RaC：通过扩展恢复与纠正实现长时程任务的机器人学习
RaC: Robot Learning for Long-Horizon Tasks by Scaling Recovery and Correction
AI总结：
RaC通过在模仿学习后引入人类干预轨迹微调，扩展策略的恢复与纠正能力，以10倍更少数据在长时程任务上超越最先进方法，并支持测试时线性扩展。
摘要：
现代机器人模仿学习范式在大量人类演示数据上训练表达力强的策略架构。然而，即使在数千次专家演示下，接触丰富、可变形物体及长时程任务的性能仍远未达到完美执行水平。这归因于基于人类遥操作的现有“专家”数据收集流程的低效性。为解决此问题，我们引入RaC，一种在模仿学习预训练之后进行人类参与式循环（human-in-the-loop）轨迹训练的新阶段。在RaC中，我们在展示恢复与纠正行为的人类干预轨迹上微调机器人策略。具体而言，在策略执行过程中，当失败即将发生时，人类操作员进行干预，首先将机器人回退至一个熟悉的、分布内状态，然后提供一段纠正片段以完成当前子任务。在此数据组合上训练，扩展了机器人技能库，使其包含重试与适应行为，我们证明这些行为对于提升长时程任务的效率与鲁棒性至关重要。在三个真实世界双臂控制任务（衬衫悬挂、密封容器盖密封、外卖盒打包）以及一个模拟装配任务中，RaC以10倍更少的数据收集时间和样本量超越了先前最先进方法。我们还表明，RaC支持测试时扩展：训练后的RaC策略的性能随其展现的恢复机动次数线性增长。学习策略的视频可在 https://rac-scaling-robot.github.io/ 获取。
英文摘要：
Modern paradigms for robot imitation train expressive policy architectures on large amounts of human demonstration data. Yet performance on contact-rich, deformable-object, and long-horizon tasks plateau far below perfect execution, even with thousands of expert demonstrations. This is due to the inefficiency of existing ``expert'' data collection procedures based on human teleoperation. To address this issue, we introduce RaC, a new phase of training on human-in-the-loop rollouts after imitation learning pre-training. In RaC, we fine-tune a robotic policy on human intervention trajectories that illustrate recovery and correction behaviors. Specifically, during a policy rollout, human operators intervene when failure appears imminent, first rewinding the robot back to a familiar, in-distribution state and then providing a corrective segment that completes the current sub-task. Training on this data composition expands the robotic skill repertoire to include retry and adaptation behaviors, which we show are crucial for boosting both efficiency and robustness on long-horizon tasks. Across three real-world bimanual control tasks: shirt hanging, airtight container lid sealing, takeout box packing, and a simulated assembly task, RaC outperforms the prior state-of-the-art using 10$\times$ less data collection time and samples. We also show that RaC enables test-time scaling: the performance of the trained RaC policy scales linearly in the number of recovery maneuvers it exhibits. Videos of the learned policy are available at https://rac-scaling-robot.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。
