ROMar 7

Towards Scalable Probabilistic Human Motion Prediction with Gaussian Processes for Safe Human-Robot Collaboration

arXiv:2603.07096v1
Predicted impact top 63% in RO · last 90 daysOriginality Incremental advance
AI Analysis

This work is significant for human-robot collaboration, providing a scalable probabilistic model for real-time human motion prediction with well-calibrated uncertainty, which is crucial for safe robot operation.

This paper proposes a structured multitask variational Gaussian Process (GP) framework for full-body human motion prediction, achieving up to 50 lower kernel density estimate negative log-likelihood (KDE NLL) than strong baselines on Human3.6M (H3.6M) and a mean continuous ranked probability score (CRPS) of 0.021 m. While its deterministic mean angle error (MAE) is 3-18% higher than competitive deep learning methods, the model requires 8 times fewer parameters and exhibits modest inference times.

Accurate human motion prediction with well-calibrated uncertainty is critical for safe human-robot collaboration (HRC), where robots must anticipate and react to human movements in real time. We propose a structured multitask variational Gaussian Process (GP) framework for full-body human motion prediction that captures temporal correlations and leverages joint-dimension-level factorization for scalability, while using a continuous 6D rotation representation to preserve kinematic consistency. Evaluated on Human3.6M (H3.6M), our model achieves up to 50 lower kernel density estimate negative log-likelihood (KDE NLL) than strong baselines, a mean continuous ranked probability score (CRPS) of 0.021 m, and deterministic mean angle error (MAE) that is 3-18% higher than competitive deep learning methods. Empirical coverage analysis shows that the fraction of ground-truth outcomes contained within predicted confidence intervals gradually decreases with horizon, remaining conservative for lower-confidence intervals and near-nominal for higher-confidence intervals, with only modest calibration drift at longer horizons. Despite its probabilistic formulation, our model requires only 0.24-0.35 M parameters, roughly eight times fewer than comparable approaches, and exhibits modest inference times, indicating suitability for real-time deployment. Extensive ablation studies further validated the choice of 6D rotation representation and Matern 3/2 + Linear kernel, and guided the selection of the number of inducing points and latent dimensionality. These results demonstrate that scalable GP-based models can deliver competitive accuracy together with reliable and interpretable uncertainty estimates for downstream robotics tasks such as motion planning and collision avoidance.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes