Stability Enhancement in 4-Wheel Electric Vehicles using Deep Neural Networks

4-wheel electric vehicles (4WEVs) often face challenges in lateral stability during corning driving conditions. Nonlinear Model Predictive Control (NMPC) improves stability but struggles with high computational demands and adaptability to different operating conditions. This study proposes a novel approach to address this issue using artificial neural networks (ANNs) trained on simulated NMPC-controlled vehicle data incorporating tuning parameters as inputs. This way, the trained model represents a family of predictive controllers that can adjust the controller post-implementation to adapt efficiently to changes in operating conditions. The simulations show improvement in performance, robustness, and computation time.