IMU-based Real-Time Crutch Gait Phase and Step Detections in Lower-Limb Exoskeletons

TL;DR

This paper introduces a low-cost, IMU-based system for real-time gait phase and step detection in lower-limb exoskeletons, using deep learning and biomechanical constraints to improve accuracy and latency.

Contribution

It presents a novel minimalist framework with a single IMU and deep learning models, outperforming traditional methods in real-time gait detection for exoskeletons.

Findings

Achieved 94% success rate in crutch step detection

Temporal Convolutional Network (TCN) outperformed other architectures

System generalized to a paralyzed user despite training on healthy subjects

Abstract

Lower limb exoskeletons and prostheses require precise, real time gait phase and step detections to ensure synchronized motion and user safety. Conventional methods often rely on complex force sensing hardware that introduces control latency. This paper presents a minimalist framework utilizing a single, low cost Inertial-Measurement Unit (IMU) integrated into the crutch hand grip, eliminating the need for mechanical modifications. We propose a five phase classification system, including standard gait phases and a non locomotor auxiliary state, to prevent undesired motion. Three deep learning architectures were benchmarked on both a PC and an embedded system. To improve performance under data constrained conditions, models were augmented with a Finite State Machine (FSM) to enforce biomechanical consistency. The Temporal Convolutional Network (TCN) emerged as the superior architecture, yielding the highest success rates and lowest latency. Notably, the model generalized to a paralyzed user despite being trained exclusively on healthy participants. Achieving a 94% success rate in detecting crutch steps, this system provides a high performance, cost effective solution for real time exoskeleton control.