An End-to-End Differentiable Framework for Contact-Aware Robot Design
An End-to-End Differentiable Framework for Contact-Aware Robot Design
复制标题
DOI：
10.15607/rss.2021.xvii.008
复制
发表时间：
2021-07
期刊：
影响因子：
--
通讯作者：
Jie Xu;Tao Chen;Lara Zlokapa;Michael Foshey;W. Matusik;S. Sueda;Pulkit Agrawal
中科院分区：
文献类型：
--
作者：
Jie Xu;Tao Chen;Lara Zlokapa;Michael Foshey;W. Matusik;S. Sueda;Pulkit Agrawal
当前机器人操作的主流范式涉及两个独立阶段：操纵器设计和控制。由于机器人的形态及其控制方式密切相关，设计和控制的联合优化可显著提高性能。现有的协同优化方法存在局限性，无法探索丰富的设计空间。主要原因是接触丰富的任务所需的设计复杂性与制造、优化、接触处理等实际限制之间的权衡。我们通过构建一个用于接触感知机器人设计的端到端可微框架克服了其中一些挑战。该框架的两个关键组件是：一种基于变形的新颖参数化方法，它允许设计具有任意复杂几何形状的关节式刚性机器人；以及一个可微刚体模拟器，它能够处理接触丰富的场景，并计算全范围的运动学和动力学参数的解析梯度。在多个操作任务上，我们的框架优于现有的方法，这些方法要么仅针对控制进行优化，要么使用替代表示进行设计优化，要么使用无梯度方法进行协同优化。
The current dominant paradigm for robotic manipulation involves two separate stages: manipulator design and control. Because the robot's morphology and how it can be controlled are intimately linked, joint optimization of design and control can significantly improve performance. Existing methods for co-optimization are limited and fail to explore a rich space of designs. The primary reason is the trade-off between the complexity of designs that is necessary for contact-rich tasks against the practical constraints of manufacturing, optimization, contact handling, etc. We overcome several of these challenges by building an end-to-end differentiable framework for contact-aware robot design. The two key components of this framework are: a novel deformation-based parameterization that allows for the design of articulated rigid robots with arbitrary, complex geometry, and a differentiable rigid body simulator that can handle contact-rich scenarios and computes analytical gradients for a full spectrum of kinematic and dynamic parameters. On multiple manipulation tasks, our framework outperforms existing methods that either only optimize for control or for design using alternate representations or co-optimize using gradient-free methods.