Robotics Engineering - PhD Dissertation Defense - Enabling Motion Planning and Execution for Tasks Involving Deformation and Uncertainty

Tuesday, May 16, 2017
10:00 am to 12:00 pm
Floor/Room #: 
RBE Conference room 209

PhD Dissertation Defense Calder Phillips-Grafflin Title: Enabling Motion Planning and Execution for Tasks Involving Deformation and Uncertainty

Abstract: Many outstanding problems in robotic motion and manipulation involve tasks where degrees of freedom (DoF) cannot be accurately controlled. These DoF, be they part of the robot, an object being manipulated, or the surrounding environment, cannot be accurately controlled by the actuators of the robot alone. In particular, we focus on two important areas of poorly controlled robotic manipulation: motion planning for deformable objects and in deformable environments; and manipulation with uncertainty. Here, the high number of DoF that arise from the deformable materials cannot be controlled directly, but rather are influenced primarily by gravity and contact. The limitations of real robotic actuators and sensors result in uncertainty that we must address to reliably perform fine manipulation. Here, the poorly-controlled DoF arise from the uncertainty of the actuators, which can be influenced by the dynamics of the robot and contact with the environment. Notably, both areas share a common principle: contact, which is usually avoided in robot motion and prohibited in motion planners, is not only sometimes unavoidable, but often necessary to accurately complete the task at hand. This thesis makes four contributions that enable robot manipulation in these poorly controlled tasks: First, an efficient discretized representation of elastic deformable objects and cost function that assess a "cost of deformation" for a specific configuration of a deformable object that enables deformable object manipulation tasks to be performed without physical simulation. Second, a method using active learning and inverse-optimal control to build these discretized representations from expert demonstrations. Third, a motion planner and policy-based execution approach to manipulation with uncertainty which incorporates contact with the environment and compliance of the robot to generate motion policies which are then adapted during execution to reflect actual robot behavior. Fourth, a path quality metric for paths executed with actuation uncertainty that can be used inside a motion planner or trajectory optimizer. Committee members: Prof. Dmitry Berenson – Advisor, University of Michigan Prof. Cagdas Onal – WPI Prof. Raghvendra Cowlagi – WPI Prof. Alberto Rodriguez - MIT