---
title: "TrajAR: Long-Term Trajectory Prediction at Urban Intersections via Multi-scale Interaction Perception"
authors:
  - "Letian Gong"
  - "Yan Lin"
  - "Xinyue Zhang"
  - "Yiwei Shuang"
  - "Guanyu Yao"
  - "Cheng Long"
  - "Shengnan Guo"
  - "Youfang Lin"
  - "Huaiyu Wan"
doi: "10.24963/ijcai.2026/293"
url: "https://ijcai.org/proceedings/2026/293"
pdf: "https://ijcai.org/proceedings/2026/0293.pdf"
venue: "Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence"
year: 2026
pages: "2635-2643"
track: "Main Track"
keywords:
  - "Data Mining: Mining spatial and/or temporal data"
---

# TrajAR: Long-Term Trajectory Prediction at Urban Intersections via Multi-scale Interaction Perception

Letian Gong, Yan Lin, Xinyue Zhang, Yiwei Shuang, Guanyu Yao, Cheng Long, Shengnan Guo, Youfang Lin, Huaiyu Wan

*Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence*, pages 2635-2643. DOI: [10.24963/ijcai.2026/293](https://doi.org/10.24963/ijcai.2026/293)

## Abstract

Accurate trajectory prediction of multiple road users at urban intersections--including motorized and nonmotorized vehicles and pedestrians--is critical for cooperative vehicle-infrastructure systems and intelligent transportation systems. This study focuses on multiple road users' trajectory prediction in urban intersections. Such predictions face two key challenges: modeling interactions among multiple road users in complex scenarios and achieving accurate long-term prediction. Existing solutions inadequately incorporate these interactions and suffer from error accumulation or overall bias when performing long-term prediction. To overcome these challenges, we propose a long-term Trajectory prediction multi-scale AutoRegressive framework (TrajAR), which follows an encoder-decoder structure. The encoder dynamically perceives road users' motion trends, types, signals, and implicit interactions for effective handling of complex scenarios. The decoder employs a multi-scale prediction strategy that progressively refines the predicted trajectory from coarse to fine scales, where coarse-scale predictions establish long-term path backbones and finer scales enhance precision. These designs allow TrajAR to achieve accurate long-term prediction in real-world scenarios, demonstrated through experiments on four real-world urban datasets from different intersections. Our results show an average improvement of 23.8%. We provide the code of TrajAR at https://github.com/LetianGong/TrajAR.