Ruben Martinez-Cantin, Nando de
Freitas, Eric Brochu, José Castellanos, Arnaud Doucet
Autonomous Robots, August 2009
Summary
The paper is about path planning for optimal
sensing with a mobile robot, a typical case in which the robot needs to learn
about its pose and the environment in time constrained, being then the problem
notoriously hard because robots are exhibit to complex dynamics and face
unknown uncertainties.
The authors propose a
Partially Observed Markov Decision Process (POMDP) with a utility function that depends on the belief state to
model the finite horizon planning problem.
