arXiv 2411.021892024-11-04cs.ROcs.LG

DiffSim2Real：在可微分仿真中纯训练的四足运动策略部署

DiffSim2Real: Deploying Quadrupedal Locomotion Policies Purely Trained in Differentiable Simulation

Robotic Systems Lab, ETH Zürich（苏黎世联邦理工学院机器人系统实验室）；Georgia Institute of Technology（佐治亚理工学院）；The AI Institute（人工智能研究所）；Institute for Research in Technology, ICAI School of Engineering, Comillas Pontifical University（科米利亚斯主教大学技术研究所（ICAI工程学院））

Joshua Bagajo, Clemens Schwarke, Victor Klemm, Ignat Georgiev, Jean-Pierre Sleiman, Jesus Tordesillas, Animesh Garg, Marco Hutter

备注：: Presented at the CoRL 2024 Workshop 'Differentiable Optimization Everywhere'

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

本文提出DiffSim2Real，利用可微分仿真器的解析梯度训练四足运动策略，并通过平滑接触模型兼顾梯度信息与物理精度，首次实现纯可微分仿真训练策略在真实四足机器人上的成功迁移。

摘要：

可微分仿真器提供解析梯度，能够实现更样本高效的学习算法，并为诸如从图像学习等数据密集型学习任务铺平道路。在这项工作中，我们证明了使用来自可微分仿真器的解析梯度训练的运动策略能够成功迁移到现实世界。通常，提供丰富梯度的仿真器缺乏用于仿真到现实迁移所需的物理精度，反之亦然。我们成功的一个关键因素是采用了一种平滑接触模型，该模型结合了信息丰富的梯度与物理精度，确保学习行为能够有效迁移。据我们所知，这是首次有真实四足机器人在仅于可微分仿真中训练后能够实现运动。

英文摘要：

Differentiable simulators provide analytic gradients, enabling more sample-efficient learning algorithms and paving the way for data intensive learning tasks such as learning from images. In this work, we demonstrate that locomotion policies trained with analytic gradients from a differentiable simulator can be successfully transferred to the real world. Typically, simulators that offer informative gradients lack the physical accuracy needed for sim-to-real transfer, and vice-versa. A key factor in our success is a smooth contact model that combines informative gradients with physical accuracy, ensuring effective transfer of learned behaviors. To the best of our knowledge, this is the first time a real quadrupedal robot is able to locomote after training exclusively in a differentiable simulation.

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。