Vehicle Trajectory Prediction Using Intention-based Conditional Variational Autoencoder

Feng, Xu; Cen, Zhepeng; Hu, Jianming; Zhang, Yi

doi:10.1109/itsc.2019.8917482

Cited by 38 publications

(19 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Note that the input vectors are embedded using a 64 unit dense layer before the Long-Short Term Memory (LSTM) layer, so the situation encoding representation is 64-dimensional as in this present article. A very similar representation can be found in the research of Feng et al [11]. They propose a Conditional Variational Autoencoder for intention-based trajectory prediction.…”

Section: Introductionmentioning

confidence: 78%

“…Thus, the result is the Binary Cross-Entropy (BCE) of the output generated image distribution and the ground-truth image plus the KLD between the latent and prior distribution. Returning to the assumptions about the latent distribution taken in Equations ( 1) and (2), one can explicitly calculate the second term of Equation (11). Substituting Equation (2) into Equation (11), it yields the loss function for the Variational Autoencoder using Bernoulli distribution as prior:…”

Section: Methodsmentioning

confidence: 99%

See 1 more Smart Citation

Learning Latent Representation of Freeway Traffic Situations from Occupancy Grid Pictures Using Variational Autoencoder

et al. 2021

View full text Add to dashboard Cite

Several problems can be encountered in the design of autonomous vehicles. Their software is organized into three main layers: perception, planning, and actuation. The planning layer deals with the sort and long-term situation prediction, which are crucial for intelligent vehicles. Whatever method is used to make forecasts, vehicles’ dynamic environment must be processed for accurate long-term forecasting. In the present article, a method is proposed to preprocess the dynamic environment in a freeway traffic situation. The method uses the structured data of surrounding vehicles and transforms it to an occupancy grid which a Convolutional Variational Autoencoder (CVAE) processes. The grids (2048 pixels) are compressed to a 64-dimensional latent vector by the encoder and reconstructed by the decoder. The output pixel intensities are interpreted as probabilities of the corresponding field is occupied by a vehicle. This method’s benefit is to preprocess the structured data of the dynamic environment and represent it in a lower-dimensional vector that can be used in any further tasks built on it. This representation is not handmade or heuristic but extracted from the database patterns in an unsupervised way.

show abstract

Section: Introductionmentioning

confidence: 78%

Section: Methodsmentioning

confidence: 99%

Learning Latent Representation of Freeway Traffic Situations from Occupancy Grid Pictures Using Variational Autoencoder

et al. 2021

View full text Add to dashboard Cite

show abstract

“…The trajectory prediction module must be able to handle uncertainties, i.e., multiple futures. To this end, we adopted a multi-maneuver and VAE-based encoder–decoder architecture [ 10 , 12 ]. The proposed architecture consists of maneuver recognition and trajectory regression parts.…”

Section: Problem Statement and Methodologymentioning

confidence: 99%

“…In addition, a few studies [ 18 , 19 ] showed that trajectory prediction can be improved by handling multi-modal uncertainty with maneuver recognition such as lane change left (LCL), lane change right (LCR), and lane keeping (LK). Subsequently, various deep learning structures have been proposed by combining the LSTM encoder–decoder with conditional VAE [ 10 , 11 , 12 ] for generating diverse trajectories. These studies focus mainly on the deep learning architecture to improve the prediction accuracy and to solve the uncertain nature of the trajectory prediction problem.…”

Section: Related Workmentioning

confidence: 99%

“…However, the longer the prediction horizon, the lower is its accuracy, since KF does not account for the uncertain nature of the driver’s maneuvering. To tackle this limitation, many studies have adopted learning-based approaches, such as recurrent neural network (RNN) variants [ 7 , 8 , 9 ] and a combinatorial model of a variational autoencoder (VAE) and an RNN encoder–decoder structure, to improve the prediction accuracy [ 10 , 11 , 12 ] of the employed network.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Road-Aware Trajectory Prediction for Autonomous Driving on Highways

Yoon

Kim

Lee

et al. 2020

Sensors

View full text Add to dashboard Cite

For driving safely and comfortably, the long-term trajectory prediction of surrounding vehicles is essential for autonomous vehicles. For handling the uncertain nature of trajectory prediction, deep-learning-based approaches have been proposed previously. An on-road vehicle must obey road geometry, i.e., it should run within the constraint of the road shape. Herein, we present a novel road-aware trajectory prediction method which leverages the use of high-definition maps with a deep learning network. We developed a data-efficient learning framework for the trajectory prediction network in the curvilinear coordinate system of the road and a lane assignment for the surrounding vehicles. Then, we proposed a novel output-constrained sequence-to-sequence trajectory prediction network to incorporate the structural constraints of the road. Our method uses these structural constraints as prior knowledge for the prediction network. It is not only used as an input to the trajectory prediction network, but is also included in the constrained loss function of the maneuver recognition network. Accordingly, the proposed method can predict a feasible and realistic intention of the driver and trajectory. Our method has been evaluated using a real traffic dataset, and the results thus obtained show that it is data-efficient and can predict reasonable trajectories at merging sections.

show abstract

Beyond the Data Imbalance: Employing the Heterogeneous Datasets for Vehicle Maneuver Prediction

Jeon,

Kim,

Syamil

et al. 2024

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Vehicle Trajectory Prediction Using Intention-based Conditional Variational Autoencoder

Cited by 38 publications

References 10 publications

Learning Latent Representation of Freeway Traffic Situations from Occupancy Grid Pictures Using Variational Autoencoder

Learning Latent Representation of Freeway Traffic Situations from Occupancy Grid Pictures Using Variational Autoencoder

Road-Aware Trajectory Prediction for Autonomous Driving on Highways

Beyond the Data Imbalance: Employing the Heterogeneous Datasets for Vehicle Maneuver Prediction

Contact Info

Product

Resources

About