失敗から学ぶ：長期的タスク・動作計画におけるバックジャンピング
Learning to Correct Mistakes: Backjumping in Long-Horizon Task and Motion Planning
長期的なタスク・動作計画において、行き詰まりの原因となる行動を教師あり学習で特定し、効率的に探索を修正するバックジャンピング手法を提案した。
著者: Yoonchang Sung, Zizhao Wang, Peter Stone
分類: cs.RO
原文アブストラクト
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 on 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.
