Lane Change Trajectory Prediction based on Spatiotemporal Attention Mechanism

Yang, Shichun; Chen, Yu-Yi; Cao, Yaoguang; Wang, Rui; Shi, Runwu; Lu, Jiayi

doi:10.1109/itsc55140.2022.9922250

Cited by 3 publications

(3 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Among these, self-attention only extracts information from the input without utilizing additional information. Self-attention is more suitable for practical engineering applications since it requires fewer parameters and computes more quickly [55]. In light of this, the self-attention mechanism is employed to construct an LC risk recognition model [56].…”

Section: Attention Mechanismmentioning

confidence: 99%

“…The softmax function has been widely used in attention mechanism for LC prediction and risk recognition [55,56]. By using the softmax as the activation function in the attention mechanism, we can effectively capture and highlight important features related to LC risk.…”

Section: Attention Mechanismmentioning

confidence: 99%

“…The softmax function can transform raw atten scores into a probability distribution that ranges from 0 to 1 and sums to 1 [57]. That bles the model to learn and concentrate its attention on important parts relevant to current task, while reducing the weights of other parts to ignore irrelevant informa The softmax function has been widely used in attention mechanism for LC prediction risk recognition [55,56]. By using the softmax as the activation function in the atten mechanism, we can effectively capture and highlight important features related to LC…”

mentioning

confidence: 99%

See 2 more Smart Citations

A Comprehensive Investigation of Lane-Changing Risk Recognition Framework of Multi-Vehicle Type Considering Key Features Based on Vehicles’ Trajectory Data

Zheng,

Liu

2024

Electronics

View full text Add to dashboard Cite

To comprehensively investigate the key features of lane-changing (LC) risk for different vehicle types during left and right LC, and to improve the accuracy of LC risk recognition, this paper proposes a key feature selection and risk recognition model based on vehicle trajectory data. Based on a HighD high-precision vehicle trajectory dataset, the trajectory data of LC vehicles and surrounding vehicles of each vehicle type are extracted. SDI (stop distance index) and CI (crash index) are selected as surrogate indicators to calculate the risk exposure level (REL) and risk severity level (RSL). The K-means algorithm is used to cluster the REL and RSL to obtain the LC risk level, which is divided into three levels. The combination of basic features and interaction features of LC vehicles and surrounding vehicles with LC risk levels is constructed as the LC risk feature dataset. Based on the LightGBM (light gradient boosting machine) algorithm, the importance of features is sorted. Finally, a CNN-BiLSTM-Attention model is established to recognize the LC risk of each vehicle type during left and right LC. The results indicate that significant differences exist among different vehicle types and LC directions. Compared with CNNs (convolutional neural networks), LSTM (long short-term memory), and BiLSTM (bi-directional long short-term memory), CNN-BiLSTM-Attention performs best in recognizing the risk of LC in all cases. Moreover, the key feature groups that have the optimal result of recognizing the risk of LC in different cases are obtained.

show abstract

Section: Attention Mechanismmentioning

confidence: 99%

Section: Attention Mechanismmentioning

confidence: 99%

mentioning

confidence: 99%

See 1 more Smart Citation