Recent advances in multi-agent human trajectory prediction: A comprehensive review
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. Furthermore, we highlight key challenges and future research directions in multi-agent HTP.
Authors
- Ioannis Karamouzas (ORCID: https://orcid.org/0009-0000-4315-6556)
- Julien Pettré (ORCID: https://orcid.org/0000-0003-1812-1436)
- Sylvie Le Hégarat‐Mascle (ORCID: https://orcid.org/0000-0001-8494-2289)
- Jean-Bernard Hayet (ORCID: https://orcid.org/0000-0002-6662-2553)
- Emanuel Aldea (ORCID: https://orcid.org/0000-0001-7065-4809)
- Stephane Da Silva Martins
- Céline Finet
Institutions
- Mathematics Research Center (MX)
- Institut national de recherche en sciences et technologies du numérique (FR)
- University of California System (US)
- Laboratoire des systèmes et applications des technologies de l'information et de l'énergie (FR)
Publication Details
- Journal
- The International Journal of Robotics Research
- Published
- 2026-11-21
- DOI
- https://doi.org/10.1177/02783649261505482
- Citations
- 9
- Primary Topic
- Autonomous Vehicle Technology and Safety
- Type
- article
- Field-Weighted Citation Impact
- 5.41
Funders
- National Science Foundation
- Agence Nationale de la Recherche