This work proposes an end-to-end differentiable physics engine for tensegrity robots, which introduces a data-efficient linear contact model for accurately predicting collision responses that arise due to contacting surfaces, and a linear actuator model that can drive these robots by expanding and contracting their flexible cables. To the best of the authors' knowledge, this is the \emph{first} differentiable physics engine for tensegrity robots that supports cable modeling, contact, and actuation. This engine can be used inside an off-the-shelf, RL-based locomotion controller in order to provide training examples. This paper proposes a progressive training pipeline for the differentiable physics engine that helps avoid local optima during the training phase and reduces data requirements. It demonstrates the data-efficiency benefits of using the differentiable engine for learning locomotion policies for NASA's icosahedron SUPERballBot. In particular, after the engine has been trained with few trajectories to match a ground truth simulated model, then a policy learned on the differentiable engine is shown to be transferable back to the ground-truth model. Training the controller requires orders of magnitude more data than training the differential engine.

中文翻译：

---

张拉整体机器人的端到端可微但可解释的物理引擎：建模和控制

这项工作提出了一种用于张拉整体机器人的端到端可微物理引擎，它引入了一种数据高效的线性接触模型，用于准确预测由于接触表面而产生的碰撞响应，以及一种可以通过扩展和驱动这些机器人的线性致动器模型。收缩他们的柔性电缆。据作者所知，这是用于支持电缆建模、接触和驱动的张拉整体机器人的 \emph{first} 可微物理引擎。该引擎可用于现成的、基于 RL 的运动控制器，以提供训练示例。本文为可微物理引擎提出了一种渐进式训练管道，有助于在训练阶段避免局部最优并减少数据需求。它展示了使用可微引擎为 NASA 的二十面体 SUPERballBot 学习运动策略的数据效率优势。特别是，在引擎用很少的轨迹训练以匹配地面实况模拟模型之后，在可微引擎上学习的策略被证明可以转移回地面实况模型。训练控制器比训练差分引擎需要更多数量级的数据。