Robust Rearrangement Planning using Nonprehensile Interaction

As we work to move robots out of factories and into human environments, we must empower robots to interact freely in unstructured, cluttered spaces. Humans do this easily, using diverse, whole-arm, nonprehensile actions such as pushing or pulling in everyday tasks. These interaction strategies make difficult tasks easier and impossible tasks possible. In this thesis, we aim to enable robots with similar capabilities. In particular, we formulate methods for planning robust open-loop trajectories that solve the rearrangement planning problem. In these problems, a robot must plan in a cluttered environment, reasoning about moving multiple objects in order to achieve a goal. The problem is difficult because we must plan in continuous, high-dimensional state and action spaces. Additionally, during planning we must respect the physical constraints induced by the nonprehensile interaction between the robot and the objects in the scene. Our key insight is that by embedding physics models directly into our planners we can naturally produce solutions that use nonprehensile interactions such as pushing. This also allows us to easily generate plans that exhibit full arm manipulation and simultaneous object interaction without the need for programmer defined high-level primitives that specifically encode this interaction. We show that by generating these diverse actions, we are able to find solutions for motion planning problems in highly cluttered, unstructured environments. The first focus of this thesis will formulate the rearrangement planning problem as a classical motion planning problem. We show that we can embed physics simulators into randomized planners. We propose methods for reducing the search space and speeding planning time in order to make the planners useful in real-world scenarios. The second focus of this thesis will aim to deal with the imperfect and imprecise worlds that reflect the true reality for robots working in human environments. We pose the rearrangement planning under uncertainty problem as an instance of conformant probabilistic planning and offer methods for solving the problem. We believe the methods we develop in this thesis have broad impact. This thesis will demonstrate the power of these planners on the home care robot HERB. We will show that this planner improves autonomous operation of the robot, allowing HERB to work better in high clutter, completing previously infeasible tasks and speeding feasible task execution. In addition, we will show these planners increase autonomy for the NASA rover K-Rex. Our planner will allow the rover to actively interact with the environment. We will demonstrate that this interaction leads to faster traversal in cluttered areas and adds new autonomous capabilities, such as landing site clearing. Finally, we provide open-source implementations of our algorithms so that they may continue to be applied in new domains.