Grasping POMDPs: Theory and Experiments

Abstract

Abstract — We describe a method for planning under uncertainty for robotic manipulation of objects by partitioning the configuration space into a set of regions that are closed under compliant motions. These regions can be treated as states in a partially observable Markov decision process (POMDP), which can be solved to yield optimal control policies under uncertainty. We demonstrate the approach on simple grasping problems, showing that it can construct highly robust, efficiently executable solutions. In this paper we describe some initial experimentation with a Barrett arm and a Barret hand, instrumented with some contact sensors of our own design. This paper is based on [7]. I.