Uncertainty Reduction via Heuristic Search Planning on Hybrid Metric/Topological Map

This paper presents an extension of our previous work on hybrid metric/topological maps to enable uncertainty reduction planning through the map, taking into account both map uncertainty and distance. An enhancement of the edge structure which enables the simulation of bidirectional edge propagation through an extended Kalman filter is proposed in our heuristic search planning algorithm to plan for maximal map uncertainty reduction. This work expands on the heuristic search framework proposed in [1] to apply in hybrid metric/topological maps instead of more constrained camera sensor networks. Experimental results from realistic simulations and deployment on a real robotic system are presented to show the efficacy of the proposed algorithm and validate our approach for uncertainty reduction.