arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2503.01007cs.RO
收藏

从模糊指令到任务计划:基于LLM的反馈驱动HRC任务规划框架

From Vague Instructions to Task Plans: A Feedback-Driven HRC Task Planning Framework based on LLMs

University of Illinois Chicago(伊利诺伊大学芝加哥分校);Toyota Technological Institute at Chicago(芝加哥丰田理工学院)

Afagh Mehri Shervedani, Matthew R. Walter, Milos Zefran

AI总结:

提出一种结合LLMs与人类反馈的混合框架,能从模糊指令推理并基于实时反馈动态生成符合人类意图的人机协作任务计划,且仅需单一简洁提示词即可广泛适用。

摘要:

大型语言模型(LLMs)的最新进展展示了其作为人机协作(HRC)场景中规划器的潜力,为传统规划方法提供了一种有前景的替代方案。LLMs能够通过对自然语言输入进行推理来生成结构化计划,具备跨多样化任务泛化及适应人类指令的能力。本文研究了LLMs在人机协作任务规划中发挥促进作用的潜力,重点关注其从高层、模糊的人类输入中进行推理,以及基于实时反馈微调计划的能力。我们提出了一种结合LLMs与人类反馈的新型混合框架,用于创建动态的、具备上下文感知的任务计划。我们的工作还强调了如何将单一、简洁的提示词广泛应用于各种任务和环境,从而克服以往研究中通常使用的冗长、详细结构化提示词的局限性。通过将用户偏好整合到规划循环中,我们确保生成的计划不仅有效,而且符合人类意图。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑