Prediction of lane change by echo state networks

Griesbach, Karoline; Hoffmann, Karl Heinz; Beggiato, Matthias

doi:10.1016/j.trc.2020.102841

Cited by 6 publications

(1 citation statement)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Driver attribute information contains driver physiological information (e.g., age, gender, and eye gaze direction) and psychological information (e.g., personality, emotion, and psychological stress). Scholars have selected different input variables from these three categories to form multidimensional variables as inputs for HDV lane-change intention recognition and its trajectory prediction model, for example, Griesbach et al used three input variables, namely the driver’s gaze direction, the distance between the lane-change vehicle and other vehicles, and the speed of lane-change vehicle, to classify and predict lane-change intention ( 7 ). Lee et al used three variables, namely the driver’s gaze direction, the lane-change vehicle speed, and the heading angle, to predict vehicle lane-change intention ( 8 ).…”

mentioning

confidence: 99%

Bayesian Global Optimization Gated Recurrent Unit Model for Human-Driven Vehicle Lane-Change Trajectory Prediction Considering Hyperparameter Optimization

Chen

Zhao

et al. 2023

Transportation Research Record: Journal of the Transportation R

View full text Add to dashboard Cite

To address the low accuracy and inefficiency of current lane-change trajectory prediction methods for human-driven vehicles, this study develops a neural network lane-change trajectory prediction model with hyperparametric optimization capability using Bayesian optimization and gated recurrent units to consider the effect of lane-change intention on vehicle lane-change behavior and to predict it. The proposed model was instantiated using trajectory data of 8,721 vehicles. The results show that the overall recognition accuracy of intention recognition under the optimal input is 93.54%, and the recognition accuracy of keeping straight, left lane-change and right lane-change is 95.59%, 91.72%, and 93.30%, respectively. The root mean square errors of the predicted and actual trajectories to the left and to the right under the optimal input are 0.2582 and 0.2957, respectively. This paper demonstrates that, for the intention recognition module, the low-dimensional input enables the model to obtain high prediction accuracy, while for the trajectory prediction module, the high-latitude input enables the model to obtain a low prediction error. The developed trajectory prediction model can be used to assist in driving decision-making, path planning, and so forth.

show abstract

mentioning

confidence: 99%