# 控制器调参与机器人学习中贝叶斯优化的十年：教程、综述与未来展望

> 原文链接：https://robotics.hellobike.com/papers/2026-09-08-2609-09403
> 频道：papers | 更新日期：2026-09-08 | 标签：arxiv, cs.RO
> 核心摘要：本文面向自动控制器调参与机器人学习，综述贝叶斯优化方法、应用与挑战，并提出控制与机器人轻量级基准。

# 控制器调参与机器人学习中贝叶斯优化的十年：教程、综述与未来展望

::: v-pre
> 原文链接：[A Decade of Bayesian Optimization for Controller Tuning and Robot Learning: Tutorial, Review, and Future Prospects](https://arxiv.org/abs/2609.09403)（arXiv 2609.09403 · 发布日期：2026-09-08）

**A Decade of Bayesian Optimization for Controller Tuning and Robot Learning: Tutorial, Review, and Future Prospects**

本文面向自动控制器调参与机器人学习，综述贝叶斯优化方法、应用与挑战，并提出控制与机器人轻量级基准。

## 核心要点

- 过去十年BO成为自动控制器调参与机器人学习的强大框架，需要系统梳理进展、应用与方向。
- 文章从实践者视角出发，通过代表性控制器调参示例说明如何有效设置BO。
- 综述多类面向复杂问题和特定应用的BO方法，并讨论其在控制系统与机器人中的适用场景。
- 指出控制相关应用缺少标准化基准，启动轻量级基准套件并给出比较指标与最佳实践。

**验证范围与局限**：本文为教程与综述，摘要未描述具体仿真或真机实验验证。

## 英文摘要 (Abstract)

In the past decade, Bayesian optimization (BO) has emerged as a powerful and adaptable framework for automatic controller tuning and robot learning. This article offers a comprehensive overview of the state-of-the-art in BO, designed to support both researchers and practitioners in understanding recent advancements, practical applications, and future research directions. We begin by adopting a practitioner's perspective, illustrating how to effectively set up BO through a representative controller tuning example. We position BO within the broader context of learning paradigms, ranging from deep reinforcement learning to data-driven control, and highlight scenarios where BO is most advantageous. Next, we discuss the diverse range of BO methods that have been developed to tackle complex problems and specific applications. This article provides a unified perspective on the current landscape of BO, emphasizing its relevance to control systems and robotics, and it highlights future prospects by identifying key research challenges and promising avenues for advancing BO in the field. This includes addressing a significant gap in the BO landscape: the lack of standardized benchmark problems specifically for control-related applications. To foster future research and ensure rigorous evaluation, we start an effort towards a lightweight benchmark suite for control engineering and robotics. We also present metrics and best practices to facilitate direct comparisons between new BO algorithms and established state-of-the-art methods.

作者：David Stenger, Paul Brunzema, Johanna Menn, Alexander von Rohr, Angela P. Schoellig, Sebastian Trimpe
:::

## 原始参考来源 (Sources)

- [arXiv 2609.09403：A Decade of Bayesian Optimization for Controller Tuning and Robot Learning: Tutorial, Review, and Future Prospects](https://arxiv.org/abs/2609.09403)