首页|Cooperative Merging in Mixed Traffic: A Mobile-Edge Hybrid Control Framework

Cooperative Merging in Mixed Traffic: A Mobile-Edge Hybrid Control Framework

扫码查看
原文链接
  • NETL
  • NSTL
  • IEEE
This paper addresses decision-making challenges in mixed traffic environments comprising both conventional human-operated vehicles (HVs) and connected automated vehicles (CAVs). Our proposed framework is exemplified using a ramp merging scenario and is structured as an optimization problem, in which a merge sequencing problem and a trajectory planning problem are embedded and solved by a bi-level hybrid centralized-decentralized model predictive control (HMPC) approach. The HMPC framework we introduce leverages centralized edge computing for efficient merge decision optimization through a dynamic-programming approach and decentralized mobile computing for distributed trajectory planning through three different optimization algorithms. Simulation results show that compared to open-loop control, the proposed framework can ensure system efficient ramp-merging control, and exhibits robustness in the presence of uncertainty caused by the stochastic driving behaviors of HVs. In addition, it is found that mobile-edge hybrid framework can reduce the computational time to the millisecond-level, potentially meeting real-time computational requirements.

MergingTrajectoryOptimizationUncertaintySequential analysisDecision makingSunCentralized controlTransportationTrajectory planning

Zhanbo Sun、Ziyan Gao、Xiangyu He、Zheyi Li、Tianyu Huang

展开 >

School of Transportation and Logistics and the National Engineering Laboratory of Integrated Transportation Big Data Application Technology, Southwest Jiaotong University, Chengdu, China

SenseTime, Shanghai, China

School of Transportation and Logistics, Southwest Jiaotong University, Chengdu, China

Department of Civil and Environmental Engineering, Carnegie Mellon University, Pittsburgh, PA, USA

College of Air Traffic Management, Civil Aviation Flight University of China, Guanghan, China

展开 >

2025

10.1109/TITS.2025.3540136

IEEE transactions on intelligent transportation systems

IEEE transactions on intelligent transportation systems

ISSN：
年,卷(期)：2025.26(4)
  • 54