A novel cooperative collision avoidance system for vehicular communication based on deep learning

Global road traffic injuries represent a significant safety challenge, with the highest fatality rates worldwide stemming from a combination of drivers' reckless behavior and the ever-expanding number of vehicles on the roads. In light of these factors, Autonomous Vehicles (AVs) have received a lot of attention as a technology that has the potential to revolutionize various industries and solve a lot of problems. The rise of the Internet of Vehicles (IoV) and Connected Vehicles (CVs) enables AVs to perceive and react swiftly in complex road scenarios, prioritizing safety. These vehicles prioritize individual safety in all situations, significantly enhancing road safety. Mobile Edge Computing (MEC) plays a crucial role thanks to its capacity for minimal latency and high bandwidth capabilities, enabling critical vehicular applications. In this paper, we introduce a cooperative collision avoidance system based on MEC, named 2CAS-MEC, that proactively identifies and locates road hazards. Our system is based on MEC servers positioned alongside roads, it consistently analyzes traffic and hazard data, issuing targeted alerts to nearby vehicles regarding potential risks. Particularly, our work introduces an advanced deep learning system that utilizes 5G, mobile edge computing, and cloud intelligence to prevent vehicle collisions. The experimental results show that our system outperforms the existing related works and exhibits the anticipated performance, effectively helping drivers in accident avoidance.