Model-free Learning to Avoid Constraint Violations: An Explicit Reference Governor Approach
Model-free Learning to Avoid Constraint Violations: An Explicit Reference Governor Approach
复制标题
无模型学习以避免约束违规：显式参考调控器方法
DOI：
10.23919/acc.2019.8814772
复制
发表时间：
2019
期刊：
影响因子：
--
通讯作者：
A. Girard
中科院分区：
文献类型：
--
作者：
Kaiwen Liu;Nan I. Li;Denise M. Rizzo;E. Garone;I. Kolmanovsky;A. Girard
在先进的地面车辆和推进系统及其组件中，尤其是在这些系统小型化的情况下，热、动力、牵引和侧翻限制以及执行器范围和速率限制等限制因素普遍存在。这些车辆和系统将在未知环境中运行，需要识别和避免退化或损坏。本文提出了一种无模型学习算法，该算法随着时间的推移修改显式参考调控器（ERG）方案的参数，以便在充分提供信息的学习阶段后避免违反预先指定的约束。ERG将设定值命令修改为标称闭环系统。我们的学习算法基于在学习阶段观察到的约束违反来修改ERG参数，从而在学习完成后消除约束违反。分析了该算法的理论特性，并给出了若干实例，说明了该算法的有效性。
Constraints, including thermal, power, traction and rollover limits, as well as actuator range and rate limits, are ubiquitous in advanced ground vehicles and propulsion systems, and in their components, especially as these systems are downsized. These vehicles and systems will be operating in unknown environments where the recognition and avoidance of degradation or damage will be required. This paper proposes a model-free learning algorithm that over time modifies the parameters of an explicit reference governor (ERG) scheme so that violations of pre-specified constraints are avoided after a sufficiently informative learning phase. The ERG modifies setpoint commands to a nominal closed-loop system. Our learning algorithm modifies the ERG parameters based on observed constraint violations during a learning phase so as to eliminate constraint violations after learning is completed. Theoretical properties of the algorithm are analyzed and several examples that illustrate its effectiveness are presented.