AI for Robotic Exoskeletons and Prostheses

A special issue of Robotics (ISSN 2218-6581). This special issue belongs to the section "Neurorobotics".

Deadline for manuscript submissions: 31 August 2024 | Viewed by 7400

Special Issue Editor


E-Mail Website1 Website2
Guest Editor
Faculty of Technological and Innovation Sciences, Universitas Mercatorum, Rome, Italy
Interests: human-robot interaction; computer vision; artificial intelligence

Special Issue Information

Dear Colleagues,

Artificial Intelligence (AI) is already a pervasive technology in ICT systems that is changing people's lives, encompassing digital voice assistance, smart homes, facial recognition, and chatbots. Simultaneously, robotic exoskeletons and prostheses have revolutionized the healthcare sector, assisting people with daily activities, especially in the last decade. This Special Issue aims to investigate the empowerment that AI can bring to robotic exoskeletons and prostheses by presenting innovative AI-based approaches for robot modeling, control, interaction, and application in real-world scenarios. We seek original contributions reporting on the development of AI-based solutions that improve the quality of life of people who use these types of robots from one or more perspectives. Contributions demonstrating superior and more innovative technological performance are also relevant to this Special Issue.

Dr. Claudio Loconsole
Guest Editor

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Robotics is an international peer-reviewed open access monthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 1800 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

Keywords

  • biomedical sensors
  • computer vision
  • gesture detection
  • human-robot interaction (HRI)
  • image processing
  • machine learning techniques
  • neurodegeneration
  • neurological diseases
  • NUI (natural user interface)
  • object tracking
  • reinforcement learning
  • robotic exoskeleton
  • robotic prostheses
  • smart wearable/rehabilitation technologies and robotics

Published Papers (5 papers)

Order results
Result details
Select all
Export citation of selected articles as:

Research

23 pages, 7567 KiB  
Article
A Framework for Modeling, Optimization, and Musculoskeletal Simulation of an Elbow–Wrist Exosuit
by Ali KhalilianMotamed Bonab, Domenico Chiaradia, Antonio Frisoli and Daniele Leonardis
Robotics 2024, 13(4), 60; https://doi.org/10.3390/robotics13040060 - 06 Apr 2024
Viewed by 359
Abstract
The light weight and compliance of exosuits are valuable benefits not present rigid exoskeleton devices, yet these intriguing features make it challenging to properly model and simulate their interaction with the musculoskeletal system. Tendon-driven exosuits adopt an electrical motor combined with pulleys and [...] Read more.
The light weight and compliance of exosuits are valuable benefits not present rigid exoskeleton devices, yet these intriguing features make it challenging to properly model and simulate their interaction with the musculoskeletal system. Tendon-driven exosuits adopt an electrical motor combined with pulleys and cable transmission in the actuation stage. An important aspect of the design of these systems for the load transfer efficacy and comfort of the user is the anchor point positioning. In this paper, we propose a framework, whose first purpose is as a design methodology for the synthesis of an exosuit device, achieved by optimizing the anchor point location. The optimization procedure finds the best 3D position of the anchor points based on the interaction forces between the exosuit and the upper arm. The computation of the forces is based on the combination of a mathematical model of a wrist–elbow exosuit and a dynamic model of the upper arm. Its second purpose is the simulation of the kinematic and physiological effects of the interaction between the arm, the exosuit, and the complex upper limb musculoskeletal system. It offers insights into muscular and exoskeleton loading during operation. The presented experiments involve the development and validation of personalized musculoskeletal models, with kinematic, anthropometric, and electromyographic data measured in a load-lifting task. Simulation of the exosuit operation—coupled with the musculoskeletal model—showed the efficacy of the suit in assisting the wrist and elbow muscles and provided interesting highlights about the impact of the assistance on shoulder muscles. Finally, we provide a possible design of an elbow and wrist exosuit based on the optimized results. Full article
(This article belongs to the Special Issue AI for Robotic Exoskeletons and Prostheses)
Show Figures

Figure 1

13 pages, 837 KiB  
Article
Investigation of the Effectiveness of the Robotic ReStore Soft Exoskeleton in the Development of Early Mobilization, Walking, and Coordination of Stroke Patients: A Randomized Clinical Trial
by Szilvia Kóra, Adrienn Bíró, Nándor Prontvai, Mónika Androsics, István Drotár, Péter Prukner, Tamás Haidegger, Klaudia Széphelyi and József Tollár
Robotics 2024, 13(3), 44; https://doi.org/10.3390/robotics13030044 - 05 Mar 2024
Viewed by 1424
Abstract
Medical robotics nowadays can prevent, treat, or alleviate numerous severe conditions, including the dire consequences of stroke. Our objective was to determine the effect of employing a robotic soft exoskeleton in therapy on the development of the early mobilization, gait, and coordination in [...] Read more.
Medical robotics nowadays can prevent, treat, or alleviate numerous severe conditions, including the dire consequences of stroke. Our objective was to determine the effect of employing a robotic soft exoskeleton in therapy on the development of the early mobilization, gait, and coordination in stroke patients. The ReStore™ Soft Exo-Suit, a wearable exosuit developed by a leading company with exoskeleton technology, was utilized. It is a powered, lightweight device intended for use in stroke rehabilitation for people with lower limb disability. We performed a randomized clinical intervention, using a before–after trial design in a university hospital setting. A total of 48 patients with a history of stroke were included, of whom 39 were randomized and 30 completed the study. Interventions: Barthel Index and modified Rankin scale (mRS) patients were randomly assigned to a non-physical intervention control (n = 9 of 39 completed, 30 withdrew before baseline testing), or to a high-intensity agility program (15 sessions, 5 weeks, n = 30 completed). The main focus of assessment was on the Modified Rankin Scale. Additionally, we evaluated secondary factors including daily life functionality, five dimensions of health-related quality of life, the Beck depression inventory, the 6 min walk test (6MWT), the Berg Balance Scale (BBS), and static balance (center of pressure). The Robot-Assisted Gait Therapy (ROB/RAGT) program led to significant improvements across various measures, including a 37% improvement in Barthel Index scores, a 56% increase in 10 m walking speed, and a 68% improvement in 6 min walking distance, as well as notable enhancements in balance and stability. Additionally, the intervention group demonstrated significant gains in all these aspects compared to the control group. In conclusion, the use of robotic therapy can be beneficial in stroke rehabilitation. These devices support the restoration and improvement of movement in various ways and contribute to restoring balance and stability. Full article
(This article belongs to the Special Issue AI for Robotic Exoskeletons and Prostheses)
Show Figures

Figure 1

29 pages, 13682 KiB  
Article
Design and Control of the Rehab-Exos, a Joint Torque-Controlled Upper Limb Exoskeleton
by Domenico Chiaradia, Gianluca Rinaldi, Massimiliano Solazzi, Rocco Vertechy and Antonio Frisoli
Robotics 2024, 13(2), 32; https://doi.org/10.3390/robotics13020032 - 17 Feb 2024
Viewed by 1172
Abstract
This work presents the design of the Rehab-Exos, a novel upper limb exoskeleton designed for rehabilitation purposes. It is equipped with high-reduction-ratio actuators and compact elastic joints to obtain torque sensors based on strain gauges. In this study, we address the torque sensor [...] Read more.
This work presents the design of the Rehab-Exos, a novel upper limb exoskeleton designed for rehabilitation purposes. It is equipped with high-reduction-ratio actuators and compact elastic joints to obtain torque sensors based on strain gauges. In this study, we address the torque sensor performances and the design aspects that could cause unwanted non-axial moment load crosstalk. Moreover, a new full-state feedback torque controller is designed by modeling the multi-DOF, non-linear system dynamics and providing compensation for non-linear effects such as friction and gravity. To assess the proposed upper limb exoskeleton in terms of both control system performances and mechanical structure validation, the full-state feedback controller was compared with two other benchmark-state feedback controllers in both a transparency test—ten subjects, two reference speeds—and a haptic rendering evaluation. Both of the experiments were representative of the intended purpose of the device, i.e., physical interaction with patients affected by limited motion skills. In all experimental conditions, our proposed joint torque controller achieved higher performances, providing transparency to the joints and asserting the feasibility of the exoskeleton for assistive applications. Full article
(This article belongs to the Special Issue AI for Robotic Exoskeletons and Prostheses)
Show Figures

Figure 1

26 pages, 5465 KiB  
Article
NOHAS: A Novel Orthotic Hand Actuated by Servo Motors and Mobile App for Stroke Rehabilitation
by Ebenezer Raj Selvaraj Mercyshalinie, Akash Ghadge, Nneka Ifejika and Yonas Tadesse
Robotics 2023, 12(6), 169; https://doi.org/10.3390/robotics12060169 - 08 Dec 2023
Viewed by 2159
Abstract
The rehabilitation process after the onset of a stroke primarily deals with assisting in regaining mobility, communication skills, swallowing function, and activities of daily living (ADLs). This entirely depends on the specific regions of the brain that have been affected by the stroke. [...] Read more.
The rehabilitation process after the onset of a stroke primarily deals with assisting in regaining mobility, communication skills, swallowing function, and activities of daily living (ADLs). This entirely depends on the specific regions of the brain that have been affected by the stroke. Patients can learn how to utilize adaptive equipment, regain movement, and reduce muscle spasticity through certain repetitive exercises and therapeutic interventions. These exercises can be performed by wearing soft robotic gloves on the impaired extremity. For post-stroke rehabilitation, we have designed and characterized an interactive hand orthosis with tendon-driven finger actuation mechanisms actuated by servo motors, which consists of a fabric glove and force-sensitive resistors (FSRs) at the tip. The robotic device moves the user’s hand when operated by mobile phone to replicate normal gripping behavior. In this paper, the characterization of finger movements in response to step input commands from a mobile app was carried out for each finger at the proximal interphalangeal (PIP), distal interphalangeal (DIP), and metacarpophalangeal (MCP) joints. In general, servo motor-based hand orthoses are energy-efficient; however, they generate noise during actuation. Here, we quantified the noise generated by servo motor actuation for each finger as well as when a group of fingers is simultaneously activated. To test ADL ability, we evaluated the device’s effectiveness in holding different objects from the Action Research Arm Test (ARAT) kit. Our device, novel hand orthosis actuated by servo motors (NOHAS), was tested on ten healthy human subjects and showed an average of 90% success rate in grasping tasks. Our orthotic hand shows promise for aiding post-stroke subjects recover because of its simplicity of use, lightweight construction, and carefully designed components. Full article
(This article belongs to the Special Issue AI for Robotic Exoskeletons and Prostheses)
Show Figures

Figure 1

17 pages, 3772 KiB  
Article
A Semiautonomous Control Strategy Based on Computer Vision for a Hand–Wrist Prosthesis
by Gianmarco Cirelli, Christian Tamantini, Luigi Pietro Cordella and Francesca Cordella
Robotics 2023, 12(6), 152; https://doi.org/10.3390/robotics12060152 - 13 Nov 2023
Cited by 1 | Viewed by 1651
Abstract
Alleviating the burden on amputees in terms of high-level control of their prosthetic devices is an open research challenge. EMG-based intention detection presents some limitations due to movement artifacts, fatigue, and stability. The integration of exteroceptive sensing can provide a valuable solution to [...] Read more.
Alleviating the burden on amputees in terms of high-level control of their prosthetic devices is an open research challenge. EMG-based intention detection presents some limitations due to movement artifacts, fatigue, and stability. The integration of exteroceptive sensing can provide a valuable solution to overcome such limitations. In this paper, a novel semiautonomous control system (SCS) for wrist–hand prostheses using a computer vision system (CVS) is proposed and validated. The SCS integrates object detection, grasp selection, and wrist orientation estimation algorithms. By combining CVS with a simulated EMG-based intention detection module, the SCS guarantees reliable prosthesis control. Results show high accuracy in grasping and object classification (≥97%) at a fast frame analysis frequency (2.07 FPS). The SCS achieves an average angular estimation error ≤18° and stability ≤0.8° for the proposed application. Operative tests demonstrate the capabilities of the proposed approach to handle complex real-world scenarios and pave the way for future implementation on a real prosthetic device. Full article
(This article belongs to the Special Issue AI for Robotic Exoskeletons and Prostheses)
Show Figures

Figure 1

Back to TopTop