Toward interpretable anomaly detection for autonomous vehicles with denoising variational transformer

Haigen Min, Xiaoping Lei, Xia Wu, Yukun Fang, Shixiang Chen, Wuqi Wang, Xiangmo Zhao

Abstract: Highlights•An interpretable anomaly detection framework for autonomous vehicle sensor data.•An innovative unsupervised model named DVT based on variational attention.•A low computational cost and simple implementation residual interpreter.