Cooperative perception with learning-based V2V communications

Liu, C.; Chen, Y.; Chen, J.; Payton, R.; Riley, M.; Yang, S.

Abstract

Cooperative perception has been widely used in autonomous driving to alleviate the inherent limitation of single automated vehicle perception. To enable cooperation, vehicleto- vehicle (V2V) communication plays an indispensable role. This work analyzes the performance of cooperative perception accounting for communications channel impairments. Different fusion methods and channel impairments are evaluated. A new late fusion scheme is proposed to leverage the robustness of intermediate features. In order to compress the data size incurred by cooperation, a convolution neural network-based autoencoder is adopted. Numerical results demonstrate that intermediate fusion is more robust to channel impairments than early fusion and late fusion, when the SNR is greater than 0 dB. Also, the proposed fusion scheme outperforms the conventional late fusion using detection outputs, and autoencoder provides a good compromise between detection accuracy and bandwidth usage.

Citation

Liu, C., Chen, Y., Chen, J., Payton, R., Riley, M., & Yang, S. (2023). Cooperative perception with learning-based V2V communications. IEEE Wireless Communications Letters, https://doi.org/10.1109/LWC.2023.3295612

• Journal Article Type: Article
• Acceptance Date: Jul 10, 2023
• Online Publication Date: Jul 14, 2023
• Publication Date: 2023
• Deposit Date: Jul 14, 2023
• Publicly Available Date: Jul 14, 2023
• Journal: IEEE Wireless Communications Letters
• Print ISSN: 2162-2337
• Electronic ISSN: 2162-2345
• Publisher: Institute of Electrical and Electronics Engineers
• Peer Reviewed: Peer Reviewed
• DOI: https://doi.org/10.1109/LWC.2023.3295612
• Public URL: https://durham-repository.worktribe.com/output/1168770
• Publisher URL: https://ieeexplore.ieee.org/xpl/RecentIssue.jsp?punumber=5962382