仅用一次演示，让机器人学会复杂长程视觉动作并抗干扰
One-Shot Robust Imitation Learning for Long-Horizon Visuomotor Tasks from Unsegmented Demonstrations
- 用动态运动基元与元学习融合框架，从不分割的演示中学习长程任务
- 单次演示即可适应新任务，执行时抗外部扰动和视觉遮挡
- 适合需要灵活应变的机器人操作场景，如家庭服务、工业装配
与单一技能任务不同，长程任务在日常生活中至关重要，例如倒水需完成接近、抓取和倾倒等子任务的合理组合。作为将人类技能迁移到机器人的高效方法，模仿学习在过去二十年取得了显著进展。然而，在学习长程视觉-运动技能时，模仿学习通常需要大量语义分割的演示数据，且性能易受外部扰动和视觉遮挡影响。本文提出一种新框架MiLa（Meta-Imitation Learning with Adaptive Dynamical Primitives），结合动态运动基元与元学习，实现从非分割演示中学习长程任务，并仅凭一次演示即可适应未见任务。该方法在执行过程中具备抵抗外部干扰和视觉遮挡的能力。真实机器人实验表明，无论是否存在视觉遮挡或随机扰动，MiLa均表现出优越性能。
原文摘要 · Abstract (English)
In contrast to single-skill tasks, long-horizon tasks play a crucial role in our daily life, e.g., a pouring task requires a proper concatenation of reaching, grasping and pouring subtasks. As an efficient solution for transferring human skills to robots, imitation learning has achieved great progress over the last two decades. However, when learning long-horizon visuomotor skills, imitation learning often demands a large amount of semantically segmented demonstrations. Moreover, the performance of imitation learning could be susceptible to external perturbation and visual occlusion. In this paper, we exploit dynamical movement primitives and meta-learning to provide a new framework for imitation learning, called Meta-Imitation Learning with Adaptive Dynamical Primitives (MiLa). MiLa allows for learning unsegmented long-horizon demonstrations and adapting to unseen tasks with a single demonstration. MiLa can also resist external disturbances and visual occlusion during task execution. Real-world robotic experiments demonstrate the superiority of MiLa, irrespective of visual occlusion and random perturbations on robots.
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。