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

TL;DR

This paper introduces an end-to-end differentiable framework that jointly optimizes robot design and control, enabling contact-aware manipulation with complex geometries and outperforming existing methods.

Contribution

It presents a novel deformation-based parameterization and a differentiable rigid body simulator for joint design and control optimization in contact-rich tasks.

Findings

Outperforms existing design-only and control-only optimization methods

Handles complex geometries in articulated robots

Effective in contact-rich manipulation scenarios

Abstract

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.