Recent Advances in Multi-Agent Human Trajectory Prediction: A Comprehensive Review

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Finet, Céline, Martins, Stephane Da Silva, Hayet, Jean-Bernard, Karamouzas, Ioannis, Amirian, Javad, Hégarat-Mascle, Sylvie Le, Pettré, Julien, Aldea, Emanuel
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913058602876928
author Finet, Céline
Martins, Stephane Da Silva
Hayet, Jean-Bernard
Karamouzas, Ioannis
Amirian, Javad
Hégarat-Mascle, Sylvie Le
Pettré, Julien
Aldea, Emanuel
author_facet Finet, Céline
Martins, Stephane Da Silva
Hayet, Jean-Bernard
Karamouzas, Ioannis
Amirian, Javad
Hégarat-Mascle, Sylvie Le
Pettré, Julien
Aldea, Emanuel
contents With the emergence of powerful data-driven methods in human trajectory prediction (HTP), gaining a finer understanding of multi-agent interactions lies within hand's reach, with important implications in areas such as social robot navigation, autonomous driving, and crowd modeling. This survey reviews some of the most recent advancements in deep learning-based multi-agent trajectory prediction, focusing on studies published between 2020 and 2025. We categorize the existing methods based on their architectural design, their input representations, and their overall prediction strategies, placing a particular emphasis on models evaluated using the ETH/UCY benchmark. Furthermore, we highlight key challenges and future research directions in the field of multi-agent HTP.
format Preprint
id arxiv_https___arxiv_org_abs_2506_14831
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Recent Advances in Multi-Agent Human Trajectory Prediction: A Comprehensive Review
Finet, Céline
Martins, Stephane Da Silva
Hayet, Jean-Bernard
Karamouzas, Ioannis
Amirian, Javad
Hégarat-Mascle, Sylvie Le
Pettré, Julien
Aldea, Emanuel
Computer Vision and Pattern Recognition
Machine Learning
Robotics
With the emergence of powerful data-driven methods in human trajectory prediction (HTP), gaining a finer understanding of multi-agent interactions lies within hand's reach, with important implications in areas such as social robot navigation, autonomous driving, and crowd modeling. This survey reviews some of the most recent advancements in deep learning-based multi-agent trajectory prediction, focusing on studies published between 2020 and 2025. We categorize the existing methods based on their architectural design, their input representations, and their overall prediction strategies, placing a particular emphasis on models evaluated using the ETH/UCY benchmark. Furthermore, we highlight key challenges and future research directions in the field of multi-agent HTP.
title Recent Advances in Multi-Agent Human Trajectory Prediction: A Comprehensive Review
topic Computer Vision and Pattern Recognition
Machine Learning
Robotics
url https://arxiv.org/abs/2506.14831