Pre- and Post-Contact Policy Decomposition for Planar Contact Manipulation Under Uncertainty

Michael Koval, Nancy Pollard, Siddhartha Srinivasa
2014 Robotics: Science and Systems X  
We consider the problem of using real-time feedback from contact sensors to create closed-loop pushing actions. To do so, we formulate the problem as a partially observable Markov decision process (POMDP) with a transition model based on a physics simulator and a reward function that drives the robot towards a successful grasp. We demonstrate that it is intractable to solve the full POMDP with traditional techniques and introduce a novel decomposition of the policy into pre-and post-contact
more » ... es to reduce the computational complexity. Our method uses an offline point-based solver on a variableresolution discretization of the state space to solve for a postcontact policy as a pre-computation step. Then, at runtime, we use an A * search to compute a pre-contact trajectory. We prove that the value of the resulting policy is within a bound of the value of the optimal policy and give intuition about when it performs well. Additionally, we show the policy produced by our algorithm achieves a successful grasp more quickly and with higher probability than a baseline policy.
doi:10.15607/rss.2014.x.034 dblp:conf/rss/KovalPS14 fatcat:xsgv2um4zbfitdftgr4rmainbu