Identifying Driver Behaviors Using Trajectory Features for Vehicle Navigation

Cheung, Ernest; Bera, Aniket; Kubin, Emily; Manocha, Dinesh

doi:10.1109/iros.2018.8594348

Cited by 31 publications

(26 citation statements)

References 42 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Scholars have also studied how to determine the driver's aggressiveness and level of distraction. After analyzing the vehicle trajectory to identify the driver's behavior, the automatic vehicle navigation algorithm (Autono Vi) was optimized and extended to reduce the influence of navigation on the driving behavior [23]. Cheung proposed an autonomous driving planning algorithm that considered the behavior of neighboring drivers' behaviors, which greatly improved the safety and effectiveness of the navigation system [24].…”

Section: Introductionmentioning

confidence: 99%

Research on the Influence of Smartphone Navigation on Driving Behavior Based on Real Vehicle Driving

Dong

Rong-guo

Zhang

et al. 2019

Mobile Information Systems

View full text Add to dashboard Cite

This paper discusses a study of the influence of different positions and modes of smartphone navigation devices on driving behavior based on real vehicle driving. Twenty professional drivers participated in the experiment in free-flowing traffic and good weather conditions. The eye movement and vehicle control data obtained in the experiment were used as indicators for evaluation. Comparison of the mean, variance, and significance analysis shows that a smartphone navigation device placed on the right side of the car dashboard (position 1) has less impact on driving behavior than when placed above the air conditioning vent (position 2). A smaller angle of view can increase the fixation frequency and the length of time that the driver spends looking out the windshield and reduce the range and time spent in glancing at the navigation device. Using only sound navigation (the audio group in this paper) has the least influence on driving behavior because the driver’s visual attention is not transferred inside the vehicle rather than on the road ahead, and the vehicle is operated in the most stable state. These findings have practical significance for reducing the negative influence of smartphone navigation.

show abstract

Section: Introductionmentioning

confidence: 99%

Research on the Influence of Smartphone Navigation on Driving Behavior Based on Real Vehicle Driving

Dong

Rong-guo

Zhang

et al. 2019

Mobile Information Systems

View full text Add to dashboard Cite

show abstract

“…Some are more aggressive while others more conservative. We model these behaviors as they directly influence the outcome of various interactions [7], thereby affecting the road agents' navigation.…”

Section: Traphic: Trajectory Prediction In Heterogeneous Trafficmentioning

confidence: 99%

“…Since we include these parameters into our statespace representation, we implicitly take into consideration each agent's turning radius constraints as well. Driver Behavior: As stated in [7], velocity and acceleration (both relative and average ) are clear indicators of driver aggressiveness. For instance, a road agent with a relative velocity (and/or acceleration) much higher than the average velocity (and/or acceleration) of all road agents in a given traffic scenario would be deemed as aggressive.…”

Section: Implicit Constraintsmentioning

confidence: 99%

TraPHic: Trajectory Prediction in Dense and Heterogeneous Traffic Using Weighted Interactions

Chandra

Bhattacharya

Bera³

et al. 2019

2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

Self Cite

243

188

View full text Add to dashboard Cite

We present a new algorithm for predicting the near-term trajectories of road agents in dense traffic videos. Our approach is designed for heterogeneous traffic, where the road agents may correspond to buses, cars, scooters, bi-cycles, or pedestrians. We model the interactions between different road agents using a novel LSTM-CNN hybrid network for trajectory prediction. In particular, we take into account heterogeneous interactions that implicitly account for the varying shapes, dynamics, and behaviors of different road agents. In addition, we model horizon-based interactions which are used to implicitly model the driving behavior of each road agent. We evaluate the performance of our prediction algorithm, TraPHic, on the standard datasets and also introduce a new dense, heterogeneous traffic dataset corresponding to urban Asian videos and agent trajectories. We outperform state-of-the-art methods on dense traffic datasets by 30%. Code for our implementation can be found on our project webpage.

show abstract

“…where (x i , y i ) represents the coordinates of the vehicle at i time, and (x i−1 , y i−1 ) indicates the coordinates of the vehicle at i−1 time. According to the change rate of heading angle θ between the two trajectory points of the vehicle,ω marks the vehicle behavior Label, as in formula (8). A total of five behaviors are marked, including going straight, turning left and right, and changing left and right lanes, which are represented by 0, 1, 2, 3, and 4, respectively: Journal of Advanced Transportation…”

Section: Calculate Angle Vel_x Vel_y and Behaviormentioning

confidence: 99%

“…e existing methods are basically separate research on vehicle behavior recognition and vehicle trajectory prediction, and there are not many methods to combine the two to make a more accurate trajectory prediction [5][6][7][8][9][10]. Improving the accuracy of vehicle trajectory prediction is the most urgent problem to be solved.…”

Section: Introductionmentioning

confidence: 99%

UB-LSTM: A Trajectory Prediction Method Combined with Vehicle Behavior Recognition

Xiao

Wang

et al. 2020

Journal of Advanced Transportation

View full text Add to dashboard Cite

In order to make an accurate prediction of vehicle trajectory in a dynamic environment, a Unidirectional and Bidirectional LSTM (UB-LSTM) vehicle trajectory prediction model combined with behavior recognition is proposed, and then an acceleration trajectory optimization algorithm is proposed. Firstly, the interactive information with the surrounding vehicles is obtained by calculation, then the vehicle behavior recognition model is established by using LSTM, and the vehicle information is input into the behavior recognition model to identify vehicle behavior. Then, the trajectory prediction model is established based on Unidirectional and Bidirectional LSTM, and the identified vehicle behavior and the input information of the behavior recognition model are input into the trajectory prediction model to predict the horizontal and vertical speed and coordinates of the vehicle in the next 3 seconds. Experiments are carried out with NGSIM data sets, and the experimental results show that the mean square error (MSE) between the predicted trajectory and the actual trajectory obtained by this method is 0.124, which is 97.2% lower than that of the method that does not consider vehicle behavior and directly predicts the trajectory. The test loss is 0.000497, which is 95.68% lower than that without considering vehicle behavior. The predicted trajectory is obviously optimized, closer to the actual trajectory, and the performance is more stable.

show abstract

Identifying Driver Behaviors Using Trajectory Features for Vehicle Navigation

Cited by 31 publications

References 42 publications

Research on the Influence of Smartphone Navigation on Driving Behavior Based on Real Vehicle Driving

Research on the Influence of Smartphone Navigation on Driving Behavior Based on Real Vehicle Driving

TraPHic: Trajectory Prediction in Dense and Heterogeneous Traffic Using Weighted Interactions

UB-LSTM: A Trajectory Prediction Method Combined with Vehicle Behavior Recognition

Contact Info

Product

Resources

About