Multi-intelligent connected vehicle longitudinal collision avoidance control and exhaust emission evaluation based on parallel theory

Abstract

With the increasing of vehicle volume and driving speed, traffic accidents and environmental safety have become social concerns. Vehicle traffic accidents, especially multi-vehicle chain accidents, cause damage to property and human lives. Meanwhile, traffic pollution will lead to continuous harm to living environment and health. This is a coupled human-vehicle-environment interaction system, which is difficult to model with traditional mathematical methods. Parallel theory is an effective method to solve such complex problems based on advanced artificial intelligence and computer technology. In this paper, a parallel system is built to analyze and control multi-intelligent connected vehicle based on parallel theory. The parallel system is also used to analyze and assess the exhaust emission of multi-intelligent connected vehicle. The parallel system is carried out with three steps: 1) modeling and representation of multi-intelligent connected vehicle system using artificial societies; 2) analysis and evaluation by computational experiments; 3) control, management and exhaust emission evaluation through parallel execution of real and artificial systems and big data. The parallel control methods, models and conclusions obtained from this paper can be used to enhance the experience of safety in multi-vehicle control under vehicle to everything environment and make the safety intervention measures more efficient.