VISION-BASED MOTION PLANNING AND EXPLORATION ALGORITHMS FOR MOBILE ROBOTS

This paper considers the problem of systematically exploring an unfami liar environment in search of one or more recognizable targets. The pr oposed exploration algorithm is based on a novel representation of env ironments containing visual landmarks called the boundary place graph. This representation records the set of recognizable objects (landmark s) that are visible from the boundary of each configuration space obst acle. No metric information about the scene geometry is recorded nor a re explicit prescriptions for moving between places stored. The explor ation algorithm constructs the boundary place graph incrementally from sensor data. Once the robot has completely explored an environment, i t can use the constructed representation to carry out further navigati on tasks. In order to precisely characterize the set of environments i n which this algorithm is expected to succeed, we provide a necessary and sufficient condition under which the algorithm is guaranteed to di scover all landmarks. This algorithm has been implemented on our mobil e robot platform RT, and results from these experiments are presented. Importantly, this research demonstrates that it is possible to design and implement provably correct exploration and navigation algorithms that do not require global positioning systems or metric representatio ns of the environment.