Research on key scene trajectory generation method based on BLA-VAE

• Published in: 2024 27th International Conference on Computer Supported Cooperative Work in Design (CSCWD) pp. 1923 - 1930
• Main Authors: Wang, Yong, Zhang, Wei, Zhang, Daifeng, Li, Yanqiang, Zhang, Dongbing
• Format: Conference Proceeding
• Language: English
• Published: IEEE 08-05-2024
• Subjects: Autonomous driving tests; Data models; deep learning; Life estimation; Prediction algorithms; Predictive models; Safety; scenario generation; Training; Trajectory; trajectory prediction
• ISSN: 2768-1904
• DOI: 10.1109/CSCWD61410.2024.10580658

To promote the development of self-driving cars and ensure the safety of their functions, testing is an indispensable part, especially for functioning tests under critical scenarios. However, existing natural driving datasets mainly contain data under regular scenarios with a limited proportion of critical edge driving scenarios, which makes it difficult to extract useful critical scenario data from large-scale natural driving data, and test the performance of autonomous driving algorithms under critical scenarios becomes a challenge. To address this challenge, this paper proposes a deep learning-based β-VAE generative modeling framework (BLA-VAE), which combines BiLSTM and Attention mechanism to efficiently and reasonably generate vehicle trajectory data under critical scenarios, and use the data generated by the model to train autonomous driving prediction algorithms. The results show that the generated critical trajectory data has a stronger generalization ability and effectively improves the prediction ability of the automatic driving trajectory prediction algorithm in dangerous scenarios.