Research on Dynamic Path Planning of Internet of Vehicles Based on Edge Computing

Abstract

Vehicles in the Internet of Vehicles can be regarded as a mobility platform integrating perception, communication and computing capabilities. The vehicle can collect the surrounding environment data in real time through the vehicle-mounted sensor system, make intelligent decisions by using the vehicle computing resources, and realize the circular feedback of control decisions through the information interaction between workshops, thus forming an autonomous system to improve the traffic efficiency. Due to the limited local computing resources of vehicles, it is difficult to meet the performance requirements of real-time decision-making based on computation-intensive tasks such as image recognition and video processing in complex and highly dynamic scenes. As one of the key technologies of intelligent vehicles, path planning has a wide application prospect not only in intelligent vehicles, but also in similar mobile robots. In this paper, aiming at the dynamic path planning of vehicle navigation, a dynamic path planning algorithm of vehicle networking based on edge computing is proposed. In order to solve the shortage of local computing resources for vehicles, the mobile edge computing is used to unload the vehicle tasks to the mobile edge computing server, which reduces the overall network energy consumption and meets the task delay requirements. Intelligent vehicle is a hot research topic at home and abroad at present. It has made breakthrough progress in many key technologies, and will be officially launched in the next decade. However, in the Internet of Vehicles, the dissemination of road information lacks a trust mechanism, which easily leads to attacks. The vehicle can collect the surrounding environment data in real time through the vehicle-mounted sensor system, make intelligent decisions by using the vehicle computing resources, and realize the circular feedback of control decisions through the information interaction between workshops, thus forming an autonomous system to improve the traffic efficiency. Due to the limited local computing resources of vehicles, it is difficult to meet the real-time decision-making performance requirements based on computing intensive tasks such as image recognition and video processing in complex and high dynamic scenes. As one of the key technologies of intelligent vehicles, path planning has a wide application prospect not only in intelligent vehicles, but also in similar mobile robots. Artificial immune system is designed based on the model of biological immune system. It has strong abilities of learning and memory, information processing, feature extraction and body defense. It is widely used in many industries.