用随机函数建模未知系统，无需先验假设即可安全优化控制参数。
Safe learning-based control via function-based uncertainty quantification
- 将未知函数视为可采样的随机函数，通过采样构建高概率不确定性区间。
- 在真实倒立摆上实现安全控制参数调优，避免传统方法对平滑性的依赖。
- 适合需高安全性且模型未知的机器人控制场景，尤其处理突变或不连续系统。
在安全关键系统中部署基于学习的控制方法时，不确定性量化至关重要。现有方法通常依赖对未知函数的强假设，如已知函数范数或Lipschitz常数的上界，难以处理间断情况。本文将未知函数建模为可生成独立同分布实现的随机函数，利用情景法构造高概率成立的不确定性区间，仅依赖采样结果。将这些不确定性区间集成到安全贝叶斯优化算法中，并在真实Furuta摆上成功实现了控制参数的安全调优。
原文摘要 · Abstract (English)
Uncertainty quantification is essential when deploying learning-based control methods in safety-critical systems. This is commonly realized by constructing uncertainty tubes that enclose the unknown function of interest, e.g., the reward and constraint functions or the underlying dynamics model, with high probability. However, existing approaches for uncertainty quantification typically rely on restrictive assumptions on the unknown function, such as known bounds on functional norms or Lipschitz constants, and struggle with discontinuities. In this paper, we model the unknown function as a random function from which independent and identically distributed realizations can be generated, and construct uncertainty tubes via the scenario approach that hold with high probability and rely solely on the sampled realizations. We integrate these uncertainty tubes into a safe Bayesian optimization algorithm, which we then use to safely tune control parameters on a real Furuta pendulum.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。