面向精准落脚点的动力学在线感知运动控制
Locomotion with Online Awareness of Dynamics for Precision Footholds
AI总结：
该研究提出结合显式惯性估计与隐式动力学特征的LOAD框架，通过循环模块与知识蒸馏实现窄梁精准运动，在仿真与硬件实验中验证其可应对不同负载，性能接近特权策略。
摘要：
未知 payload（负载）会改变机器人动力学，当落脚点余量较小时，会使精准接触执行变得困难。我们提出 LOAD，一种感知型运动框架，结合显式惯性估计与隐式动力学特征以实现窄梁穿越。独立的循环模块从本体感觉中推断躯干惯性变化与任务相关历史，同时将高度图教师模型蒸馏为基于深度的学生模型。我们在仿真与硬件平台上，针对不同梁宽与负载配置，对 LOAD 及其变体进行了广泛评估。结果显示，隐式动力学特征可加速训练，而显式惯性估计能进一步提升穿越成功率；将两者结合可使 LOAD 的性能接近提供真实惯性参数的特权策略。硬件实验表明，该框架可在 10 cm 梁上承受单侧 6 kg 负载、15 cm 梁上承受单侧 9 kg 负载，以及 15 cm 梁上承受均匀分布的 11 kg 负载。这些结果支持将物理估计与历史特征结合，用于处理未知负载下的精准运动控制。
英文摘要：
Unknown payloads alter robot dynamics and make precise contact execution difficult when foothold margins are small. We present LOAD, a perceptive locomotion framework that combines explicit inertial estimates with implicit dynamics features for narrow-beam traversal. Separate recurrent modules infer torso inertial changes and task-relevant history from proprioception, while a height-map teacher is distilled into a depth-based student. We extensively evaluate LOAD and its variants in simulation and on hardware across beam widths and payload configurations. The results show that implicit dynamics features accelerate training, while explicit inertial estimation further improves traversal success; combining both enables LOAD to approach the performance of a privileged policy supplied with ground-truth inertial parameters. Hardware experiments demonstrate traversal with unilateral payloads of 6 kg on a 10 cm beam and 9 kg on a 15 cm beam, and an evenly distributed 11 kg payload on a 15 cm beam. These results support combining physical estimates and history features for precision locomotion under unknown loads.
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。
