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

• URL: http://arxiv.org/abs/2606.17455v1
• Date: Tue, 16 Jun 2026 03:17:49 GMT
• Title: Continual Online Personalization of Exoskeleton Control via Manifold-Aware Experience Replay
• Abstract summary: Personalizing exoskeleton control remains a critical challenge for clinical users with gait disabilities.<n>Online adaptation (OA) offers an effective solution by adapting in real time to subject variability, device fit, and diverse locomotor tasks.<n>Here, we develop a manifold-aware experience replay-based online personalization framework designed to maintain user-specific representations.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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.

Related papers

• Skill Self-Play: Pushing the Frontier of LLM Capability with Co-Evolving Skills [53.15216425100295]
  We introduce Skill Self-Play (Skill-SP), a co-evolutionary framework comprising a proposer, a solver, and a skill controller.<n>The proposer generates challenging tasks conditioned on dynamically sampled skills; the solver explores candidate solutions to push its capability boundaries; and the skill controller collects execution feedback to update and expand the skill library.<n>This interactive co-evolution effectively bridges the gap between structured verification and open-ended exploration.
  arXiv  Detail & Related papers  (2026-07-24T17:59:22Z)
• Knowledge Reutilization in Meta-Reinforcement Learning [51.07319647819108]
  We propose a meta-knowledge reutilization framework that learns task-level knowledge on a dynamics-simplified agent and transfers it to heterogeneous agents.<n>We show that our framework reduces final-step tracking error by 94.75% -- 99.79% compared with recent state-of-the-art baselines.
  arXiv  Detail & Related papers  (2026-06-16T16:32:28Z)
• From Articulated Kinematics to Routed Visual Control for Action-Conditioned Surgical Video Generation [43.4347713269043]
  Action-conditioned surgical video generation is a critical yet highly challenging problem for robotic surgery.<n>We propose a kinematic-to-visual lifting paradigm that converts articulated kinematics into a unified set of five image-aligned control modalities.<n>Our method consistently improves action faithfulness, visual fidelity, and cross-domain generalization over diverse baselines.
  arXiv  Detail & Related papers  (2026-05-09T05:48:51Z)
• Personalized Gait Patterns During Exoskeleton-Aided Training May Have Minimal Effect on User Experience. Insights from a Pilot Study [0.8572409162523734]
  Most exoskeletons rely on pre-recorded, non-personalized gait trajectories constrained to the sagittal plane.<n>We present a data-driven gait personalization framework for an exoskeleton that supports multi-planar motion.
  arXiv  Detail & Related papers  (2025-12-19T10:23:29Z)
• CHIP: Adaptive Compliance for Humanoid Control through Hindsight Perturbation [70.5382178207975]
  hIsight Perturbation (CHIP) is a plug-and-play module that enables controllable end-effector stiffness.<n>CHIP is easy to implement and requires neither data augmentation nor additional reward tuning.<n>We show that a generalist motion-tracking controller trained with CHIP can perform a diverse set of forceful manipulation tasks.
  arXiv  Detail & Related papers  (2025-12-16T18:56:04Z)
• ExoGait-MS: Learning Periodic Dynamics with Multi-Scale Graph Network for Exoskeleton Gait Recognition [20.076175885171413]
  Current exoskeleton control methods often face challenges in delivering personalized treatment.<n>Personal gait is essential for the effectiveness of exoskeleton robots, as it directly impacts their adaptability, comfort, and rehabilitation outcomes for individual users.<n>We propose a novel approach, which uses Multi-Scale Global Dense Graph Convolutional Networks (GCN) in the spatial domain to identify latent joint synergy patterns.<n>Our experimental results demonstrate that our method achieves an impressive accuracy of 94.34% on this dataset, surpassing the current state-of-the-art (SOTA) by 3.77%.
  arXiv  Detail & Related papers  (2025-05-23T15:24:25Z)
• Continual Diffuser (CoD): Mastering Continual Offline Reinforcement Learning with Experience Rehearsal [54.93261535899478]
  In real-world applications, such as robotic control of reinforcement learning, the tasks are changing, and new tasks arise in a sequential order.<n>This situation poses the new challenge of plasticity-stability trade-off for training an agent who can adapt to task changes and retain acquired knowledge.<n>We propose a rehearsal-based continual diffusion model, called Continual diffuser (CoD), to endow the diffuser with the capabilities of quick adaptation (plasticity) and lasting retention (stability)
  arXiv  Detail & Related papers  (2024-09-04T08:21:47Z)
• SkeleTR: Towrads Skeleton-based Action Recognition in the Wild [86.03082891242698]
  SkeleTR is a new framework for skeleton-based action recognition. It first models the intra-person skeleton dynamics for each skeleton sequence with graph convolutions. It then uses stacked Transformer encoders to capture person interactions that are important for action recognition in general scenarios.
  arXiv  Detail & Related papers  (2023-09-20T16:22:33Z)
• Self-Supervised Multi-Object Tracking For Autonomous Driving From Consistency Across Timescales [53.55369862746357]
  Self-supervised multi-object trackers have tremendous potential as they enable learning from raw domain-specific data. However, their re-identification accuracy still falls short compared to their supervised counterparts. We propose a training objective that enables self-supervised learning of re-identification features from multiple sequential frames.
  arXiv  Detail & Related papers  (2023-04-25T20:47:29Z)
• An adaptive closed-loop ECoG decoder for long-term and stable bimanual control of an exoskeleton by a tetraplegic [91.6474995587871]
  High performance control of diverse effectors for complex tasks must be robust over time and of high decoding performance without continuous recalibration of the decoders. We developed an adaptive online tensor-based decoder: the Recursive Exponentially Weighted Markov-Switching multi- Linear Model (REW-MSLM) We demonstrated over a period of 6 months the stability of the 8-dimensional alternative bimanual control of the exoskeleton and its virtual avatar using REW-MSLM without recalibration of the decoder.
  arXiv  Detail & Related papers  (2022-01-25T16:51:29Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.