Reactive Motion Planning in Uncertain Environments via Mutual Information Policies

This paper addresses path planning with real-time reaction to environmental uncertainty. The environment is represented as a graph and is uncertain in that the edges of the graph are unknown to the robot a priori. Instead, the robots prior information consists of a distribution over candidate edge sets. At each vertex, the robot can take a measurement to determine the presence or absence of an edge.Within this model, the Reactive Planning Problem (RPP) provides the robot with a start location and a goal location and asks it to compute a policy that minimizes the expected travel and observation cost. In contrast to computing paths that maximize the probability of success, we focus on complete policies (i.e., policies that produce a path, or determine no such path exists). We prove that the RPP is NP-Hard and provide a suboptimal, but computationally e cient, solution. This solution, based on mutual information, returns a complete policy and a bound on the gap between the policy’s expected cost and the optimal. Finally, simulations are run on a flexible factory scenario to demonstrate the scalability of the proposed approach.