# Ostrich: Taking Large Strides Through Stiff Contact in Differentiable Dynamics

arXiv: https://arxiv.org/abs/2609.08800 · HTML: https://mlsanity.com/paper/2609.08800/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 18 of its 32 references that are in the map.
- First posted on arXiv 8 Sep 2026.

## Builds on (most cited first, 18 of 18)

- [Brax -- A Differentiable Physics Engine for Large Scale Rigid Body Simulation](https://mlsanity.com/paper/2106.13281/) (2021)
- [DiffTaichi: Differentiable Programming for Physical Simulation](https://mlsanity.com/paper/1910.00935/) (2019)
- [A Differentiable Physics Engine for Deep Learning in Robotics](https://mlsanity.com/paper/1611.01652/) (2016)
- [Accelerated Policy Learning with Parallel Differentiable Simulation](https://mlsanity.com/paper/2204.07137/) (2022)
- [Do Differentiable Simulators Give Better Policy Gradients?](https://mlsanity.com/paper/2202.00817/) (2022)
- [Gradients are Not All You Need](https://mlsanity.com/paper/2111.05803/) (2021)
- [NeuralSim: Augmenting Differentiable Simulators with Neural Networks](https://mlsanity.com/paper/2011.04217/) (2020)
- [Scalable Differentiable Physics for Learning and Control](https://mlsanity.com/paper/2007.02168/) (2020)
- [Efficient Differentiable Simulation of Articulated Bodies](https://mlsanity.com/paper/2109.07719/) (2021)
- [Learning Quadruped Locomotion Using Differentiable Simulation](https://mlsanity.com/paper/2403.14864/) (2024)
- [A Review of Differentiable Simulators](https://mlsanity.com/paper/2407.05560/) (2024)
- [Dojo: A Differentiable Physics Engine for Robotics](https://mlsanity.com/paper/2203.00806/) (2022)
- [Bundled Gradients through Contact via Randomized Smoothing](https://mlsanity.com/paper/2109.05143/) (2021)
- [Rethinking Optimization with Differentiable Simulation from a Global Perspective](https://mlsanity.com/paper/2207.00167/) (2022)
- [Learning on the Fly: Rapid Policy Adaptation via Differentiable Simulation](https://mlsanity.com/paper/2508.21065/) (2025)
- [Non-Smooth Newton Methods for Deformable Multi-Body Dynamics](https://mlsanity.com/paper/1907.04587/) (2019)
- [Differentiable Simulation of Hard Contacts with Soft Gradients for Learning and Control](https://mlsanity.com/paper/2506.14186/) (2025)
- [ContactSDF: Signed Distance Functions as Multi-Contact Models for Dexterous Manipulation](https://mlsanity.com/paper/2408.09612/) (2024)

## Abstract (arXiv)

Three properties determine whether a differentiable simulator can drive gradient-based optimization through contact: simulation accuracy, gradient reliability, and per-iteration cost. Tape-based engines such as MJX and Newton Semi-Implicit require timesteps small enough to keep contacts numerically tractable, and their backpropagation memory grows linearly with the number of timesteps T. Surrogate models bound memory by approximating contact away, but the resulting gradients lose the geometry the optimization depends on. We present Ostrich, a GPU-accelerated rigid-body simulator that resolves hard contacts and friction with non-smooth Newton iteration at large timesteps (h ~ 0.1 s), and differentiates the converged residual via the implicit function theorem, reusing the forward Schur complement to compute the adjoint at O(1) memory per timestep. On real-robot trajectories over a pallet obstacle, Ostrich holds MuJoCo's sim-to-real accuracy up to a 50x larger timestep. Its gradients converge from random initializations where MJX descends slowly and Newton Semi-Implicit stalls; a warm iteration runs 211x faster than MJX's and 4.7x faster than Semi-Implicit's. On the same scene Ostrich differentiates 8,192 parallel worlds on a single 24 GB GPU, sustaining 29x checkpointed MJX's optimization throughput; without checkpointing both baselines exhaust memory at far fewer worlds. We close with a gradient-based trajectory optimization demonstration over triangle-mesh terrain across a 10 s horizon, a setting where prior engines either restrict to primitive geometry or face the convergence and memory limits shown above.