven discussing to start RoboCup Rescue. |
Nov. 1998 |
Discussion about definite plan of research & competition starts. |
Jun. 1999 |
Development of prototype simulator (version 0) starts. |
Dec. 1999 |
RoboCup Rescue Symposium in Kobe. |
Mar. 2000 |
Organized Session in Annual Conference of Information Processing Society Japan |
May 2000 |
Japan Open 2000 Hakodate demonstration. Version 0 simulator is open to the public. |
Aug. 2000 |
RoboFesta Kansai Pre-Festival demonstration |
Aug. 2000 |
RoboCup World Cup 2000 Melbourne demonstration. Version 0 simulator is demonstrated and explained. Call for project participants starts. |
Nov. 2000 |
Demonstration in IEEE/RSJ International Conference on Intelligence Systems and Robots (IROS2000) |
Dec. 2000 |
Organized Session in Society of Instruments and Control Engineers, System Integration Division Annual Conference (SI2000) |
More than 30 teams from all around the world (Portugal, Iran, Denmark...).
The RoboCupRescue - Robot League - competition is an international evaluation conference for the RoboCupRescue Robotics and Infrastructure Project research.
The RoboCupRescue Robotics and Infrastructure Project studies future standards for robotic infrastructure built to support human welfare. Currently the NIST USAR arena has been used in several RoboCupRescue and AIAA competitions.
A team of multiple (autonomous or tele-operated) robots moves inside this testbed, divided in 3 regions of increasing difficulty levels, searching for victims and building maps of the surrounding environment, to be transmitted and/or brought back by the robot(s) to the human operators.
The goal of annual RoboCup Rescue Robot League competitions is to increase awareness of the challenges involved in urban search and rescue (USAR) applications, provide objective evaluation of robotic implementations in representative environments, and promote collaboration between researchers.
The objective for each robot in the competition, and the incentive to traverse every corner of each arena, is to find simulated victims. Each simulated victim is a clothed mannequin emitting body heat and other signs of life, including motion (shifting, waving), sound (moaning, yelling, tapping), and/or carbon dioxide to simulate breathing. Particular combinations of these sensor signatures imply the victim's state: unconscious, semi-conscious, or aware.
It requires robots to demonstrate their capabilities in mobility, sensory perception, planning, mapping, and practical operator interfaces, while searching for simulated victims in unstructured environments. As robot teams begin demonstrating repeated successes against the obstacles posed in the arenas, the level of difficulty will be increased accordingly so that the arenas provide a stepping-stone from the laboratory to the real world. Meanwhile, the yearly competitions will provide direct comparison of robotic approaches, objective performance evaluation, and a public proving ground for field-able robotic systems that will ultimately be used to save lives.
The ultimate goal, of course, is to develop complete and effective robotic systems that can be deployed in the field to save lives.
The agent competition is a modular large-scale disaster simulation in real time, to which multiple agent teams can connect in order to reduce human casualties and damage to buildings. Typical agent types are police forces, ambulance teams, and fire brigades. The rescue domain represents a real multi-agent scenario since most of the encountered problems cannot be solved by a single agent. For example, fire brigades depend on police forces to clear blocked roads in order to extinguish fires. Therefore, team cooperation and coordination is highly required in this domain. Moreover, the task is challenging due to the limited communication bandwidth, the agent's limited perception and the difficulty of predicting how disasters evolve over time.
The purpose of the infrastructure competition is to foster the development of software components for simulation, such as the simulation of fire spread. This is necessary, since in the RSL, teams compete against a disastrous environment rather than against opponents, as it is the case in other leagues. The teams are requested to provide their components under an Open Source policy for the next year's agent competition.
This competition is based upon the robot simulator USARSim , which is based on the game engine from the commercial computer game Unreal Tournament. USARSim allows high fidelity simulations of multi-robot systems. It currently offers the possibility to simulate commercial as well as self-developed robot platforms.
USARSim complements the current league in an ideal way with a realistic physics simulation of teams of robots operating within collapsed buildings. On the one hand, it offers the possibility to simulate search and rescue scenarios where every agent has capabilities comparable with those found on real robots, such as sensing with laser range finders or thermo sensors. On the other hand, it opens the door for investigating aspects of autonomous multi-robot cooperation within unknown and unstructured domains.
RoboCup Rescue Robot League
he RoboCupRescue - Robot League - competition is an international evaluation conference for the RoboCupRescue Robotics and Infrastructure Project research. The RoboCupRescue Robotics and Infrastructure Project studies future standards for robotic infrastructure built to support human welfare. Currently the NIST USAR arena has been used in several RoboCupRescue and AIAA competitions.
A team of multiple (autonomous or tele-operated) robots moves inside this testbed, divided in 3 regions of increasing difficulty levels, searching for victims and building maps of the surrounding environment, to be transmitted and/or brought back by the robot(s) to the human operators.
The goal of annual RoboCup Rescue Robot League competitions is to increase awareness of the challenges involved in urban search and rescue (USAR) applications, provide objective evaluation of robotic implementations in representative environments, and promote collaboration between researchers.
The objective for each robot in the competition, and the incentive to traverse every corner of each arena, is to find simulated victims. Each simulated victim is a clothed mannequin emitting body heat and other signs of life, including motion (shifting, waving), sound (moaning, yelling, tapping), and/or carbon dioxide to simulate breathing. Particular combinations of these sensor signatures imply the victim’s state: unconscious, semi-conscious, or aware.
It requires robots to demonstrate their capabilities in mobility, sensory perception, planning, mapping, and practical operator interfaces, while searching for simulated victims in unstructured environments. As robot teams begin demonstrating repeated successes against the obstacles posed in the arenas, the level of difficulty will be increased accordingly so that the arenas provide a stepping-stone from the laboratory to the real world. Meanwhile, the yearly competitions will provide direct comparison of robotic approaches, objective performance evaluation, and a public proving ground for field-able robotic systems that will ultimately be used to save lives.
The ultimate goal, of course, is to develop complete and effective robotic systems that can be deployed in the field to save lives.