Uncertainty-aware Probabilistic 3D Human Motion Forecasting via Invertible Networks
This work addresses uncertainty estimation in human motion forecasting for safety-critical contexts like human-robot collaboration, representing an incremental improvement with a novel method for a known bottleneck.
The paper tackles the problem of 3D human motion forecasting by proposing ProbHMI, which uses invertible networks to enable uncertainty quantification, achieving strong performance on benchmarks and validating uncertainty calibration for safety-critical applications.
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.