.png){kind=icon}
.png){kind=icon}
Return
A Multi-Intersection Vehicular Cooperative Control Based on End-Edge-Cloud Computing
.png){kind=icon}
OA
AI
DOI：10.1109/TVT.2022.3143828.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Cooperative Intelligent Transportation Systems (C-ITS) will change the modes of road safety and traffic management, especially at intersections without traffic lights, namely unsignalized intersections. Existing researches focus on vehicle control within a small area around an unsignalized intersection. This paper expands the control domain to a large area with multiple intersections. In particular, a Multi-intersection Vehicular Cooperative Control (MiVeCC) is proposed to enable cooperation among vehicles in a large area with multiple unsignalized intersections. Firstly, a vehicular end-edge-cloud computing framework is proposed to facilitate end-edge-cloud vertical cooperation and horizontal cooperation among vehicles. Under the framework, a two-stage reinforcement learning is implemented to obtain the optimal policy for vehicle control. To support RL in the proposed framework, a multi-vehicle state representation method and a safety-oriented value representation method are designed. The former structures the collected vehicle information, and the latter evaluates the traffic condition. A multi-intersection simulation platform is developed to evaluate the proposed scheme. Simulation results show that the proposed MiVeCC can improve travel efficiency at multiple intersections by up to 4.59 times without collision compared with benchmark methods.
Keywords:
Cloud computing
Task analysis
Safety
Roads
Training
Real-time systems
Optimization
Cooperative intelligent transportation systems
connected and autonomous vehicles
deep reinforcement learning
end-edge-cloud
Journal
IF:
7.1
Papers:
1.8W
Citations:
6.6W