Bundled Contact Gradients: Stabilizing Differentiable Simulation for Deployable Dynamic Tasks

Published September 28, 2026 · Category: Robotics

Overview

arXiv:2609.30951v1 Announce Type: new Abstract: Differentiable simulation provides analytic gradients of robot dynamics, enabling fast and sample-efficient first-order policy optimization. However, obtaining smooth and informative gradients through rigid-body contact typically requires softened contact models, often at the expense of physical fidelity and thereby limiting learned policies largely to simulation. This trade-off becomes particularly consequential for dynamic humanoid motions, where accurate contact dynamics are critical for transferring policies to the real world. Increasing contact stiffness in rigid-body simulation improves the fidelity of interactions, but also makes the dynamics increasingly sensitive to small state perturbations, producing high-variance gradients that can destabilize first-order policy learning. To address this, we propose \emph{Bundled Contact Gradients (BCG)}, a contact-local randomized smoothing framework for differentiable policy learning. When stiff contact is detected, our method evaluates a local bundle of randomized perturbation rollouts around the stiff contact configuration and aggregates their gradient signal thereby reducing gradient variance. We demonstrate the effectiveness of our method by successfully training and transferring dynamic motions zero-shot onto a real-world Unitree G1 humanoid platform. Videos and supplementary information can be found at https://bundledcontactgradients.github.io/

Source

Originally published at arxiv.org.

Related Articles

• Privacy-Preserving Prompted Policy Search for Robotic Control
• Evaluation Is All You Need for Multi-Modal Autonomous Driving
• HIRE: History-Conditioned Interaction Reasoning and High-Rate Execution for Visually Aliased Precision Manipulation