.png){kind=icon}
.png){kind=icon}
Return
NEURAL NETWORK-BASED OPTIMAL CONTROL: THEORY AND IMPLEMENTATION
.png){kind=icon}
PRE
AI
DOI：10.3934/dcdss.2026013.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
This paper presents a novel neural network-based framework for solving optimal control problems. The approach combines deep learning with traditional optimal control theory to handle complex dynamics and constraints. We introduce a neural network architecture that generates optimal control sequences while satisfying system dynamics and operational constraints. The proposed method is evaluated by two cases: a traditional linear quadratic regulation problem and a real-world unmanned aerial vehicle scenario. When benchmarked against conventional solvers, the proposed approach demonstrates superior performance.
Keywords:
Optimal control theory
neural network
optimization
Journal
D
IF:
1
Papers:
188
Citations:
0