EUVIMEDEUVIMED entdecken
ÜbersichtsarbeitOpen Access · CC BY 4.0

A Survey of Deep Learning-Based Pedestrian Trajectory Prediction: Challenges and Solutions

Jiaming Jiang, Kai Yan, Xindong Xia, Biao Yang

Sensors · 05.02.2025 · 25 (3) · 957

DOI: 10.3390/s25030957 ↗

Kurz gefasst

Übersichtsarbeit in der Zeitschrift Sensors, online erschienen am 05.02.2025. Verfasst von Jiaming Jiang und 3 weiteren Autor:innen. Beteiligte Einrichtung: Wang Zheng Institute of Microelectronics, Changzhou University, Changzhou 213000, China. Die Arbeit wurde bisher 40-mal zitiert (Crossref) und nennt 105 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: General Project of Jiangsu Provincial Department of Science and Technology, Changzhou science and technology support plan.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Pedestrian trajectory prediction is widely used in various applications, such as intelligent transportation systems, autonomous driving, and social robotics. Precisely forecasting surrounding pedestrians’ future trajectories can assist intelligent agents in achieving better motion planning. Currently, deep learning-based trajectory prediction methods have demonstrated superior prediction performance to traditional approaches by learning from trajectory data. However, these methods still face many challenges in improving prediction accuracy, efficiency, and reliability. In this survey, we research the main challenges in deep learning-based pedestrian trajectory prediction methods and study this problem and its solutions through literature collection and analysis. Specifically, we first investigate and analyze the existing literature and surveys on pedestrian trajectory prediction. On this basis, we summarize several main challenges faced by deep learning-based pedestrian trajectory prediction, including motion uncertainty, interaction modeling, scene understanding, data-related issues, and the interpretability of prediction models. We then summarize solutions for each challenge. Subsequently, we introduce mainstream trajectory prediction datasets and analyze the state-of-the-art (SOTA) results reported on them. Finally, we discuss potential research prospects in trajectory prediction, aiming to promote the trajectory prediction community.

Schlagwörter

Stichwörter der Autor:innen

interaction modelinginterpretabilitymotion uncertaintyscene semantic understandingtrajectory prediction

Autor:innen und Institutionen

  • Wang Zheng Institute of Microelectronics, Changzhou University, Changzhou 213000, China.

Förderung

  • General Project of Jiangsu Provincial Department of Science and Technology
  • Changzhou science and technology support plan

Zitieren

APA

Jiang, J., Yan, K., Xia, X., & Yang, B. (2025). A Survey of Deep Learning-Based Pedestrian Trajectory Prediction: Challenges and Solutions. Sensors, 25(3), 957. https://doi.org/10.3390/s25030957

Vancouver

Jiang J, Yan K, Xia X, Yang B. A Survey of Deep Learning-Based Pedestrian Trajectory Prediction: Challenges and Solutions. Sensors. 2025;25(3):957. doi:10.3390/s25030957

BibTeX
@article{Jiang2025,
  author = {Jiang, Jiaming and Yan, Kai and Xia, Xindong and Yang, Biao},
  title = {A Survey of Deep Learning-Based Pedestrian Trajectory Prediction: Challenges and Solutions},
  journal = {Sensors},
  year = {2025},
  volume = {25},
  number = {3},
  pages = {957},
  doi = {10.3390/s25030957}
}
Kostenlos starten →