纯在可微仿真中训练的四足机器人成功实现在真实世界行走
DiffSim2Real: Deploying Quadrupedal Locomotion Policies Purely Trained in Differentiable Simulation
- 使用可微仿真中的解析梯度优化运动策略
- 首次实现四足机器人仅在仿真中训练即完成真实行走
- 平滑接触模型兼顾物理准确性和梯度有效性
可微仿真器提供解析梯度，使学习算法更具样本效率，并推动图像驱动等数据密集型任务的发展。本文证明，基于可微仿真中解析梯度训练的运动策略可成功迁移到真实世界。通常，能提供有效梯度的仿真器缺乏物理准确性，反之亦然。本工作成功的关键在于一种结合了信息性梯度与物理准确性的平滑接触模型，确保所学行为的有效迁移。据我们所知，这是首个仅在可微仿真中训练即实现在真实世界行走的四足机器人。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。