Shucai Xu
9 Papers
Shucai Xu is an academic researcher. The author has contributed to research in topics: Computer science & Frame (networking). The author has co-authored 3 publications.
Chat about Author
Papers
Adaptive Signal Control and Coordination for Urban Traffic Control in Connected Vehicle Environment: A Review
TL;DR: This review summarizes existing CV-based urban traffic signal control systems, highlighting their components, structures, and issues, and discusses future research directions to improve next-generation urban traffic signal control methods and systems in connected vehicle environments.
6
MT-Net: Fast video instance lane detection based on space time memory and template matching
TL;DR: In this paper , a fast video instance lane detection network, called MT-Net, based on space-time memory and template matching was proposed to mitigate jitter from scene changes and other disturbances.
6
V2V‐enabled cooperative adaptive cruise control strategy for improving driving safety and travel efficiency of semi‐automated vehicle fleet
Liqun Peng,Ju Huang,Tuqiang Zhou,Shucai Xu +3 more
TL;DR: The improved CACC model can adapt more accurately and quickly to the maneouvre of vehicle ahead in V2V environment, which can effectively improve the capacity of heterogeneous traffic flow and the safety and comfort of driving.
5
Distributed edge signal control for cooperating pre-planned connected automated vehicle path and signal timing at edge computing-enabled intersections
Jiangchen Li,Liqun Peng,Shucai Xu,Zhixiong Li +3 more
TL;DR: A distributed edge signal control system is proposed to address issues in connected automated vehicle (CAV) technology, integrating automated vehicle path planning information to estimate local demand and optimize signal timing, improving waiting time by up to 30% and time loss by up to 20%.
5
Pursuit Path Planning for Multiple Unmanned Ground Vehicles Based on Deep Reinforcement Learning
Hongda Guo,Youchun Xu,Yulin Ma,Shucai Xu,Zhixiong Li +4 more
TL;DR: Path planning for multiple unmanned ground vehicles based on deep reinforcement learning (DRL) is explored. The proposed method incorporates prioritized experience replay (PER) and a multiple-agent double deep Q-learning network (PER-GDMADDQN) to achieve superior performance in pursuit tasks.
1