Probabilistic robot navigation in partially observable environments

摘要: Autonomous mobile robots need very reliable navigation capabilities in order to operate unattended for long periods of time. This paper reports on first results a research program that uses par tially observable Markov models robustly track location office environments and direct its goal-oriented actions. The approach explicitly maintains probability distribution over the possible locations robot taking into account various sources uncertainly including approximate knowledge environment actuator sensor uncertainty. A novel feature our is integration topological map information with metric information. We demonstrate robustness this controlling an actual indoor navigating corridors.