Robust Closed-Loop Manipulation via Contact Sensing
Contact sensors can provide robots with with the feedback vital to robustly manipulating objects in uncertain environments. However, there are three principal challenges to using contact sensing. First, contact is inherently discontinuous. Second, contact sensors only provide rich information while in contact. Third, planning for contact requires reasoning about the physics of interaction.
Our work addresses these challenges by formulating contact manipulation as a partially observable Markov decision process (POMDP) in the joint space of robot configuration and object poses. Policies generated from this POMDP naturally take information-gathering actions when necessary to complete the task. For example, the robot may force an object into a contact sensor to localize it before attempting to push it into the goal region. We specifically consider the case of quasistatic manipulation via planar pushing.
Pre- and Post-Contact Policy Decomposition
We show that the optimal policy decouples into pre- and post-contact stages. We present an algorithm that leverages this insight to reuse one post-contact policy across multiple problem instances.
Heuristic Search with Configuration Lattices
We perform an online search in a lazily-constructed configuration space lattice to guarantee that all actions the robot takes are feasible. The search is efficient because it is guided by heuristics derived from a relaxation of the full-dimensional problem.
We validate the efficacy of our approaches in simulation and real-robot experiments on HERB, a manipulator with a 7-DOF Barrett WAM arm and a BarrettHand end-effector. We show that our approach successfully completes a planar pushing task more often than baseline algorithms that do not take information-gathering actions. Finally, through my collaboration with NASA, I demonstrates that this approach generalizes between robots by using the same algorithm to generate successful policies for Robonaut 2, an anthropomorphic humanoid robot.
Michael C. Koval. Robust Manipulation via Contact Sensing. PhD thesis, Carnegie Mellon University, 2016
M.C. Koval, N.S. Pollard, and S.S. Srinivasa. Pre- and post-contact policy decomposition for planar contact manipulation under uncertainty. IJRR, 35(1-3):244–264, 2016.
M.C. Koval, D. Hsu, N.S. Pollard, and S.S. Srinivasa. Configuration lattices for planar contact manipulation under uncertainty. In WAFR. December 2016.