无需奖励工程、从演示中学习多模态富接触技能
Learning Multimodal Contact-Rich Skills from Demonstrations Without Reward Engineering
AI总结：
针对富接触操作中多模态融合与奖励工程难题，提出无模型从演示学习框架及多模态传感器表示，并在 Sawyer 上验证清洁、书写、削皮技能。
摘要：
削皮、清洁和书写等日常富接触任务需要多模态感知，才能有效且精确地执行。然而，这些任务给机器人带来了新的挑战，因为机器人缺乏组合这些多模态刺激以完成富接触任务的能力。基于学习的方法已尝试对多模态富接触任务建模，但它们通常需要大量训练样本和特定于任务的奖励函数，这限制了其实用性和适用范围。因此，我们提出一种可泛化的无模型从演示学习框架，使机器人无需显式奖励工程即可学习富接触技能。我们提出了一种新颖的多模态传感器数据表示，可提升富接触技能的学习性能。我们使用真实 Sawyer 机器人针对清洁、书写和削皮三项日常富接触技能进行了训练和实验。值得注意的是，该框架在削皮和书写技能上达到 100% 的成功率，在清洁技能上达到 80%。因此，该技能学习框架可扩展用于学习其他物理操作技能。
英文摘要：
Everyday contact-rich tasks, such as peeling, cleaning, and writing, demand multimodal perception for effective and precise task execution. However, these present a novel challenge to robots as they lack the ability to combine these multimodal stimuli for performing contact-rich tasks. Learning-based methods have attempted to model multi-modal contact-rich tasks, but they often require extensive training examples and task-specific reward functions which limits their practicality and scope. Hence, we propose a generalizable model-free learning-from-demonstration framework for robots to learn contact-rich skills without explicit reward engineering. We present a novel multi-modal sensor data representation which improves the learning performance for contact-rich skills. We performed training and experiments using the real-life Sawyer robot for three everyday contact-rich skills -- cleaning, writing, and peeling. Notably, the framework achieves a success rate of 100\% for the peeling and writing skill, and 80\% for the cleaning skill. Hence, this skill learning framework can be extended for learning other physical manipulation skills.
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。
