arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2012.14964eess.SYcs.ROcs.SY
收藏

系统动力学贝叶斯学习中的控制障碍

Control Barriers in Bayesian Learning of System Dynamics

University of Maine(缅因大学);Massachusetts Institute of Technology(麻省理工学院);University of California San Diego(加利福尼亚大学圣迭戈分校)

Vikas Dhiman, Mohammad Javad Khojasteh, Massimo Franceschetti, Nikolay Atanasov

摘要:

本文的重点是在线学习系统动力学模型,同时满足安全约束。我们的目标是避免离线系统辨识或手动指定的模型,并允许系统在操作过程中安全自主地估计和调整自己的模型。给定系统状态的流观测,我们使用贝叶斯学习来获得系统动态的分布。具体来说,我们提出了一个新的矩阵变量高斯过程(MVGP)回归方法与有效的协方差分解学习漂移和输入增益项的非线性控制仿射系统。MVGP分布被用来优化系统的行为,并确保高概率的安全性,通过指定控制李雅普诺夫函数(CLF)和控制障碍函数(CBF)的机会约束。通过求解二阶锥规划(SOCP),我们证明了对于具有任意相对度和概率CLF-CBF约束的系统,可以合成一个安全的控制策略。最后,我们将我们的设计扩展到自触发公式,自适应地确定需要应用新的控制输入以保证安全的时间。

英文摘要:

This paper focuses on learning a model of system dynamics online while satisfying safety constraints. Our objective is to avoid offline system identification or hand-specified models and allow a system to safely and autonomously estimate and adapt its own model during operation. Given streaming observations of the system state, we use Bayesian learning to obtain a distribution over the system dynamics. Specifically, we propose a new matrix variate Gaussian process (MVGP) regression approach with an efficient covariance factorization to learn the drift and input gain terms of a nonlinear control-affine system. The MVGP distribution is then used to optimize the system behavior and ensure safety with high probability, by specifying control Lyapunov function (CLF) and control barrier function (CBF) chance constraints. We show that a safe control policy can be synthesized for systems with arbitrary relative degree and probabilistic CLF-CBF constraints by solving a second order cone program (SOCP). Finally, we extend our design to a self-triggering formulation, adaptively determining the time at which a new control input needs to be applied in order to guarantee safety.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑