Repository logo

Infoscience

  • English
  • French
Log In
Logo EPFL, École polytechnique fédérale de Lausanne

Infoscience

  • English
  • French
Log In
  1. Home
  2. Academic and Research Output
  3. Preprints and Working Papers
  4. Social-Pose: Enhancing Trajectory Prediction with Human Body Pose
 
preprint

Social-Pose: Enhancing Trajectory Prediction with Human Body Pose

Gao, Yang  
•
Saadatnejad, Saeed  
•
Alahi, Alexandre  
July 30, 2025

Accurate human trajectory prediction is one of the most crucial tasks for autonomous driving, ensuring its safety. Yet, existing models often fail to fully leverage the visual cues that humans subconsciously communicate when navigating the space. In this work, we study the benefits of predicting human trajectories using human body poses instead of solely their Cartesian space locations in time. We propose 'Social-pose', an attention-based pose encoder that effectively captures the poses of all humans in a scene and their social relations. Our method can be integrated into various trajectory prediction architectures. We have conducted extensive experiments on state-of-the-art models (based on LSTM, GAN, MLP, and Transformer), and showed improvements over all of them on synthetic (Joint Track Auto) and real (Human3.6M, Pedestrians and Cyclists in Road Traffic, and JRDB) datasets. We also explored the advantages of using 2D versus 3D poses, as well as the effect of noisy poses and the application of our pose-based predictor in robot navigation scenarios.

  • Files
  • Details
  • Metrics
Type
preprint
Author(s)
Gao, Yang  

EPFL

Saadatnejad, Saeed  

EPFL

Alahi, Alexandre  

EPFL

Date Issued

2025-07-30

Subjects

Pedestrians

•

Human trajectory prediction

•

Deep learning

•

Pose keypoints

•

Transformers

Note

Submitted to and accepted by: IEEE Transactions on Intelligent Transportation Systems (ISSN 1558-0016)

Editorial or Peer reviewed

REVIEWED

Written at

EPFL

EPFL units
VITA  
Available on Infoscience
July 31, 2025
Use this identifier to reference this record
https://infoscience.epfl.ch/handle/20.500.14299/252794
Logo EPFL, École polytechnique fédérale de Lausanne
  • Contact
  • infoscience@epfl.ch

  • Follow us on Facebook
  • Follow us on Instagram
  • Follow us on LinkedIn
  • Follow us on X
  • Follow us on Youtube
AccessibilityLegal noticePrivacy policyCookie settingsEnd User AgreementGet helpFeedback

Infoscience is a service managed and provided by the Library and IT Services of EPFL. © EPFL, tous droits réservés