MEGA Hub

Differentiable Contact Dynamics for Legged Locomotion: Policy Learning and Contact-Implicit Trajectory Optimization

Authors

Do you know Gijeong Kim?You can claim authorship or link another user.Do you know Seungbin Oh?You can claim authorship or link another user.Do you know Dongyun Kang?You can claim authorship or link another user.Do you know Hae-Won Park?You can claim authorship or link another user.

Abstract

This paper proposes a smooth analytic gradient for frictional contact and applies it to policy learning and contact-implicit trajectory optimization for legged locomotion. The exact contact sensitivity is available in closed form but describes changes within the current contact mode, providing no first-order information toward neighboring contact modes. The proposed gradient replaces this sensitivity only in the backward pass, leaving the hard-contact forward solve unchanged and the realized rollout feasible. A central-path relaxation of the de Saxcé-corrected second-order-cone complementarity problem for Coulomb friction smooths the conditions defining the separating, clamping, and sliding modes. The relaxed sensitivity is evaluated at a point on the central path obtained by a Newton iteration initialized from the hard-contact solution. The sensitivity remains continuous through contact-mode transitions and converges to the exact sensitivity as the relaxation vanishes. Using 100,000 samples and less than 2 min of training on a desktop PC, policy learning with the proposed gradient produces a policy that transfers to hardware without fine-tuning. On hardware, the robot under a trotting policy withstands pushes and traverses debris and slippery ground. In trajectory optimization, the proposed gradient reaches contact-rich solutions missed by exact and Signorini-relaxed gradients. Project page: https://diffcontact.github.io

Community

00

Publication notes

Author note
Submitted to Transactions on Robotics