Deep‐learning‐based vehicle trajectory prediction: A review

Vehicle trajectory prediction enables autonomous vehicles to better reason about fast‐changing driving scenarios and thus perform well‐informed decision‐making tasks. Among different prediction approaches, deep learning‐based (DL‐based) methodologies stand out because of their capabilities to efficiently summarise historical data, infer nonlinear behavioural patterns from human driving data, and perform long‐horizon prediction. This work reviews the DL‐based methods that have shown promising results, organising them in terms of usage of the input data, separating the encodings of the target vehicle's historical data, surrounding vehicle's historical data, and road layout data. In particular, this paper explores the relationships between the scope of the prediction components and the input data formats, as well as the connections with other elements in the same prediction framework, including vehicle interaction and road scene mining. This information is crucial to understand complex architectural decisions and to provide guidance for the design of improved solutions. This work also compares the performance of the most successful prediction models, establishing that appropriate encodings of vehicle interactions and road scenes improve trajectory prediction accuracy, with the best performance achieved by attention mechanism and Transformer‐based models. Finally, this work discusses future research directions, including considerations for real‐time applications.

• Publication year

  2025

• Venue

  IET Intelligent Transport Systems

• Publication date

  2025-01-01

• Fields of study

  Not labeled

• Identifiers
  DOI 10.1049/itr2.70001
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• Traj-LLM: A New Exploration for Empowering Trajectory Prediction With Pre-Trained Large Language Models

  2025cited by this paper
• Lane change trajectory prediction considering driving style uncertainty for autonomous vehicles

  2024cited by this paper
• Multi-head attention-based intelligent vehicle lane change decision and trajectory prediction model in highways

  2024cited by this paper
• Hierarchical vector transformer vehicle trajectories prediction with diffusion convolutional neural networks

  2024cited by this paper
• Reliable trajectory prediction in scene fusion based on spatio-temporal Structure Causal Model

  2024cited by this paper
• Surrounding vehicle trajectory prediction under mixed traffic flow based on graph attention network

  2024cited by this paper
• Vehicle trajectory prediction based on attention optimized with real-scene sampling

  2024cited by this paper
• A Hierarchical LSTM-Based Vehicle Trajectory Prediction Method Considering Interaction Information

  2024cited by this paper
• LAformer: Trajectory Prediction for Autonomous Driving with Lane-Aware Scene Constraints

  2023cited by this paper
• BAT: Behavior-Aware Human-Like Trajectory Prediction for Autonomous Driving

  2023cited by this paper
• A Review of Deep Learning-Based Vehicle Motion Prediction for Autonomous Driving

  2023cited by this paper
• SEPT: Towards Efficient Scene Representation Learning for Motion Prediction

  2023cited by this paper
• Intention-convolution and hybrid-attention network for vehicle trajectory prediction

  2023cited by this paper
• SSL-Lanes: Self-Supervised Learning for Motion Forecasting in Autonomous Driving

  2022cited by this paper
• Map-enhanced generative adversarial trajectory prediction method for automated vehicles

  2022cited by this paper
• Wayformer: Motion Forecasting via Simple & Efficient Attention Networks

  2022cited by this paper
• Multi‐future Transformer: Learning diverse interaction modes for behaviour prediction in autonomous driving

  2022cited by this paper
• HOME: Heatmap Output for future Motion Estimation

  2021cited by this paper
• LaneRCNN: Distributed Representations for Graph-Centric Motion Forecasting

  2021cited by this paper
• Multi-modal anticipation of stochastic trajectories in a dynamic environment with Conditional Variational Autoencoders

  2021cited by this paper
• Learning to Predict Vehicle Trajectories with Model-based Planning

  2021cited by this paper
• Generative Adversarial Networks

  2021cited by this paper
• A Dynamic and Static Context-Aware Attention Network for Trajectory Prediction

  2021cited by this paper
• GOHOME: Graph-Oriented Heatmap Output for future Motion Estimation

  2021cited by this paper
• Scene Transformer: A unified architecture for predicting multiple agent trajectories

  2021cited by this paper
• THOMAS: Trajectory Heatmap Output with learned Multi-Agent Sampling

  2021cited by this paper
• Multi‐modal vehicle trajectory prediction based on mutual information

  2020cited by this paper
• SMART: Simultaneous Multi-Agent Recurrent Trajectory Prediction

  2020cited by this paper
• Trajectory Forecasts in Unknown Environments Conditioned on Grid-Based Plans

  2020cited by this paper
• SpAGNN: Spatially-Aware Graph Neural Networks for Relational Behavior Forecasting from Sensor Data

  2019cited by this paper
• MultiPath: Multiple Probabilistic Anchor Trajectory Hypotheses for Behavior Prediction

  2019cited by this paper
• Trajectories Prediction of Vehicles at the Intersection Based on LSTM Neural Network

  2019cited by this paper
• Multi-Agent Tensor Fusion for Contextual Trajectory Prediction

  2019cited by this paper
• TrafficPredict: Trajectory Prediction for Heterogeneous Traffic-Agents

  2018cited by this paper
• Intention-aware Long Horizon Trajectory Prediction of Surrounding Vehicles using Dual LSTM Networks

  2018cited by this paper
• Short-term Motion Prediction of Traffic Actors for Autonomous Driving using Deep Convolutional Networks

  2018cited by this paper
• Semi-Supervised Classification with Graph Convolutional Networks

  2016cited by this paper
• Neural Machine Translation by Jointly Learning to Align and Translate

  2014cited by this paper
• A survey on motion prediction and risk assessment for intelligent vehicles

  2014cited by this paper
• Learning Phrase Representations using RNN Encoder–Decoder for Statistical Machine Translation

  2014cited by this paper
• Sequence to Sequence Learning with Neural Networks

  2014cited by this paper
• Safety of Lane Change Maneuver Through A Priori Prediction of Trajectory Using Neural Networks

  2012cited by this paper
• The perceptron: a probabilistic model for information storage and organization in the brain.

  1958cited by this paper

• MELON: Hierarchical multi-agent trajectory prediction with spatio-temporal uncertainty adaptation

  2026cites this paper
• A Survey on Vehicle Trajectory Prediction Procedures for Intelligent Driving

  2025cites this paper
• Advancing Map-Matching and Route Prediction: Challenges, Methods, and Unified Solutions

  2025cites this paper
• Future occupancy guidance under multi-view collaboration for trajectory prediction

  2025cites this paper
• SemAgent: Semantic-Driven Agentic AI Empowered Trajectory Prediction in Vehicular Networks

  2025cites this paper
• Goal oriented trajectory prediction conditioned on reachable road context

  2025cites this paper
• MST-GCAN: multiscale spatio-temporal graph convolutional attention network for vehicle trajectory prediction

  2025cites this paper
• Vehicle Trajectory Prediction Based on Hierarchical Spatio-Temporal Interaction Transformer

  2025cites this paper
• An Optimization Method for Solving Three‐Phase Unbalance and Vehicle‐to‐Grid Reactive Power Compensation Utilizing Three‐Phase Inverter Control

  2025cites this paper
• Lane Centerline Extraction Based on Surveyed Boundaries: An Efficient Approach Using Maximal Disks

  2025cites this paper
• Accelerating the Approval of Automated Driving Vehicles through standardized XiL test environments

  2025cites this paper