A review of integrated perception and decision-making for autonomous driving

In recent years, end-to-end solutions integrating perception and decision-making have made groundbreaking progress, providing new approaches to enhancing the safety and reliability of autonomous driving. Existing reviews often focus on the perception of the external environment by individual vehicles, overlooking the complex interactions in multi-agent collaboration. Based on the current state of research, integrated perception and decision-making methods for single agents were explored from an application perspective, and methods under multi-agent collaborative conditions were analyzed. Firstly, foundational technologies for integrated perception and decision-making in autonomous driving were summarized. Secondly, the latest research advancements in integrated perception and decision-making technologies for autonomous driving were highlighted. Thirdly, large-scale public datasets commonly used in the field of autonomous driving were elaborated upon. Then, the evaluation methods currently employed for integrated perception and decision-making in autonomous driving were introduced. Finally, a summary and outlook on integrated perception and decision-making in autonomous driving were presented.