通过可微分物理引擎实现缆驱张拉整体机器人控制的 Real2Sim2Real 迁移
Real2Sim2Real Transfer for Control of Cable-driven Robots via a Differentiable Physics Engine
AI总结：
本文提出 Real2Sim2Real 策略，利用可微分物理引擎和少量真实机器人数据迭代优化仿真模型，从而发现可直接迁移到真实张拉整体机器人的运动控制策略。
摘要：
张拉整体机器人由刚性杆和柔性缆索组成，具有高强度重量比和显著变形能力，使其能够在非结构化地形中导航并承受剧烈冲击。然而，由于高维度、复杂动力学和耦合架构，它们难以控制。基于物理的仿真是开发可迁移到真实机器人的运动策略的有前景途径。尽管如此，由于存在显著的 sim2real 差距，对张拉整体机器人进行建模是一项复杂任务。为解决这一问题，本文描述了一种针对张拉整体机器人的 Real2Sim2Real（R2S2R）策略。该策略基于一个可微分物理引擎，该引擎可以利用来自真实机器人的有限数据进行训练。这些数据包括物理属性的离线测量，例如各种机器人组件的质量和几何尺寸，以及使用随机控制策略对一条轨迹的观测。利用来自真实机器人的数据，该引擎可以被迭代优化，并用于发现可直接迁移到真实机器人的运动策略。除了 R2S2R 流程之外，本工作的关键贡献还包括：在接触点处计算非零梯度、用于匹配张拉整体运动步态的损失函数，以及一种在训练期间避免梯度评估冲突的轨迹分割技术。R2S2R 过程的多次迭代在一个真实的 3 杆张拉整体机器人上进行了演示和评估。
英文摘要：
Tensegrity robots, composed of rigid rods and flexible cables, exhibit high strength-to-weight ratios and significant deformations, which enable them to navigate unstructured terrains and survive harsh impacts. They are hard to control, however, due to high dimensionality, complex dynamics, and a coupled architecture. Physics-based simulation is a promising avenue for developing locomotion policies that can be transferred to real robots. Nevertheless, modeling tensegrity robots is a complex task due to a substantial sim2real gap. To address this issue, this paper describes a Real2Sim2Real (R2S2R) strategy for tensegrity robots. This strategy is based on a differentiable physics engine that can be trained given limited data from a real robot. These data include offline measurements of physical properties, such as mass and geometry for various robot components, and the observation of a trajectory using a random control policy. With the data from the real robot, the engine can be iteratively refined and used to discover locomotion policies that are directly transferable to the real robot. Beyond the R2S2R pipeline, key contributions of this work include computing non-zero gradients at contact points, a loss function for matching tensegrity locomotion gaits, and a trajectory segmentation technique that avoids conflicts in gradient evaluation during training. Multiple iterations of the R2S2R process are demonstrated and evaluated on a real 3-bar tensegrity robot.
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。
