Learning to Correct Mistakes: Backjumping in Long-Horizon Task and Motion PlanningDownload PDF

16 Jun 2022, 10:45 (modified: 15 Nov 2022, 02:16)CoRL 2022 PosterReaders: Everyone
Student First Author: no
Keywords: task and motion planning, heuristic learning, supervised leanring
Abstract: As robots become increasingly capable of manipulation and long-term autonomy, long-horizon task and motion planning problems are becoming increasingly important. A key challenge in such problems is that early actions in the plan may make future actions infeasible. When reaching a dead-end in the search, most existing planners use backtracking, which exhaustively reevaluates motion-level actions, often resulting in inefficient planning, especially when the search depth is large. In this paper, we propose to learn backjumping heuristics which identify the culprit action directly using supervised learning models to guide the task-level search. Based on evaluations of two different tasks, we find that our method significantly improves planning efficiency compared to backtracking and also generalizes to problems with novel numbers of objects.
Supplementary Material: zip
18 Replies