A Weight-aware-based Multi-source Unsupervised Domain Adaptation Method for Human Motion Intention Recognition

📄 arXiv: 2404.15366v2 📥 PDF

作者: Xiao-Yin Liu, Guotao Li, Xiao-Hu Zhou, Xu Liang, Zeng-Guang Hou

分类: eess.SP, cs.LG

发布日期: 2024-04-19 (更新: 2025-04-28)

备注: Accepted by IEEE Transactions on Cybernetics

💡 一句话要点

提出基于权重的多源无监督领域适应方法以解决人类运动意图识别问题

🎯 匹配领域: 支柱七：动作重定向 (Motion Retargeting) 支柱八：物理动画 (Physics-based Animation)

关键词: 人类运动意图识别 无监督领域适应 多源学习 权重调整 对抗学习 外骨骼机器人 实时分类

📋 核心要点

  1. 现有的无监督领域适应方法在处理多源主体数据时，未能考虑源主体之间的差异，导致分类准确性降低。
  2. 本文提出了一种基于权重的多源UDA算法（WMDD），通过自适应调整源域权重来有效识别HMI。
  3. 实验结果表明，WMDD在HMI识别任务中优于现有UDA方法，验证了理论分析的有效性。

📝 摘要（中文）

准确识别人类运动意图（HMI）有助于提高外骨骼机器人的穿戴舒适度，实现自然的人机交互。由于个体运动特征的差异，基于标记源主体训练的分类器在未标记目标主体上的表现较差。现有的无监督领域适应（UDA）方法忽视了各源主体之间的差异，导致分类准确性降低。本文提出了一种新的理论和算法，通过扩展边际差异不一致性（MDD）到多源UDA理论，提出了一种新颖的基于权重的多源UDA算法（WMDD），并通过实验验证了其有效性。

🔬 方法详解

问题定义：本文旨在解决在多源主体数据下进行人类运动意图识别时，现有无监督领域适应方法未考虑源主体间差异的问题，导致分类性能下降。

核心思路：提出了一种基于权重的多源UDA算法（WMDD），通过引入源域权重，动态调整源主体与目标主体之间的差异，从而提高分类准确性。

技术框架：整体框架包括特征生成器和集成分类器，通过对抗学习增强模型的泛化能力，同时将MDD理论转化为优化问题，确保理论与算法的有效结合。

关键创新：最重要的创新在于将边际差异不一致性（MDD）扩展到多源UDA理论，并提出自适应源域权重的概念，显著提升了分类性能。

关键设计：在算法设计中，采用轻量级网络结构以保证实时分类，并设置了特定的损失函数以优化源域权重的调整过程。

🖼️ 关键图片

fig_0
fig_1
fig_2

📊 实验亮点

实验结果显示，WMDD在HMI识别任务中相较于传统UDA方法有显著提升，具体表现为分类准确率提高了XX%，验证了理论分析的有效性和实用性。

🎯 应用场景

该研究的潜在应用领域包括外骨骼机器人、智能助理和人机交互系统等。通过提高人类运动意图的识别准确性，能够显著提升这些系统的用户体验和交互自然性，具有重要的实际价值和未来影响。

📄 摘要（原文）

Accurate recognition of human motion intention (HMI) is beneficial for exoskeleton robots to improve the wearing comfort level and achieve natural human-robot interaction. A classifier trained on labeled source subjects (domains) performs poorly on unlabeled target subject since the difference in individual motor characteristics. The unsupervised domain adaptation (UDA) method has become an effective way to this problem. However, the labeled data are collected from multiple source subjects that might be different not only from the target subject but also from each other. The current UDA methods for HMI recognition ignore the difference between each source subject, which reduces the classification accuracy. Therefore, this paper considers the differences between source subjects and develops a novel theory and algorithm for UDA to recognize HMI, where the margin disparity discrepancy (MDD) is extended to multi-source UDA theory and a novel weight-aware-based multi-source UDA algorithm (WMDD) is proposed. The source domain weight, which can be adjusted adaptively by the MDD between each source subject and target subject, is incorporated into UDA to measure the differences between source subjects. The developed multi-source UDA theory is theoretical and the generalization error on target subject is guaranteed. The theory can be transformed into an optimization problem for UDA, successfully bridging the gap between theory and algorithm. Moreover, a lightweight network is employed to guarantee the real-time of classification and the adversarial learning between feature generator and ensemble classifiers is utilized to further improve the generalization ability. The extensive experiments verify theoretical analysis and show that WMDD outperforms previous UDA methods on HMI recognition tasks.