A method of vehicle networking environment information sharing based on distributed fountain code

Abstract

The exchange of perceptual information between autonomous vehicles could significantly improve driving safety. In general, obtaining more information means driving more safely. However, Frequent information sharing consumes a significant amount of channel bandwidth resources, which will reduce transmission efficiency and increase delay, especially in crowded cities. This paper presents a novel method of motion prediction compensation to solve this problem. Firstly, we propose a distributed fountain coding scheme to improve transmission efficiency and reduce vehicles’ delay in acquiring peripheral information. Secondly, we design a mobile prediction model and information transmission control algorithm to reduce traffic while ensuring information reliability. The simulation results show that the prediction accuracy of this method is above 94 %, the information transmission is reduced by more than 50 %, and the vehicle perception rate is increased by 34 %.

Keywords

• Cooperative perception
• Mobility prediction
• Autonomous vehicles
• V2V
• Vehicular ad-hoc network
• Neural network