通过内在动力学头部实现动态感知的四足运动
Dynamics Aware Quadrupedal Locomotion via Intrinsic Dynamics Head
AI总结：
本文提出一种新的训练框架，通过内在动力学头部学习状态到力矩的动力学，使控制策略能理解和推理物理动力学，从而提升四足机器人的运动效率和稳定性。
摘要：
四足运动在使机器人在复杂地形上实现敏捷、多用途运动方面起着关键作用。理解并估计底层物理动力学对于实现高效稳定的四足运动至关重要。我们提出了一种新的训练框架，使控制策略能够理解和推理物理动力学。在模拟中，我们同时训练一个内在动力学（ID）头部，学习状态到力矩的动力学，并定义由ID头部启用的动力学奖励，鼓励策略朝更可预测的动力学行为发展。我们还提供了一种机制，通过控制ID头部的训练系数来调整所学动力学。我们的模拟实验表明，这种机制在广泛的标准四足运动奖励范围内驱动收敛到更好的极值，产生更高效和流畅的策略。我们的真实机器人实验展示了这些改进的仿真到现实的迁移，带来了扭矩效率（16.8%）、动作率（18.6%）和机械功率（12.8%）的显著提升，同时提高了安全扭矩占用（6.4%）.
英文摘要：
Quadrupedal locomotion plays a critical role in enabling agile, versatile movement across complex terrains. Understanding and estimating the underlying physical dynamics are essential for achieving efficient and stable quadrupedal locomotion. We propose a novel training framework for quadrupedal locomotion that enables the Control Policy to understand and reason about physical dynamics. In simulation, we concurrently train an Intrinsic Dynamics (ID) Head that learns state-to-torque dynamics alongside the Control Policy, and we define a dynamics reward enabled by the ID Head that encourages the Policy toward more predictable dynamical behavior. We also provide a mechanism to tune the learned dynamics in the resulting Policy by controlling the training coefficients of the ID Head. Our simulation experiments show that this mechanism drives convergence to better optima across a wide range of standard quadrupedal locomotion rewards, yielding more efficient and smoother policies. Our real-robot experiments demonstrate sim-to-real transfer of these improvements, with significant gains in torque efficiency (16.8%), action rate (18.6%), and mechanical power (12.8%), while improving safe torque occupancy by 6.4%.
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。
