Portable IoT-enabled rehabilitation glove with flex sensors and servo drive

Abstract

A portable rehabilitation glove system consisting of: a sensor glove configured for wear on a healthy hand and containing multiple bending sensors positioned along the respective finger segments, each bending sensor designed to detect bending displacements by registering resistance fluctuations; a processing unit comprising a microcontroller electrically connected to the plurality of bending sensors, the microcontroller being configured to convert resistance values ​​into digital angle data representing the joint displacement; an actuating glove configured for wear on an impaired hand, wherein the actuating glove contains a plurality of servomotors mechanically connected to the finger joints via linkages or tendon-like cables; a wireless communication module integrated into the microcontroller for transmitting control signals and rehabilitation data; a rechargeable power supply that is operationally connected to both gloves and enables wireless operation; the microcontroller is configured to transmit processed angle data to the actuating glove, so that each servo motor drives the corresponding impaired finger to replicate the movement detected by the bending sensor on the healthy hand, thus enabling mirrored rehabilitation therapy.

Description

Technical field of the invention

[0001] The present invention relates to the fields of biomedical engineering and wearable mechatronics. Specifically, it concerns an IoT-enabled rehabilitation glove system that integrates flex sensors, servo motors, and a microcontroller platform for gesture-based physiotherapy. The invention is particularly suitable for the motor rehabilitation of patients with hand paralysis, stroke, or injury, and enables cost-effective, wearable, and remotely monitored rehabilitation. Background of the invention

[0002] The rehabilitation of impaired motor function in individuals with partial or complete hand paralysis is a complex and resource-intensive process. Conventional rehabilitation methods typically involve repeated sessions under the supervision of a physical therapist in clinical settings. These frequent visits increase patients' dependence on healthcare facilities, incur significant treatment costs, and often slow recovery due to inconsistent therapy adherence.

[0003] Existing rehabilitation technologies such as robotic exoskeletons, electromyography (EMG)-guided devices, and visually controlled gesture tracking systems have seen incremental improvements, but they also have significant drawbacks. Robotic exoskeletons are bulky, heavy, and expensive, limiting their use in home settings. While EMG-based devices are precise, they require complex calibration and specialized electrodes, making them impractical for everyday use. Visual systems require significant computing power and are limited by environmental conditions such as lighting. These limitations underscore the need for a lightweight, affordable, and portable rehabilitation system that can be used in real-world patient environments while still allowing for therapist monitoring.

[0004] The present invention addresses these shortcomings with a rehabilitation glove that uses flex sensors on the healthy hand to capture natural finger movements, which are then processed by an ESP32 microcontroller. Servo drives on the glove of the affected hand mimic these movements, ensuring symmetry and stimulating muscle memory. Furthermore, IoT integration with the Blynk platform enables physicians to remotely monitor, log, and adjust therapy plans, thus connecting home care with clinical expertise.

[0005] Restoring motor function in individuals with partial or complete hand paralysis is one of the most persistent challenges in rehabilitation technology. Due to its complex musculoskeletal and neural structure, the human hand requires fine motor skills, coordination, and repeated practice to regain lost functionality. Traditional rehabilitation has long relied on physiotherapist-led sessions in clinics or hospitals, where patients are instructed to perform repetitive hand exercises aimed at muscle strengthening, stimulation of neural plasticity, and relearning motor skills. While this model is theoretically effective, it places a significant burden on patients and healthcare systems. Outside of clinic sessions, patients often struggle to adhere to prescribed exercise routines, resulting in inconsistent progress.Furthermore, frequent hospital stays result in high costs, increasing fatigue, and a lack of treatment continuity. This gap has driven research into technological solutions that can complement or replace traditional rehabilitation practices.

[0006] Among the earliest approaches in rehabilitation technology are robotic exoskeleton gloves. These devices use motors, pneumatic drives, or mechanical links to assist patients in performing hand movements. Exoskeleton gloves have proven capable of executing repetitive, precise movements that support motor learning and the strengthening of muscle memory.

[0007] Despite their clinical potential, robotic exoskeletons have significant drawbacks that hinder widespread adoption. They are typically bulky, heavy, and expensive to manufacture, making them impractical for personal use and home therapy. Their weight often causes discomfort during prolonged wear, and their size limits portability, restricting their use to specialized hospital settings. Furthermore, their high cost makes them unaffordable for most patients, particularly in developing regions where affordability and accessibility are critical factors.

[0008] Another class of rehabilitation technologies that has garnered attention are electromyography (EMG)-based systems. These systems capture electrical muscle activity using surface or invasive electrodes and then process this data to control robotic drives or virtual rehabilitation environments. The main advantage of EMG-based systems is that they provide direct insights into the patient's neuromuscular activity, enabling precise and patient-specific rehabilitation. They are capable of detecting even minimal voluntary efforts and translating them into assistive movements, thereby promoting active participation. However, EMG-based rehabilitation devices do have limitations. The sensors require complex calibration and precise placement on the muscle groups, often necessitating the involvement of skilled technicians or therapists.Furthermore, EMG signals are susceptible to noise, interference, and fluctuations caused by sweat, electrode displacement, or changes in skin impedance. This makes consistent, long-term use in non-clinical settings difficult. For patients, especially elderly users, these systems are less practical compared to simpler solutions due to their technical complexity and the need for monitoring.

[0009] Image-based gesture tracking systems represent another branch of rehabilitation technology development. These systems use cameras and advanced image processing techniques to monitor hand movements, analyze gestures, and guide patients through prescribed exercises. The greatest strength of image-based systems lies in their non-contact operation, eliminating the need to wear sensors or actuators. This makes them less intrusive and, theoretically, more comfortable for patients.

[0010] However, there are also significant disadvantages. Image-based systems are highly dependent on environmental conditions such as lighting and background brightness, which can severely affect tracking accuracy. Furthermore, they require considerable computing resources for real-time image processing, limiting their use to environments with powerful hardware. In addition, these systems are often not portable, as they use stationary cameras or depth sensors, restricting their application to controlled indoor spaces. The fact that they cannot provide tactile or haptic feedback further reduces their effectiveness in stimulating muscle memory and regaining fine motor skills.

[0011] In parallel, some rehabilitation solutions are based on simple mechanical aids or spring-loaded devices that enable repetitive finger movements. While these mechanical aids are affordable and readily available, they lack intelligence, adaptability, and feedback mechanisms. They cannot be individually tailored to the patient's needs, nor is objective progress monitoring possible. Due to their low technical complexity, they are only suitable for supplementary exercises under the supervision of a therapist and are not self-contained rehabilitation systems capable of guiding recovery.

[0012] Recent advances in wearable technologies have enabled the development of sensor-based rehabilitation systems. Flex sensors, inertial measurement units (IMUs), and force-sensitive resistances have been integrated into gloves to capture patients' hand movements in real time. These systems provide quantitative data on range of motion, speed, and exercise accuracy, which can be valuable for both patients and therapists. However, despite improvements in data acquisition, many sensor-based gloves are limited to monitoring functions. They can record and transmit movement data, but they cannot actively stimulate or assist the injured hand during movement, which is crucial in cases of severe paralysis without voluntary movement. Therefore, such systems are better suited for progress monitoring than for active motor rehabilitation.

[0013] The integration of IoT technologies into healthcare has opened up new possibilities for remote rehabilitation. IoT platforms enable real-time data collection, cloud storage, and remote access to patient information by therapists. This connectivity can significantly reduce the need for in-person visits, allow for continuous monitoring, and improve patient adherence to therapy. Several experimental systems have been developed that combine wearable sensors with IoT-based data management. However, these systems are often insufficient to provide comprehensive rehabilitation support. They lack the necessary physical actuation mechanisms to replicate or control movements of the affected hand, which limits their therapeutic effectiveness.Furthermore, many IoT-integrated rehabilitation prototypes are still in the research phase and have not yet matured into commercially viable, user-friendly products.

[0014] A recurring problem with existing solutions is striking a balance between affordability, portability, and effectiveness. High-end robotic exoskeletons and EMG-controlled systems offer precision and control but are prohibitively expensive and complex. Vision-based systems provide touchless operation but are limited by environmental dependencies and lack active control. Cost-effective mechanical aids offer access but fail to deliver measurable or adaptive rehabilitation outcomes. Sensor-based monitoring gloves and IoT-integrated prototypes contribute to progress tracking but often lack the necessary active intervention to promote motor recovery. Therefore, a significant gap remains in the search for a rehabilitation solution that combines affordability, portability, ease of use, and effective control.

[0015] Another drawback of existing solutions is their limited adaptability to patient-specific needs. Rehabilitation is inherently personalized, as patients differ in the severity of their impairment, their rate of recovery, and their motivation. Many conventional systems are rigid and do not offer adaptable therapy protocols. For example, robotic exoskeletons typically operate with preset movement patterns rather than dynamically adapting to the patient's progress. While EMG-controlled systems can be personalized, they require professional calibration each time, limiting their usability in home settings. Vision-based and mechanical systems lack the ability to adjust therapy intensity or provide progressive challenges. This lack of personalization often leads to patient disengagement and suboptimal recovery outcomes.

[0016] Furthermore, conventional technologies often lack data-driven insights into rehabilitation. Therapists and clinicians need objective information about patient adherence, performance consistency, and long-term trends to make informed decisions. Most conventional devices do not provide such analyses, relying instead on subjective reports or limited session-based observations. The lack of continuous, reliable data hinders the development of evidence-based treatment plans and delays timely interventions when progress stalls.

[0017] Accessibility is another challenge that existing solutions do not adequately address. In rural and resource-poor regions, access to modern rehabilitation technologies is often impossible due to cost, infrastructure requirements, or technical complexity. Patients in such environments have minimal options, which slows recovery and prolongs their dependence on caregivers. High costs also exclude a large portion of the population in developing countries, where strokes and paralysis are increasing due to aging populations and lifestyle-related diseases. The global need for affordable, home-based rehabilitation solutions is therefore urgent and is not met by existing technologies.

[0018] Finally, psychological and motivational aspects play a crucial role in rehabilitation. Many patients experience a loss of trust, frustration, or dependence on caregivers, which discourages them from consistent adherence to their treatment plan. Technologies that are intimidating, cumbersome, or require constant monitoring can exacerbate these problems. Exoskeletons and EMG systems, despite their complexity, are often overwhelming for patients, while purely monitoring systems lack motivating features for continuous use. The absence of intuitive, user-friendly, and motivating solutions limits patient acceptance and long-term therapy adherence.

[0019] In summary, while significant technological advances have been made in the development of rehabilitation systems for hand paralysis, existing solutions have critical limitations that restrict their effectiveness, accessibility, and acceptance. Robotic exoskeletons are bulky and expensive, EMG-based systems are complex and dependent on monitoring, visual trackers are subject to environmental limitations and lack control, mechanical aids are simple and non-adaptive, and sensor-based IoT prototypes are largely limited to monitoring functions without active rehabilitation. These shortcomings make an integrated solution urgently needed—one that is lightweight, affordable, portable, and patient-friendly, and that can combine gesture-based control with IoT-enabled remote monitoring.Such a system would not only close the gaps in existing technologies, but also bridge the gap between hospital therapy and independent rehabilitation at home, thus accelerating recovery while reducing the strain on the healthcare infrastructure. Objectives of the invention

[0020] The main objective of the invention is to provide a wearable rehabilitation glove system that restores motor function in people with limited hand mobility through gesture-controlled operation and IoT-enabled monitoring.

[0021] Another goal is to provide a cost-effective, portable and user-friendly device that eliminates the need for bulky exoskeletons and reduces the need for frequent hospital visits.

[0022] Another goal is to enable symmetrical rehabilitation by mirroring the movements of the patient's healthy hand onto the affected hand using flex sensors and servo actuation, thereby strengthening muscle memory and accelerating recovery.

[0023] Another goal is the integration of IoT functions that enable training planning, data logging and real-time monitoring, allowing therapists to provide personalized rehabilitation protocols remotely. Summary of the invention

[0024] The invention comprises a rehabilitation glove with flex sensors, servo motors, a microcontroller (ESP32), wireless connectivity, and a power supply. The glove on the non-paralyzed hand detects the flexion angles of the fingers via flex sensors that register changes in resistance proportional to finger movement. These signals are processed by the ESP32 microcontroller and converted into angular values. Corresponding commands are transmitted to servo motors integrated into a glove on the paralyzed hand, which replicate the movement of the healthy hand.

[0025] IoT functionality is provided via the Blynk application. This enables remote exercise planning, real-time monitoring of training progress, and data storage in the cloud. The system is powered by a rechargeable lithium-ion battery, ensuring wireless, portable operation suitable for home therapy. The glove incorporates safety features such as torque-limited servos to prevent accidental overstretching and an ergonomic design for patient comfort.

[0026] This integrated system enables continuous, personalized rehabilitation with remote monitoring by a therapist and combines clinical care with patient-led therapy in everyday environments.

[0027] The present invention was developed with the primary objective of providing an intelligent, cost-effective, and wearable rehabilitation glove that restores motor function to patients with hand paralysis, stroke, or injury-related disabilities. A key objective is the development of a system that utilizes the natural hand movements of the patient's healthy hand, captured via flex sensors, and transfers these gestures to the injured hand using a servo motor. This strengthens muscle memory and promotes symmetrical rehabilitation. Another important objective of the invention is the integration of IoT functionalities via a microcontroller platform and a mobile application. This enables training planning, progress tracking, and real-time remote monitoring by physicians or nursing staff, thereby reducing the need for frequent hospital visits.The invention is also intended to offer a cost-effective alternative to bulky exoskeletons and complex electromyography-guided systems, ensuring that advanced rehabilitation technology is accessible to patients in diverse economic and geographic regions, including rural and resource-poor areas. Furthermore, the invention aims to make the glove lightweight, ergonomic, and user-friendly to ensure comfort even during extended sessions and to minimize the psychological barriers often associated with intimidating rehabilitation technologies. The device is also designed to improve adherence to rehabilitation routines by enabling interactive and supervised therapy that can be performed at home. This reduces the burden on healthcare professionals while simultaneously allowing patients greater independence on their path to recovery.Ultimately, an overarching goal of the invention is to bridge the gap between clinical physiotherapy and everyday therapy by providing a system that is safe, adaptable and scalable for future enhancements, including advanced data analysis and AI-supported therapy adjustments. BRIEF DESCRIPTION OF THE FIGURE

[0028] These and other features, aspects, and advantages of the present invention will be better understood if the following detailed description is read with reference to the accompanying drawing, in which the same symbols consistently represent the same parts. The following applies: Fig. Figure 1 shows a block diagram of a wearable IoT-enabled rehabilitation glove with flex sensors and servo drive.

[0029] Experts will also recognize that the elements in the drawing are shown for the sake of simplicity and are not necessarily to scale. For example, the flowcharts illustrate the process by highlighting the main steps to enhance understanding of the aspects of this disclosure. Furthermore, with regard to the design of the device, one or more components of the device may be represented in the drawing by conventional symbols, and the drawing may show only the specific details relevant to understanding the embodiments of this disclosure, so as not to clutter the drawing with details that are readily apparent to those skilled in the art after reading this description. Detailed description of the invention

[0030] For a better understanding of the inventive principles, reference is made below to the embodiment shown in the drawing, which is described in specific terminology. However, this does not limit the scope of the invention. Changes and further modifications of the illustrated system, as well as further applications of the inventive principles, are possible, as would normally occur to a person skilled in the art in the field of invention.

[0031] It is clear to the person skilled in the art that the preceding general description and the following detailed description are exemplary and explanatory of the invention and are not intended as a limitation of it.

[0032] References in this specification to “an aspect”, “another aspect”, or similar expressions mean that a particular feature, structure, or property described in connection with the embodiment is included in at least one embodiment of the present disclosure. Therefore, occurrences of the expressions “in one embodiment”, “in another embodiment”, and similar expressions in this specification may all refer to the same embodiment, but need not.

[0033] The terms "includes," "include," or other variations thereof are intended to cover non-exclusive inclusion, such that a process or method that includes a list of steps may not only contain those steps but may also include other steps not expressly listed or inherent in such process or method. Likewise, the statement "includes..." in the case of one or more devices, subsystems, elements, structures, or components does not, without further limitations, preclude the existence of other devices, subsystems, elements, structures, components, or additional devices, subsystems, elements, structures, or components.

[0034] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as understood by a person skilled in the art in the field of the invention. The systems, methods, and examples provided herein serve only for illustration and are not to be construed as limitations.

[0035] Embodiments of the present disclosure are described in detail below with reference to the attached drawing.

[0036] In Fig.Figure 1 shows the block diagram of a wearable IoT-enabled rehabilitation glove with flex sensors and servo drives. The system 100 comprises: a sensor glove (102) configured for wear on a healthy hand, containing multiple flex sensors positioned along the respective finger segments, each sensor capable of detecting flexion displacements by registering resistance fluctuations; a processing unit (104) comprising an ESP32 microcontroller (104a) electrically connected to the multiple flex sensors, the ESP32 converting resistance values ​​into digital angle data representing joint displacement; and an actuation glove (106) configured for wear on an impaired hand, containing multiple servo motors (106a) mechanically connected to the finger joints via linkages or tendon-like cables.a wireless communication module (108) integrated into the ESP32 for transmitting control signals and rehabilitation data; a rechargeable power supply (110) that is operationally connected to both gloves and enables wireless operation; wherein the ESP32 is configured to transmit processed angle data to the actuating glove so that each servo motor drives the corresponding impaired finger to replicate the movement detected by the flex sensor on the healthy hand, thus enabling mirrored rehabilitation therapy.

[0037] In one embodiment, the ESP32 microcontroller (104a) is configured with calibration techniques that normalize the resistance values ​​of the flex sensors by converting raw analog signals into angular degrees of freedom corresponding to the metacarpophalangeal and interphalangeal joints, thereby ensuring a highly accurate translation of finger flexion and extension.

[0038] In one embodiment, the torque of each servomotor (106a) embedded in the actuating glove is limited by firmware-based pulse width modulation thresholds, so that the mechanical output torque does not exceed a predefined safety limit. This prevents accidental overstretching, tissue strain, or injury to the affected hand during rehabilitation exercises.

[0039] In one embodiment, the wireless communication module (108) of the ESP32 is configured to connect to a cloud-based IoT platform via WLAN, so that therapy-related data such as joint angles, exercise repetitions, ranges of motion and session duration are logged in real time and made available remotely to authorized physicians via a mobile application interface.

[0040] In one embodiment, the IoT platform is also configured to enable remote planning of rehabilitation sessions, with parameters such as exercise duration, frequency, and actuation intensity being transmitted from the clinician's interface to the ESP32 microcontroller, allowing servo actuation profiles to be dynamically adapted to personalized therapy plans.

[0041] In one embodiment, the actuating glove (106) further comprises mechanical couplings consisting of lightweight, tendon-like cable mechanisms running along the finger sheaths, each cable being driven and tensioned by a micro-servo coil arrangement to replicate healthy finger movements and thus ensure natural articulation with minimal mechanical effort.

[0042] In one embodiment, the sensor glove (102) is made of flexible textile material with integrated sensor housings. The arrangement is configured to ensure precise contact with the finger joints while maintaining comfort, breathability, and durability during extended therapy sessions.

[0043] In one embodiment, the rechargeable power supply (110) consists of a 3.7 V lithium-ion battery with an integrated battery management system. The system is configured to regulate the charging process, provide overcurrent and over-discharge protection, and supply a stable voltage to both the sensor and actuator gloves to ensure uninterrupted wireless operation for more than two hours per session.

[0044] In one embodiment, the ESP32 microcontroller (104a) is also configured with firmware that enables bidirectional communication, allowing feedback signals from servo position sensors to be processed along with flex sensor inputs. This enables control that ensures the actuation angles of the impaired hand precisely match the measured gestures of the healthy hand.

[0045] In one embodiment, the operating glove (106) also features ergonomic reinforcement pads and a soft inner lining. The design is such that the servo-induced forces are distributed evenly across the finger joints, thereby reducing local pressure points and preventing patient discomfort during repeated rehabilitation exercises.

[0046] The invention is embodied in a wearable, IoT-enabled rehabilitation glove system that integrates sensors, signal processing, actuation, and wireless communication into a unified therapeutic framework. The detailed description of the system explains how the sensor glove, actuation glove, processing unit, and IoT connectivity interact via a structured technical control process to achieve mirror-image rehabilitation for patients with limited hand mobility.

[0047] The sensor glove is equipped with flex sensors strategically placed along the finger joints of the healthy hand. These sensors operate on the principle of variable resistance, where bending the finger changes the resistance of the conductive strip within the sensor. The ESP32 microcontroller, using its integrated analog-to-digital converter, samples the analog voltage levels corresponding to these resistance changes. During the initial calibration phase, baseline resistance values ​​for both the unflexed and fully flexed positions are acquired and stored in the firmware. The system then maps this input range into angular degrees of freedom associated with finger joints such as the metacarpophalangeal and interphalangeal joints. A linear or polynomial interpolation function is applied to ensure an accurate translation of the intermediate resistance values ​​into angular displacements.This illustration ensures that subtle finger movements are captured with a precision sufficient to achieve a gesture recognition accuracy of over 90 percent.

[0048] Once the angle data is calculated, the system performs a filtering stage to suppress noise and temporary fluctuations in the sensor values. A moving average filter, or digital low-pass filter, is implemented in the ESP32 firmware to smooth the signal and provide stable angle values. The processed angle data is then passed to the servo drive control logic, which forms the core of the rehabilitation technology. The drive glove, worn on the affected hand, contains micro servo motors mechanically connected to the finger segments via tendon-like cables or articulated joints. Each motor is connected to a flex sensor, ensuring a one-to-one correspondence between the healthy and affected fingers of the hand.The servo control logic receives angle displacement commands and converts them into corresponding pulse width modulation signals that move the motor to the desired position.

[0049] To ensure safety, servo drive technology is limited by torque and angle limits. Embedded thresholds are configured so that the motor stops at the safe maximum position if the target angle exceeds the natural anatomical range of the finger joint. Additionally, torque limiting routines are executed in real time based on current measurement. If the current draw of a servo motor exceeds a threshold indicating resistance or obstruction of finger movement, the system immediately cuts the motor torque to prevent injury. Improved versions also employ a closed-loop feedback mechanism where the servo's internal position sensors provide the actual angular positions. These values ​​are compared with the target angles to detect deviations.If deviations exceed a preset tolerance, the control system takes corrective measures to achieve a precise reproduction of healthy hand movements.

[0050] In addition to real-time gesture mirroring, the technology also supports an autonomous exercise mode. In this mode, the ESP32 accesses pre-configured actuation sequences stored in memory or downloaded from a doctor's prescription via the IoT platform. These sequences define rehabilitation routines that include specific finger flexion and extension patterns, repetitions, and hold times. The firmware executes the sequences with progressive resistance or increasing repetitions to enable stepwise rehabilitation tailored to the patient's recovery phase. Switching between modes is controlled via the IoT interface, allowing patients or therapists to configure therapy sessions remotely.

[0051] IoT integration is achieved via the ESP32's Wi-Fi capabilities, establishing communication with a cloud-based platform like Blynk. The rehabilitation technology includes routines that log training data such as angle trajectories, repetitions completed, training duration, and motor performance. This data is structured into packets and securely transmitted to the cloud. Physicians can remotely access this information in real time, enabling them to assess patient adherence, identify performance deviations, and adjust therapy plans accordingly. Furthermore, control signals can be sent back to the ESP32 from the physician interface, dynamically altering parameters such as exercise intensity, training duration, or resistance levels.

[0052] The energy management subsystem operates in parallel with the technology to ensure uninterrupted performance. A rechargeable lithium-ion battery supplies sensors, the processor, and servo motors with 3.7 V. The battery management circuit regulates the charging process and prevents overcurrent or deep discharge. Simultaneously, it provides the stable voltage levels required for precise sensor and motor operation. The rehabilitation technology monitors the battery level by continuously checking the voltage. When the battery is low, the system automatically terminates ongoing exercises and issues alerts via the IoT application to prevent incomplete or unsafe sessions.

[0053] A key element of the invention is the personalization of the rehabilitation technology. Using historical data stored on the IoT platform, the system dynamically adjusts the therapy intensity. For example, if progress is detected in range of motion or repetition accuracy, the technology can gradually increase the difficulty level by requiring larger angular movements or greater resistance in the servo actuation. Conversely, in the event of setbacks or fatigue, the technology reduces the intensity to prevent discouragement or injury to the patient. This adaptive approach ensures that the therapy is always tailored to the patient's evolving condition.

[0054] The detailed functionality of the technology integrates data acquisition from flex sensors, signal filtering, angle mapping, servo control with safety limitations, closed-loop feedback correction, autonomous mode execution, IoT-supported logging and remote monitoring, as well as adaptive progression of therapy protocols. By embedding all these steps in a compact and portable system, the invention bridges the gap between physiotherapy in hospitals and independent rehabilitation at home. Patients can exercise regularly and under supervision in their familiar environment, while physicians can monitor and remotely control the therapy parameters. The combination of gesture mirroring, IoT integration, and adaptive control offers an unprecedented balance of affordability, ease of use, and therapeutic efficacy that existing solutions cannot achieve.

[0055] The device consists of two main components: (i) the sensor glove, which is worn on the non-paralyzed hand, and (ii) the actuation glove, which is worn on the paralyzed hand.

[0056] The sensor glove integrates multiple flex sensors on each finger. These sensors detect angular displacements through variable resistance, which is digitized by the ESP32 microcontroller. The analog output of each sensor is processed by embedded firmware that converts resistance fluctuations into precise angular data representing the movements of the finger joints.

[0057] The actuating glove features miniaturized servomotors attached to mechanical links aligned with the patient's finger joints. Based on the sensor glove's angular data, the ESP32 calculates corresponding actuation signals for the servomotors. The servomotors replicate the movement of the healthy hand on the affected hand, thus ensuring mirror-image rehabilitation exercises. A torque limiter integrated into the firmware prevents overextension and ensures patient safety.

[0058] Wireless connectivity is provided via the ESP32's integrated Wi-Fi module. Processed data is transmitted to a cloud server via the Blynk application. Therapists can remotely access real-time movement logs, plan training routines, and adjust rehabilitation intensity to patient progress. The IoT platform also enables reminders and therapy adherence tracking, thereby reducing gaps in therapy compliance.

[0059] The entire system is powered by a rechargeable 3.7V lithium-ion battery integrated into the glove, ensuring lightweight, wireless operation. Its modular design allows for the independent replacement of flex sensors, servo motors, or the microcontroller unit, thus increasing durability and ease of maintenance.

[0060] Experimental tests confirmed a gesture recognition accuracy of 92.3% with low latency, thus validating the system's effectiveness. The ergonomic design ensures long wearing times and high wearing comfort, while user tests demonstrated easy setup and daily usability.

[0061] The invention thus offers a compact, portable, and cost-effective solution for motor rehabilitation. Its dual functionality of gesture mirroring and IoT-based training planning distinguishes it from conventional exoskeletons and EMG-controlled systems, ensuring improved accessibility and clinical benefit.

[0062] The drawing and the preceding description show examples of embodiments. Those skilled in the art will recognize that one or more of the described elements can be combined to form a single functional element. Alternatively, certain elements can be divided into several functional elements. Elements of one embodiment can be added to another embodiment. For example, the sequence of the processes described here can be changed and is not limited to the manner described here. Furthermore, the actions of a flowchart need not be implemented in the sequence shown; nor does it necessarily have to be performed by all actions. Actions that are not dependent on other actions can also be performed in parallel with the other actions. The scope of the embodiments is in no way limited by these specific examples.Numerous variations are possible, whether explicitly stated in the specification or not, such as differences in structure, dimensions, and material use. The range of embodiments is at least as broad as specified in the following claims.

[0063] Advantages, further benefits, and problem solutions have been described above with reference to specific embodiments. However, the advantages, benefits, problem solutions, and all components that can lead to an advantage, benefit, or solution occurring or becoming more apparent are not to be construed as critical, necessary, or essential features or components of individual or all claims. REFERENCES 100 A portable IoT-enabled rehabilitation glove with flex sensors and servo drive. 102 Sensor glove 104 processing units 104a ESP32 microcontroller 106 Operating glove 106a Servomotors 108 Wireless Communication Module 110 Rechargeable Power Supplies

Claims

[1] A portable rehabilitation glove system consisting of: a sensor glove configured for wear on a healthy hand and containing multiple bending sensors positioned along the respective finger segments, each bending sensor designed to detect bending displacements by registering resistance fluctuations; a processing unit comprising a microcontroller electrically connected to the plurality of bending sensors, the microcontroller being configured to convert resistance values ​​into digital angle data representing the joint displacement; an actuating glove configured for wear on an impaired hand, wherein the actuating glove contains a plurality of servomotors mechanically connected to the finger joints via linkages or tendon-like cables; a wireless communication module integrated into the microcontroller for transmitting control signals and rehabilitation data; a rechargeable power supply that is operationally connected to both gloves and enables wireless operation; the microcontroller is configured to transmit processed angle data to the actuating glove, so that each servo motor drives the corresponding impaired finger to replicate the movement detected by the bending sensor on the healthy hand, thus enabling mirrored rehabilitation therapy. [2] System according to claim 1, wherein the microcontroller is configured with calibration techniques that normalize resistance values ​​from the bending sensors by mapping raw analog signals into angular degrees of freedom corresponding to the metacarpophalangeal and interphalangeal joints, thereby ensuring a highly accurate translation of finger flexion and extension. [3] System according to claim 1, wherein the torque of each servomotor embedded in the actuating glove is limited by firmware-based pulse width modulation thresholds, so that the mechanical output torque does not exceed a predefined safety limit and thereby prevents accidental overstretching, tissue strain or injury of the affected hand during rehabilitation exercises. [4] System according to claim 1, wherein the wireless communication module of the microcontroller is configured to connect to a cloud-based IoT platform via Wi-Fi, so that therapy-related data, including joint angles, exercise repetitions, ranges of motion and session duration, are logged in real time and made available remotely to authorized physicians via a mobile application interface. [5] System according to claim 4, wherein the IoT platform is further configured to enable remote planning of rehabilitation sessions, with parameters such as exercise duration, frequency and actuation intensity being transmitted from the clinician's interface to the ESP32 microcontroller so that servo actuation profiles are dynamically adapted to personalized therapy plans. [6] System according to claim 1, wherein the actuating glove further comprises mechanical couplings consisting of lightweight, tendon-like cable mechanisms running along the finger sheaths, each cable being driven and tensioned by a micro-servo coil arrangement to replicate healthy finger movements and thus ensure natural articulation with minimal mechanical effort. [7] System according to claim 1, wherein the sensor glove is made of flexible textile material with integrated sensor housings, the arrangement being configured to ensure accurate contact with the finger joints while maintaining comfort, breathability and durability during longer therapy sessions. [8] System according to claim 1, wherein the rechargeable power supply comprises a 3.7 V lithium-ion battery integrated into a battery management system, the system being configured to regulate the charging process, provide protection against overcurrent and over-discharge, and supply a stable voltage to both the sensor and actuation gloves to ensure uninterrupted wireless operation for more than two hours per session. [9] System according to claim 1, wherein the microcontroller is further configured with firmware that enables bidirectional communication, so that feedback signals from servo position encoders are processed together with flex sensor inputs, thereby enabling control that ensures that the actuation angles of the impaired hand correspond exactly to the measured gestures of the healthy hand. [10] System according to claim 1, wherein the actuating glove further comprises ergonomic reinforcement pads and a soft inner lining, wherein the design is configured such that the servo-induced forces are distributed evenly across the finger joints, thereby reducing local pressure points and avoiding patient discomfort during repeated rehabilitation exercises.

Images