Safe controller optimization for quadrotors with Gaussian processes

TLDR

Tuning controller parameters is a fundamental challenge in dynamic system design, often requiring manual adjustment on real systems, and while machine learning methods like Bayesian optimization have been used, they risk safety‑critical failures during exploration. This work applies the SafeOpt algorithm for the first time to automatically tune controller parameters while ensuring safety. SafeOpt models performance as a Gaussian process and iteratively explores only those controller settings that, with high probability, exceed a predefined safe performance threshold, starting from a low‑performance baseline. Experiments on a quadrotor demonstrate that this approach achieves rapid, fully automated, and safe controller optimization without human intervention.

Abstract

One of the most fundamental problems when designing controllers for dynamic systems is the tuning of the controller parameters. Typically, a model of the system is used to obtain an initial controller, but ultimately the controller parameters must be tuned manually on the real system to achieve the best performance. To avoid this manual tuning step, methods from machine learning, such as Bayesian optimization, have been used. However, as these methods evaluate different controller parameters on the real system, safety-critical system failures may happen. In this paper, we overcome this problem by applying, for the first time, a recently developed safe optimization algorithm, SafeOpt, to the problem of automatic controller parameter tuning. Given an initial, low-performance controller, SafeOpt automatically optimizes the parameters of a control law while guaranteeing safety. It models the underlying performance measure as a Gaussian process and only explores new controller parameters whose performance lies above a safe performance threshold with high probability. Experimental results on a quadrotor vehicle indicate that the proposed method enables fast, automatic, and safe optimization of controller parameters without human intervention.