发表机构
Zhejiang University; ZJU-Hangzhou Global Scientific and Technological Innovation Center; MirrorMe Robotics Co., Ltd.（浙江大学; 浙江大学杭州国际科创中心; 镜我机器人有限公司）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对四足机器人高速运动中的执行器非线性与仿真到现实差距问题，提出精细化执行器建模与两阶段课程及自适应指令调度的强化学习框架，在BP2机器人上实现13.2米/秒跑步机与11.65米/秒户外速度，创世界纪录。
AI 中文摘要
实现四足机器人的高速运动仍然极具挑战性，因为执行器在其物理极限附近运行并表现出显著的非线性特性。然而，许多现有方法在训练过程中忽略了执行器的非线性和物理约束，导致在高度动态运动下出现显著的仿真到现实差距，并限制了可实现的性能。为解决这一问题，我们提出了一种高速运动框架，该框架可减小仿真到现实的差异，并在广泛的指令分布上稳定学习过程。一种精细化的执行器模型显式地捕捉了高速电压耦合和磁饱和效应，从而能够更准确地表示扭矩-速度包络线。此外，一种结合两阶段课程和自适应指令调度（ACS）的强化学习框架确保了训练的稳定性。在重达36.5公斤的四足机器人BlackPanther2（BP2）上进行的实验表明，其在跑步机上的速度可达13.2米/秒，在户外可达11.65米/秒，创下了新的最先进水平，并且据我们所知，这是四足机器人运动的世界纪录。结果进一步强调了精确执行器建模在防止非物理策略利用方面的重要性，并表明ACS在不牺牲性能的情况下提高了鲁棒性。
英文摘要
Achieving high-speed locomotion in quadrupedal robots remains highly challenging, as actuators operate near their physical limits and exhibit pronounced nonlinearities. However, many existing methods neglect actuator nonlinearities and physical constraints during training, leading to a significant sim-to-real gap under highly dynamic motions and limiting achievable performance. To address this issue, we propose a high-speed locomotion framework that reduces sim-to-real discrepancies and stabilizes learning over a wide command distribution. A refined actuator model explicitly captures high-speed voltage coupling and magnetic saturation, enabling a more accurate representation of the torque-speed envelope. In addition, a reinforcement learning framework incorporating a two-stage curriculum and adaptive command scheduling (ACS) ensures stable training. Experiments on the 36.5 kg quadruped BlackPanther2 (BP2) demonstrate speeds of up to 13.2 m/s on a treadmill and 11.65 m/s outdoors, establishing a new state-of-the-art and, to the best of our knowledge, a world record for quadrupedal robot locomotion. The results further highlight the importance of accurate actuator modeling in preventing non-physical policy exploitation, and show that ACS improves robustness without sacrificing performance.
CommentsAccepted for publication in IEEE Robotics and Automation Letters (RA-L)
Journal refIEEE Robotics and Automation Letters, Early Access, pp. 1-8, 2026
