Planning under uncertainty for robotic tasks with mixed observability

Partially observable Markov decision processes (POMDPs) provide a principled, general framework for robot motion planning in uncer-tain and dynamic environments. They have been applied to various robotic tasks. However, solving POMDPs exactly is computationally intractable. A major challenge is to scale up POMDP algorithms for complex robotic tasks. Robotic systems often have mixed observabil-ity: even when a robot’s state is not fully observable, some compo-nents of the state may still be so. We use a factored model to represent separately the fully and partially observable components of a robot’s state and derive a compact lower-dimensional representation of its belief space. This factored representation can be combined with any point-based algorithm to compute approximate POMDP solutions. Experimental results show that on standard test problems, our ap-proach improves the performance of a leading point-based POMDP algorithm by many times. KEY WORDS—motion planning, motion planning with uncertainty, Markov decision process, partially observable Markov decision proces