Input Convex LSTM: A Convex Approach for Fast Model Predictive Control

arXiv:2311.07202v4 Announce Type: replace
Abstract: Leveraging Input Convex Neural Networks (ICNNs), ICNN-based Model Predictive Control (MPC) successfully attains globally optimal solutions by upholding convexity within the MPC framework. However, current ICNN architectures encounter the issue of exploding gradients, which limits their ability to serve as deep neural networks for complex tasks. Additionally, the current neural network-based MPC, including conventional neural network-based MPC and ICNN-based MPC, faces slower convergence speed when compared to MPC based on first-principles models. In this study, …

abstract architectures arxiv control cs.ce cs.lg cs.sy current eess.sy framework however issue lstm mpc networks neural networks predictive serve solutions type