用传感器物体提升机器人学习穿衣架插入效率
Instrumentation for Imitation Learning: Enhancing Training Datasets for Clothes Hanger Insertion
- 在衣物架上集成传感器，提供精准状态信息辅助训练
- 使用180次远程操控数据，融合传感器信息的模型性能提升14-25个百分点
- 无需明确指导，模型能自动优先利用传感器信号，适合做机器人操作优化
大型行为模型已革新机器人操作领域，但高昂的数据需求阻碍了其像视觉语言模型一样实现革命性突破。我们认为，通过在物体中集成传感器（即仪器化），可提供宝贵的状态信息，从而实现更高效的机器人操作学习。本文提出基于仪器化的模仿学习方法，用于衣服架插入任务。使用180次远程操控示范数据，训练了有无仪器数据访问的扩散策略。结果表明，利用仪器数据的策略相比仅依赖视觉的策略性能提升14-25个百分点，且任务感知更强。关键发现是：一个黑箱模仿学习策略能在没有显式指导的情况下，学会优先使用仪器信号。此外，通过将仪器化专家策略生成的轨迹加入远程操控数据集，使纯视觉的学生策略达到与仪器化专家相当的性能，超越了原始的纯视觉策略。这些结果确立了仪器化作为增强机器人模仿学习的有效策略。数据集可在Zenodo获取。
原文摘要 · Abstract (English)
Large behaviour models have transformed the field of robotic manipulation, but prohibitive data requirements have thus far prevented a revolution similar to vision language models. We believe that instrumentation, i.e. sensor integration in objects, can provide invaluable state information and enable efficient learning for robotic manipulation. In this paper, we present instrumented imitation learning of clothes hanger insertion. Using 180 teleoperated demonstrations, we train diffusion policies with and without access to instrumentation data. Results show that policies leveraging instrumentation outperform vision-only counterparts by 14-25 %pt and exhibit greater task awareness. Crucially, a black-box imitation learning policy learns to prioritise instrumentation signals without explicit guidance. In addition, enhancing the teleoperation dataset with rollouts from an instrumented expert policy, enables a vision-only student policy to achieve performance comparable to the instrumented expert, thereby surpassing the original vision-only policy. These findings establish instrumentation as a promising strategy to enhance imitation learning for robotic manipulation. Datasets are available on Zenodo.
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。