English

Bundled Gradients through Contact via Randomized Smoothing

Robotics 2022-01-25 v3

Abstract

The empirical success of derivative-free methods in reinforcement learning for planning through contact seems at odds with the perceived fragility of classical gradient-based optimization methods in these domains. What is causing this gap, and how might we use the answer to improve gradient-based methods? We believe a stochastic formulation of dynamics is one crucial ingredient. We use tools from randomized smoothing to analyze sampling-based approximations of the gradient, and formalize such approximations through the gradient bundle. We show that using the gradient bundle in lieu of the gradient mitigates fast-changing gradients of non-smooth contact dynamics modeled by the implicit time-stepping, or the penalty method. Finally, we apply the gradient bundle to optimal control using iLQR, introducing a novel algorithm which improves convergence over using exact gradients. Combining our algorithm with a convex implicit time-stepping formulation of contact, we show that we can tractably tackle planning-through-contact problems in manipulation.

Keywords

Cite

@article{arxiv.2109.05143,
  title  = {Bundled Gradients through Contact via Randomized Smoothing},
  author = {H. J. Terry Suh and Tao Pang and Russ Tedrake},
  journal= {arXiv preprint arXiv:2109.05143},
  year   = {2022}
}

Comments

The first two authors contributed equally. Accepted to Robotics and Automation Letters (RA-L)

R2 v1 2026-06-24T05:52:30.396Z