Event Location: NSH 3305

Abstract: For robots to be useful in our homes they must be able to interact with our everyday environments and obey constraints on their motion. This thesis focuses on manipulation planning algorithms, which use search and optimization to quickly compute trajectories that allow a robot to interact with its environment. Planning for manipulation gives rise to a rich variety of tasks that include constraints on collision-avoidance, torque, balance, closed-chain kinematics, and end-effector pose. We develop a broad representation of constraints on a robot’s configuration and identify general strategies to manage these constraints during the planning process. We also present a suite of manipulation planning algorithms capable of planning with very stringent constraints. These algorithms quickly compute trajectories, base placements, and grasps for fixed-base arms, mobile manipulators, and humanoids.

Committee:Siddhartha Srinivasa, Co-chair

James Kuffner, Co-chair

Matthew Mason

Thierry Simeon, LAAS-CNRS, France