Meta-Policy Learning over Plan Ensembles for Robust Articulated Object Manipulation

Constantinos Chamzas, Caelan Reed Garrett, Balakumar Sundaralingam, Lydia E Kavraki, Dieter Fox

Keywords: Task and Motion Planning, Policy Learning, Robotic Manipulation

TL;DR: This paper present a meta-policy learning framework over plan ensembles for robust articulated object manipulation

Abstract: Model-based robotic planning techniques, such as inverse kinematics and motion planning, can endow robots with the ability to perform complex manipulation tasks, such as grasping, object manipulation, and precise placement. However, these methods often assume perfect world knowledge and leverage approximate world models. For example, tasks that involve dynamics such as pushing or pouring are difficult to address with model-based techniques as it is difficult to obtain accurate characterizations of these object dynamics. Additionally, uncertainty in perception prevents them populating an accurate world state estimate. In this work, we propose using a model-based motion planner to build an ensemble of plans under different environment hypotheses. Then, we train a meta-policy to decide online which plan to track based on the current history of observations. By leveraging history, this policy is able to switch ensemble plans to circumvent getting “stuck” in order to complete the task. We tested our method on a 7-DOF Franka-Emika robot pushing a cabinet door in simulation. We demonstrate that a successful meta-policy can be trained to push a door in settings high environment uncertainty all while requiring little data.