This article presents an adaptive predictive model control solution for autonomous vehicles that does not depend on the vehicle's learning model. The adaptive forecaster uses historical information to predict and adjust future performance, updating the model based on real-time feedback. Adaptive predictive control is computationally intensive, requiring powerful hardware. The adaptive model prediction method enhances the vehicle's autonomous capabilities in navigating complex driving problems. Apd_MPC provides a solution that promises to improve vehicle autonomy in complex driving situations. Based on the foundation of Apd_MPC, developing predictive control systems for autonomous vehicles helps optimize vehicle control and creates a flexible and precise mechanism for handling complex traffic situations. Applying Apd_MPC in autonomous vehicles helps improve prediction capabilities and optimizes operating procedures, assisting vehicles to move more safely and efficiently in diverse street environments. Advances in this field promise to bring essential breakthroughs in autonomous vehicle technology in the future.
Trajectory Tracking Control for Autonomous Cars Navigation Using an Adaptive Prediction Model Controller: An Experiment
Lect. Notes in Networks, Syst.
International Conference on Advances in Information and Communication Technology ; 2024 ; Thai Nguyen, Vietnam November 16, 2024 - November 17, 2024
11.03.2025
10 pages
Aufsatz/Kapitel (Buch)
Elektronische Ressource
Englisch
Trajectory Tracking and Navigation Model for Autonomous Vehicles Using Reinforcement Learning
Springer Verlag | 2024
|Adaptive trajectory tracking control for autonomous vehicle platoons
British Library Conference Proceedings | 2023
|Bayesian model prediction trajectory tracking control method for autonomous vehicle
Europäisches Patentamt | 2024
|