VLM推論によるタスク・動作計画の制約生成
Using VLM Reasoning to Constrain Task and Motion Planning
大規模視覚言語モデルの常識的な空間推論を活用し、タスク計画の下向き詳細化の問題を事前に特定して制約を抽出することで、動作計画の失敗を減らし計画時間を大幅に短縮する手法VIZ-COASTを提案。
詳しい要約
1. どんなもの?
2. 先行研究と比べてどこがすごい?
3. 技術・手法の肝は?
4. どうやって有効だと検証した?
5. 議論はある?
6. 次に読むべき論文は?
※ AIが要旨から生成した要約です。正確性は原文をご確認ください。
著者: Muyang Yan, Miras Mengdibayev, Ardon Floros, Weihang Guo, Lydia E. Kavraki, Zachary Kingston
分類: cs.RO
原文アブストラクト
In task and motion planning, high-level task planning is done over an abstraction of the world to enable efficient search in long-horizon robotics problems. However, the feasibility of these task-level plans relies on the downward refinability of the abstraction into continuous motion. When a domain's refinability is poor, task-level plans that appear valid may ultimately fail during motion planning, requiring replanning and resulting in slower overall performance. Prior works mitigate this by encoding refinement issues as constraints to prune infeasible task plans. However, these approaches only add constraints upon refinement failure, expending significant search effort on infeasible branches. We propose VIZ-COAST, a method of leveraging the common-sense spatial reasoning of large pretrained Vision-Language Models to identify issues with downward refinement a priori, bypassing the need to fix these failures during planning. Experiments on three challenging TAMP domains show that our approach is able to extract plausible constraints from images and domain descriptions, drastically reducing planning times and, in some cases, eliminating downward refinement failures altogether, generalizing to a diverse range of instances from the broader domain.
