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

Sensors, Journal Year: 2021, Volume and Issue: 21(6), P. 2146 - 2146

Published: March 18, 2021

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

Language: Английский

---

Review on Patient-Cooperative Control Strategies for Upper-Limb Rehabilitation Exoskeletons

Frontiers in Robotics and AI, Journal Year: 2021, Volume and Issue: 8

Published: Dec. 7, 2021

Technology-supported rehabilitation therapy for neurological patients has gained increasing interest since the last decades. The literature agrees that goal of robots should be to induce motor plasticity in subjects undergoing treatment by providing with repetitive, intensive, and task-oriented treatment. As a key element, robot controllers adapt patients’ status recovery stage. Thus, design effective training modalities their hardware implementation play crucial role robot-assisted strongly influence outcome. objective this paper is provide multi-disciplinary vision patient-cooperative control strategies upper-limb exoskeletons help researchers bridge gap between human aspects, desired modalities, implementations. To aim, we propose three-level classification based on 1) “high-level” 2) “low-level” strategies, 3) “hardware-level” implementation. Then, examples show how three levels have been combined obtain given high-level behavior, which specifically designed promote relearning during Finally, emphasize need development compliant collaboration exoskeleton wearer, report findings physical human-robot interaction neurorehabilitation, insights suggestions future works.

Language: Английский

---

Converging Robotic Technologies in Targeted Neural Rehabilitation: A Review of Emerging Solutions and Challenges

Sensors, Journal Year: 2021, Volume and Issue: 21(6), P. 2084 - 2084

Published: March 16, 2021

Recent advances in the field of neural rehabilitation, facilitated through technological innovation and improved neurophysiological knowledge impaired motor control, have opened up new research directions. Such increase relevance existing interventions, as well allow novel methodologies synergies. New approaches attempt to partially overcome long-term disability caused by spinal cord injury, using either invasive bridging technologies or noninvasive human–machine interfaces. Muscular dystrophies benefit from electromyography sensors that shed light on underlying neuromotor mechanisms people with Duchenne. Novel wearable robotics devices are being tailored specific patient populations, such traumatic brain stroke, amputated individuals. In addition, developments robot-assisted rehabilitation may enhance learning generate movement repetitions decoding activity patients during therapy. This is further artificial intelligence algorithms coupled faster electronics. The practical impact integrating treatment can be substantial. They potentially empower nontechnically trained individuals—namely, family members professional carers—to alter programming robotic setups, actively get involved intervene promptly at point care. narrative review considers emerging perspective replacing restoring functions, enhancing, improving natural output, promoting recruiting dormant neuroplasticity. Upon conclusion, we discuss future directions for research, diagnosis, based discussed their major roadblocks. eventually become possible evolution convergence mutually beneficial create hybrid solutions.

Language: Английский

---

A systematic review on the usability of robotic and virtual reality devices in neuromotor rehabilitation: patients’ and healthcare professionals’ perspective

BMC Health Services Research, Journal Year: 2022, Volume and Issue: 22(1)

Published: April 20, 2022

The application of virtual reality (VR) and robotic devices in neuromotor rehabilitation has provided promising evidence terms efficacy, so far. Usability evaluations these technologies have been conducted extensively, but no overviews on this topic reported yet.A systematic review the studies patients' healthcare professionals' perspective through searching PubMed, Medline, Scopus, Web Science, CINAHL, PsychINFO (2000 to 2021) was conducted. Descriptive data regarding study design, participants, technological devices, interventions, quantitative qualitative usability were extracted meta-synthetized.Sixty-eight included. VR perceived as having good a tool promoting engagement motivation during treatment, well providing strong potential for customized sessions. By contrast, they suffered from effect learnability judged potentially requiring more mental effort. Robotics implementation received positive feedback along with high satisfaction safety throughout treatment. Robot-assisted considered useful it supported increased treatment intensity contributed improved physical independence psychosocial well-being. Technical design-related issues may limit applicability making difficult physically straining. Moreover, cognitive communication deficits remarked barriers.Overall, usable far, reflecting acceptance programs. limitations raised by participants should be further improve maximise effectiveness.PROSPERO registration ref. CRD42021224141 .

Language: Английский

---

Combining robot-assisted therapy with virtual reality or using it alone? A systematic review on health-related quality of life in neurological patients

Health and Quality of Life Outcomes, Journal Year: 2023, Volume and Issue: 21(1)

Published: Feb. 21, 2023

Abstract Background In the field of neurorehabilitation, robot-assisted therapy (RAT) and virtual reality (VR) have so far shown promising evidence on multiple motor functional outcomes. The related effectiveness patients’ health-related quality life (HRQoL) has been investigated across neurological populations but still remains unclear. present study aimed to systematically review studies investigating effects RAT alone with VR HRQoL in patients different diseases. Methods A systematic evaluating impact combined affected by diseases (i.e., stroke, sclerosis, spinal cord injury, Parkinson’s Disease) was conducted according PRISMA guidelines. Electronic searches PubMed, Web Science, Cochrane Library, CINAHL, Embase, PsychINFO (2000–2022) were performed. Risk bias evaluated through National Institute Health Quality Assessment Tool. Descriptive data regarding design, participants, intervention, rehabilitation outcomes, robotic device typology, measures, non-motor factors concurrently investigated, main results extracted meta-synthetized. Results identified 3025 studies, which 70 met inclusion criteria. An overall heterogeneous configuration found design adopted, intervention procedures technological devices implemented, outcomes both upper lower limb impairment), measures administered, evidence. Most reported significant plus HRQoL, whether they adopted generic or disease-specific measures. Significant post-intervention within-group changes mainly populations, while fewer between-group comparisons, then, mostly stroke. Longitudinal investigations also observed (up 36 months), longitudinal exclusively stroke sclerosis. Finally, concurrent evaluations beside included cognitive memory, attention, executive functions) psychological mood, satisfaction treatment, usability, fear falling, motivation, self-efficacy, coping, well-being) variables. Conclusions Despite heterogeneity among included, HRQoL. However, further targeted short- long-term investigations, are strongly recommended for specific subcomponents adoption defined assessment methodology.

Language: Английский

---

Research on Control Strategy Technology of Upper Limb Exoskeleton Robots: Review

Machines, Journal Year: 2025, Volume and Issue: 13(3), P. 207 - 207

Published: March 3, 2025

Upper limb exoskeleton robots, as highly integrated wearable devices with the human body structure, hold significant potential in rehabilitation medicine, performance enhancement, and occupational safety health. The rapid advancement of high-precision, low-noise acquisition intelligent motion intention recognition algorithms has led to a growing demand for more rational reliable control strategies. Consequently, systems strategies robots are becoming increasingly prominent. This paper innovatively takes hierarchical system entry point comprehensively compares current technologies upper analyzing their applicable scenarios limitations. research still faces challenges such insufficient real-time limited individualized adaptation capabilities. It is recognized that no single traditional algorithm can fully meet interaction requirements between exoskeletons body. integration many advanced artificial intelligence into remains restricted. Meanwhile, quality closely related perception decision-making system. Therefore, combination multi-source information fusion cooperative methods expected enhance efficient human–robot personalized rehabilitation. Transfer learning edge computing enable lightweight deployment, ultimately improving work efficiency life end-users.

Language: Английский

---

Review on Control Strategies for Lower Limb Rehabilitation Exoskeletons

IEEE Access, Journal Year: 2021, Volume and Issue: 9, P. 123040 - 123060

Published: Jan. 1, 2021

Research on lower limb exoskeleton (LLE) for rehabilitation have developed rapidly to meet the need of population with neurologic injuries. LLEs include therapeutic that aim restore walking ability patients, and assistive offer support activities in daily life. A substantial part them can serve both purposes. However, these devices are yet reach final goal performing human-machine joint movement agilely smartly. Control strategy plays an important role achieving their designed goal. At present, control strategies face three major challenges: how detect human intention, do motion given intentions, optimize parameters suit different individuals. As a contribution, this paper offers overview state-of-the-art by classifying into eight categories, each which is presented technical summary tabulated information representative papers. Moreover, current approaches addressing challenges discussed macroscopic perspective. Finally, it has been explored requirements future should maximizing performance LLEs.

Language: Английский

---

An Adaptive Sliding Mode Variable Admittance Control Method for Lower Limb Rehabilitation Exoskeleton Robot

Applied Sciences, Journal Year: 2020, Volume and Issue: 10(7), P. 2536 - 2536

Published: April 7, 2020

As passive rehabilitation training with fixed trajectory ignores the active participation of patients, in order to increase patients and improve effect training, this paper proposes an innovative adaptive sliding mode variable admittance (ASMVA) controller for Lower Limb Rehabilitation Exoskeleton Robot. The ASMVA consists outer loop inner controller. It estimates wearer’s muscle strength movement intention by judging deviation between actual standard interaction force leg exoskeleton, thereby adaptively changing parameters alter intensity. Three healthy volunteers engaged further experimental studies, including tracking experiments no admittance, adjustment. results show that proposed control scheme has high accuracy. Besides, can not only intensity according patient during positive (so as patient), but also amount adjustment negative ensure safety patient.

Language: Английский

---

Combined Use of EMG and EEG Techniques for Neuromotor Assessment in Rehabilitative Applications: A Systematic Review

Sensors, Journal Year: 2021, Volume and Issue: 21(21), P. 7014 - 7014

Published: Oct. 22, 2021

Electroencephalography (EEG) and electromyography (EMG) are widespread well-known quantitative techniques used for gathering biological signals at cortical muscular levels, respectively. Indeed, they provide relevant insights increasing knowledge in different domains, such as physical cognitive, research fields, including neuromotor rehabilitation. So far, EEG EMG have been independently exploited to guide or assess the outcome of rehabilitation, preferring one technique over other according aim investigation. More recently, combination started be considered a potential breakthrough approach improve rehabilitation effectiveness. However, since it is relatively recent field, we observed that no comprehensive reviews available nor standard procedures setups simultaneous acquisitions processing identified. Consequently, this paper presents systematic review applications specifically aimed evaluating assessing performance, focusing on cortico-muscular interactions field. A total 213 articles were identified from scientific databases, and, following rigorous scrutiny, 55 analyzed detail review. Most focused study stroke patients, target usually upper lower limbs. Regarding methodological approaches acquire process data, our results show acquisition quite common but mostly performed with support more specific approaches. Non-specific methods EEG-EMG coherence combined EEG/EMG signal analysis, rarely both using state-of-the-art gold-standard each two domains. Future directions may oriented toward multi-domain able exploit full EMG, example targeting wider range pathologies implementing structured clinical trials confirm current pilot studies.

Language: Английский

---

The Efficacity of the NeuroAssist Robotic System for Motor Rehabilitation of the Upper Limb—Promising Results from a Pilot Study

Journal of Clinical Medicine, Journal Year: 2023, Volume and Issue: 12(2), P. 425 - 425

Published: Jan. 4, 2023

The research aimed to evaluate the efficacy of NeuroAssist, a parallel robotic system comprised three modules equipped with human-robot interaction capabilities, an internal sensor for torque monitoring, and external real-time patient monitoring motor rehabilitation shoulder, elbow, wrist. study enrolled 10 consecutive patients right upper limb paresis caused by stroke, traumatic spinal cord disease, or multiple sclerosis admitted Neurology I Department Cluj-Napoca Emergency County Hospital. were evaluated clinically electrophysiologically before (T1) after intervention (T2). consisted five daily sessions 30-45 min each 30 passive repetitive movements performed robot. There significant differences (Wilcoxon signed-rank test) between baseline end-point clinical parameters, specifically Barthel Index (53.00 ± 37.72 vs. 60.50 36.39, p = 0.016) Activities Daily Living (4.70 3.43 5.50 3.80, 0.038). goniometric parameters improved: shoulder flexion (70.00 56.61 80.00 63.59, 0.026); wrist flexion/extension (34.00 28.75 42.50 33.7, 0.042)/(30.00 22.97 41.00 30.62, 0.042); ulnar deviation (23.50 19.44 33.50 24.15, 0.027); radial (17.50 18.14 27.00 24.85, 0.027). was difference in muscle activation extensor digitorum communis (1.00 0.94 1.40 1.17, 0.046). optimized dependable NeuroAssist Robotic System improved range motion functional scores, regardless cause deficit. However, further investigations are necessary establish its definite role recovery.

Language: Английский

---