Few-shot recognition of lane-changing intention in connected vehicle environment: A meta-transformer approach
- 1School of Business, Xinjiang University, Urumqi, China.
- 2School of Transportation, Tongji University, Shanghai, China.
- 3The Key Laboratory of Road and Traffic Engineering of the Ministry of Education, Tongji University, Shanghai, China.
Abstract
This paper proposes a Meta-Transformer model for few-shot accurate lane-changing intention recognition in connected vehicle environment. Given the velocity, acceleration, distance headway, time headway and time to collision of a vehicle at past time steps, a transformer model is developed to recognize the lane changing intention of the vehicle at the current time step. The multi-head attention layer of the Transformer model is capable of effectively extracting features from the multivariate time serie input. This enhances the accuracy of lane-changing intention recognition. The Transformer model is combined with a model -agnostic meta-learning (MAML) algorithm to be able to perform well with small amount of training data. The meta-learning consists of meta-training and meta-testing. During the meta-training, a task is sampled from the distribution over tasks. The tasks include recognition of intention of lane-keeping, lane-changing to left lane, and lane-changing to right lane. The model is trained with few samples and feedback from the loss function defined on the tasks. The loss function is defined as the categorical cross entropy of the errors between the labels and the results generated by the proposed model. During the meta-testing, the model is tested on new data from the distribution of the transition from a feature and the label to another feature. The model is trained by minimizing the test error. Experimental results show that the proposed model can achieve 8.7 percentage points higher accuracy than a transformer model.
Related
- A freshwater resilient and connected network to sustain biodiversity under a changing climate
- A human CHRNA6 3' UTR variant alters the molecular environment and microRNA engagement of the adolescent VTA without changing Chrna6 transcript abundance
- UniHAR: A unified hierarchical transformer with multi-scale temporal modeling for wearable human activity recognition
- Lightweight frequency-aware hybrid vision transformer for fine-grained plant disease recognition
- Lightweight CNN and transformer detectors for real-time single-fruit date-variety recognition on edge GPU hardware
BibTeX
@article{liu2026fewshot,
title = {{Few-shot recognition of lane-changing intention in connected vehicle environment: A meta-transformer approach}},
author = {Xiaoqian Liu and Wenxin Jiang and Yining Ren},
journal = {PLOS One},
year = {2026},
month = oct,
doi = {10.1371/journal.pone.0361594},
url = {https://doi.org/10.1371/journal.pone.0361594},
note = {CC BY},
}
RIS
TY - JOUR
TI - Few-shot recognition of lane-changing intention in connected vehicle environment: A meta-transformer approach
AU - Xiaoqian Liu
AU - Wenxin Jiang
AU - Yining Ren
PY - 2026
DA - 2026/10/29
JO - PLOS One
DO - 10.1371/journal.pone.0361594
UR - https://doi.org/10.1371/journal.pone.0361594
AB - This paper proposes a Meta-Transformer model for few-shot accurate lane-changing intention recognition in connected vehicle environment. Given the velocity, acceleration, distance headway, time headway and time to collision of a vehicle at past time steps, a transformer model is developed to recognize the lane changing intention of the vehicle at the current time step. The multi-head attention layer of the Transformer model is capable of effectively extracting features from the multivariate time serie input. This enhances the accuracy of lane-changing intention recognition. The Transformer model is combined with a model -agnostic meta-learning (MAML) algorithm to be able to perform well with small amount of training data. The meta-learning consists of meta-training and meta-testing. During the meta-training, a task is sampled from the distribution over tasks. The tasks include recognition of intention of lane-keeping, lane-changing to left lane, and lane-changing to right lane. The model is trained with few samples and feedback from the loss function defined on the tasks. The loss function is defined as the categorical cross entropy of the errors between the labels and the results generated by the proposed model. During the meta-testing, the model is tested on new data from the distribution of the transition from a feature and the label to another feature. The model is trained by minimizing the test error. Experimental results show that the proposed model can achieve 8.7 percentage points higher accuracy than a transformer model.
SN - 1932-6203
ER -