Tese: Nonlinear identification and predictive control of vehicle dynamics
Aluno(a) : Lucas Castro SousaOrientador(a): Helon Ayala
Área de Concentração: Mecânica Aplicada
Data: 14/02/2023
Link para tese/dissertação: https://doi.org/10.17771/PUCRio.acad.62096
Resumo: Autonomous vehicles are those in which some aspects of a safety critical control function (e.g., steering, braking) occur without direct driver interference increasing safety and improving energy efficiency. Moreover, autonomous vehicles can understand the environment to navigate safely at a determined trajectory, enhancing driver comfort, traffic flow, and transportation costs. One critical part is establishing accurate and computationally efficient vehicle models. Thus, to cope with these problems, the present work applies artificial neural networks and system identification methods to perform vehicle modeling and trajectory tracking control. First, a neural architecture is used to capture tire characteristics present in the interaction between lateral and longitudinal vehicle dynamics, reducing computational costs for predictive controllers. Secondly, a combination of black-box models is used to improve predictive control. Then, a hybrid approach combines data-driven models with black-box modeling of the discrepancies. This approach is chosen to improve the accuracy of vehicle modeling by proposing a discrepancy model to capture mismatches between vehicle models and measured data. Results are shown when the novel methods are applied to systems with simulated and real data and compare them with approaches found in the literature, showing overall favorable results for the proposed approaches herein.