Zhongxia Yan

Papers

Total Citations

H-Index

About

Zhongxia Yan is an emerging researcher at the forefront of intelligent transportation systems, autonomous driving, and multi-agent coordination. His work bridges reinforcement learning, robotics, and control theory to address some of the most pressing challenges in modern mobility. Yan's most influential contribution, "Unified Automatic Control of Vehicular Systems With Reinforcement Learning" (2022, 54 citations), demonstrates his pioneering application of deep reinforcement learning to nonlinear vehicular dynamics, offering unified frameworks for mitigating traffic congestion and improving system-wide efficiency across varying levels of vehicle automation. This work has become a key reference for researchers exploring data-driven approaches to transportation control. Building on this foundation, Yan has expanded his research into cooperative autonomous driving, leveraging multi-agent path finding (MAPF) algorithms — traditionally developed in robotics — to coordinate connected and automated vehicles at intersections. Notably, his 2024 studies tackle both fully automated fleets and the more realistic, complex scenario of mixed autonomy traffic, where autonomous vehicles must coexist and coordinate with human-driven counterparts. Yan's research trajectory reflects a sophisticated understanding that real-world deployment demands solutions robust to human unpredictability, making his contributions particularly valuable to both academic researchers and transportation engineers working toward scalable autonomous mobility systems.