ExoTraj: A General Lower-limb Exoskeleton Assistance Policy for Complex Environments

📄 arXiv: 2606.16876v1 📥 PDF

作者: Xiao-Yin Liu, Guotao Li, Long Sun, Xu Liang, Zeng-Guang Hou

分类: cs.RO

发布日期: 2026-06-15

备注: 28 pages, 19 figures, project page: https://xiaoyinliu0714.github.io/Home_ExoTraj/

💡 一句话要点

提出ExoTraj以解决复杂环境下下肢外骨骼的适应性辅助问题

🎯 匹配领域: 支柱一：机器人控制 (Robot Control) 支柱二：RL算法与架构 (RL & Architecture)

关键词: 外骨骼 轨迹预测 模型预测控制 自适应辅助 动态系统 人机协作 运动捕捉

📋 核心要点

  1. 现有方法在复杂环境中进行下肢外骨骼的适应性扭矩预测时，依赖昂贵的动作捕捉系统，限制了其应用。
  2. 本文提出了一种快速流匹配方法，结合模型预测控制，优化扭矩以实现实时的适应性辅助。
  3. 实验结果显示，ExoTraj在跨主体预测误差上降低14.0%，并显著降低代谢率和心率，提升了辅助效果。

📝 摘要（中文）

在动态外骨骼场景中，自适应扭矩预测通常需要昂贵的动作捕捉系统，这在复杂的户外环境中不可行。轨迹预测已成为解决此问题的有效方法。然而，外骨骼轨迹预测面临两个核心挑战：一是从多模态特征到轨迹信息的映射，二是从轨迹到扭矩的映射。为此，本文提出了一种快速流匹配方法，能够实现准确的轨迹预测和更好的泛化性能。同时，利用模型预测控制设计新的优化目标，以优化扭矩，确保外骨骼实现舒适且稳健的辅助。实验结果表明，ExoTraj在在线阶段将跨主体预测误差降低了14.0%，并在外部噪声下保持稳健性。

🔬 方法详解

问题定义：本文旨在解决复杂环境下下肢外骨骼的适应性辅助问题。现有方法多依赖于昂贵的动作捕捉系统，且在轨迹预测中忽视了个体间的差异，限制了预测的泛化能力。

核心思路：论文提出的快速流匹配方法通过利用轨迹生成误差和编码观察来指导训练方向，实现准确的轨迹预测。同时，结合模型预测控制优化扭矩，以确保外骨骼提供舒适且稳健的辅助。

技术框架：整体架构包括两个主要模块：轨迹预测模块和扭矩优化模块。轨迹预测模块负责从多模态特征生成轨迹信息，扭矩优化模块则基于预测的轨迹进行扭矩调整。

关键创新：最重要的技术创新在于快速流匹配方法的提出，使得轨迹预测不仅准确且具备良好的泛化能力，克服了传统方法的局限性。

关键设计：在设计中，采用了特定的损失函数来平衡轨迹生成误差与扭矩优化目标，同时在网络结构上进行了优化，以适应高动态的人机系统。通过这些设计，ExoTraj能够在复杂环境中实现高效的适应性辅助。

🖼️ 关键图片

fig_0
fig_1
fig_2

📊 实验亮点

实验结果显示，ExoTraj在在线阶段将跨主体预测误差降低了14.0%，相较于零扭矩条件，代谢率降低了11.5-24.4%，心率降低了1.7-19.5%，峰值肌肉激活水平降低了10.9-41.3%，表现出显著的性能提升。

🎯 应用场景

该研究的潜在应用领域包括康复机器人、助行器和其他需要人机协作的外骨骼设备。通过降低对高成本数据采集的依赖，ExoTraj有望在实际应用中提供更为经济和高效的解决方案，推动外骨骼技术的普及与发展。

📄 摘要（原文）

Adaptive torque prediction in dynamic exoskeleton scenarios requires expensive motion capture systems, which are infeasible in complex outdoor environments. Trajectory prediction has emerged as one of the effective approaches to address such an issue. However, the core challenges of exoskeleton trajectory prediction are twofold: establishing the mapping from multi-modal features to trajectory information; constructing the mapping from trajectory to torque. For the former, most existing methods perform only single-step prediction and neglect inter-subject trajectory variability, thereby limiting the trajectory optimization space and prediction generalization. To address this, this paper proposes a fast flow matching method that enables accurate trajectory prediction and better generalization for real-time performance, where trajectory generation errors and encoded observations are used to guide the training direction. For the second challenge, due to the high dynamics of the human-robot system and the strong coupling between perception and control, simple control methods struggle to achieve efficient assistance based on the predicted trajectory. This paper utilizes model predictive control and designs a novel optimization objective to optimize torque, ensuring the exoskeleton achieves comfortable and robust assistance. By integrating the above two components, the unified policy, denoted as ExoTraj, is developed to enable adaptive assistance in complex outdoor scenarios without high data acquisition cost. Experimental results show that compared to traditional methods, ExoTraj reduces cross-subject prediction error by 14.0% during the online phase and maintains robustness against external noise. Relative to the zero torque condition, ExoTraj decreases metabolic rate by 11.5-24.4%, heart rate by 1.7-19.5%, and peak muscle activation levels by 10.9-41.3%, respectively.