用高斯过程实现可扩展的人体运动概率预测，兼顾精度与实时性。
Towards Scalable Probabilistic Human Motion Prediction with Gaussian Processes for Safe Human-Robot Collaboration
- 基于多任务变分高斯过程，通过关节维度分解提升计算效率。
- 在H3.6M数据集上，负对数似然降低50%，置信区间覆盖率达近名义水平。
- 参数量仅为同类方法的1/8，适合机器人实时协同场景。
准确且不确定性校准的人体运动预测对安全人机协作至关重要，要求机器人能实时预判并响应人类动作。本文提出一种结构化多任务变分高斯过程框架，用于全身运动预测，捕捉时间相关性，并通过关节维度级因子分解实现可扩展性，同时采用连续6D旋转表示以保持运动学一致性。在Human3.6M（H3.6M）数据集上，模型负对数似然（KDE NLL）比强基线低50%，平均连续排序概率分数（CRPS）为0.021米，确定性角度误差（MAE）比先进深度学习方法高出3-18%。实证覆盖率分析显示，预测置信区间随预测时域增长覆盖比例缓慢下降，低置信度区间仍保守，高置信度区间接近名义水平，长时程校准漂移微小。尽管为概率模型，其参数量仅0.24-0.35百万，约为同类方法的八分之一，推理延迟低，适合实时部署。大量消融实验验证了6D旋转表示和Matern 3/2 + Linear核的有效性，并指导了诱导点数与隐维度的选择。结果表明，可扩展的高斯过程模型可在下游机器人任务中提供兼具竞争力精度与可靠、可解释不确定性估计的能力。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。