Simulated Learning Robots

Jump to: navigation, search

This project aims at using USARSim 3D simulator for experiments with learning and robots.


Large-scale coordination tasks in hazardous, uncertain, and time stressed environments are becoming increasingly important for fire, rescue, and military operations. Substituting robots for people in the most dangerous activities could greatly reduce the risk to human life. Because such emergencies are relatively rare and demand full focus on the immediate problems there is little opportunity to insert and experiment with robots. USARSim was designed as a high fidelity simulation of urban search and rescue (USAR) robots and environments intended as a research tool for the study of human-robot interaction (HRI) and multirobot coordination. High fidelity at low cost is made possible by building the simulation on top of a game engine. The commercial platform which provides superior visual rendering and physical modeling is that of the game Unreal Tournament 2004.In this way, the main effort of the simulator's developers was devoted to the robotics-specific tasks of modeling platforms, control systems, sensors, interface tools and environments. These tasks are in turn, accelerated by the advanced editing and development tools integrated with the game engine leading to a virtuous spiral in which a widening range of platforms can be modeled with greater fidelity in less time. The current release of the simulation consists of: various environmental models (levels), models of commercial and experimental robots, and sensor models. As a simulation user, you are expected to supply the user interfaces, automation, and coordination logic you wish to test. More informations can be found in the USARSim manual.

On Going work


People involved

  • Alessandro Lazaric, PhD Student
  • Marcello Restelli, PhD
  • Moreno De Amicis, Master Student
  • Emanuele Venneri, Master Student