Robust Deep Reinforcement Learning in Autonomous Car Path Planning
Year: 2024
Type: article
Abstract: The rapid advancements in autonomous vehicle technology have emphasized the need for adaptable and dependable control systems. Deep Reinforcement Learning (DRL) has emerged as a key method to address the complexity involved in autonomous driving. This research explores how DRL can enhance path planning and control mechanisms in self-driving vehicles, with a particular focus on its ability to handle dynamic traffic environments. The challenges in training DRL models, including generalization, safety, and real-time decision-making, are analyzed. The paper also suggests potential research directions for improving DRL's application in autonomous driving, offering insights into its strengths and limitations in the current technological landscape
Authors: Dr. Vikas Mahandule, Mrs. Harsha Patil, Mr. Ayush Thakur
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: diamond
OpenAlex ID: W4404494626