VIEW：基于航路点的视觉模仿学习
VIEW: Visual Imitation Learning with Waypoints
AI总结：
VIEW算法通过提取紧凑先验轨迹、采用智能体无关奖励函数和航路点周围高效探索，显著提升人-机器人视觉模仿学习的样本效率，支持从任意长视频中学习多对象操作任务，并在30分钟内从单视频演示学会标准操作。
摘要：
机器人可以利用视觉模仿学习（VIL）从视频演示中学习操作任务。然而，由于视频数据的高维特性，将视觉观察转化为可执行的机器人策略具有挑战性。当视频演示由人类执行任务时，人类与机器人之间的形态差异进一步加剧了这一挑战。为解决这些问题，我们提出了基于航路点的视觉模仿学习（VIEW）算法，该算法显著提升了人-机器人视觉模仿学习的样本效率。VIEW通过多管齐下的方法实现这一效率：提取捕捉演示者意图的紧凑先验轨迹，采用与智能体无关的奖励函数为机器人的动作提供反馈，以及利用一种在提取轨迹的航路点周围高效采样的探索算法。VIEW还将人类轨迹分割为抓取阶段和任务阶段，以进一步提高学习效率。通过全面的仿真和真实世界实验，VIEW展示了相较于当前最先进的VIL方法的性能提升。VIEW使机器人能够从任意长的视频演示中学习涉及多个对象的操作任务。此外，它能在不到30分钟内，通过少于20次真实世界 rollout，从单个视频演示中学习如推或移动物体等标准操作任务。代码和视频见：https://collab.me.vt.edu/view/
英文摘要：
Robots can use Visual Imitation Learning (VIL) to learn manipulation tasks from video demonstrations. However, translating visual observations into actionable robot policies is challenging due to the high-dimensional nature of video data. This challenge is further exacerbated by the morphological differences between humans and robots, especially when the video demonstrations feature humans performing tasks. To address these problems we introduce Visual Imitation lEarning with Waypoints (VIEW), an algorithm that significantly enhances the sample efficiency of human-to-robot VIL. VIEW achieves this efficiency using a multi-pronged approach: extracting a condensed prior trajectory that captures the demonstrator's intent, employing an agent-agnostic reward function for feedback on the robot's actions, and utilizing an exploration algorithm that efficiently samples around waypoints in the extracted trajectory. VIEW also segments the human trajectory into grasp and task phases to further accelerate learning efficiency. Through comprehensive simulations and real-world experiments, VIEW demonstrates improved performance compared to current state-of-the-art VIL methods. VIEW enables robots to learn manipulation tasks involving multiple objects from arbitrarily long video demonstrations. Additionally, it can learn standard manipulation tasks such as pushing or moving objects from a single video demonstration in under 30 minutes, with fewer than 20 real-world rollouts. Code and videos here: https://collab.me.vt.edu/view/
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。
