Real-time Hybrid Locomotion Mode Recognition for Lower-limb Wearable Robots

Andrea Parri, Kebin Yuan, Dario Marconi, Tingfang Yan, Simona Crea, Marko Munih, Raffaele Molino Lova, Nicola Vitiello, Qining Wang

Research output: Contribution to journalArticle

12 Citations (Scopus)

Abstract

Real-time recognition of locomotion-related activities is a fundamental skill that the controller of lower-limb wearable robots should possess. Subject-specific training and reliance on electromyographic interfaces are the main limitations of existing approaches. This study presents a novel methodology for real-time locomotion mode recognition of locomotion-related activities in lower-limb wearable robotics. A hybrid classifier can distinguish among seven locomotion-related activities. First, a time-based approach classifies between static and dynamical states based on gait kinematics data. Second, an event-based fuzzy logic method triggered by foot pressure sensors operates in a subject-independent fashion on a minimal set of relevant biomechanical features to classify among dynamical modes. The locomotion mode recognition algorithm is implemented on the controller of a portable powered orthosis for hip assistance. An experimental protocol is designed to evaluate the controller performance in an out-of-lab scenario without the need for a subject-specific training. Experiments are conducted on six healthy volunteers performing locomotion-related activities at slow, normal, and fast speeds under the zero-torque and assistive mode of the orthosis. The overall accuracy rate of the controller is 99.4% over more than 10,000 steps, including seamless transitions between different modes. The experimental results show a successful subject-independent performance of the controller for wearable robots assisting locomotion-related activities.

Original languageEnglish
JournalIEEE/ASME Transactions on Mechatronics
Early online dateOct 2017
DOIs
Publication statusE-pub ahead of print - Oct 2017

Fingerprint

Robots
Controllers
Pressure sensors
Fuzzy logic
Kinematics
Robotics
Classifiers
Torque
Network protocols
Experiments

Keywords

  • fuzzy-logic classifier
  • gait assistance
  • Locomotion mode recognition
  • lower-limb wearable robots

ASJC Scopus subject areas

  • Control and Systems Engineering
  • Computer Science Applications
  • Electrical and Electronic Engineering

Cite this

Real-time Hybrid Locomotion Mode Recognition for Lower-limb Wearable Robots. / Parri, Andrea; Yuan, Kebin; Marconi, Dario; Yan, Tingfang; Crea, Simona; Munih, Marko; Lova, Raffaele Molino; Vitiello, Nicola; Wang, Qining.

In: IEEE/ASME Transactions on Mechatronics, 10.2017.

Research output: Contribution to journalArticle

Parri, Andrea ; Yuan, Kebin ; Marconi, Dario ; Yan, Tingfang ; Crea, Simona ; Munih, Marko ; Lova, Raffaele Molino ; Vitiello, Nicola ; Wang, Qining. / Real-time Hybrid Locomotion Mode Recognition for Lower-limb Wearable Robots. In: IEEE/ASME Transactions on Mechatronics. 2017.
@article{66104fa23aee499794d80f7318a2e671,
title = "Real-time Hybrid Locomotion Mode Recognition for Lower-limb Wearable Robots",
abstract = "Real-time recognition of locomotion-related activities is a fundamental skill that the controller of lower-limb wearable robots should possess. Subject-specific training and reliance on electromyographic interfaces are the main limitations of existing approaches. This study presents a novel methodology for real-time locomotion mode recognition of locomotion-related activities in lower-limb wearable robotics. A hybrid classifier can distinguish among seven locomotion-related activities. First, a time-based approach classifies between static and dynamical states based on gait kinematics data. Second, an event-based fuzzy logic method triggered by foot pressure sensors operates in a subject-independent fashion on a minimal set of relevant biomechanical features to classify among dynamical modes. The locomotion mode recognition algorithm is implemented on the controller of a portable powered orthosis for hip assistance. An experimental protocol is designed to evaluate the controller performance in an out-of-lab scenario without the need for a subject-specific training. Experiments are conducted on six healthy volunteers performing locomotion-related activities at slow, normal, and fast speeds under the zero-torque and assistive mode of the orthosis. The overall accuracy rate of the controller is 99.4{\%} over more than 10,000 steps, including seamless transitions between different modes. The experimental results show a successful subject-independent performance of the controller for wearable robots assisting locomotion-related activities.",
keywords = "fuzzy-logic classifier, gait assistance, Locomotion mode recognition, lower-limb wearable robots",
author = "Andrea Parri and Kebin Yuan and Dario Marconi and Tingfang Yan and Simona Crea and Marko Munih and Lova, {Raffaele Molino} and Nicola Vitiello and Qining Wang",
year = "2017",
month = "10",
doi = "10.1109/TMECH.2017.2755048",
language = "English",
journal = "IEEE/ASME Transactions on Mechatronics",
issn = "1083-4435",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - JOUR

T1 - Real-time Hybrid Locomotion Mode Recognition for Lower-limb Wearable Robots

AU - Parri, Andrea

AU - Yuan, Kebin

AU - Marconi, Dario

AU - Yan, Tingfang

AU - Crea, Simona

AU - Munih, Marko

AU - Lova, Raffaele Molino

AU - Vitiello, Nicola

AU - Wang, Qining

PY - 2017/10

Y1 - 2017/10

N2 - Real-time recognition of locomotion-related activities is a fundamental skill that the controller of lower-limb wearable robots should possess. Subject-specific training and reliance on electromyographic interfaces are the main limitations of existing approaches. This study presents a novel methodology for real-time locomotion mode recognition of locomotion-related activities in lower-limb wearable robotics. A hybrid classifier can distinguish among seven locomotion-related activities. First, a time-based approach classifies between static and dynamical states based on gait kinematics data. Second, an event-based fuzzy logic method triggered by foot pressure sensors operates in a subject-independent fashion on a minimal set of relevant biomechanical features to classify among dynamical modes. The locomotion mode recognition algorithm is implemented on the controller of a portable powered orthosis for hip assistance. An experimental protocol is designed to evaluate the controller performance in an out-of-lab scenario without the need for a subject-specific training. Experiments are conducted on six healthy volunteers performing locomotion-related activities at slow, normal, and fast speeds under the zero-torque and assistive mode of the orthosis. The overall accuracy rate of the controller is 99.4% over more than 10,000 steps, including seamless transitions between different modes. The experimental results show a successful subject-independent performance of the controller for wearable robots assisting locomotion-related activities.

AB - Real-time recognition of locomotion-related activities is a fundamental skill that the controller of lower-limb wearable robots should possess. Subject-specific training and reliance on electromyographic interfaces are the main limitations of existing approaches. This study presents a novel methodology for real-time locomotion mode recognition of locomotion-related activities in lower-limb wearable robotics. A hybrid classifier can distinguish among seven locomotion-related activities. First, a time-based approach classifies between static and dynamical states based on gait kinematics data. Second, an event-based fuzzy logic method triggered by foot pressure sensors operates in a subject-independent fashion on a minimal set of relevant biomechanical features to classify among dynamical modes. The locomotion mode recognition algorithm is implemented on the controller of a portable powered orthosis for hip assistance. An experimental protocol is designed to evaluate the controller performance in an out-of-lab scenario without the need for a subject-specific training. Experiments are conducted on six healthy volunteers performing locomotion-related activities at slow, normal, and fast speeds under the zero-torque and assistive mode of the orthosis. The overall accuracy rate of the controller is 99.4% over more than 10,000 steps, including seamless transitions between different modes. The experimental results show a successful subject-independent performance of the controller for wearable robots assisting locomotion-related activities.

KW - fuzzy-logic classifier

KW - gait assistance

KW - Locomotion mode recognition

KW - lower-limb wearable robots

UR - http://www.scopus.com/inward/record.url?scp=85030635415&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85030635415&partnerID=8YFLogxK

U2 - 10.1109/TMECH.2017.2755048

DO - 10.1109/TMECH.2017.2755048

M3 - Article

AN - SCOPUS:85030635415

JO - IEEE/ASME Transactions on Mechatronics

JF - IEEE/ASME Transactions on Mechatronics

SN - 1083-4435

ER -