发表机构
Great Bay University; Tsinghua University; The University of Hong Kong; University of Belgrade; The Hong Kong Polytechnic University（大湾区大学; 清华大学; 香港大学; 贝尔格莱德大学; 香港理工大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对机器人整臂操作超大物体难题，提出CALM框架，利用电机电流反馈分阶段学习抬升任务，并通过因果电流映射实现仿真到现实迁移，在仿真和实物上分别达到76.2%和73.3%的成功率。
AI 中文摘要
大多数机器人仅通过末端执行器操作物体，而人类在搬运超大物体时，会灵活利用前臂、肘部等不同身体部位。学习这种整臂操作极具挑战性，原因在于长时程稀疏奖励、有限的接触感知，以及接触与执行器动力学中的仿真到现实差距。为解决这些挑战，我们提出了电流对齐连杆操作（Current-Aligned Link Manipulation），这是一个利用电机电流作为关节负载相关反馈来学习长时程接触丰富操作的框架。三个阶段特定的策略首先利用特权仿真信息分别学习重新定位、抓取和抬升，并由一个阶段路由器对它们进行排序，以生成完整的任务演示。为实现仿真到现实的迁移，一个因果电流映射器根据仿真关节历史预测物理电机电流，使仿真与硬件之间的执行器电流观测对齐。随后，一个统一的学生策略仅使用可部署的传感器观测从这些演示中学习，并通过DAgger进一步优化。任务策略完全在仿真中训练，最终的学生策略部署在硬件上。实验表明，在仿真中顺序超大物体抬升的完整任务成功率为76.2%（762/1000次试验），在物理机器人上成功率为73.3%（22/30次试验）。
英文摘要
Most robots manipulate objects solely with their end effectors, whereas humans flexibly leverage different body parts, such as the forearm and elbow, especially when handling oversized objects. Learning such whole-arm manipulation is chal-lenging due to long-horizon sparse rewards, limited contact sens-ing, and the sim-to-real gap in contact and actuator dynamics. To address these challenges, we propose Current-Aligned Link Manipulation, a framework for learning long-horizon contact-rich manipulation using motor current as joint load related feedback. Three stage-specific policies first learn repositioning, grasping, and lifting using privileged simulation information, and a stage router sequences them to generate complete task demonstrations. For sim-to-real transfer, a causal current mapper predicts physical motor current from simulated joint histories, aligning the actuator current observation between simulation and hardware. A unified student policy then learns from these demonstrations using only deployable sensor observations and is further refined with DAgger. The task policies are trained entirely in simulation, and the final student is deployed on hardware. Experiments demonstrate 76.2% (762/1000 trials) complete-task success in simulation and 73.3% success (22/30 trials) on the physical robot for sequential oversized-object lifting.
