Policy-Guided Lazy Search with Feedback for Task and Motion Planning
This work addresses efficiency problems in robotics planning for rearrangement and manipulation tasks, representing an incremental improvement over existing PDDLStream methods.
The paper tackles the long runtime issue in PDDLStream solvers for Task and Motion Planning by proposing LAZY, an integrated solver that lazily samples motions and uses learned policies to guide task planning, resulting in significant speed-ups in finding feasible solutions across varied test environments.
PDDLStream solvers have recently emerged as viable solutions for Task and Motion Planning (TAMP) problems, extending PDDL to problems with continuous action spaces. Prior work has shown how PDDLStream problems can be reduced to a sequence of PDDL planning problems, which can then be solved using off-the-shelf planners. However, this approach can suffer from long runtimes. In this paper we propose LAZY, a solver for PDDLStream problems that maintains a single integrated search over action skeletons, which gets progressively more geometrically informed, as samples of possible motions are lazily drawn during motion planning. We explore how learned models of goal-directed policies and current motion sampling data can be incorporated in LAZY to adaptively guide the task planner. We show that this leads to significant speed-ups in the search for a feasible solution evaluated over unseen test environments of varying numbers of objects, goals, and initial conditions. We evaluate our TAMP approach by comparing to existing solvers for PDDLStream problems on a range of simulated 7DoF rearrangement/manipulation problems.