Dexterous manipulation with simple grippers

Abstract

This thesis focuses on enabling robots, specially those with simple grippers, to dexterously manipulate an object in a grasp. The dexterity of a robot is not limited to the intrinsic capability of a gripper. The robot can roll the object in the gripper using gravity, or adjust the object's pose by pressing it against a surface, or it can even toss the object in the air and catch it in a different pose. All these techniques rely on resources extrinsic to the hand, either gravity, external contacts or dynamic arm motions. We refer to such techniques collectively as "extrinsic dexterity". We focus on empowering robots to autonomously reason about using extrinsic dexterity, particularly, pushes against external contacts. We develop mechanics and algorithms for simulating, planning, and controlling motions of an object pushed in a grasp. We show that the force-motion relationship at contacts can be captured well with complementarity constraints and the mechanics of prehensile pushing in a general setting can be formulated as a mixed nonlinear complementarity problem. For computational efficiency, we derive the abstraction of the mechanics in the form of motion cones. A motion cone defines the set of object motions a pusher can induce using frictional contact. Building upon these mechanics models, we develop a sampling-based planner and an MPC-based controller for in-hand manipulation. The planner generates a series of pushes, possibly from different sides of the object, to move the object to a desired grasp. The controller generates local corrective pushes to keep the object close to the planned pushing strategy. With a variety of regrasp examples, we demonstrate that our planner-controller framework allows the robot to handle uncertainty in physical parameters and external disturbances during manipulation to successfully move the object to a desired grasp.