Reliable mobile robot navigation from unreliable visual cues

Vision-based mobile robot navigation requires robust methods for planning and executing tasks due to the unreliability of visual information. In this paper we propose a new method forreliable vision-based navigation in an unmodeled dynamic environment. Arti cial landmarks are used as visual cues for navigation. Our system builds a visibility graph among landmark locations during an exploration phase and then uses that graph for navigation. To deal with temporary occlusion of landmarks, long-term changes in the environment, and inherent uncertainties in the landmark detection process, we use a probabilistic model of landmark visibility. Based on the history of previous observations made, each visibility edge in the graph is annotated with an estimated probability of landmark detection. To solve a navigation task, our algorithm computes the expected shortest paths between all landmarks and the speci ed goal, by solving a special instance of a Markov decision process. The paper presents both the probabilistic expected shortest path planner and the landmark design and detection algorithm, which nds landmark patterns under general a ne transformations in real-time.