Design and Application of Deep Learning-Based Crash Damage Prediction Model for Self-Driving Cars

Abstract

Abstract The collision damage of automated cars has grown in importance as self-driving car technology has advanced to the pilot operation stage. To enhance the safety of autonomous vehicles by predicting and preventing potential hazards during autonomous driving, this study presents a model for collision damage prediction in automated driving cars. The model optimizes deep convolutional neural networks using the self-attention mechanism and incorporates a degree convolutional neural network algorithm with the attention mechanism. Its application is key to reduce risks in autonomous driving. The results demonstrated that the accuracy, reliability, specificity, and Mathews correlation coefficient of the improved algorithm were 94.0%, 94.8%, 93.6%, and 0.88, respectively, resulting in a high overall performance. The prediction model's accuracy during training on the training data set and validation data set was 100% and 98%, respectively, demonstrating its efficacy. The prediction model's prediction accuracy in calculating the degree of auto collision damage for 10 working conditions in the validation data set was 83.3%. The prediction results were essentially consistent with the trend of the actual collision damage degree curve, demonstrating both the viability and high prediction accuracy of the prediction model. The aforementioned findings demonstrated the model's strong performance and great application value in the field of self-driving car collision avoidance and warning.