Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2507.14694 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866908456911372288 |
|---|---|
| author | Ma, Yue Zhou, Kanglei Yu, Fuyang Li, Frederick W. B. Liang, Xiaohui |
| author_facet | Ma, Yue Zhou, Kanglei Yu, Fuyang Li, Frederick W. B. Liang, Xiaohui |
| contents | 3D human motion forecasting aims to enable autonomous applications. Estimating uncertainty for each prediction (i.e., confidence based on probability density or quantile) is essential for safety-critical contexts like human-robot collaboration to minimize risks. However, existing diverse motion forecasting approaches struggle with uncertainty quantification due to implicit probabilistic representations hindering uncertainty modeling. We propose ProbHMI, which introduces invertible networks to parameterize poses in a disentangled latent space, enabling probabilistic dynamics modeling. A forecasting module then explicitly predicts future latent distributions, allowing effective uncertainty quantification. Evaluated on benchmarks, ProbHMI achieves strong performance for both deterministic and diverse prediction while validating uncertainty calibration, critical for risk-aware decision making. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_14694 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Uncertainty-aware Probabilistic 3D Human Motion Forecasting via Invertible Networks Ma, Yue Zhou, Kanglei Yu, Fuyang Li, Frederick W. B. Liang, Xiaohui Robotics Computer Vision and Pattern Recognition 3D human motion forecasting aims to enable autonomous applications. Estimating uncertainty for each prediction (i.e., confidence based on probability density or quantile) is essential for safety-critical contexts like human-robot collaboration to minimize risks. However, existing diverse motion forecasting approaches struggle with uncertainty quantification due to implicit probabilistic representations hindering uncertainty modeling. We propose ProbHMI, which introduces invertible networks to parameterize poses in a disentangled latent space, enabling probabilistic dynamics modeling. A forecasting module then explicitly predicts future latent distributions, allowing effective uncertainty quantification. Evaluated on benchmarks, ProbHMI achieves strong performance for both deterministic and diverse prediction while validating uncertainty calibration, critical for risk-aware decision making. |
| title | Uncertainty-aware Probabilistic 3D Human Motion Forecasting via Invertible Networks |
| topic | Robotics Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2507.14694 |