「それはするな!」:大規模言語モデルによる制約生成で身体性システムを導く
"Don't Do That!": Guiding Embodied Systems through Large Language Model-based Constraint Generation
大規模言語モデルを用いて「してはいけないこと」という自然言語制約を実行可能なPython関数に変換し、ロボットナビゲーションの計画に組み込むフレームワークSTPRを提案した。
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: Amin Seffo, Aladin Djuhera, Masataro Asai, Holger Boche
分類: cs.AI, cs.RO
原文アブストラクト
Recent advancements in large language models (LLMs) have spurred interest in robotic navigation that incorporates complex spatial, mathematical, and conditional constraints from natural language into the planning problem. Such constraints can be informal yet highly complex, making it challenging to translate into a formal description that can be passed on to a planning algorithm. In this paper, we propose STPR, a constraint generation framework that uses LLMs to translate constraints (expressed as instructions on ``what not to do'') into executable Python functions. STPR leverages the LLM's strong coding capabilities to shift the problem description from language into structured and interpretable code, thus circumventing complex reasoning and avoiding potential hallucinations. We show that these LLM-generated functions accurately describe even complex mathematical constraints, and apply them to point cloud representations with traditional search algorithms. Experiments in a simulated Gazebo environment show that STPR ensures full compliance across several constraints and scenarios, while having short runtimes. We also verify that STPR can be used with smaller code LLMs, making it applicable to a wide range of compact models with low inference cost.
