Probabilistic state estimation of dynamic objects with a moving mobile robot

Mobile service robots are designed to operate in dynamic and populated envi ronments. To plan their missions and to perform them successfully, mobile r obots need to keep track of relevant changes in the environment. For exampl e, office delivery or cleaning robots must be able to estimate the state of doors or the position of waste-baskets in order to deal with the dynamics of the environment, In this paper we present a probabilistic technique for estimating the state oi dynamic objects in the environment of a mobile robo t. Our method matches real sensor measurements against expected measurement s obtained by a sensor simulation to efficiently and accurately identify th e most likely state of each object even if the robot is in motion. The prob abilistic approach allows us to incorporate the robot's uncertainty in its position into the state estimation process. The method has been implemented and tested on a real robot. We present different examples illustrating the efficiency and robustness of our approach. (C) 2001 Elsevier Science B.V. All rights reserved.