曖昧な指示からタスク計画へ：LLMに基づくフィードバック駆動型HRCタスクプランニングフレームワーク
From Vague Instructions to Task Plans: A Feedback-Driven HRC Task Planning Framework based on LLMs
大規模言語モデル（LLM）と人間のフィードバックを組み合わせ、曖昧な高レベル指示から人間とロボットの協調タスク計画を動的に生成・修正するハイブリッドフレームワークを提案した。
著者: Afagh Mehri Shervedani, Matthew R. Walter, Milos Zefran
分類: cs.RO
原文アブストラクト
Recent advances in large language models (LLMs) have demonstrated their potential as planners in human-robot collaboration (HRC) scenarios, offering a promising alternative to traditional planning methods. LLMs, which can generate structured plans by reasoning over natural language inputs, have the ability to generalize across diverse tasks and adapt to human instructions. This paper investigates the potential of LLMs to facilitate planning in the context of human-robot collaborative tasks, with a focus on their ability to reason from high-level, vague human inputs, and fine-tune plans based on real-time feedback. We propose a novel hybrid framework that combines LLMs with human feedback to create dynamic, context-aware task plans. Our work also highlights how a single, concise prompt can be used for a wide range of tasks and environments, overcoming the limitations of long, detailed structured prompts typically used in prior studies. By integrating user preferences into the planning loop, we ensure that the generated plans are not only effective but aligned with human intentions.
