ロボット制御のためのエージェントAI:柔軟だが依然として脆い
Agentic AI for Robot Control: Flexible but still Fragile
推論可能な言語モデルがロボットスキルを選択・実行するエージェント型制御システムを2つの実機で試し、柔軟性と脆弱性の両面を明らかにした。
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: Oscar Lima, Marc Vinci, Martin Günther, Marian Renz, Alexander Sung, Sebastian Stock, Johannes Brust, Lennart Niecksch, Zongyao Yi, Felix Igelbrink, Benjamin Kisliuk, Martin Atzmueller, Joachim Hertzberg
分類: cs.RO
原文アブストラクト
Recent work leverages the capabilities and commonsense priors of generative models for robot control. In this paper, we present an agentic control system in which a reasoning-capable language model plans and executes tasks by selecting and invoking robot skills within an iterative planner and executor loop. We deploy the system on two physical robot platforms in two settings: (i) tabletop grasping, placement, and box insertion in indoor mobile manipulation (Mobipick) and (ii) autonomous agricultural navigation and sensing (Valdemar). Both settings involve uncertainty, partial observability, sensor noise, and ambiguous natural-language commands. The system exposes structured introspection of its planning and decision process, reacts to exogenous events via explicit event checks, and supports operator interventions that modify or redirect ongoing execution. Across both platforms, our proof-of-concept experiments reveal substantial fragility, including non-deterministic suboptimal behavior, instruction-following errors, and high sensitivity to prompt specification. At the same time, the architecture is flexible: transfer to a different robot and task domain largely required updating the system prompt (domain model, affordances, and action catalogue) and re-binding the same tool interface to the platform-specific skill API.
