Digital Twins Based VR Simulation for Accident Prevention of Intelligent Vehicle

Abstract

This work aims to prevent Traffic Accident (TA) and ensure drivers’ and pedestrians’ life and property safety. A TA prevention and prediction system is established based on Digital Twins (DTs) and Artificial Intelligence (AI). Firstly, the double-scale decomposition equation decomposes the original TA Time Series Data (TSD) into multiple sub-layers. The Long-Short Term Memory (LSTM) network is used to predict the low-frequency sub-layers. Then, the double-scale LSTM network prediction model is constructed based on the prediction results. Secondly, a Particle Filter (PF) is proposed based on target block tracking and improved resampling against the possible occlusion problem in target tracking. The proposed PF can improve particle dilution. Finally, the proposed target tracking algorithm and DTs are combined and applied to TA processing, and a motor vehicle road TA-oriented video analysis system is designed. Then, the proposed system is tested. The results corroborate that the proposed research model can effectively predict the TSD of TA compared with other models and has strong robustness. Compared with the original LSTM model and Stacked Auto Encoders (SAEs) prediction model, the prediction accuracy of the proposed model is improved by 6% and 8%, respectively. Besides, the training and prediction time of the proposed model is less than the original LSTM and SAEs models. The optimized Particle Swarm Optimization (PSO) model makes the target identification easier. Additionally, the proposed model has good generalization performance. In short, the proposed system can effectively improve the efficiency of TA handling and ensure accuracy and fairness, which provides some data support for applying DTs in intelligent transportation.

Topics & Concepts