通过加性高斯过程实现复杂控制系统安全贝叶斯优化
Safe Bayesian Optimization for Complex Control Systems via Additive Gaussian Processes
AI总结：
本文提出SafeCtrlBO方法，通过加性高斯过程核减少样本复杂度，实现多耦合控制器的同时优化，实验显示在较少硬件评估下达到高性能参数并保证安全。
摘要：
自动控制器调优对机器人和机电系统具有吸引力，但直接黑盒优化可能不安全。本文提出SafeCtrlBO方法，利用加性高斯过程核编码低阶结构，减少密集全维核的样本复杂度，并用边界基于扩展规则替代潜在扩展计算，实验证明在合成基准和PMSM速度控制平台中，SafeCtrlBO在较少硬件评估下达到高性能参数，同时维持高概率安全标准并避免硬件中的硬信号安全约束违规。代码在https://github.com/hxwangnus/SafeCtrlBO公开。
英文摘要：
Automatic controller tuning is attractive for robotics and mechatronic systems whose dynamics are difficult to model accurately, but direct black-box optimization can be unsafe because each query is executed on the physical plant. Existing safe Bayesian optimization (BO) methods provide high-probability safety guarantees, yet their practical use in multi-loop control is limited by two coupled difficulties: the controller parameter space is often moderately high-dimensional, and hardware evaluations are too expensive to allow hundreds or thousands of exploratory trials. This paper proposes \textsc{SafeCtrlBO}, a safe BO method for simultaneously tuning multiple coupled controllers. The method uses additive Gaussian-process kernels to encode low-order structure across controller gains and reduce the sample complexity associated with dense full-dimensional kernels. It also replaces the expensive potential-expander computation used in \textsc{SafeOpt}-style exploration with a boundary-based expansion rule that preserves the intended safe-set expansion behavior under explicit geometric conditions and is validated empirically. Experiments on synthetic benchmarks and on a permanent magnet synchronous motor (PMSM) speed-control platform show that \textsc{SafeCtrlBO} reaches high-performing controller parameters with fewer hardware evaluations than representative safe BO baselines, while maintaining the prescribed high-probability safety criterion and avoiding violations of the hard signal-safety constraint in the hardware study. The code implementation is publicly available at https://github.com/hxwangnus/SafeCtrlBO.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
