用自然语言让机器人自主调整动作，无需重新训练
IROSA: Interactive Robot Skill Adaptation using Natural Language
- 通过预训练大模型选择工具实现开放词汇技能适配
- 在7自由度机械臂上成功完成轴承装配任务的自然语言控制
- 保持安全透明，适合工业场景中人机协作
基础模型在多个领域展现出强大能力，而模仿学习则为从有限数据中适应机器人技能提供了可靠方法。将二者结合对机器人直接应用具有重要意义，但当前研究关注较少，尤其在工业部署方面。本文提出一种新框架，通过基于工具的架构实现开放词汇的技能适配，同时在语言模型与机器人硬件间保留保护性抽象层。该方法利用预训练的大语言模型（LLM）选择并配置特定工具，以适应机器人技能，无需微调或直接模型-机器人交互。我们在一台7-DoF力控机械臂上验证了该框架，使其能够通过自然语言指令完成轴承环插入任务中的速度调节、轨迹修正和避障操作，同时保证安全性、透明性和可解释性。
原文摘要 · Abstract (English)
Foundation models have demonstrated impressive capabilities across diverse domains, while imitation learning provides principled methods for robot skill adaptation from limited data. Combining these approaches holds significant promise for direct application to robotics, yet this combination has received limited attention, particularly for industrial deployment. We present a novel framework that enables open-vocabulary skill adaptation through a tool-based architecture, maintaining a protective abstraction layer between the language model and robot hardware. Our approach leverages pre-trained LLMs to select and parameterize specific tools for adapting robot skills without requiring fine-tuning or direct model-to-robot interaction. We demonstrate the framework on a 7-DoF torque-controlled robot performing an industrial bearing ring insertion task, showing successful skill adaptation through natural language commands for speed adjustment, trajectory correction, and obstacle avoidance while maintaining safety, transparency, and interpretability.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。