DiffLoop: Tuning PID controllers by differentiating through the feedback loop
Not on the map. Why?
Abstract (arXiv)
Since most industrial control applications use PID controllers, PID tuning and anti-windup measures are significant problems. This paper investigates tuning the feedback gains of a PID controller via back-calculation and automatic differentiation tools. In particular, we episodically use a cost function to generate gradients and perform gradient descent to improve controller performance. We provide a theoretical framework for analyzing this non-convex optimization and establish a relationship between back-calculation and disturbance feedback policies. We include numerical experiments on linear systems with actuator saturation to show the efficacy of this approach.
Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Builds on 11 of its 32 references that are in the map. First posted on arXiv 19 Jun 2021.
Builds on
11 of 32 references.
References · 11
- 2014Adam: A Method for Stochastic Optimizationcited by 36,960
- 2017OptNet: Differentiable Optimization as a Layer in Neural Networkscited by 588
- 2018A Tour of Reinforcement Learning: The View from Continuous Controlcited by 129
- 2016A Compositional Object-Based Approach to Learning Physical Dynamicscited by 119
- 2016A Differentiable Physics Engine for Deep Learning in Roboticscited by 107
- 2019Online Control with Adversarial Disturbancescited by 92
- 2020Improper Learning for Non-Stochastic Controlcited by 83
- 2019The Nonstochastic Control Problemcited by 52
- 2019Policy Optimization for H2 Linear Control with H_∞ Robustness Guarantee: Implicit Regularization and Global Convergencecited by 39
- 2020Optimal PID and Antiwindup Control Design as a Reinforcement Learning Problemcited by 4
- 2017Model-Based Policy Search for Automatic Tuning of Multivariate PID Controllerscited by 2
Built on by
Citing papers per year: 2022: 1; 2023: 0; 2024: 2.
3 papers.