Neural Solvers for Fast and Accurate Numerical Optimal Control

Author name not available (Why is that?)

Publication date: 13 March 2022

Abstract: Synthesizing optimal controllers for dynamical systems often involves solving optimization problems with hard real-time constraints. These constraints determine the class of numerical methods that can be applied: computationally expensive but accurate numerical routines are replaced by fast and inaccurate methods, trading inference time for solution accuracy. This paper provides techniques to improve the quality of optimized control policies given a fixed computational budget. We achieve the above via a hypersolvers approach, which hybridizes a differential equation solver and a neural network. The performance is evaluated in direct and receding-horizon optimal control tasks in both low and high dimensions, where the proposed approach shows consistent Pareto improvements in solution accuracy and control performance.

Has companion code repository: https://github.com/diffeqml/diffeqml-research

This page was built for publication: Neural Solvers for Fast and Accurate Numerical Optimal Control

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6393780)