Vehicle Trajectory Prediction Research Articles

Patterns of vehicle lights: Addressing complexities of camera-based vehicle light datasets and metrics

This paper explores the representation of vehicle lights in computer vision and its implications for various pattern recognition tasks in autonomous driving. Different representations for vehicle lights, including bounding boxes, center points, corner points, and segmentation masks, are discussed in terms of their strengths and weaknesses toward a variety of domain tasks, as well as associated data collection and annotation challenges. This leads to the introduction of the LISA Vehicle Lights Dataset, providing light annotations related to position, state, color, and signal, specifically designed for downstream applications in vehicle detection, intent and trajectory prediction, and safe path planning. A comparison of existing vehicle light datasets is provided, highlighting the unique features and limitations of each dataset. Because occlusions from vehicle pose and passing objects can limit camera observation, we introduce a group of Light Visibility neural networks, which take as input a detected vehicle image and return as output whether a corresponding vehicle light is present in the image. This is especially important for the evaluation of light localizations, states, and signals, as systems decisions should account for differences of lights being in unknown states due to occlusion versus model uncertainty. We show that our trained Light Visibility Models achieve over 90% accuracy on each of the four light classes. Our dataset and model are made available at https://cvrr.ucsd.edu/vehicle-lights-dataset.

IMA‐LSTM: An Interaction‐Based Model Combining Multihead Attention with LSTM for Trajectory Prediction in Multivehicle Interaction Scenario

The rapid development of vehicle‐to‐vehicle (V2V) communication technology provides more opportunities to improve traffic safety and efficiency, which facilitates the exchange of multivehicle information to mine potential patterns and hidden associations in vehicle trajectory prediction. To address the importance of fine‐grained vehicle interaction modelling in vehicle trajectory prediction, the present work proposes an integrated vehicle trajectory prediction model that combines the multihead attention mechanism with long short‐term memory (IMA‐LSTM) in multivehicle interaction scenarios. Compared to existing studies, a dedicated feature extraction module including both individual features and interactive features is designed and sophisticated multihead attention mechanism is applied with LSTM framework to capture the variation of spatial‐temporal interactions between vehicles. The performance of the proposed model in different scenarios is examined using both the high‐D and the NGSIM dataset through comprehensive comparison experiments. The results indicate that the proposed IMA‐LSTM model presents great improvement in vehicle trajectory prediction performance in different scenarios compared to the model that does not consider multivehicle interaction features. Moreover, it outperforms other existing models in 3–5s prediction horizons and such superiority is more evident in left lane‐changing (LLC) scenarios than lane‐keeping (LK) and right lane‐changing (RLC) scenarios. The outcomes fully address the importance of fine‐grained interactive feature modelling in improving vehicle trajectory performance in complex multivehicle interaction scenarios and could further contribute to more refined traffic safety and traffic efficiency management.

Vehicle trajectory prediction in weaving area of expressway based on transfer learning

Vehicle trajectory prediction in weaving area of expressway based on transfer learning

Vehicle Trajectory Prediction Using Hierarchical LSTM and Graph Attention Network

Vehicle Trajectory Prediction Using Hierarchical LSTM and Graph Attention Network

Vehicle Trajectory Prediction with Multimodal and Dynamics-Aware Interaction Neural Networks

Vehicle Trajectory Prediction with Multimodal and Dynamics-Aware Interaction Neural Networks

Conditional Goal-Oriented Trajectory Prediction for Interacting Vehicles.

Predicting future trajectories of pairwise traffic agents in highly interactive scenarios, such as cut-in, yielding, and merging, is challenging for autonomous driving. The existing works either treat such a problem as a marginal prediction task or perform single-axis factorized joint prediction, where the former strategy produces individual predictions without considering future interaction, while the latter strategy conducts conditional trajectory-oriented prediction via agentwise interaction or achieves conditional rollout-oriented prediction via timewise interaction. In this article, we propose a novel double-axis factorized joint prediction pipeline, namely, conditional goal-oriented trajectory prediction (CGTP) framework, which models future interaction both along the agent and time axes to achieve goal and trajectory interactive prediction. First, a goals-of-interest network (GoINet) is designed to extract fine-grained features of goal candidates via hierarchical vectorized representation. Furthermore, we propose a conditional goal prediction network (CGPNet) to produce multimodal goal pairs in an agentwise conditional manner, along with a newly designed goal interactive loss to better learn the joint distribution of the intermediate interpretable modes. Explicitly guided by the goal-pair predictions, we propose a goal-oriented trajectory rollout network (GTRNet) to predict scene-compliant trajectory pairs via timewise interactive rollouts. Extensive experimental results confirm that the proposed CGTP outperforms the state-of-the-art (SOTA) prediction models on the Waymo open motion dataset (WOMD), Argoverse motion forecasting dataset, and In-house cut-in dataset. Code is available at https://github.com/LiDinga/CGTP/.

Dynamic Spatio-temporal Graph Neural Network for Surrounding-aware Trajectory Prediction of Autonomous Vehicles

Dynamic Spatio-temporal Graph Neural Network for Surrounding-aware Trajectory Prediction of Autonomous Vehicles

Driving Style Based Trajectory Prediction of the Surrounding Vehicles using LSTM & ARIMA in Autonomous Driving

Driving Style Based Trajectory Prediction of the Surrounding Vehicles using LSTM & ARIMA in Autonomous Driving

A data-driven approach to traffic vehicle intent recognition and trajectory prediction

A data-driven approach to traffic vehicle intent recognition and trajectory prediction

A Temporal Multi-Gate Mixture-of-Experts Approach for Vehicle Trajectory and Driving Intention Prediction

A Temporal Multi-Gate Mixture-of-Experts Approach for Vehicle Trajectory and Driving Intention Prediction

Hybrid Kalman Recurrent Neural Network for Vehicle Trajectory Prediction

Hybrid Kalman Recurrent Neural Network for Vehicle Trajectory Prediction

Research on Vehicle Trajectory Prediction Methods in Urban Main Road Scenarios

Research on Vehicle Trajectory Prediction Methods in Urban Main Road Scenarios

An Enhanced Vehicle Trajectory Prediction Model Leveraging LSTM and Social-Attention Mechanisms

An Enhanced Vehicle Trajectory Prediction Model Leveraging LSTM and Social-Attention Mechanisms

Efficient Vehicle Trajectory Prediction With Goal Lane Segments and Dual-Stream Cross Attention

Efficient Vehicle Trajectory Prediction With Goal Lane Segments and Dual-Stream Cross Attention

Spatio-Temporal-Attention-Based Vehicle Trajectory Prediction Considering Multi-Vehicle Interaction in Mixed Traffic Flow

As a link connecting the environmental perception system and the decision-making system, accurate obstacle trajectory prediction provides a reliable guarantee of correct decision-making by autonomous vehicles. Oriented toward a mixed human-driven and machine-driven traffic environment, a vehicle trajectory prediction algorithm based on an encoding–decoding framework composed of a multiple-attention mechanism is proposed. Firstly, a directed graph is used to describe vehicle–vehicle motion dependencies. Then, by calculating the repulsive force between vehicles using a priori edge information based on the artificial potential field theory, vehicle–vehicle interaction coefficients are extracted via a graph attention mechanism (GAT). Subsequently, after concatenating the vehicle–vehicle interaction feature with the encoded vehicle trajectory vectors, a spatio-temporal attention mechanism is applied to determine the coupling relationship of hidden vectors. Finally, the predicted trajectory is generated by a gated recurrent unit (GRU) decoder. The training and evaluation of the proposed model were conducted on the NGSIM public dataset. The test results demonstrated that compared with existing baseline models, our approach has fewer prediction errors and better robustness. In addition, introducing artificial potential fields into the attention mechanism causes the model to have better interpretability.

A Physical Law Constrained Deep Learning Model for Vehicle Trajectory Prediction

A Physical Law Constrained Deep Learning Model for Vehicle Trajectory Prediction

Vehicle Trajectory Prediction Based on Graph Convolutional Networks in Connected Vehicle Environment

Vehicle trajectory prediction is an important research basis for the decision making and path planning of the intelligent and connected vehicle. In the connected vehicle environment, vehicles share information and drive cooperatively, and the intelligent and connected vehicles are able to obtain more accurate and rich perception information, which provides a data basis for accurate prediction of vehicle trajectories. However, attaining accurate and effective vehicle trajectory predictions poses technical challenges due to insufficient extraction of vehicular spatial–temporal interaction features. In this paper, we propose a vehicle trajectory prediction model based on graph convolutional neural network (GCN) in a connected vehicle environment. Specifically, using the driving scene information obtained by the intelligent and connected vehicle, the spatial graph and temporal graph are constructed based on the spatial interaction coefficient (SIC) and self-attention mechanism, respectively. Then, the graph data are entered into the interaction extraction module, and the spatial interaction features and temporal interaction features are extracted separately using the graph convolutional networks, which are fused to obtain the spatial–temporal interaction information. Finally, the interaction features are learned based on the convolutional neural networks to output the future trajectory information of all vehicles in the scene by one forward operation rather than a step-by-step process. The ablation experiment results show that the method proposed in this study to model the spatiotemporal interaction among vehicles based on SIC and self-attention mechanism reduces the prediction error by 5% and 12%, respectively. The results from the model comparison experiment show that the proposed method engenders an 8% improvement in prediction accuracy over the state-of-the-art solution, providing technical and theoretical support for trajectory prediction research of intelligent and connected vehicles.

TCN-SA: A Social Attention Network Based on Temporal Convolutional Network for Vehicle Trajectory Prediction

Vehicle trajectory prediction can provide important support for intelligent transportation systems in areas such as autonomous driving, traffic control, and traffic flow optimization. Predicting vehicle trajectories is an extremely challenging task that not only depends on the vehicle’s historical trajectory but also on the dynamic and complex social-temporal relationships of the surrounding traffic network. The trajectory of the target vehicle is influenced by surrounding vehicles. However, existing methods have shortcomings in considering both time dependency and interactive dependency between vehicles or insufficient consideration of the impact of surrounding vehicles. To address this issue, we propose a hybrid deep learning model based on a temporal convolutional network (TCN) that considers local and global interactions between vehicles. Specifically, we use a social convolutional pooling layer to capture local interaction features between vehicles and a multihead self-attention layer to capture global interaction features between vehicles. Finally, we combine these two features using an encoder-decoder structure to predict vehicle trajectories. Through experiments on the Next-Generation Simulation (NGSIM) public dataset and ablation experiments, we validate the effectiveness of our model.

Lifelong Vehicle Trajectory Prediction Framework Based on Generative Replay

Lifelong Vehicle Trajectory Prediction Framework Based on Generative Replay

STIF: A Spatial–Temporal Integrated Framework for End-to-End Micro-UAV Trajectory Tracking and Prediction With 4-D MIMO Radar

The early trajectory prediction of micro unmanned aerial vehicles (micro-UAVs) with random behavior intentions facilitates the elimination of potential safety hazards. However, due to the property of a small radar cross-section (RCS), the backscattered radar signals from micro-UAVs may be submerged under strong background clutters, leading to distorted tracking and false prediction. To this end, this paper presents a spatial-temporal integrated framework (STIF) for end-to-end micro-UAV trajectory tracking and prediction based on a four-dimensional (4D) multiple-input-multiple-output (MIMO) radar. Especially, to obtain accurate trajectories in low signal-to-noise ratio (SNR) conditions, the target detection and tracking are considered to be interdependent and addressed jointly in this work, rather than treating them as two separate processes in conventional methods. The advantage is that with the assistance of tracking, all consecutive spatial information encoded in raw radar streams can be incorporated to enhance the continuous detection performance, avoiding information loss using only one single scan. Subsequently, to accommodate high maneuvering scenarios, an intention-aware end-to-end transformer-based prediction framework is presented to simultaneously discover both spatial and temporal dependencies hiding in long-term estimated trajectories. Consequently, a 4D frequency modulated continuous wave (FMCW) radar is utilized to evaluate the proposed system. Numerous simulation and experimental results indicate that STIF outperforms competing state-of-the-art methods and achieve superior prediction performance with the accuracy of 0.3851m in low SNR conditions.