An End-to-End Differentiable Framework for Contact-Aware Robot Design
This work addresses the challenge of improving robotic manipulation performance by enabling more efficient exploration of complex designs, which is incremental as it builds on prior co-optimization efforts.
The authors tackled the problem of jointly optimizing robot design and control for manipulation tasks by developing an end-to-end differentiable framework, which outperformed existing methods that optimize control or design separately or use gradient-free co-optimization.
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.