K2MUSE: A human lower limb multimodal dataset under diverse conditions for facilitating rehabilitation robotics

2025-04-20

AI Summary

Existing lower-limb datasets suffer from single-modality acquisition, limited sample size, and inadequate modeling of realistic disturbances—hindering natural human–robot interaction and adaptive control in rehabilitation robotics. To address this, we introduce K2MUSE, the first multimodal lower-limb dataset specifically designed for rehabilitation robot development. It comprises synchronized kinematic, kinetic, amplitude-mode ultrasound (AUS), and surface electromyography (sEMG) data from 30 healthy subjects under diverse conditions: multiple inclinations and walking speeds, as well as physiological and technical disturbances—including muscle fatigue, electrode displacement, and inter-day variability. K2MUSE uniquely integrates AUS and sEMG systemically, acquired synchronously via Vicon motion capture, an instrumented treadmill, and bilateral 13-channel sEMG/AUS hardware. We publicly release an open-source dataset containing over 100,000 gait cycles (k2muse.github.io), filling a critical gap in large-scale, high-fidelity, disturbance-rich multimodal lower-limb data to advance adaptive control algorithms and neuro-musculoskeletal mechanism analysis.

Technology Category

• Intelligent Robots: Multimodal Perception & Sensor Fusion
• Machine Learning: Multimodal Learning
• Data Mining & Knowledge Management: Mining of Visual, Multimedia & Multimodal Data

Application Category

• Web Mining and Content Analysis: Mining multimedia, multimodal, multilingual, cross-lingual Web data
• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Economics, Online Markets and Human Computation: Data quality aspects of human-annotated datasets

Abstract

The natural interaction and control performance of lower limb rehabilitation robots are closely linked to biomechanical information from various human locomotion activities. Multidimensional human motion data significantly deepen the understanding of the complex mechanisms governing neuromuscular alterations, thereby facilitating the development and application of rehabilitation robots in multifaceted real-world environments. However, currently available lower limb datasets are inadequate for supplying the essential multimodal data and large-scale gait samples necessary for effective data-driven approaches, and they neglect the significant effects of acquisition interference in real applications.To fill this gap, we present the K2MUSE dataset, which includes a comprehensive collection of multimodal data, comprising kinematic, kinetic, amplitude-mode ultrasound (AUS), and surface electromyography (sEMG) measurements. The proposed dataset includes lower limb multimodal data from 30 able-bodied participants walking under different inclines (0$^circ$, $pm$5$^circ$, and $pm$10$^circ$), various speeds (0.5 m/s, 1.0 m/s, and 1.5 m/s), and different nonideal acquisition conditions (muscle fatigue, electrode shifts, and inter-day differences). The kinematic and ground reaction force data were collected via a Vicon motion capture system and an instrumented treadmill with embedded force plates, whereas the sEMG and AUS data were synchronously recorded for thirteen muscles on the bilateral lower limbs. This dataset offers a new resource for designing control frameworks for rehabilitation robots and conducting biomechanical analyses of lower limb locomotion. The dataset is available at https://k2muse.github.io/.

Problem

• Lack of multimodal lower limb data for rehabilitation robotics
• Insufficient gait samples for data-driven approaches
• Neglecting real-world acquisition interference effects

Innovation

• Multimodal dataset with kinematic and kinetic data
• Includes ultrasound and electromyography measurements
• Covers diverse walking conditions and interferences