RobotMover：从人类演示中学习移动大型物体
RobotMover: Learning to Move Large Objects From Human Demonstrations
AI总结：
提出 RobotMover，利用人-物交互演示和 Interaction Chain 模仿学习大型物体操作策略，并通过域随机化实现 Spot 机器人零样本真机迁移。
摘要：
移动家具或电器等大型物体，是机器人在人类环境中作业的一项关键能力。该任务带来了独特挑战，包括通过全身协调避免碰撞，以及处理笨重、沉重物体的动力学。在本工作中，我们提出 RobotMover，这是一个用于大型物体操作的基于学习的系统，利用人-物交互演示来训练机器人控制策略。RobotMover 将操作问题表述为模仿学习，使用一种称为 Interaction Chain（交互链）的简化空间表示，该表示以可跨不同机器人本体泛化的方式捕捉关键交互动力学。我们将这种 Interaction Chain 纳入奖励函数，并在仿真中使用域随机化训练策略，从而实现向真实机器人的零样本迁移。所得策略使 Spot 机器人能够操作各种大型物体，包括椅子、桌子和落地灯。通过在仿真和真实世界中的大量实验，我们表明 RobotMover 在能力、鲁棒性和可控性方面取得了优异表现，优于学习型基线和遥操作基线。该系统还通过将学习到的策略与简单规划模块相结合，支持实际应用，以执行长时域物体运输和重排任务。
英文摘要：
Moving large objects, such as furniture or appliances, is a critical capability for robots operating in human environments. This task presents unique challenges, including whole-body coordination to avoid collisions and managing the dynamics of bulky, heavy objects. In this work, we present RobotMover, a learning-based system for large object manipulation that uses human-object interaction demonstrations to train robot control policies. RobotMover formulates the manipulation problem as imitation learning using a simplified spatial representation called the Interaction Chain, which captures essential interaction dynamics in a way that generalizes across different robot bodies. We incorporate this Interaction Chain into a reward function and train policies in simulation using domain randomization to enable zero-shot transfer to real-world robots. The resulting policies allow a Spot robot to manipulate various large objects, including chairs, tables, and standing lamps. Through extensive experiments in both simulation and the real world, we show that RobotMover achieves strong performance in terms of capability, robustness, and controllability, outperforming both learned and teleoperation baselines. The system also supports practical applications by combining learned policies with simple planning modules to perform long-horizon object transport and rearrangement tasks.
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。
