Dojo - A Differentiable Simulator for Robotics

Dojo - A Differentiable Simulator for Robotics

We present a differentiable rigid-body-dynamics simulator for robotics that prioritizes physical accuracy and differentiability, Dojo. The simulator utilizes an expressive maximal-coordinates representation, achieves stable simulation at low sample rates, and conserves energy and momentum by employing a variational integrator. A nonlinear complementarity problem, with nonlinear friction cones, models hard contact and is reliably solved using a custom primal-dual interior-point method. The implicit-function theorem enables efficient differentiation of an intermediate relaxed problem and computes smooth gradients from the contact model. We demonstrate the usefulness of the simulator and its gradients through a number of examples including: simulation, trajectory optimization, reinforcement learning, and system identification.

Related Papers

People

Taylor Howell
Model-predictive control and differentiable simulators for contact
Simon Le Cleac'h
Game-theoretic optimization and optimization through contact
Jan Bruedigam
PhD student at TU Munich
Zac Manchester
Assistant Professor
Last updated: 2022-03-07