DocumentCode :
676967
Title :
Applying Bayesian learning to multi-robot patrol
Author :
Portugal, David ; Couceiro, Micael S. ; Rocha, Rui P.
Author_Institution :
Inst. of Syst. & Robot. (ISR), Univ. of Coimbra (UC), Coimbra, Portugal
fYear :
2013
fDate :
21-26 Oct. 2013
Firstpage :
1
Lastpage :
6
Abstract :
Performing a patrolling mission with multiple mobile robots is a challenging task that requires effective coordination between agents. While predefined patrol circuits may lead to suitable routing performance, their deterministic nature eases the task of potential intruders. Therefore, the need to propose probabilistic strategies becomes evident. In this paper, a new multi-robot patrolling strategy is proposed, in which concurrent learning agents adapt their moves to the state of the system at the time, using Bayesian decision. When patrolling a given site, each agent evaluates the context and adopts a reward-based learning technique that influences future moves. Experiments show the potential of the approach, which outperforms several other state-of-the-art strategies.
Keywords :
Bayes methods; intelligent robots; learning systems; mobile robots; multi-agent systems; multi-robot systems; Bayesian learning; concurrent learning agents; multiple mobile robots; multirobot patrolling strategy; patrolling mission; probabilistic strategies; reward-based learning technique; routing performance; Adaptation models; Bayes methods; Collision avoidance; Decision making; Entropy; Robot kinematics;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Safety, Security, and Rescue Robotics (SSRR), 2013 IEEE International Symposium on
Conference_Location :
Linkoping
Print_ISBN :
978-1-4799-0879-0
Type :
conf
DOI :
10.1109/SSRR.2013.6719325
Filename :
6719325
Link To Document :
بازگشت