# Uncertainty-Aware Ankle Exoskeleton Control

## TL;DR

This paper introduces an uncertainty-aware control framework for ankle exoskeletons that enhances safety and adaptability by automatically disengaging assistance when encountering unfamiliar movements, enabling real-world application.

## Contribution

The paper presents a novel uncertainty estimation approach using ensemble models to improve exoskeleton safety and adaptability in unstructured environments.

## Key findings

- Online uncertainty estimator accurately detects out-of-distribution movements (F1: 89.2)
- Ensemble of gait phase estimators effectively switches assistance on/off
- Framework enables safe, autonomous support in diverse real-world scenarios

## 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.