| 引用本文: | 任瑞,邹媛媛,李少远.具有安全性保证的基于增强主动学习的模型预测控制(英文)[J].控制理论与应用,2021,38(11):1735~1742.[点击复制] |
| REN Rui,ZOU Yuan-yuan,LI Shao-yuan.Enhanced active learning for model-based predictive control with safety guarantees[J].Control Theory and Technology,2021,38(11):1735~1742.[点击复制] |
|
| 具有安全性保证的基于增强主动学习的模型预测控制(英文) |
| Enhanced active learning for model-based predictive control with safety guarantees |
| 摘要点击 1948 全文点击 466 投稿时间：2021-08-25 修订日期：2021-11-15 |
| 查看全文 查看/发表评论 下载PDF阅读器 |
| DOI编号 10.7641/CTA.2021.10796 |
| 2021,38(11):1735-1742 |
| 中文关键词 模型预测控制 主动学习 高斯过程回归 对偶控制 信息增益 |
| 英文关键词 model predictive control active learning Gaussian process regression dual control information gain |
| 基金项目 科技创新2030“新一代人工智能”重大项目（2018AAA0101701） |
|
| 中文摘要 |
| 本文提出了一种基于主动学习的增强模型预测控制方法. 该方案克服了大多数基于学习的方法的缺点, 即只能
被动地利用可获得的系统数据并导致学习缓慢. 首先应用高斯过程来评估残差模型的不确定性并构建多步预测模型. 然
后提出了一个两阶段主动学习策略, 通过在优化问题中引入信息增益作为对偶目标来激励系统探测. 最后, 基于鲁棒不
变集定义了安全控制输入集保证了状态约束满足与系统安全性. 本文提出的方法在保证系统安全的情况下提高了学习
能力和闭环控制性能, 实验说明了本文方案的优越性. |
| 英文摘要 |
| This paper proposes an active learning-based MPC scheme that overcomes the shortcomings of most learningbased
methods which passively leverage the available system data and result in slow learning. We first apply Gaussian
process regression to assess the residual model uncertainty and construct multi-step predictive model. Then we propose a
two-step active learning strategy and reward the system probing by introducing information gain as dual objective in the
optimization problem. Finally, the safe control input set is defined based on robust admissible input set to robustly guarantee
state constraint satisfaction. The proposed method improves the learning ability and closed-loop performance with safety
guarantees. The advantages of our proposed active learning-based MPC scheme are illustrated in the experiments. |