HPNet: Dynamic Trajectory Forecasting with Historical Prediction Attention

2024/04/09 by Xiaolong Tang, Meina Kan, Tang, Xiaolong +9 · 11 citations
Computer Science · Engineering · #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Image Processing and 3D Reconstruction #Time Series Analysis and Forecasting #Traffic Prediction and Management Techniques

paper · pdf · doi:10.48550/arxiv.2404.06351

openalex publication_date 2024/04/09 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

Predicting the trajectories of road agents is essential for autonomous driving systems. The recent mainstream methods follow a static paradigm, which predicts the future trajectory by using a fixed duration of historical frames. These methods make the predictions independently even at adjacent time steps, which leads to potential instability and temporal inconsistency. As successive time steps have largely overlapping historical frames, their forecasting should have intrinsic correlation, such as overlapping predicted trajectories should be consistent, or be different but share the same motion goal depending on the road situation. Motivated by this, in this work, we introduce HPNet, a novel dynamic trajectory forecasting method. Aiming for stable and accurate trajectory forecasting, our method leverages not only historical frames including maps and agent states, but also historical predictions. Specifically, we newly design a Historical Prediction Attention module to automatically encode the dynamic relationship between successive predictions. Besides, it also extends the attention range beyond the currently visible window benefitting from the use of historical predictions. The proposed Historical Prediction Attention together with the Agent Attention and Mode Attention is further formulated as the Triple Factorized Attention module, serving as the core design of HPNet.Experiments on the Argoverse and INTERACTION datasets show that HPNet achieves state-of-the-art performance, and generates accurate and stable future trajectories. Our code are available at https://github.com/XiaolongTang23/HPNet.

Cited by

• TrajDiff: End-to-end Autonomous Driving without Perception Annotation
• V2X-RECT: An Efficient V2X Trajectory Prediction Framework via Redundant Interaction Filtering and Tracking Error Correction
• A Trajectory Generator for High-Density Traffic and Diverse Agent-Interaction Scenarios
• Adaptive Output Steps: FlexiSteps Network for Dynamic Trajectory Prediction
• CoPAD : Multi-source Trajectory Fusion and Cooperative Trajectory Prediction with Anchor-oriented Decoder in V2X Scenarios
• MultiPark: Multimodal Parking Transformer with Next-Segment Prediction
• Historical Prediction Attention Mechanism based Trajectory Forecasting for Proactive Work Zone Safety in a Digital Twin Environment
• Generative Active Learning for Long-tail Trajectory Prediction via Controllable Diffusion Model
• Foresight in Motion: Reinforcing Trajectory Prediction with Reward Heuristics
• ILNet: Trajectory Prediction with Inverse Learning Attention for Enhancing Intention Capture
• SRefiner: Soft-Braid Attention for Multi-Agent Trajectory Refinement

Related

• Motion Forecasting in Continuous Driving
• GAMDTP: Dynamic Trajectory Prediction with Graph Attention Mamba Network
• Trajectory Forecasting on Temporal Graphs
• FFINet: Future Feedback Interaction Network for Motion Forecasting
• ILNet: Trajectory Prediction with Inverse Learning Attention for Enhancing Intention Capture