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

TL;DR

This paper introduces a scalable Gaussian Process framework for full-body human motion prediction that provides accurate, well-calibrated uncertainty estimates, suitable for real-time safe human-robot interaction.

Contribution

It presents a novel structured multitask variational Gaussian Process model with a 6D rotation representation, achieving high accuracy and efficiency for human motion prediction.

Findings

Up to 50 lower KDE NLL than baselines

CRPS of 0.021 meters indicating accurate uncertainty quantification

Model uses only 0.24-0.35 million parameters, enabling real-time inference

Abstract

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.