Gast ::
| Hauptseite > Publikationsdatenbank > Human Motion Prediction Under Unexpected Perturbation |
| Hauptseite > Publikationsdatenbank > Human Motion Prediction Under Unexpected Perturbation |
| Contribution to a conference proceedings | FZJ-2025-00301 |
; ; ; ;
2024
IEEE
This record in other databases: 
Please use a persistent id in citations: doi:10.1109/CVPR52733.2024.00149 doi:10.34734/FZJ-2025-00301
Abstract: 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 differentiable physics and deep neural networks, leading to an explicit Latent Differentiable 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.
|
The record appears in these collections: |
PDF