Novel Algorithms for Smoothly Differentiable and Efficiently Vectorizable Contact Manifold Construction
For researchers in robot learning and simulation, this work addresses a key bottleneck in enabling first/second-order optimization methods for contact-rich tasks.
The paper addresses the challenge of obtaining useful gradients for contact-rich robot simulation by proposing a method for smoothly differentiable and massively vectorizable collision detection. The method uses analytical SDF primitives and a novel contact manifold generation routine.
Generating intelligent robot behavior in contact-rich settings is a research problem where zeroth-order methods currently prevail. Developing methods that make use of first/second order information about the dynamics holds great promise in terms of increasing the solution speed and computational efficiency. The main bottleneck in this research direction is the difficulty in obtaining useful gradients and Hessians, due to pathologies in all three steps of a common simulation pipeline: i) collision detection, ii) contact dynamics, iii) time integration. This abstract proposes a method that can address the collision detection part of the puzzle in a manner that is smoothly differentiable and massively vectorizable. This is achieved via two contributions: i) a highly expressive class of analytical SDF primitives that can efficiently represent complex 3D surfaces, ii) a novel contact manifold generation routine that makes use of this geometry representation.