Safe Bayesian Optimization for Complex Control Systems via Additive Gaussian Processes
- 22 September 2025
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Robotics and Automation Letters
- Vol. 10 (11) , 11538-11545
Abstract
Controller tuning and optimization have long been recognized as fundamental challenges in robotics and mechatronic systems. Traditional controller design techniques are usually model-based, and their closed-loop performance depends on the fidelity of the mathematical model. Subsequent tuning of the controller parameters is frequently carried out via empirical rules, which may still suffer from model inaccuracies. In control applications with complex dynamics, obtaining a precise model is often challenging, leading us towards a data-driven approach. While various researchers have explored the optimization of a single controller, it remains a challenge to obtain the optimal controller parameters safely and efficiently when multiple controllers are involved. In this letter, a method called SAFECTRLBO is proposed to optimize multiple controllers simultaneously while ensuring safety. The exploration process in existing safe Bayesian optimization is simplified to reduce computational effort without sacrificing expansion capability. Additionally, additive Gaussian kernels are employed to enhance the efficiency of Gaussian process updates for unknown functions. Hardware experiments on a permanent magnet synchronous motor (PMSM) demonstrate that, compared to baseline safe Bayesian optimization algorithms, SAFECTRLBO attains the best overall performance while ensuring safety.Keywords
All Related Versions
This publication has 21 references indexed in Scilit:
- Safety and Optimality in Learning-Based Control at Low Computational CostIEEE Transactions on Automatic Control, 2025
- Robotic Control Optimization Through Kernel Selection in Safe Bayesian Optimization2024
- Safe-Control-Gym: A Unified Benchmark Suite for Safe Learning-Based Control and Reinforcement Learning in RoboticsIEEE Robotics and Automation Letters, 2022
- Tuning particle accelerators with safety constraints using Bayesian optimizationPhysical Review Accelerators and Beams, 2022
- Hybrid Active–Passive Robust Control Framework of a Flexure-Joint Dual-Drive Gantry Robot for High-Precision Contouring TasksIEEE Transactions on Industrial Electronics, 2022
- Safety-Aware Cascade Controller Tuning Using Constrained Bayesian OptimizationIEEE Transactions on Industrial Electronics, 2022
- Safe controller optimization for quadrotors with Gaussian processes2016
- Effects of Rotor Position Error in the Performance of Field Oriented Controlled PMSM Drives for Electric Vehicle Traction ApplicationsIEEE Transactions on Industrial Electronics, 2016
- The Bayesian approach to global optimization2005
- Field-Oriented Control of a Standard AC Motor Using MicroprocessorsIEEE Transactions on Industry Applications, 1980