Accelerating Autonomy: Navigating the Roads with Deep Reinforcement Learning in Autonomous Driving Systems

EasyChair Preprint 11944

Abstract

This research explores the application of deep reinforcement learning (DRL) techniques in autonomous driving systems, aiming to enhance decision-making capabilities and overall performance. By leveraging advanced neural networks and reinforcement learning algorithms, the proposed model demonstrates improved adaptability to dynamic environments, enabling autonomous vehicles to navigate complex road scenarios effectively. The study evaluates the effectiveness of the DRL approach through simulations and real-world experiments, highlighting its potential to revolutionize the landscape of autonomous driving technology.

Keyphrases: Adaptability, Deep Reinforcement Learning, autonomous driving, decision making, neural networks, real-world experiments, simulation

@booklet{EasyChair:11944,
  author    = {Asad Ali and Mugil Raja},
  title     = {Accelerating Autonomy: Navigating the Roads with Deep Reinforcement Learning in Autonomous Driving Systems},
  howpublished = {EasyChair Preprint 11944},
  year      = {EasyChair, 2024}}