Linear ordinary differential equations constrained Gaussian Processes for solving optimal control problems
Linear ordinary differential equations constrained Gaussian Processes for solving optimal control problems
This paper presents an intrinsic approach for addressing control problems with systems governed by linear ordinary differential equations (ODEs). We use computer algebra to constrain a Gaussian Process on solutions of ODEs. We obtain control functions via conditioning on datapoints. Our approach thereby connects Algebra, Functional Analysis, Machine Learning and Control theory. We discuss the optimality of the control functions generated by the posterior mean of the Gaussian Process. We present numerical examples which underline the practicability of our approach.
Andreas Besginow、Markus Lange-Hegermann、J?rn Tebbe
自动化基础理论自动化技术、自动化技术设备
Andreas Besginow,Markus Lange-Hegermann,J?rn Tebbe.Linear ordinary differential equations constrained Gaussian Processes for solving optimal control problems[EB/OL].(2025-04-17)[2025-05-17].https://arxiv.org/abs/2504.12775.点此复制
评论