Suggested Citation:
Zhao, Jingyuan and Andrew Burke (2025)

Deep Learning for Planning and Control in Autonomous Vehicles

In autonomous systems, path planning and control are critical for ensuring safety, efficiency, and comfort. Deep learning has significantly enhanced these aspects by introducing adaptability and real-time responsiveness into autonomous operations. Reinforcement learning-based motion planning algorithms, for example, are adept at devising optimal navigation paths even within intricate environments. Moreover, trajectory prediction models, particularly those employing recurrent neural networks, excel in anticipating the movements of nearby objects accurately. Furthermore, the integration of end-to-end methodologies has augmented the capabilities of autonomous control systems, providing a more streamlined approach to decision-making processes. The application of explainable AI techniques brings a layer of transparency to these technologies, elucidating the reasoning behind decisions and fostering trust among users. Herein, we explore these technological advancements and examine their impact on the development of autonomous vehicle technology.