Learning to Search in Task and Motion Planning with Streams
This work addresses the problem of long-horizon reasoning with large numbers of objects in robotics, which is incremental as it builds upon existing methods like PDDLStream.
The paper tackles the inefficiency of exhaustive breadth-first search in task and motion planning by introducing a geometrically informed symbolic planner that uses a Graph Neural Network to prioritize expansions in a best-first manner, demonstrating improved planning in difficult scenarios and application to a 7DOF robotic arm in block-stacking tasks.
Task and motion planning problems in robotics combine symbolic planning over discrete task variables with motion optimization over continuous state and action variables. Recent works such as PDDLStream have focused on optimistic planning with an incrementally growing set of objects until a feasible trajectory is found. However, this set is exhaustively expanded in a breadth-first manner, regardless of the logical and geometric structure of the problem at hand, which makes long-horizon reasoning with large numbers of objects prohibitively time-consuming. To address this issue, we propose a geometrically informed symbolic planner that expands the set of objects and facts in a best-first manner, prioritized by a Graph Neural Network that is learned from prior search computations. We evaluate our approach on a diverse set of problems and demonstrate an improved ability to plan in difficult scenarios. We also apply our algorithm on a 7DOF robotic arm in block-stacking manipulation tasks.