Agent Simulation

Home / Competitions / Agent Simulation

RoboCup Rescue Simulation

What is RoboCup Rescue Simulation Platform

The Robocup Rescue Simulation Platform is a comprehensive simulation environment for research in disaster response management.

During rescue operations after a disaster, cooperation is a must. In general the problem is not solvable by a single agent, and a heterogeneous team that dynamically combines individual capabilities in order to solve the task is needed. This requirement is due to the structural diversity of disaster areas, variety of evidence the sensors can perceive and to the necessity of quickly and reliably examining large regions.
Yet, the performance of a joint rescue team depends on assembling the right mixture of capabilities and has to be designed as a whole. The goal of this league is to take this technological and scientific challenge and extend current rescue robot platforms with planning, learning, and information exchange capabilities needed to coordinate their efforts and to accomplish the rescue mission as a team.

Robocup Rescue Simulation is an education and research project intended to promote the development of robotic agents for search and rescue. The project was initiated in reaction to the Great Hanshin earthquake, which hit Hyōgo Prefecture, Japan, on 17 January 1995, killing more than six thousand people, most of them in the city of Kobe.

The intention 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 [can] all [be] integrated into comprehensive systems in future.

The RoboCup Rescue Simulation Project challenges teams of researchers to design virtual robots to solve various challenges, or to build real, autonomous robots, which are evaluated in specially designed rescue simulations.

The goal of the urban search and rescue (USAR) robot competitions is to increase awareness of the challenges involved in search and rescue applications, provide objective evaluation of robotic implementations in representative environments, and promote collaboration between researchers. A generic urban disaster simulation environment is constructed on network computers. Heterogeneous intelligent agents such as fire fighters, commanders, victims, volunteers, etc. conduct search and rescue activities in this virtual disaster world. Real-world interfaces such as helicopter image synchronizes the virtuality and the reality by sensing data. Mission-critical human interfaces such as PDA support disaster managers, disaster relief brigades, residents and volunteers to decide their action to minimize the disaster damage.

RoboCup Rescue Simulation Project is an open resource of research results. Various people worldwide participate in this simulator for research, entertainment, training, or education via the Internet. A diverse spectrum of possibilities of this technology will contribute to the creation of the safer social system in the future.

In the other words, RoboCup Rescue Simulation is a Large Multi-Agent System which its aim is to manage the disaster when an earthquake happens. It’s main purpose is to provide emergency decision support by integration of disaster information, prediction and planning. This system is one of the prominent systems for AI and Multi-Agent researches.

Design and development of intelligent agents including FireBrigades, AmbulanceTeams and PoliceForces is the main issue of this league. RoboCup Rescue uses real simulated city maps in order to make the process of disaster management more practical in future. Simulators and Rescue Kernel recently updated in order to become more realistic for the league’s purpose.

Natural disasters are major adverse events that cause large-scale economic, human, and environmental losses. They are usually difficult to predict and
it is even more challenging to prevent them from happening. These characteristics demand disaster management strategies to be in place for the mitigation of damaging consequences when a disaster happen. The mission of the RoboCup Rescue Agent Simulation League is to promote research and development in this socially significant domain at various levels. The effective implementation of this mission is translated into three main league’s objectives. First, the league aims to provide a simulation software infrastructure able to realistically represent natural disaster scenarios where response plans may be assessed. Second, it aims to define evaluation benchmarks for response plans that may be used by policy-makers. Finally, it aims to promote the research and development by conducting competitions to stimulate the exchange of ideas and experience of practitioners, which may help in the development of more sophisticated and formalized plans to efficaciously respond to natural disasters.

The are three competitions in the league:

– The agent competition

– The infrastructure competition

– The virtual robot competition

Agent Simulation Competition

The competition involves primarily evaluating the performance of agent teams on different maps of the RoboCup Rescue Agent Simulation (RCRS) platform ( Specifically, it involves evaluating the effectiveness of Ambulances, Police Forces, and Fire Brigades agents on rescuing civilians and extinguishing fires in cities where an earthquake has just happened. The Agent Simulation competition is composed of a preliminary round, a semi-final round, and a final round. Each round is composed of a set of maps representing different possible situations used for evaluating and scoring each agent team at each round. A consolidated score is assigned to each team per round.
In the preliminary round, in addition to the agent’s teams performance evaluations on the maps, the teams are also evaluated by a presentation of the strategy implemented. This presentation aims to share the knowledge of the teams and improve the academic research aspects of the league. Each team will have 20 minutes to present their implementation and another 10 minutes for questions and answers. The presentation will be evaluated by a panel of experts and these evaluations will be incorporated into the score of the preliminary round. The presentation ranking will be considered as an additional map in the scoring system of the preliminary round.
The participation in the Agent Simulation competition requires the submission of a detailed Team Description Paper (TDP) describing the strategies
implemented in the agent’s code. The three teams with the highest scores at the final round receive a prize.