Surrounding Vehicles’ Lane Change Maneuver Prediction and Detection for Intelligent Vehicles: A Comprehensive Review

Song, Ruitao; Li, Bin

doi:10.1109/tits.2021.3076164

Cited by 37 publications

(10 citation statements)

References 123 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As a sub-category of manoeuvre prediction, lane change prediction has been widely studied in recent years. Studies on lane change prediction can be further divided into ego vehicle lane change prediction (also known as driver lane change inference) and surrounding vehicle lane change prediction, which are separately reviewed in [22] and [23], respectively. The focus of this paper is on lane change manoeuvre prediction of surrounding vehicles in highway driving scenarios.…”

Section: Related Workmentioning

confidence: 99%

Early Lane Change Prediction for Automated Driving Systems Using Multi-Task Attention-Based Convolutional Neural Networks

Mozaffari

Arnold

Dianati

et al. 2022

IEEE Trans. Intell. Veh.

View full text Add to dashboard Cite

Section: Related Workmentioning

confidence: 99%

Early Lane Change Prediction for Automated Driving Systems Using Multi-Task Attention-Based Convolutional Neural Networks

Mozaffari

Arnold

Dianati

et al. 2022

IEEE Trans. Intell. Veh.

View full text Add to dashboard Cite

“…Under the driving situation, if there is no other vehicle blocking, lane-changing behavior will be avoided as much as possible. If the front vehicle speed is too slow or the driving space in the adjacent lane is sufficient, the timing of the lane change will be judged according to the state of the surrounding vehicles, and the lane change behavior will occur [23]. Our research assumes that sensors of the ego-vehicle could detect the state of the vehicle cluster in their detection range.…”

Section: Intent Prediction Modelmentioning

confidence: 99%

Vehicle Interaction Behavior Prediction with Self-Attention

Xin

Lian

et al. 2022

Sensors

View full text Add to dashboard Cite

The structured road is a scene with high interaction between vehicles, but due to the high uncertainty of behavior, the prediction of vehicle interaction behavior is still a challenge. This prediction is significant for controlling the ego-vehicle. We propose an interaction behavior prediction model based on vehicle cluster (VC) by self-attention (VC-Attention) to improve the prediction performance. Firstly, a five-vehicle based cluster structure is designed to extract the interactive features between ego-vehicle and target vehicle, such as Deceleration Rate to Avoid a Crash (DRAC) and the lane gap. In addition, the proposed model utilizes the sliding window algorithm to extract VC behavior information. Then the temporal characteristics of the three interactive features mentioned above will be caught by two layers of self-attention encoder with six heads respectively. Finally, target vehicle’s future behavior will be predicted by a sub-network consists of a fully connected layer and SoftMax module. The experimental results show that this method has achieved accuracy, precision, recall, and F1 score of more than 92% and time to event of 2.9 s on a Next Generation Simulation (NGSIM) dataset. It accurately predicts the interactive behaviors in class-imbalance prediction and adapts to various driving scenarios.

show abstract

“…Lígia [15] studied variable lanes in an autonomous vehicle context and used mixed integer nonlinear mathematical models to design a variable lane network and assign traffic flow. Song [16] provided a comprehensive overview of the state-of-the-art research on the surrounding vehicles' lane change maneuver prediction and detection. First, various driver behavior modeling and classification methods were reviewed and analyzed.…”

Section: Literature Reviewmentioning

confidence: 99%

An Interactive Traffic Signal Optimization Approach with Dynamic Variable Guidance Lane Control

Zhao

Pan

et al. 2022

Journal of Advanced Transportation

View full text Add to dashboard Cite

The purpose of setting up variable guidance lanes is to ease the traffic pressure on lanes with more traffic under the condition of ensuring the traffic capacity of the intersection. This study proposes a bi-level model-interactive relationship between variable guidance lane design and signal control and carry out a case study for a road in Wuhan, China. The design plan for the goal, combined with the design plan of the variable guidance lane, optimizes the signal timing plan of the intersection. A real case is modeled in VISSIM to simulate the design scheme of variable guidance lanes to verify the reliability and effectiveness of the bi-level model. The results showed that the average vehicle delay at the intersection was reduced by 20.65% after the bi-level model was optimized. The average error between model calculation results and simulation results is 9.88%. Moreover, the influencing factors of the proposed model are also carried out. The results show that when the traffic flow is greater than 1,000 pcu/h, the optimization effect of the model is more significant. When the traffic capacity gradually increases, the average vehicle delay calculated by the model is smaller. The design scheme and signal timing scheme proposed by the bi-level model can ensure the overall traffic efficiency of the intersection, improve the traffic efficiency of the traffic-stressed lanes, and further promote the space-time resource utilization of the intersection, optimize the space-time resources of the road network, and provide a scientific basis and new ideas and methods.

show abstract

Surrounding Vehicles’ Lane Change Maneuver Prediction and Detection for Intelligent Vehicles: A Comprehensive Review

Cited by 37 publications

References 123 publications

Early Lane Change Prediction for Automated Driving Systems Using Multi-Task Attention-Based Convolutional Neural Networks

Early Lane Change Prediction for Automated Driving Systems Using Multi-Task Attention-Based Convolutional Neural Networks

Vehicle Interaction Behavior Prediction with Self-Attention

An Interactive Traffic Signal Optimization Approach with Dynamic Variable Guidance Lane Control

Contact Info

Product

Resources

About