arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2606.17455cs.RO

基于流形感知经验回放的外骨骼控制持续在线个性化

Continual Online Personalization of Exoskeleton Control via Manifold-Aware Experience Replay

Carnegie Mellon University(卡内基梅隆大学)

Changseob Song, Inseung Kang

AI总结:

提出流形感知经验回放框架,通过回放缓冲区保留用户特定表征,避免在线适应中的灾难性遗忘,在模拟偏瘫步态中扭矩和步态相位跟踪精度分别提升40%和60%。

摘要:

个性化外骨骼控制对于步态障碍的临床用户仍然是一个关键挑战。在线适应(OA)通过实时适应受试者变异性、设备适配性和不同运动任务提供了一种有效解决方案。然而,OA涉及连续的用户状态数据流,可能导致先前学习的运动情境的灾难性遗忘。在此,我们开发了一种基于流形感知经验回放的在线个性化框架,旨在在外骨骼控制的OA过程中跨不同任务维护用户特定表征。通过从回放缓冲区重放先前经历的任务,我们保留了跨所有学习任务的个性化外骨骼辅助。此外,我们捕获了一个区分不同运动任务的步态流形,消除了在选择目标回放区间时对显式任务标签的需求。我们在模拟偏瘫步态(与健全模式有显著偏差)上评估了我们的框架,涉及速度和坡度转换的多个遗忘场景。与没有回放的基线框架(在任务转换期间表现出灾难性遗忘)相比,我们的流形感知回放框架在扭矩和步态相位跟踪精度上分别实现了40%和60%的提升。这表明我们提出的框架在临床人群的日常行走中跨不同运动情境实时个性化外骨骼控制。

英文摘要:

Personalizing exoskeleton control remains a critical challenge for clinical users with gait disabilities. Online adaptation (OA) offers an effective solution by adapting in real time to subject variability, device fit, and diverse locomotor tasks. However, OA involves a continual stream of user state data, which can lead to catastrophic forgetting of previously learned locomotor contexts. Here, we develop a manifold-aware experience replay-based online personalization framework designed to maintain user-specific representations across diverse tasks during OA of exoskeleton control. By replaying previously experienced tasks from a replay buffer, we preserve the personalized exoskeleton assistance across all learned tasks. Furthermore, we capture a gait manifold that distinguishes between different locomotor tasks, removing the need for explicit task labeling when selecting target replay bins. We evaluated our framework on emulated hemiplegic gait, which largely deviates from able-bodied patterns, across multiple forgetting scenarios with speed and incline transitions. Our manifold-aware replay framework achieved 40% and 60% improvements in torque and gait phase tracking accuracy, respectively, compared to a baseline framework without replay, which exhibited catastrophic forgetting during task transitions. This demonstrates that our proposed framework personalizes exoskeleton control in real time across diverse locomotor contexts in daily ambulation of clinical populations.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑