Research On Video Control Decision Algorithm For Remote Driving

With the continuous development of the automobile manufacturing industry,the number of private car ownership is growing rapidly in China,which leads to increasingly serious traffic congestion and travel safety problems,therefore there is an urgent need for the establishment of intelligent transportation systems.With the continuous development of vehicle networking technology in recent years,it has attracted widespread attention in the automotive industry.Remote driving technology is an important part of it,it can track the driving status of the vehicle in real-time,and take over the vehicle by the remote control center in time in the case of emergency,so as to realize remote driving,prevent danger,and improve vehicle safety.When the vehicle is driving remotely on the road,the real-time video information returned by the vehicle terminal through the network is an important basis for the remote control center to carry out remote driving.The vehicle terminal usually drives in the coverage of many different standard wireless networks,which requires the vehicle terminal to maintain a stable return of video images through effective internetwork switching and adaptive adjustment of the video transmission rate.This thesis focuses on the wireless network switching problem and the adaptive adjustment of bit rate for real-time video transmission when vehicles are driven remotely in a connected vehicle environment,and proposes corresponding solutions.A multi-attribute vertical switching algorithm based on vehicle network is proposed to address the problems of untimely response when making network switches and the ping-pong effect caused by too many switching times when the vehicle terminal performs network switching in the vertical networking scenario.This algorithm first pre-filters the networks to be accessed and selects those that meet the conditions,and then determines the weights of the network attributes by Fuzzy Analytic Hierarchy Process(FAHP),The TOPSIS algorithm determines the optimal network and finally switches the optimal network.Simulation results show that the algorithm in this paper can successfully perform network switching,and can reduce the frequency of switching,reduce the ping-pong effect,and improve the switching performance and stability of the vehicle-side network system.In the process of real-time video transmission at the vehicle terminal,due to the change of the network environment,the video transmission rate can not be adaptively adjusted,which result in delay and congestion.To address these problems,we improved an adaptive rate adjustment method based on detection method.This algorithm uses the network evaluation parameters fed back by the video receiver as the basis for predicting the real-time network environment and introduces the delay jitter as a new evaluation parameter on the basis of the original network state evaluation parameter,then according to the improved video transmission rate adjustment mechanism in this paper to make timely response to the change of network state,so that the video data transmission rate and the network channel match in real-time.The test results show that the improved algorithm can accurately adjust the video transmission rate and better meet the transmission requirements at the vehicle terminal.