Contact-UAN：作为人形机器人控制残差世界模型的无监督执行器网络
Contact-UAN: Unsupervised Actuator Networks as a Residual World Model for Humanoid Control
AI总结：
Contact-UAN是保留仿真物理先验并校正执行器动力学的残差世界模型，基于6.5分钟真实行走数据训练的UAN，可使人形机器人策略无缝迁移至现实，降低运行扭矩与力跟踪误差，实现柔顺阻抗控制及鲁棒跳跃。
摘要：
在仿真环境中训练的人形机器人策略可以在质量上迁移到硬件，但无法迁移训练期间学习到的力交互，这会损害扭矩效率、负载调节和抗冲击鲁棒性。这种失败可能源于执行器的仿真到现实的差距，因为力取决于执行器扭矩。我们引入Contact-UAN，这是一种残差世界模型，它保留了仿真器的物理先验，同时校正执行器动力学，使仿真 rollout 与记录的硬件 rollout 对齐。对于存在接触的人形机器人运动，这需要接触一致的重放：如果仿真中的硬件回放从接触 wrench 不对齐开始，残差模型会学习校正重置伪影而非执行器差异。仅使用机载本体感觉，Contact-UAN 可推断仿真器侧的支撑足位姿，以初始化具有一致接触力的回放。我们表明，在6.5分钟的真实世界行走数据上训练的UAN可泛化到受益于准确力和脉冲调节的任务，并产生可无缝迁移到现实世界的策略，使运行扭矩降低20%、力跟踪误差降低43%，实现极致柔顺性、准确的阻抗控制以及动态且鲁棒的跳跃。
英文摘要：
Humanoid policies trained in simulation can transfer qualitatively to hardware while failing to transfer the force interactions learned during training, compromising torque efficiency, load regulation, and robustness to impacts. This failure can arise from actuator sim-to-real gaps because forces depend on actuator torques. We introduce Contact-UAN, a residual world model that preserves a simulator's physics priors while correcting actuator dynamics to align simulated rollouts with recorded hardware rollouts. For humanoid motion with contact, this requires contact-consistent replay: if hardware playback in simulation begins with misaligned contact wrenches, the residual model learns to correct reset artifacts rather than actuator discrepancies. Using only onboard proprioception, Contact-UAN infers the simulator-side stance-foot pose needed to initialize replay with consistent contact forces. We show that a UAN trained on 6.5 minutes of real-world walking data generalizes to tasks that benefit from accurate force and impulse regulation and produces policies that transfer seamlessly to the real world, yielding 20% lower running torque, 43% lower force-tracking error, extreme compliance, accurate impedance control, and dynamic, robust jumps.
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。
