← Back ICRA 2026

Intent Recognition in Gait Transition Using Muscle Volume Sensors with Deep Learning

Geonwoo Park, MooJin Woo, Jiwoo Oh, Hyeon Chan Chei, Keonyoung Oh

PDF

AI summary

Key figure (auto-extracted from paper)

The cuff-type muscle volume sensor achieves classification accuracy comparable to insole and IMU sensors, proving its viability as a robust, wearable alternative for real-time intention recognition in assistive robotics.

Muscle volume sensors Intention recognition Deep learning Wearable robotics Gait transition LSTM classification

Problem

Conventional intention recognition methods for wearable robots rely on cumbersome setups, uncomfortable neural signals, or sensors that struggle with stationary states and external noise.

Approach

An LSTM-based deep learning model classifies gait states and detects transitions using data from a wearable cuff-type muscle volume sensor, benchmarked against IMU and insole pressure sensors.

Key results

93.04% overall classification accuracy for the MV sensor
0.455 s average transition detection latency
Faster static-to-dynamic transition detection than insole sensors
Comparable robustness and wearability to IMU and insole baselines

Why it matters

Provides a comfortable, noise-resistant sensing alternative for wearable assistive robots and gait devices to enable timely, context-aware user assistance.

Abstract

Intention recognition is essential for wearable robotics and assistive systems. However, conventional approaches often suffer from cumbersome sensor setups or sensitivity to external disturbances. To address these limitations, this study proposes an LSTM-based intention recognition method using lower-limb Muscle-Volume (MV) sensors. An insole-type pressure sensor, an IMU sensor, and a cuff-type MV sensor were used to record a series of motions, including sitting, standing, walking, and running. Deep learning techniques were then applied for classification and transition detection. Accuracies of the predicted movement states based on data from the IMU, insole-type pressure, and cuff-type MV sensors were 93.04%, 97.65%, and 93.08%, respectively. The average transition detection latencies for the IMU, insole, and MV sensor model were 0.135 s, 0.377 s, and 0.455 s, respectively. Results show that the proposed MV sensor achieves performance comparable to insole pressure sensors, demonstrating its potential as a practical and robust alternative for intention recognition in wearable systems.

Index terms

Intention Recognition Wearable Robotics Deep Learning Methods