MimicPlay: 通过观看人类玩耍进行长时域模仿学习
MimicPlay: Long-Horizon Imitation Learning by Watching Human Play
AI总结：
MimicPlay提出分层模仿学习框架，利用人类玩耍数据学习潜在计划，指导少量遥操作示范训练的低层控制，在14个真实世界长时域任务中优于现有方法。
摘要：
从人类示范中进行模仿学习是在现实世界中教授机器人操作技能的一种有前景的范式。然而，学习复杂的长时域任务通常需要难以获得的大量示范。为了降低高数据需求，我们求助于人类玩耍数据——人们用手自由与环境互动的视频序列。即使形态不同，我们假设人类玩耍数据包含丰富且显著的物理交互信息，这些信息可以轻松促进机器人策略学习。受此启发，我们引入了一个名为MimicPlay的分层学习框架，该框架从人类玩耍数据中学习潜在计划，以指导基于少量遥操作示范训练的低层视觉运动控制。通过对现实世界中14个长时域操作任务的系统评估，我们表明MimicPlay在任务成功率、泛化能力和对干扰的鲁棒性方面优于最先进的模仿学习方法。代码和视频可在https://mimic-play.github.io获取。
英文摘要：
Imitation learning from human demonstrations is a promising paradigm for teaching robots manipulation skills in the real world. However, learning complex long-horizon tasks often requires an unattainable amount of demonstrations. To reduce the high data requirement, we resort to human play data - video sequences of people freely interacting with the environment using their hands. Even with different morphologies, we hypothesize that human play data contain rich and salient information about physical interactions that can readily facilitate robot policy learning. Motivated by this, we introduce a hierarchical learning framework named MimicPlay that learns latent plans from human play data to guide low-level visuomotor control trained on a small number of teleoperated demonstrations. With systematic evaluations of 14 long-horizon manipulation tasks in the real world, we show that MimicPlay outperforms state-of-the-art imitation learning methods in task success rate, generalization ability, and robustness to disturbances. Code and videos are available at https://mimic-play.github.io
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。
