AI RESEARCH
Towards Safe Learning-Based Non-Linear Model Predictive Control through Recurrent Neural Network Modeling
arXiv CS.LG
•
ArXi:2603.24503v1 Announce Type: new The practical deployment of nonlinear model predictive control (NMPC) is often limited by online computation: solving a nonlinear program at high control rates can be expensive on embedded hardware, especially when models are complex or horizons are long. Learning-based NMPC approximations shift this computation offline but typically demand large expert datasets and costly