Trajectory Prediction for Autonomous Driving: Progress, Limitations, and Future Directions

Abstract

As the potential for autonomous vehicles to be integrated on a large scale into modern traffic systems continues to grow, ensuring safe navigation in dynamic environments is crucial for smooth integration. To guarantee safety and prevent collisions, autonomous vehicles must be capable of accurately predicting the trajectories of surrounding traffic agents. Over the past decade, significant efforts from both academia and industry have been dedicated to designing solutions for precise trajectory forecasting. These efforts have produced a diverse range of approaches, raising questions about the differences between these methods and whether trajectory prediction challenges have been fully addressed. This paper reviews a substantial portion of recent trajectory prediction methods proposing a taxonomy to classify existing solutions. A general overview of the prediction pipeline is also provided, covering input and output modalities, modeling features, and prediction paradigms existing in the literature. In addition, the paper discusses active research areas within trajectory prediction, addresses the posed research questions, and highlights the remaining research gaps and challenges.

References in corpus (62)

• Distilling the Knowledge in a Neural Network
• LLaMA: Open and Efficient Foundation Language Models
• Deep Learning-based Vehicle Behaviour Prediction For Autonomous Driving Applications: A Review
• Human Motion Trajectory Prediction: A Survey
• Motion Planning for Autonomous Driving: The State of the Art and Future Perspectives
• 3D Object Detection for Autonomous Driving: A Survey
• How would surround vehicles move? A Unified Framework for Maneuver Classification and Motion Prediction
• BoT-SORT: Robust Associations Multi-Pedestrian Tracking
• Towards Small Object Editing: A Benchmark Dataset and A Training-Free Approach
• Graph-Based Spatial-Temporal Convolutional Network for Vehicle Trajectory Prediction in Autonomous Driving
• Collaborative Perception in Autonomous Driving: Methods, Datasets and Challenges
• A Review of Tracking, Prediction and Decision Making Methods for Autonomous Driving
• Multi-Robot Collaborative Perception with Graph Neural Networks
• Probabilistic Crowd GAN: Multimodal Pedestrian Trajectory Prediction using a Graph Vehicle-Pedestrian Attention Network
• Scene-LSTM: A Model for Human Trajectory Prediction
• GRIP++: Enhanced Graph-based Interaction-aware Trajectory Prediction for Autonomous Driving
• MacFormer: Map-Agent Coupled Transformer for Real-time and Robust Trajectory Prediction
• Early Lane Change Prediction for Automated Driving Systems Using Multi-Task Attention-based Convolutional Neural Networks
• Human Trajectory Prediction using Spatially aware Deep Attention Models
• Injecting Knowledge in Data-driven Vehicle Trajectory Predictors
• A Novel Graph based Trajectory Predictor with Pseudo Oracle
• Deep Learning Driven Visual Path Prediction from a Single Image
• LC-LLM: Explainable Lane-Change Intention and Trajectory Predictions with Large Language Models
• Learning to Predict Vehicle Trajectories with Model-based Planning
• Social-WaGDAT: Interaction-aware Trajectory Prediction via Wasserstein Graph Double-Attention Network
• Deep Learning Based 3D Segmentation: A Survey
• Long-term Pedestrian Trajectory Prediction using Mutable Intention Filter and Warp LSTM
• AC-VRNN: Attentive Conditional-VRNN for Multi-Future Trajectory Prediction
• Map-Adaptive Goal-Based Trajectory Prediction
• Heterogeneous Trajectory Forecasting via Risk and Scene Graph Learning
• Joint Interaction and Trajectory Prediction for Autonomous Driving using Graph Neural Networks
• GAIA-1: A Generative World Model for Autonomous Driving
• MiniCPM-V: A GPT-4V Level MLLM on Your Phone
• Bayesian Prediction of Future Street Scenes using Synthetic Likelihoods
• DriveVLM: The Convergence of Autonomous Driving and Large Vision-Language Models
• Language Prompt for Autonomous Driving
• CMP: Cooperative Motion Prediction with Multi-Agent Communication
• ScenarioNet: Open-Source Platform for Large-Scale Traffic Scenario Simulation and Modeling
• Trajformer: Trajectory Prediction with Local Self-Attentive Contexts for Autonomous Driving
• Leveraging Future Relationship Reasoning for Vehicle Trajectory Prediction
• Towards Vehicle-to-everything Autonomous Driving: A Survey on Collaborative Perception
• Vision Language Models in Autonomous Driving: A Survey and Outlook
• DriveDreamer: Towards Real-world-driven World Models for Autonomous Driving
• LatentFormer: Multi-Agent Transformer-Based Interaction Modeling and Trajectory Prediction
• Can you text what is happening? Integrating pre-trained language encoders into trajectory prediction models for autonomous driving
• Probabilistic Trajectory Prediction for Autonomous Vehicles with Attentive Recurrent Neural Process
• Social-VRNN: One-Shot Multi-modal Trajectory Prediction for Interacting Pedestrians
• MTR-A: 1st Place Solution for 2022 Waymo Open Dataset Challenge -- Motion Prediction
• SEPT: Towards Efficient Scene Representation Learning for Motion Prediction
• What Truly Matters in Trajectory Prediction for Autonomous Driving?
• Scene Gated Social Graph: Pedestrian Trajectory Prediction Based on Dynamic Social Graphs and Scene Constraints
• Multi-Frame, Lightweight & Efficient Vision-Language Models for Question Answering in Autonomous Driving
• Pedestrian Trajectory Prediction using Context-Augmented Transformer Networks
• ALT-Pilot: Autonomous navigation with Language augmented Topometric maps
• Zelda: Video Analytics using Vision-Language Models
• Estimating Uncertainty For Vehicle Motion Prediction on Yandex Shifts Dataset
• Continuously Learning, Adapting, and Improving: A Dual-Process Approach to Autonomous Driving
• An Extensible Framework for Open Heterogeneous Collaborative Perception
• V2X-R: Cooperative LiDAR-4D Radar Fusion with Denoising Diffusion for 3D Object Detection
• Learning Cooperative Trajectory Representations for Motion Forecasting
• Characterized Diffusion and Spatial-Temporal Interaction Network for Trajectory Prediction in Autonomous Driving
• CoDynTrust: Robust Asynchronous Collaborative Perception via Dynamic Feature Trust Modulus