Processing and control systems based on artificial intelligence (AI) have progressively improved mobile robotic exoskeletons used in upper-limb motor rehabilitation. This systematic review presents the advances and trends of those technologies. A literature search was performed in Scopus, IEEE Xplore, Web of Science, and PubMed using the PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) methodology with three main inclusion criteria: (a) motor or neuromotor rehabilitation for upper limbs, (b) mobile robotic exoskeletons, and (c) AI. The period under investigation spanned from 2016 to 2020, resulting in 30 articles that met the criteria. The literature showed the use of artificial neural networks (40%), adaptive algorithms (20%), and other mixed AI techniques (40%). Additionally, it was found that in only 16% of the articles, developments focused on neuromotor rehabilitation. The main trend in the research is the development of wearable robotic exoskeletons (53%) and the fusion of data collected from multiple sensors that enrich the training of intelligent algorithms. There is a latent need to develop more reliable systems through clinical validation and improvement of technical characteristics, such as weight/dimensions of devices, in order to have positive impacts on the rehabilitation process and improve the interactions among patients, teams of health professionals, and technology.

https://www.mdpi.com/1424-8220/21/6/2146/pdf

Artificial Intelligence-Based Wearable Robotic Exoskeletons for Upper Limb Rehabilitation: A Review.

Neuromotor rehabilitation and recovery of upper limb functions are essential to improve the life quality of patients who have suffered injuries or have pathological sequels, where it is desirable to enhance the development of activities of daily living (ADLs). Modern approaches such as robotic-assisted rehabilitation provide decisive factors for effective motor recovery, such as objective assessment of the progress of the patient and the potential for the implementation of personalized training plans. This paper focuses on the design, development, and preliminary testing of a wearable robotic exoskeleton prototype with autonomous Artificial Intelligence-based control, processing, and safety algorithms that are fully embedded in the device. The proposed exoskeleton is a 1-DoF system that allows flexion-extension at the elbow joint, where the chosen materials render it compact. Different operation modes are supported by a hierarchical control strategy, allowing operation in autonomous mode, remote control mode, or in a leader-follower mode. Laboratory tests validate the proper operation of the integrated technologies, highlighting a low latency and reasonable accuracy. The experimental result shows that the device can be suitable for use in providing support for diagnostic and rehabilitation processes of neuromotor functions, although optimizations and rigorous clinical validation are required beforehand.

Design, Development, and Testing of an Intelligent Wearable Robotic Exoskeleton Prototype for Upper Limb Rehabilitation.

Mechatronic systems that allow motorized activation in robotic exoskeletons have evolved according to their specific applications and the characteristics of the actuation system, including parameters such as size, mechanical properties, efficiency, and power draw. Additionally, different control strategies and methods could be implemented in various electronic devices to improve the performance and usability of these devices, which is desirable in any application. This paper proposes the integration and testing of a high-torque, servo-driven joint and its electronic controller, exposing its use in a robotic exoskeleton prototype as a case study. Following a brief background review, the development and implementation of the proposal are presented, allowing the control of the servo-driven joint in terms of torque, rotational velocity, and position through a straightforward, closed-loop control architecture. Additionally, the stability and performance of the servo-driven joint were assessed with and without load. In conclusion and based on the obtained results, the servo-driven joint and its control system demonstrate consistent performance under the proposed test protocol (max values: angular velocity 97 °/s, torque 33 Nm, positioning RMSE 1.46°), enabling this approach for use in various applications related to robotic exoskeletons, including human performance enhancement, rehabilitation, or support for daily living activities.

Integration and Testing of a High-Torque Servo-Driven Joint and Its Electronic Controller with Application in a Prototype Upper Limb Exoskeleton.

Neuromotor function rehabilitation is a process that implies a considerable recovery period, which can be slow, costly, and ineffective. This paper presents an architecture proposal for the development of intelligent robotic exoskeletons to support upper limb rehabilitation, especially in clinical conditions such as hemiparesis, as well as to address the problems described above. A review of the literature is presented, exploring the intelligent systems of control and signal processing in medical robotics, biosignal acquisition and the integration of technologies into this type of exoskeleton. The niches of scientific research are highlighted which allow for the planning of this architecture, such as the design of control strategies focused on the patient’s clinical condition, the proper data acquisition and the establishment of methodologies that lead to the adoption of technology in the health area. It is emphasized that this proposal focuses on the use of new engineering methods and tools, where mechanical, electronic and computational systems are involved, providing advantages in areas such as medicine, health sciences and physiotherapy. Also, this proposal has a high social impact, since it allows the development of tools that help in the rehabilitation processes carried out in developing countries such as Colombia.

M. A. Velez-Guerrero

Papers

Data Acquisition and Control Architecture for Intelligent Robotic Exoskeletons in Rehabilitation