An End-to-End Differentiable Framework for Contact-Aware Robot Design

Jie Xu1     Tao Chen1     Lara Zlokapa1     Michael Foshey1     Wojciech Matusik1     Shinjiro Sueda2     Pulkit Agrawal1
1 Massachusetts Institute of Technology      2 Texas A&M University


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.


An End-to-End Differentiable Framework for Contact-Aware Robot Design
Jie Xu, Tao Chen, Lara Zlokapa, Michael Foshey, Wojciech Matusik, Shinjiro Sueda, Pulkit Agrawal
Robotics: Science and Systems (RSS) 2021
[Paper]  [Arxiv]  [Supp]  [DiffSim Doc]  [Poster]  [Video]  [Code]  [Talk]  [BibTeX]

Video Demo

Related Papers

RoboGrammar: Graph Grammar for Terrain-Optimized Robot Design
Allan Zhao, Jie Xu, Mina Konaković Luković, Josephine Hughes, Andrew Spielberg, Daniela Rus, Wojciech Matusik
ACM Transactions on Graphics 39(6) (Proc. SIGGRAPH Asia 2020)
[Project Page]

Multi-Objective Graph Heuristic Search for Terrestrial Robot Design
Jie Xu, Andrew Spielberg, Allan Zhao, Daniela Rus, Wojciech Matusik
IEEE International Conference on Robotics and Automation (ICRA 2021)
[Project Page]

REDMAX: Efficient & Flexible Approach for Articulated Dynamics
Ying Wang, Nicholas J. Weidner, Margaret A. Baxter, Yura Hwang, Danny M. Kaufman, Shinjiro Sueda
ACM Transactions on Graphics 38(4) (Proc. SIGGRAPH 2019)
[Project Page]


[MIT News]  [CSAIL News]  [Tech Explorist]