AUTHOR=Tian Yong , Tan Jun TITLE=Improvement of action recognition based on ANN-BP algorithm for auto driving cars JOURNAL=Frontiers in Mechanical Engineering VOLUME=Volume 10 - 2024 YEAR=2024 URL=https://www.frontiersin.org/journals/mechanical-engineering/articles/10.3389/fmech.2024.1400728 DOI=10.3389/fmech.2024.1400728 ISSN=2297-3079 ABSTRACT=With the development of artificial intelligence and autonomous driving technology, the application of action recognition in automobile autonomous driving becomes more and more important. The traditional feature extraction method uses adaptive search hybrid learning, which requires manual design of the feature extraction process and is difficult to meet the recognition needs in complex environments. This study presents a fusion algorithm, performs time-frequency analysis for traveling feature classification, and back propagation operation in artificial neural networks to boost the algorithm's speed of convergence. This algorithm's performance analysis experiments were carried out on the Autov dataset, and the results were compared with those of the other three algorithms. When the road sample was 547, the vehicle driving ability of the fusion algorithm was 4.7, which was the best performance among the four algorithms and indicated that the fusion algorithm has strong adaptability. Following the car action coefficient of 227, the judgment accuracy of the four algorithms were 0.98, 0.94, 0.93, and 0.95, respectively, indicating that the fusion algorithm has stability. The experimental findings demonstrate the accuracy and practicality of the fusion algorithm suggested in the study for action identification of automated vehicle driving, as well as its ability to lower operating vehicle risk.