Long-term prediction of vehicle trajectory based on a deep neural network

Jeong, Donggi; Baek, M.; Sun, Woong

doi:10.1109/ictc.2017.8190764

Cited by 24 publications

(10 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Currently, the study of Microscopic vehicle trajectory prediction mainly focuses on automatic driving vehicle control [18], collision detection [19], traffic data mining [8] [20] [21], and vehicle network dynamic planning [22]. Vehicle trajectory prediction methods can be roughly divided into two categories, physical/maneuver-based models and interaction awarenessbased models.…”

Section: B Vehicle Trajectory Predictionmentioning

confidence: 99%

“…These methods can provide long-term prediction results. Jeong et al [21] use vehicle speed, acceleration, yaw rate, steering, and road curvature as inputs for training the neural network model, which can produce more accurate trajectory information of vehicles in the next few seconds. In [20], the Traj-clusiVAT algorithm is used to cluster a large number of overlapping tracks in dense road network, in which the results are used to train Markov model.…”

Section: B Vehicle Trajectory Predictionmentioning

confidence: 99%

See 1 more Smart Citation

A Novel Generation-Adversarial-Network-Based Vehicle Trajectory Prediction Method for Intelligent Vehicular Networks

Zhao

Liu

Al‐Dubai

et al. 2021

IEEE Internet Things J.

View full text Add to dashboard Cite

Prediction of the future location of vehicles and other mobile targets is instrumental in intelligent transportation system applications. In fact, networking schemes and protocols based on machine learning can benefit from the results of such accurate trajectory predictions. This is because routing decisions always need to be made for the future scenario due to the inevitable latency caused by processing and propagation of the routing request and response. Thus, to predict the highprecision trajectory beyond the state-of-the-art, we propose a Generative Adversarial Network-based VEhicle trajEctory Prediction method, GAN-VEEP, for urban roads. The proposed method consists of three components, 1) vehicle coordinate transformation for data set preparation, 2) neural network prediction model trained by GAN, and 3) vehicle turning model to adjust the prediction process. The vehicle coordinate transformation model is introduced to deal with the complex spatial dependence in the urban road topology. Then, the neural network prediction model learns from the behavior of vehicle drivers. Finally, the vehicle turning model can refine the driving path based on the driver's psychology. Compared with its counterparts, the experimental results show that GAN-VEEP exhibits higher effectiveness in terms of the Average Accuracy, Mean Absolute Error, and Root Mean Squared Error.

show abstract

Section: B Vehicle Trajectory Predictionmentioning

confidence: 99%

Section: B Vehicle Trajectory Predictionmentioning

confidence: 99%

A Novel Generation-Adversarial-Network-Based Vehicle Trajectory Prediction Method for Intelligent Vehicular Networks

Zhao

Liu

Al‐Dubai

et al. 2021

IEEE Internet Things J.

View full text Add to dashboard Cite

show abstract

“…Currently, neural network based prediction mechanisms are also proposed, which are more fit for long term predictions. Paper [7] employs a deep neural network(DNN) for trajectory prediction and the time cost of training is very short. But, DNN has the problem of gradient explosion or disappearance while training network model which should be improved.…”

Section: A Destination Predictionmentioning

confidence: 99%

“…Some of the approaches are based on the Markov model [6]. And deep neural networks(DNNs) are also used in some approaches [7]. For the second problem, there are some works too.…”

Section: Introductionmentioning

confidence: 99%

Destination Prediction-Based Scheduling Algorithms for Message Delivery in IoVs

Wang¹,

Li²,

He³

et al. 2020

IEEE Access

View full text Add to dashboard Cite

Destination related applications are playing an important role in Internet of Vehicles(IoVs), which can provide people with convenience or business profit, such as traffic jam warning or parking guide. However, in reality, people hesitate to share their destination information to other people due to operation inconvenience, which requires service providers to predict vehicles' destinations in advance in order to deliver them destination related messages. Some papers have considered the delivery scheduling problem of destination related information. But, they neglect the destination prediction problem with the assumption that vehicle's destinations are known in advance. In this paper, we target the delivery scheduling problem of destination related information in the case of destinations unknown to others in IoVs. First, a realtime destination prediction framework with machine learning models is proposed, with which a vehicle's destination can be predicted while traveling. Then, we propose a delivery profit maximization algorithm for service providers to select a proper location to deliver destination related information to each vehicle. Simulations with real vehicle trajectories show that our scheduling algorithm performs well and can successfully select a proper location to disseminate destination related information.

show abstract

“…It is then necessary for AV to predict other vehicles' future trajectories accurately. Many efforts have been made to enhance prediction accuracy [1]- [5]. However, deterministic prediction is not sufficient to enable robust safety because human driver's decisions are uncertain even under the same circumstances.…”

Section: Introductionmentioning

confidence: 99%

Adaptive Probabilistic Vehicle Trajectory Prediction Through Physically Feasible Bayesian Recurrent Neural Network

Tang

Chen

Tomizuka

2019

2019 International Conference on Robotics and Automation (ICRA)

View full text Add to dashboard Cite

Probabilistic vehicle trajectory prediction is essential for robust safety of autonomous driving. Current methods for long-term trajectory prediction cannot guarantee the physical feasibility of predicted distribution. Moreover, their models cannot adapt to the driving policy of the predicted target human driver. In this work, we propose to overcome these two shortcomings by a Bayesian recurrent neural network model consisting of Bayesian-neural-network-based policy model and known physical model of the scenario. Bayesian neural network can ensemble complicated output distribution, enabling rich family of trajectory distribution. The embedded physical model ensures feasibility of the distribution. Moreover, the adopted gradient-based training method allows direct optimization for better performance in long prediction horizon. Furthermore, a particle-filter-based parameter adaptation algorithm is designed to adapt the policy Bayesian neural network to the predicted target online. Effectiveness of the proposed methods is verified with a toy example with multi-modal stochastic feedback gain and naturalistic car following data.

show abstract

Long-term prediction of vehicle trajectory based on a deep neural network

Cited by 24 publications

References 10 publications

A Novel Generation-Adversarial-Network-Based Vehicle Trajectory Prediction Method for Intelligent Vehicular Networks

A Novel Generation-Adversarial-Network-Based Vehicle Trajectory Prediction Method for Intelligent Vehicular Networks

Destination Prediction-Based Scheduling Algorithms for Message Delivery in IoVs

Adaptive Probabilistic Vehicle Trajectory Prediction Through Physically Feasible Bayesian Recurrent Neural Network

Contact Info

Product

Resources

About