# DiffTune: Auto-Tuning through Auto-Differentiation

Source: [DiffTune: Auto-Tuning through Auto-Differentiation](<https://www.sota2.com/research/paper/68fa74121e209131cea5fa42>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-26T03:02:03.292Z

Authors: Sheng Cheng, Minkyung Kim, Lin Song, Chengyu Yang, Yiquan Jin, Shenlong Wang, Naira Hovakimyan

Published: 2022-09-20T22:08:44.000Z

## Abstract

The performance of robots in high-level tasks depends on the quality of their lower-level controller, which requires fine-tuning. However, the intrinsically nonlinear dynamics and controllers make tuning a challenging task when it is done by hand. In this paper, we present DiffTune, a novel, gradient-based automatic tuning framework. We formulate the controller tuning as a parameter optimization problem. Our method unrolls the dynamical system and controller as a computational graph and updates the controller parameters through gradient-based optimization. The gradient is obtained using sensitivity propagation, which is the only method for gradient computation when tuning for a physical system instead of its simulated counterpart. Furthermore, we use $\\mathcal{L}\_1$ adaptive control to compensate for the uncertainties (that unavoidably exist in a physical system) such that the gradient is not biased by the unmodelled uncertainties. We validate the DiffTune on a Dubin's car and a quadrotor in challenging simulation environments. In comparison with state-of-the-art auto-tuning methods, DiffTune achieves the best performance in a more efficient manner owing to its effective usage of the first-order information of the system. Experiments on tuning a nonlinear controller for quadrotor show promising results, where DiffTune achieves 3.5x tracking error reduction on an aggressive trajectory in only 10 trials over a 12-dimensional controller parameter space.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Controller and Observer Gain Optimization on Differentiable Simulation JAX-based (train)](<https://www.sota2.com/research/sota/controller-and-observer-gain-optimization-on-differentiable-simulation-jax-based-train.md>): Controller and Observer Gain Optimization; Differentiable Simulation JAX-based (train); RMSE: 0.69.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2209.10021>)

[PDF](<https://arxiv.org/pdf/2209.10021.pdf>)
