Uncertainty-Aware Ankle Exoskeleton Control

2025-08-28

AI Summary

Current lower-limb exoskeleton controllers are constrained to predefined discrete motions in controlled environments, rendering them ill-suited for real-world scenarios characterized by motion uncertainty. To address this limitation, we propose the first uncertainty-aware control framework specifically designed for ankle exoskeletons. Our method leverages model ensembling to enable real-time in-distribution versus out-of-distribution motion discrimination: upon detecting an unknown gait pattern, the controller autonomously disengages assistance to ensure human–robot safety. A key innovation is the integration of a gait-phase estimator ensemble, which—when deployed online—achieves an 89.2% F1 score. This significantly enhances the system’s generalizability and autonomous decision-making capability in unstructured, dynamic environments.

Technology Category

• Intelligent Robots: State Estimation
• Reasoning under Uncertainty: Sequential Decision Making
• Multiagent Systems: Multiagent Systems under Uncertainty

Application Category

• Responsible Web: Machine-in-the-loop, human agency and autonomy
• User Modeling, Personalization and Recommendation: Attacks and countermeasures in recommendation systems
• Economics, Online Markets and Human Computation: LLM based quality controls for crowd work

Abstract

Lower limb exoskeletons show promise to assist human movement, but their utility is limited by controllers designed for discrete, predefined actions in controlled environments, restricting their real-world applicability. We present an uncertainty-aware control framework that enables ankle exoskeletons to operate safely across diverse scenarios by automatically disengaging when encountering unfamiliar movements. Our approach uses an uncertainty estimator to classify movements as similar (in-distribution) or different (out-of-distribution) relative to actions in the training set. We evaluated three architectures (model ensembles, autoencoders, and generative adversarial networks) on an offline dataset and tested the strongest performing architecture (ensemble of gait phase estimators) online. The online test demonstrated the ability of our uncertainty estimator to turn assistance on and off as the user transitioned between in-distribution and out-of-distribution tasks (F1: 89.2). This new framework provides a path for exoskeletons to safely and autonomously support human movement in unstructured, everyday environments.

Problem

• Developing uncertainty-aware control for ankle exoskeletons in diverse scenarios
• Automatically disengaging assistance during unfamiliar human movements
• Enabling safe autonomous operation in unstructured real-world environments

Innovation

• Uncertainty-aware control framework for exoskeletons
• Automatic disengagement during unfamiliar movements
• Ensemble gait phase estimators for movement classification