Human Motion Prediction Under Unexpected Perturbation - Université Rennes 2
Communication Dans Un Congrès Année : 2024

Human Motion Prediction Under Unexpected Perturbation

Julien Petrré
  • Fonction : Auteur
He Wang
  • Fonction : Auteur
  • PersonId : 1483205

Résumé

We investigate a new task in human motion prediction, which is predicting motions under unexpected physical perturbation potentially involving multiple people. Compared with existing research, this task involves predicting less controlled, unpremeditated and pure reactive motions in response to external impact and how such motions can propagate through people. It brings new challenges such as data scarcity and predicting complex interactions. To this end, we propose a new method capitalizing differential physics and deep neural networks, leading to an explicit Latent Differential Physics (LDP) model. Through experiments, we demonstrate that LDP has high data efficiency, outstanding prediction accuracy, strong generalizability and good explainability. Since there is no similar research, a comprehensive comparison with 11 adapted baselines from several relevant domains is conducted, showing LDP outperforming existing research both quantitatively and qualitatively, improving prediction accuracy by as much as 70%, and demonstrating significantly stronger generalization.

Mots clés

Fichier principal
Vignette du fichier
2403.15891v1.pdf (5.06 Mo) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-04860667 , version 1 (01-01-2025)

Licence

Identifiants

Citer

Jiangbei Yue, Baiyi Li, Armin Seyfried, Julien Petrré, He Wang. Human Motion Prediction Under Unexpected Perturbation. 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Jun 2024, Seattle, France. pp.1501-1511, ⟨10.1109/CVPR52733.2024.00149⟩. ⟨hal-04860667⟩
0 Consultations
0 Téléchargements

Altmetric

Partager

More