Title :
Value-based action selection for exploration and dynamic target observation with robot teams
Author :
Stroupe, Ashley W. ; Ravichandran, Ramprasad ; Balch, Tucker
Author_Institution :
Robotics Inst., Carnegie Mellon Univ., Pittsburgh, PA, USA
fDate :
April 26-May 1, 2004
Abstract :
Move Value Estimation for Robot Teams (MVERT) is a robot action selection algorithm for teams performing multiple competing tasks. The goal of MVERT is to select actions for robot team members to maximize the team´s joint utility toward overall mission progress in a computationally efficient manner. MVERT is fully distributed, with each robot using information about other teammates to select its action with the greatest value. MVERT selects actions for a robot team to perform multi-task exploration and dynamic target observation. Successful action selection is demonstrated in simulation for exploration and in simulation and on robots for dynamic target observation.
Keywords :
multi-robot systems; target tracking; dynamic target observation; move value estimation for robot teams; multitask exploration; robot action selection; robot teams; value based action selection; Computational modeling; Educational institutions; Large-scale systems; Multirobot systems; Orbital robotics; Particle filters; Robots; Sampling methods; Simultaneous localization and mapping; Target tracking;
Conference_Titel :
Robotics and Automation, 2004. Proceedings. ICRA '04. 2004 IEEE International Conference on
Print_ISBN :
0-7803-8232-3
DOI :
10.1109/ROBOT.2004.1308930