Vehicle lane change prediction with explainable soft mask attention mechanism and heterogeneous information encoder
- 1School of Transportation, Southeast University
Abstract
Lane-change intention prediction is critical for intelligent vehicles, and driver decisions depend on the perception and processing of driving context information. Despite advances in deep learning in this domain, further exploration of the driving context processing remains essential. This study proposes a soft mask attention mechanism to adaptively enhance or suppress input features from target and surrounding vehicles. After that, the masked features are extracted using a heterogeneous information encoder, thereby differentiating between target and surrounding vehicle information processing. The encoded features are then integrated using a multi-head attention mechanism, and the lane change probabilities are output through convolution operations and decoder layers. Experiments demonstrate: (1) The proposed SMILE-LC (Soft Mask Information with Lane-based Encoding for Lane Change) achieves optimal prediction performance across all perception ranges with strong efficiency and generalization. (2) The soft mask attention mechanism intuitively reveals the information processing patterns in prediction model. The target vehicle’s lateral acceleration is the most critical feature, while the position information of surrounding vehicles is more important than their velocity and acceleration. (3) The heterogeneous information encoder significantly improves lane change prediction performance, and the proposed lane-based encoding strategy outperforms other encoding architectures. These results can significantly advance the development of Advanced Driver Assistance Systems (ADAS) and enhance lane-change safety.
Related
- Hybrid Explainable Deep Ensemble Framework with self-attention mechanism for early prediction of depression severity using PHQ-9 clinical and behavioral data
- A multi task deep learning framework for automated health condition prediction from retinal fundus images using hybrid attention and explainable AI
- Explainable deep graph attention learning with enhanced residual SwinV2 transformer for interpretable facial paralysis severity assessment
- Does predictive accuracy reflect anatomical attention in CVM staging? evidence from explainable held-out vendor evaluation.
- HierTAC-Net: a robust and explainable hierarchical attention network for multi-configuration gastrointestinal endoscopic image classification
BibTeX
@article{bao2026vehicle,
title = {{Vehicle lane change prediction with explainable soft mask attention mechanism and heterogeneous information encoder}},
author = {Qiong Bao and Huansong Zhang and Yongjun Shen},
journal = {Scientific Reports},
year = {2026},
month = jul,
doi = {10.1038/s41598-026-62718-6},
url = {https://doi.org/10.1038/s41598-026-62718-6},
note = {CC BY},
}
RIS
TY - JOUR
TI - Vehicle lane change prediction with explainable soft mask attention mechanism and heterogeneous information encoder
AU - Qiong Bao
AU - Huansong Zhang
AU - Yongjun Shen
PY - 2026
DA - 2026/07/01
JO - Scientific Reports
DO - 10.1038/s41598-026-62718-6
UR - https://doi.org/10.1038/s41598-026-62718-6
AB - Lane-change intention prediction is critical for intelligent vehicles, and driver decisions depend on the perception and processing of driving context information. Despite advances in deep learning in this domain, further exploration of the driving context processing remains essential. This study proposes a soft mask attention mechanism to adaptively enhance or suppress input features from target and surrounding vehicles. After that, the masked features are extracted using a heterogeneous information encoder, thereby differentiating between target and surrounding vehicle information processing. The encoded features are then integrated using a multi-head attention mechanism, and the lane change probabilities are output through convolution operations and decoder layers. Experiments demonstrate: (1) The proposed SMILE-LC (Soft Mask Information with Lane-based Encoding for Lane Change) achieves optimal prediction performance across all perception ranges with strong efficiency and generalization. (2) The soft mask attention mechanism intuitively reveals the information processing patterns in prediction model. The target vehicle’s lateral acceleration is the most critical feature, while the position information of surrounding vehicles is more important than their velocity and acceleration. (3) The heterogeneous information encoder significantly improves lane change prediction performance, and the proposed lane-based encoding strategy outperforms other encoding architectures. These results can significantly advance the development of Advanced Driver Assistance Systems (ADAS) and enhance lane-change safety.
SN - 2045-2322
ER -