WO2022269641A1

WO2022269641A1 - Intelligent lower-limb orthosis system for exercise therapy and method therefor

Info

Publication number: WO2022269641A1
Application number: PCT/IN2022/050578
Authority: WO
Inventors: Harshesh GOKANI
Original assignee: Sh Forhealth Solutions Private Limited
Priority date: 2021-06-25
Filing date: 2022-06-24
Publication date: 2022-12-29

Abstract

Disclosed is an intelligent lower-limb orthosis system (150) for exercise therapy and a method therefor. The system (150) assists the patients in a variety of passive range of motion exercises, and when required, naturally resists the patients to perform active isometric and isotonic exercises. The system (150) and the method empower the caregivers to provide objective, data-backed, and controlled treatment to the patients. The system (150) and the method enable remote health monitoring and provide personalized profiles for every patient with online follow-ups and reporting.

Description

Title

Intelligent Lower-Limb Orthosis System for Exercise Therapy and Method Therefor

Field of the invention

The present invention relates to orthopedic appliances and more particularly, to an intelligent lower-limb orthosis system and a method therefor for providing robotics assistance for exercise therapy to the patients, physiotherapists, fitness enthusiasts, caregivers and the like.

Background of the invention

Amidst all global megatrends and challenges, it is undeniable that everyone strives for optimum physical ability. A driving force behind high-quality fitness and healthcare is the adoption of relentless biomechanics and intelligent technology.

Moreover, deaths and disabilities due to strokes, among many other neurological diseases have received very little attention to date. On average, every 4 seconds someone in the United States has a stroke, and every 4 minutes someone dies due to a stroke. India alone has approximately 1.8 Mn strokes each year and up to 50% of stroke survivors face chronic disability. In addition, the musculoskeletal problems like arthritis, fractures, and lower back pain are the leading causes of disabilities in the world. According to WHO, it is estimated that 1.71 Bn people in the world suffer from musculoskeletal disabilities. These affect a patient’s well being, independence, and mobility. Recovery from these disorders is mainly dependent on the intensity and frequency of therapeutic intervention and physical rehabilitation.

Due to aging populations and sedentary lifestyles, there has now been an increase in the demand for physiotherapy. Given that the physiotherapy industry is a one- one industry, such that only a physiotherapist can only work with one patient at a time, globally, both the above factors have resulted in reduced caregiving time per patient and lack of access to trained physiotherapists. Hence, regular physiotherapy today achieves only 30 exercise repetitions per session against recommended 400+ repetitions. In situations like these, robotic systems are now seen as a method to provide increased access to physiotherapy. This has made accessibility and technology in the healthcare industry more necessary than ever.

Orthosis devices and appliances commonly referred to as “orthotics,” are known in the prior art and have been utilized for many years by orthotists (a maker and fitter of orthotics), physical therapists, and occupational therapists to assist in the rehabilitation of a patient’s joints and associated limbs or adjacent skeletal parts of the patient’s body related to a variety of conditions.

Efforts are seen in the art to provide robotic systems for exercise therapy. For example, CN102949281B discloses a lower limb joint rehabilitation training robot, which is limited to passive exercises, where feedback capability from the ankle joint is not available, and it allows unwanted rotation of the leg of a patient while performing the exercise. This application does not adjust any impedance to personalize the resistance patterns.

Another document CN110812104A discloses a virtual reality-based arm exoskeleton rehabilitation system working for mobility, flexibility, and resistance with isotonic exercises. This device is fixed and has a huge seat arrangement, where variable stiffness and compliance are achieved using a linear spring and steel wire rope.

Reference may be made to IN326869 which includes a robotic limb rehabilitation apparatus. This apparatus is more focused on walking, and not on increasing range of motion and strength gaining. It is assumed that the patient has gained some control of the leg. The machine learning algorithm described in this application is for patients gain control of the limb and followed by the treatment of at least one range of motion.

Another example of Variable-Stiffness Elastic Multifunctional Driver disclosed in CN108904221A uses magnetic rheological brakes, which are expensive and very heavy for a given torque capacity as compared to multi-disc dry brakes.

The Biodex System Dynamometer is a multi-mode computerized robotic measuring instrument designed to measure muscle strength. It measures muscle strength by applying constant resistance against muscles in repetitive motions. This instrument is very big and immovable, requires many attachments, which need to bought separately and also require high setup time.

Additionally, none of the prior documents describe real-time feedback of the patient’s important parameters and mimicking the repetitive exercises for assisting and resisting patterns throughout the range of motion of the patient’s lower limb in sleeping, sitting, and standing positions. Further, most of the prior rehabilitation robots require additional attachments, which results in high set-up time and is very expensive.

Accordingly, there is a need for an intelligent lower-limb orthosis system for exercise therapy and a method therefor to assist the patients in a variety of passive range of motion exercises and when required, naturally resist the patients to perform active isometric, isotonic and isokinetic exercises.

Objects of the invention

An object of the present invention is to provide an intelligent lower-limb orthosis for assisting the patients in a variety of passive range of motion exercises, and when required, naturally resisting the patients to perform active isometric, isotonic and isokinetic exercises. Another object of the present invention is to provide a machine learning model for recording the physiotherapist’s movements and re-generating the optimised path- constrained trajectories.

Another object of the present invention is to provide a robotic system that learns from the physiotherapist in the first session and mimics the assisting and resisting patterns throughout the range of motion of the patient’s lower limb in sleeping, sitting and standing positions.

Another object of the present invention is to serve hospitals, orthopaedic centres, rehab clinics, fitness centres and old age homes to take over their repetitive tasks and exercises for recovery and daily life.

Another object of the present invention is to empower the caregivers to provide objective, data-backed, and controlled treatment to the patients.

Another object of the present invention is to eliminate monotony from the physiotherapy and gamify the rehabilitation process.

Another object of the present invention is to enable remote health monitoring and treatment at the comfort of the home with or without the help of a physiotherapist.

Yet another object of the present invention is to enable the physiotherapy industry to change from a one-one to a one-many industry, where one physiotherapist can engage with multiple patients simultaneously.

Summary of the invention

Accordingly, the present invention provides an intelligent lower-limb orthosis system (hereinafter, “the system”) for exercise therapy. The system comprises a wheeled platform, a height adjustment mechanism, a modular manipulator joint assembly, a control circuit, a control panel, an intelligent fitness management unit, a database and a server. The height adjustment mechanism is positioned on the wheeled platform for adjusting height of the system. The modular manipulator joint assembly includes at least three manipulator joints connected to each other through an adjustable link. The adjustable link includes straps for connecting to human body and restricting any unwanted movement of legs in case of muscle stiffness of users and a length adjuster. The length adjuster includes a mechanism for adjusting the height of the adjustable link, a knob for changing the length of the adjustable link, a locking lever for locking the set length and ensuring no backward movement and a display element to display the current set length of the adjustable link.

Each manipulator joint includes a first encoder, a second encoder, a strain wave gear, at least one torque sensor, a motor, at least one fail-safe brake and a joint printed circuit board. The first encoder is positioned before the strain wave gear and the second encoder is positioned after the strain wave gear. The encoders are configured to measure accurate position, velocities and accelerations to provide a feeling of natural assistance and resistance. Specifically, encoders are open optical incremental encoders and the strain wave gears are zero backlash high precision harmonic gears which maximize output torque and minimize size and weight. The at least one torque sensor is used for detecting high torque values with very low precisions. The motor includes a rotor and a stator. Specifically, the motors are brushless direct current frameless torque motors with inbuilt hall effect sensors. The joint printed circuit board distributes signals and power to individual elements of the manipulator joints. The at least one fail-safe brake is used for locking the manipulator joints.

The control circuit controls each joint of the three manipulator joints separately and simultaneously. The control circuit includes a main processor, motor drivers for each motor in corresponding joint, brake drivers, torque sensor drivers, encoder drivers, joint connectors and a control panel driver. The main processor executes all parallel threads, controls algorithms and stores real-time data. The motor drivers allow the main processor to control and maintain the speed and direction of the motors by monitoring the exact position of the motor rotors. The brake drivers being relay based circuits allows the main processor to brake individual joints in case of any safety flags or during the time of active isometric strengthening exercises. The torque sensor drivers being amplifier circuits convert and amplify the differential output from the torque sensors. The encoder drivers being voltage divider circuits read the position data from each individual encoder. The joint connectors connect a main control circuit to individual joint printed circuit boards. The control panel driver includes respective voltage stepping-up or stepping down circuits.

The database is used for storing gathered data from online and local databases. The intelligent fitness management unit is hosted by a screen element. The screen element is connected to the system through a movable arm. The movable arm is a six degree of freedom movable arm which enables a screen to be viewed from any angle. The intelligent fitness management unit is configured on a portable device of a user/caregiver and used to configure the exercises for the user and to obtain real-time parameters and user-insights and storing the data in a server. In accordance with the present invention, the exercises are selected from a passive exercise, an active assisted exercise, an active gravity eliminated exercise, an active exercise, an active resisted - isotonic exercise, an active resisted - isometric exercise, an active resisted - isokinetic exercise and a home mode exercise.

In another aspect, the present invention provides a method of performing exercise therapy using the system of the present invention.

Brief description of the drawings

The objects and advantages of the present invention will become apparent when the disclosure is read in conjunction with the following figures, wherein Figure 1 shows a side view of an intelligent lower-limb orthosis system, in accordance with the present invention;

Figure 2a shows a schematic perspective view of a modular manipulator joint assembly of the intelligent lower-limb orthosis system, in accordance with the present invention;

Figure 2b shows an exploded view of the modular manipulator joint assembly, in accordance with the present invention;

Figure 2c shows a block diagram of the modular manipulator joint assembly, in accordance with the present invention;

Figure 3a shows a handle with a record button of the modular manipulator joint assembly, in accordance with the present invention;

Figure 3b shows a display on a manipulator joint of the modular manipulator joint assembly, in accordance with the present invention;

Figures 4a-4d show components of an adjustable link, in accordance with the present invention;

Figure 5 shows a block diagram of a control circuit of the intelligent lower-limb orthosis system, in accordance with the present invention;

Figures 6a-6e show components of a control panel of the intelligent lower-limb orthosis system, in accordance with the present invention;

Figure 7 shows a data storage architecture in a database of the intelligent lower- limb orthosis system, in accordance with the present invention; Figure 8 shows a high level data architecture, in accordance with the present invention;

Figure 9 shows a low level data flow and architecture, in accordance with the present invention;

Figure 10 shows a block diagram of movement types and corresponding parameters that need to be configured while creating an entire session, in accordance with the present invention;

Figure 11 shows a flowchart of accessing the intelligent lower-limb orthosis system by a caregiver/user, in accordance with the present invention;

Figure 12 shows a flowchart of accessing the intelligent lower-limb orthosis system by a patient, in accordance with the present invention;

Figure 13 shows a flowchart of a passive exercise mode, in accordance with the present invention;

Figure 14 shows a flowchart of a home mode of exercise, in accordance with the present invention;

Figure 15 shows a flowchart of an active assisted mode of exercise, in accordance with the present invention;

Figure 16 shows a flowchart of an active gravity eliminated mode of exercise, in accordance with the present invention;

Figure 17 shows a flowchart of an active resisted - isotonic mode of exercise, in accordance with the present invention; Figure 18 shows a flowchart of an active resisted - isometric mode of exercise, in accordance with the present invention;

Figure 19 shows a flowchart of an active resisted - isokinetic mode of exercise, in accordance with the present invention;

Figure 20 shows a flowchart of an active mode of exercise, in accordance with the present invention;

Figure 21 illustrates a flowchart of steps involved in configuring compound movements, in accordance with the present invention; and

Figure 22 is a schematic view showing a caregiver interacting with the intelligent lower-limb orthosis system and patient performing exercises, in accordance with the present invention.

It should be appreciated by those skilled in the art that any block diagrams herein represent conceptual views of illustrative systems embodying the principles of the present invention. Similarly, it will be appreciated that any flowcharts, flow diagrams, and the like represent various processes which may be substantially represented in computer readable medium and so executed by a computer or processor, whether or not such computer or processor is explicitly shown.

Detailed description of the invention

The foregoing objects of the present invention are accomplished and the problems and shortcomings associated with the prior art, techniques, and approaches are overcome by the present invention as described below in the preferred embodiment.

The embodiments herein provide an intelligent lower-limb orthosis system for exercise therapy and a method therefor. Further the embodiments may be easily implemented in data, information communication and management structures. Embodiments may also be implemented as one or more applications performed by stand alone or embedded systems.

The systems and methods described herein are explained using examples with specific details for better understanding. However, the disclosed embodiments can be worked on by a person skilled in the art without the use of these specific details.

Throughout this application, with respect to all reasonable derivatives of such terms, and unless otherwise specified (and/or unless the particular context clearly dictates otherwise), each usage of:

“a” or “an” is meant to read as “at least one.”

“the” is meant to be read as “the at least one.”

References in the specification to “one embodiment” or “an embodiment” mean that a particular feature, structure, characteristic, or function described in connection with the embodiment is included in at least one embodiment. The appearances of the phrase “in one embodiment” in various places in the specification are not necessarily all referring to the same embodiment.

Hereinafter, embodiments will be described in detail. For clarity of the description, known constructions and functions will be omitted.

Parts of the description may be presented in terms of operations performed by at least one electrical / electronic circuit, a computer system, using terms such as data, state, link, fault, packet, and the like, consistent with the manner commonly employed by those skilled in the art to convey the substance of their work to others skilled in the art. As is well understood by those skilled in the art, these quantities take the form of data stored/transferred in the form of non-transitory, computer-readable electrical, magnetic, or optical signals capable of being stored, transferred, combined, and otherwise manipulated through mechanical and electrical components of the computer system; and the term computer system includes general purpose as well as special purpose data processing machines, switches, and the like, that are standalone, adjunct or embedded. For instance, some embodiments may be implemented by a processing system that executes program instructions so as to cause the processing system to perform operations involved in one or more of the methods described herein. The program instructions may be computer-readable code, such as compiled or non-compiled program logic and/or machine code, stored in a data storage that takes the form of a non-transitory computer-readable medium, such as a magnetic, optical, and/or flash data storage medium. Moreover, such processing system and/or data storage may be implemented using a single computer system or may be distributed across multiple computer systems (e.g., servers) that are communicatively linked through a network to allow the computer systems to operate in a coordinated manner.

The present invention provides an intelligent lower-limb orthosis system for exercise therapy and a method therefor. The system of the present invention is an intelligent lower-limb orthosis system that assists the patients in a variety of passive range of motion exercises, and when required, naturally resists the patients to perform active isometric and isotonic exercises. The system of the present invention is portable and can be carried from one environment setting (e.g. clinic) to another (e.g. home) by disassembling the system into two parts. The arrangement of the disassembly is such that the entire system can be converted into two travel/trolley suitcases. This enables caregivers/users to take/use this system at home without the need of the caregiver being present all the time.

The present invention is now illustrated with reference to the accompanying drawings, throughout which reference numbers indicate the corresponding parts in the various figures. These reference numbers are shown in the bracket in the following description. Referring to figures 1 to 10, an intelligent lower-limb orthosis system (150) (hereinafter ‘the system (150)’) for exercise therapy in accordance with the present invention is shown. As shown in figure 1, the system (150) comprises a wheeled platform (10), a height adjustment mechanism (20), a modular manipulator joint assembly (60) (hereinafter, “the joint assembly (60)”), a control circuit (70), a control panel (90), an intelligent fitness management unit (100) (hereinafter, “IFMU (100)”), a database (110) and a server (not shown).

The wheeled platform (10) allows the system (150) to be transported from one place to another. The wheeled platform (10) includes gripping pads (not shown), a plurality of wheels (not numbered) and a transition mechanism (not shown). The gripping pads are used when the system (150) is stationery and is in use. The gripping pads ensure that the system (150) doesn’t topple or move when the user is exercising through the system (150). The gripping pads also dampen vibrations to ensure smoothness in the system (150). The plurality of wheels enables the system (150) to be moved from one place to another. The plurality of wheels includes a common lock (not shown) which locks all the wheels when needed to park the system (150). The transition mechanism includes a cam and lever (not shown) that allows the transition of the entire system (150) from being stationery and stable to portable.

The height adjustment mechanism (20) is positioned on the wheeled platform (10). The height adjustment mechanism (20) includes slots (not shown) that allows a caregiver/user to adjust the height of the system (150) according a bed/chair height for comfortable use.

The joint assembly (60) is operably connected to the control circuit (70) and the control panel (90). The joint assembly (60) includes at least three manipulator joints. Specifically, a first manipulator joint (Jl) is provided for hip joint, a second manipulator joint (J2) is provided for knee joint and a third manipulator joint (J3) is provided for ankle joint as shown in figure 2a. However, it is understood here that the joints (Jl, J2, J3) can also be used for the upper limb exercises by changing an attachment to the third manipulator joint (J3) with a steering wheel, dumbbell rod and like in other alternative embodiments of the present invention. As shown in figures 2b-2c, each manipulator joint (Jl, J2, J3) includes a first encoder (22), a second encoder (24), a strain wave gear (26), a motor (28), at least one brake (30), at least on torque sensor (32), a record button (34), a handle (36), a display (38) and a joint printed circuit board (40) (hereinafter, “ joint PCB

(40)”)·

The first encoder (22) is positioned before the strain wave gear (26) and the second encoder (24) is positioned after the strain wave gear (26). In an embodiment, the encoders (22, 24) are open (frameless) optical incremental encoders. The encoders (22, 24) are configured to measure accurate position, velocities and accelerations to provide a feeling of natural assistance and resistance. The velocities and accelerations can be calculated using the derivative of the output with respects to time. The encoders (22, 24) also compensate for the compliance errors of the system (150). Any offset due the compliance is measured by the second encoder (24) positioned after the strain wave gear (26) and is eliminated with the help of a control algorithm. This helps in accurate positioning of the joint output. Further, based on the differences in position readings between the two encoders (22, 24), the torque can also be measured. This eliminates the need of a torque sensor in future and makes the joint much more compact.

The strain wave gears (26) are zero backlash high precision harmonic gears which maximize output torque and minimize size and weight. Thus, the strain wave gears (26) provide excellent (lowest) size: reduction ratio which cannot be equaled by conventional gear trains. Each motor (28) includes a rotor (28a) and a stator (28b). The motors (28) are brushless frameless motors. Specifically, brushless direct current (BLDC) frameless torque motors are selected in such a way to achieve most compact form factor or highest torque per volume. The BLDC motors have inbuilt hall effect sensors that makes them closed loop in nature. The hall effect sensors allow a motor driver to monitor the exact position of the rotors (28a) and maintain the desired speed.

The at least one brake (30) is a fail-safe brake. The fail-safe brakes (30) are brakes used in dry environments and in default braked condition. It disengages the brake (30) only when power is applied. Hence, in case of power failure or any kind of shut down to the system (150), the brakes (30) automatically engage and make sure that the entire system (150) doesn’t fall down.

The at least one torque sensor (32) is a static reaction torque sensor which is a thin strain gauge based disc that gives precise differential voltage as output. The torque sensors (32) also detect high torque values with very low precisions. The record button (34) is accessed by the caregiver while teaching compound exercises to the system (150). The handle (36) helps the caregiver to hold the system (150) for maneuvering thereof in a user friendly way. The display (38) is a small screen which showcases the current angle, velocity, acceleration or torque of the manipulator joint. The display (38) also has simple lighting elements to show the current status of the joint. For example, the display (38) becomes yellow when the brake is engaged or becomes red when there is a fault identified. This enables the manipulator joints (J 1 , J2, J3) to be used as a live electronic goniometer. The joint PCB (40) is a circuit board which connects the manipulator joint (J 1 , J2, J3) to a main PCB in the control circuit (70). The joint PCB (40) then distributes the corresponding signals and power to the individual elements of the manipulator joint (J 1 , J2, J3). In accordance with the present invention, the combination of the encoders (22, 24), the strain wave gears (26), the motors (28) and the torque sensors (32) provides variable stiffness and variable impedance learning control to the system (150).

The manipulator joints (J 1 , J2, J3) are connected to each other through an adjustable link (54). Each adjustable link (54) includes straps (42) and a length adjuster (not numbered). The straps (42) are connected to the adjustable link through a strapping link (44) and are used to connect to the human body. The straps (42) are designed and placed on the adjustable links (54) in such a way that they restrict any unwanted movement of the legs in case of muscle stiffness of the users. For example, during hip flexion, the straps (54) won't allow any kind of hip internal/extemal rotation, thus maintaining the right form of the exercise throughout the range of motion. The adjustable link (54) is locked to the strapping link (44) using a quick release lock (46). The length adjuster includes a mechanism (not numbered), a knob (48), a locking lever (50) and a display element (52). The mechanism, for example lead screw, rack pinion, is used to adjust the height of the adjustable link (54). The knob (48) allows the user/caregiver to interact with the mechanism for changing the length of the adjustable link (54). The locking lever (50) locks the set length and ensures no backward movement. The display element (52) is used to display the current set length of the adjustable link (54). The adjustable links (54) are designed in such a way that the neighboring links can fold into the negative space provided through this link that provides a handshake design as shown in figure 4d. This enables the folding of the system (150) to store in tight places. Each joint of the three manipulator joints (J 1 , J2, J3) is separately and simultaneously controlled by the control circuit (70) to mimic all motions of the leg, in a single plane at a time.

The control circuit (70) controls all the other elements of the system (150). The control circuit (70) sends commands and receives data from each of the joint PCBs (40) and the control panel (90). As shown in figure 5, the control circuit includes a main processor (62), motor drivers (MD1, MD2, MD3), brake drivers (BD1, BD2, BD3), torque sensor drivers (TD1, TD2, TD3), encoder drivers (Ell, E12, E21, E22, E31, E32), joint connectors (J1C, J2C, J3C), a control panel driver (64), a Bluetooth module (66), a Wi-Fi module (68) and a memory storage (not shown).

The main processor (62) executes all the parallel threads, controls algorithms and stores real-time data. The main processor (62) has 4 main external connections, namely joint 1 PCB, joint 2 PCB, joint 3 PCB and a control panel. The control circuit (70) includes one motor driver (MD1, MD2, MD3) for each frameless motor (28) in corresponding joint (Jl, J2, J3). Specifically, the motors drivers (MD1, MD2, MD3) are MOSFET based circuits that drives the frameless motors (28). These drivers (MD1, MD2, MD3) allow the main processor (62) to control and maintain the speed and direction of the motors (28) by monitoring the exact position of the motor rotors (28a) through the inbuilt hall effect sensors.

The brake drivers (BD1, BD2, BD3) are relay based circuits which allow the main processor (62) to brake individual joints (Jl, J2, J3) in case of any safety flags or during the time of active isometric strengthening exercises. The torque sensor drivers (TD1, TD2, TD3) are amplifier circuits which convert (to line voltage) and amplify the differential output from the torque sensors (32). Each torque sensor driver (TD1, TD2, TD3) includes an instrumentation amplifier, a programmable gain amplifier and an analog to digital convertor (ADC). The ADC is then connected to the main processor (62) which enables it to read real-time torque value in the individual joints (Jl, J2, J3).

The encoder drivers (Ell, E12, E21, E22, E31, E32) are voltage divider circuits to read the position data from each individual encoder (22, 24). This position data is further processed by the microprocessor to calculate and store real time velocities and accelerations. The joint connectors (J1C, J2C, J3C) connect the main control circuit to individual joint PCBs (40). Each joint connector (J1C, J2C, J3C) includes a power connector (not shown) and a control connector (not shown). The control panel driver (64) drives each of the components of the control panel (90). The control panel driver (64) contains respective voltage stepping-up or stepping down circuits. The Bluetooth module (66) is used for connection with and sending/receiving data from the IFMU (100). The Wi-Fi module (68) is used for connection with an internet (WWW) and storing all real-time data in a cloud based environment. The memory storage is a local storage of the system (150) for all data gathered. As shown in figure 6a, the control panel (90) includes an emergency stop button (72), a free drive button (74), a pause button (76), an ON/OFF button (78) and a home button (80). The emergency stop button (72) (E-Stop) is pressed in case of emergency to cut off all power supply and lock all the individual joints (J 1 , J2, J3). The free drive button (74) is used to set the system (150) in free motion. The pause button (76) is used to pause the system (150). The ON/OFF button (78) is placed under the control panel (90) as shown in figure 6b and is used to switch ON/OFF the system (150). The home button (80) is used to safely return the system (150) in a home position thereof. The system (150) is maneuvered around using a handlebar (82) as shown in figure 6c. The system (150) is provided with a height adjustment remote (84) as shown in figure 6d. The height adjustment remote (84) is removable with a retractable wire and used to control height adjustment that enables the caregiver to view the user and the bed while adjusting the height of the system (150). The control panel (90) also includes a screen element (not shown) which assists users for basic tasks like connecting the device to the IFMU (100) through the Bluetooth module (66) or pop-up notifications for the user.

The IFMU (100) is configured on a portable device of a user/caregiver. In an embodiment, the portable device is selected from anyone of a mobile device, a smartphone, a tablet, a personal computer, a laptop, and the like. In another embodiment, the IFMU (100) is configured with a web or mobile application. From the caregiver’s perspective, the IFMU (100) is used to configure the exercises for the user and also obtain real-time parameters and user- insights. For the user’s perspective, the IFMU (100) not only helps the user understand their progress through real-time user insights but also has games that can be played in conjunction with the system (150) to improve engagement and adherence to the exercises. The IFMU (100) provides real-time feedback to the patients on a display of the portable device and gamifying the treatment journey. Additionally, the IFMU (100) manages the entire treatment process, controls the individual exercises, collects real-time relevant data, and stores the data in the server. The IFMU (100) is hosted by a screen element (not numbered). The screen element (100) enables the caregiver or the user to control the system (150). The screen element (100) also displays the real-time user insights. The screen element is connected to the system (150) through a movable arm (92). The movable arm (92) is a six degree of freedom (or as adequate) movable arm which enables the screen to be viewed from any angle that the caregiver wishes to view. In an embodiment, the IFMU (100) positioned in such a way to have at least 1 m reach/distance from the system (150) to ensure complete view for both the caregiver and the user as and when required. Hence, the movable arm (92) also can be placed in such a way that the user can view the screen element (100) while performing the exercises as shown in figure 6e. The user can either play games or view their own progress while viewing the screen.

In accordance with the present invention, the live user insights that the IFMU (100) provides to the caregiver/user for each joint (J 1 , J2, J3) separately by comparing minimum, maximum, and mean of normal public data includes, but are not limiting to, Real-time range of motion, Real-time velocity / speed / rate of movement, Real-time accelerations, Real-time toque/ forces, Real-time smoothness (variance from desired trajectory), Day on day minimum, maximum, mean user range of motion, Day on day minimum, maximum, mean velocities, Day on day minimum, maximum, mean accelerations, Day on day minimum, maximum, mean torques/forces, Day on day minimum, maximum, mean smoothness (variance from desired trajectory), Day on day session, exercise, parameter history, Month on month minimum, maximum, mean user range of motion, Month on month minimum, maximum, mean velocities, Month on month minimum, maximum, mean accelerations, Month on month minimum, maximum, mean torques/forces, Month on month minimum, maximum, mean smoothness (variance from desired trajectory), Month on month session, exercise, parameter history, Year on year minimum, maximum, mean user range of motion, Year on year minimum, maximum, mean velocities, Year on year minimum, maximum, mean accelerations, Year on year minimum, maximum, mean torques/forces, Year on year minimum, maximum, mean smoothness (variance from desired trajectory) and Year on year session, exercise, parameter history.

Figure 7 shows a data storage architecture in the database (110) in accordance with the present invention. The data storage architecture consists of a tree hierarchy, starting with caregivers. Each caregiver has many users. Each user has many sessions. Each session has many movement types and exercises and the corresponding exercise parameters. The local databases keep only some required branches of this tree hierarchy. Whenever connected to the internet (cloud), it updates the corresponding branch to the entire tree. Depending on the required application, when data is fetched between the online and local databases, an entire branch at any level can be accessed.

Figure 8 shows a high level data architecture in accordance with the present invention. The high level data architecture describes how the operation is performed in case many fitness management units and many devices/systems are operating in the same environment. Each IFMU (100) is used to control multiple devices at a time. The control and data flow of the device through the IFMU (100) happens through a local wireless communication protocol (and not internet or cloud) to ensure no disruption in the connection and maximum safety. Moreover, each device is also connected to the internet (Cloud) through the Wi-Fi module (68) present in the control circuit (70). This enables the system (150) to send historical data to a cloud database which can further be accessed through the website.

Figure 9 shows a low level data flow and architecture in accordance with the present invention. The low-level architecture describes how each device’s/system’s control circuit (70) handles the data flow and makes decisions. This architecture consists of a local database management system (hereinafter “DBMS”), a parallel threads/processes and a local database. The DBMS contains all the real-time cleaned and transformed data of the sensors which can be accessed by multiple other threads/processes. The parallel threads/processes work in the main processor to ensure seamless and required control of the device. In the context of the present invention, the parallel threads/processes include a data acquisition thread/process, a safety thread/process, a control thread/process and a data management thread/process. The data acquisition thread/process continuously and in parallel keeps collecting data from the control panel and sensors (torque sensors, encoders and like) available in the system (150). The data acquisition thread/process processes the data, filters and sends the data to the safety thread. The safety thread continuously monitors all incoming data from the data acquisition thread, and based on the limit values set by the control thread, the safety thread ensures that none of the joints are working outside of the limit boundaries. In case of any of the joints working outside of the limit bounds, the safety thread kills the ongoing activity by stopping the motors and applying the brakes. The control thread is the brain of the entire control system. The control thread contains all the control algorithms. The control thread takes sensor data from the database and decides the next step of individual joints. The control thread also interacts with the fitness management unit to understand the required movement and exercise types, configuration parameters, and other interaction elements like the display element in the individual joints. The data management thread when connected to internet (cloud) through the Wi Fi module, continuously takes the data from the local database and sends the data to the online database so that the data can be fetched later through the website. The local database stores all the incoming data from the data acquisition thread and is used by all other threads for their respective applications.

In accordance with the present invention, the system (150) allows the caregiver or the user/patient to switch between at least two modes namely a passive mode and an active mode. In the passive mode, the system (150) assists the movement of the patient leg and thus helps in gaining control and different types of stretches. In the active mode, the system (150) resists the movement of the patient leg while the user tries to push it. There are three more active stages namely active, active gravity eliminated and active assisted. The active mode is further divided into three stages: an isometric stage where the joints are completely locked with the help of the brake (30) to enable isometric strengthening, an isotonic stage where the system (150) enables isotonic strengthening with the help of active impedance control, and an isokinetic stage which uses specialized motion control technique to produce a constant speed no matter how much effort the user puts to the system (150). This is a proven method to exercise and strengthen muscles during injuries. In an embodiment, the system (150) is assembled as per the user’s requirements. For, example, if only passive therapy is required in the hip and ankle joint, then the manipulator joints are assembled with only the encoders (22, 24), the strain wave gears (26), and the motors (28) whereas the knee joint would have the complete configuration.

In another aspect, the present invention provides a method of performing exercise therapy. The method is described herein below in conjunction with the system (150).

The first step of the method involves accessing the system (150) by a user using login credentials. If the user is accessing the system (150) for the first time then user has to register with the system (150). In the context of the present invention the user includes a caregiver and a patient. Figure 11 illustrates a flowchart of accessing the system (150) by the caregiver. The caregiver first needs to login and view his/her patients. The caregiver then sets the movement types, exercises types, and parameters for the patient. As illustrated in figure 11, multiple movements and exercises can be recorded at once to create a session. Once the session is created, the caregiver previews the entire session movements and exercises and then plays the session for starting the exercise therapy on the patient.

Figure 12 illustrates a flowchart of accessing the system (150) by the patient. The patient first needs to login into the IFMU (100). The patient then views and selects the required session and plays the session on the device after previewing, if required. Once the session is started, the user can choose to play a game connected to the exercise session or just view the real time user insights. After the session is complete, the user can choose to notify the caregiver.

The movement types and corresponding parameters that need to be configured for creating an entire session is shown in figure 10. In accordance with the present invention, the exemplary types of movement to be chosen includes, but are not limiting to, hip flexion, hip extension, knee flexion / knee extension, ankle dorsi flexion, ankle plantar flexion, hip abduction and compound movement. In the context of the present invention, compound movement is when multiple joints (or above movements) are happening simultaneously. In this movement type, the caregiver needs to teach the system (150) through a process and once the process is taught the caregiver can then configure the system (150) with the required parameters. However, it is understood here that the system (150) can be customized for upper limb movement types by changing the straps (42) connected to the adjustable links (54) or changing the adjustable links (54) connected to each joint (J 1, J2, J3).

In the context of the present invention, the parameters are the configuration settings that need to be input by the caregiver or the user to ensure exercises are performed in the most optimum way. Depending on the exercise type, only certain parameters need to be set. The parameters to be chosen for each exercise type includes, but are not limiting to, angle i.e. range of motion to be achieved for each joint, assistance i.e. amount of assistance to be given in each joint, resistance i.e. amount of resistance to be given in each joint, rate of movement (speed) i.e. how fast should each movement be and repetitions i.e. number of repetitions for each exercise. In case of active resisted isometric, even hold time can be a factor.

In accordance with the present invention, the system (150) allows the caregiver/patients to choose exercise types from anyone of a passive exercise, active assisted exercise, active gravity eliminated exercise, active exercise, active resisted - isotonic exercise, active resisted - isometric exercise, active resisted - isokinetic exercise and home mode. These exercise modes are controlled by the control thread. The control thread executes the chosen exercises with the set configuration parameters. The selection of various modes of exercises and execution thereof for only one joint is explained below for the sake of brevity of the invention. The selection of various modes of exercises and execution thereof is same for all the joints. In case multiple joints are moving simultaneously, these processes run in parallel for all the three joints (Jl, J2, J3).

Passive Exercise Mode:

After choosing the movement type, and corresponding exercise type as passive, the caregiver sets the parameters like angle, repetitions, assistance and rate of movement. The IFMU (100) sends the corresponding selected commands to the main processor (62) in the control circuit (70) through the Bluetooth module (66) which further carries out the corresponding passive exercise control algorithm as shown in the flowchart in figure 13. In this mode, the position and torque values are periodically (10 samples per second) read through the encoders (22, 24) and torque sensors (32) in all the joints (Jl, J2, J3) using the torque sensor drivers (TD1, TD2, TD3) and the encoder drivers (Ell, E12, E21, E22, E31, E32) through the data acquisition thread. The data acquisition thread then filters and converts the encoder and torque sensor values to meaningful position, velocity, acceleration and torque values. These values are then stored in the local database which are then accessed by the safety thread and the control thread. The safety thread in the microprocessor checks if the position, velocity, acceleration and torque values are within the limit. If not, the safety thread immediately sends a command to the motor drivers (MD1, MD2, MD3) to stop the motor (28) and alerts the caregiver through the IFMU (100). If the parameters are within the safety limit, the control thread checks if the position is close to the desired position. If the position is not close to the desired position, the control thread further checks if the motor (28) is running at the desired speed (rate of movement). If yes, the control thread continues without any changes. If no, the control thread accelerates the motor (28) based on a PID control algorithm. If position is close to the desired position, the control thread sends a command to the motor drivers (MD1, MD2, MD3) to decelerate the motor (28) based on a PID control algorithm. The control thread further check if the position has reached the desired limit, in which case the control thread sends a command to stop the motor (28). This algorithm repeats from step one until the motor (28) has reached the desired position or if the parameters are outside the limits. In this mode, the user has no or very little control over his/her legs. The user generally suffers from extreme muscle weakness, stiffness or paralysis. This system is used to pick up the legs repetitively to re-wire the connection between the brain and the body and increase the flexibility, compliance of the muscles. In this mode, only assistance is given to the patient but no resistance is given and no effort of any kind is expected from the patient.

Home mode of exercise:

The system (150) here helps the user to come back to neutral position of all joints (J 1 , J2, J3). After choosing the movement type, and corresponding exercise type as Home, the caregiver sets the parameters: repetitions, assistance, and rate of movement. The IFMU (100) sends the corresponding selected commands to the main processor (62) in the control circuit (70) through the Bluetooth module (66) which further carries out the corresponding go to home exercise control algorithm as shown in the flowchart in figure 14. The home mode is similar to the passive mode with only difference of the desired position (angle) parameter which is set to zero by default in the home mode.

Active assisted mode of exercise:

After choosing the movement type, and corresponding exercise type as active assisted, the caregiver sets the parameters like angle, repetitions, assistance and rate of movement. The IFMU (100) sends the corresponding selected commands to the main processor (62) in the control circuit (70) through the Bluetooth module (66) which further carries out the corresponding active assisted exercise control algorithm as shown in the flowchart in figure 15. Here the position and torque values are periodically (10 samples per second) read through the encoders (22, 24) and torque sensors (32) in all the joints (Jl, J2, J3) using the torque sensor drivers (TD1, TD2, TD3) and the encoder drivers (Ell, E12, E21, E22, E31, E32) through the data acquisition thread. The data acquisition thread then filters and converts the encoder and torque sensor values to meaningful position, velocity, acceleration and torque values. The safety thread in the microprocessor checks if the position, velocity, acceleration and torque values are within the limit. If not, the safety thread immediately sends a command to the motor drivers (MD1, MD2, MD3) to stop the motor (28) and alerts the caregiver through the IFMU (100). If the parameters are within the safety limit, the control thread checks if the torque on individual joints (Jl, J2, J3) has reached the required assistance level and direction. If no, it goes to step one. If yes, the control thread further checks if the position is close to the desired position. If yes, the control thread decelerates the motor (28) to avoid any jittery stops towards the end of the repetition. In case the motor (28) further reached the desired limit, the control thread stops the motor (28), otherwise it goes to step one. If no, based on the current speed, the control thread accelerates or decelerates the motor (28) based on the desired speed. If the parameters are within the safety limit, the control thread checks the position. In this mode, the user gains some control over his/her legs and achieves very little movement. The system (150) here senses the effort put by the patient and assists them to move the entire range of motion of the exercise. In this mode, only assistance is given to the patient but no resistance is given and some effort is expected from the patient.

Active gravity eliminated mode of exercise:

After choosing the movement type, and corresponding exercise type as active gravity eliminated, the caregiver sets the parameters like angle, repetitions and rate of movement. The IFMU (100) sends the corresponding selected commands to the main processor (62) in the control circuit (70) through the Bluetooth module (66) which further carries out the corresponding active gravity eliminated exercise control algorithm as shown in the flowchart in figure 16. In this mode, the user gains a full range control but can't overcome forces due to gravity i.e. can’t move legs vertically up and down but can move them horizontally. The system (150) configures itself in the free drive mode that allows the users to move their legs free of gravitational forces. In this mode, minimal assistance is given to the patient but no resistance is given and almost complete effort is expected from the patient. Here the position and torque values are periodically (10 samples per second) read through the encoders (22, 24) and the torque sensors (32) in all the joints (J 1 , J2, J3) using the torque sensor drivers (TD1, TD2, TD3) and the encoder drivers (Ell, E12, E21, E22, E31, E32) through the data acquisition thread. The data acquisition thread then filters and converts the encoder and torque sensor values to meaningful position, velocity, acceleration and torque values. The safety thread in the microprocessor checks if the position, velocity, acceleration and torque values are within the limit. If not, the safety thread immediately sends a command to the motor drivers (MD1, MD2, MD3) to stop the motor (28) and alerts the caregiver through the IFMU (100). If the parameters are within the safety limit, the control thread checks if the net torque on each joint (J 1 , J2, J3) is greater than zero. If no, the control thread first decelerates the motor (28) to avoid any jittery stops towards the end of the repetition and further checks if the position is at desired position. If yes, the control thread stops the motor (28). If no, it goes to step 1. If yes, the control thread checks if the position is at desired position. If no, the control thread accelerates the motor (28) in the desired direction. If yes, the control thread first decelerates the motor (28) to avoid any jittery stops towards the end of the repetition and further checks if the position is at desired position. If yes, the control thread stops the motor (28). If no, it goes to step 1.

Active resisted (Isotonic) mode of exercise:

After choosing the movement type, and corresponding exercise type as active resisted - isotonic, the caregiver sets the parameters like angle, repetitions, resistance and rate of movement. The IFMU (100) sends the corresponding selected commands to the main processor (62) in the control circuit (70) through the Bluetooth module (66) which further carries out the corresponding active resisted - isotonic exercise control algorithm as shown in the flowchart in figure 17. In this mode, the user gains full control and starts strengthening their muscles with help of resistive exercises. The system (150) here restricts the movement of the leg in order to strengthen the muscles. In this mode, no assistance is given but resistance is given based on recovery and complete effort is expected from the patient. Here the position and torque values are periodically (10 samples per second) read through the encoders (22, 24) and the torque sensors (32) in all the joints (J 1 , J2, J3) using the torque sensor drivers (TD1, TD2, TD3) and the encoder drivers (Ell, E12, E21, E22, E31, E32) through the data acquisition thread. The data acquisition thread then filters and converts the encoder and torque sensor values to meaningful position, velocity, acceleration and torque values. The safety thread in the microprocessor checks if the position, velocity, acceleration and torque values are within the limit. If not, the safety thread immediately sends a command to the motor drivers (MD1, MD2, MD3) to stop the motor (28) and alerts the caregiver through the IFMU (100). If the parameters are within the safety limit, the control thread checks if the net torque on each joint (J 1 , J2, J3) is greater than ‘Desired Isotonic Torque’. If no, the control thread first decelerates the motor (28) to avoid any jittery stops towards the end of the repetition and further checks if the position is at desired position. If yes, the control thread stops the motor (28). If no, it goes to step 1. If yes, the control thread checks if the position is at desired position. If no, the control thread accelerates the motor (28) in the desired direction. If yes, the control thread first decelerates the motor (28) to avoid any jittery stops towards the end of the repetition and further checks if the position is at desired position. If yes, the control thread stops the motor (28). If no, it goes to step 1.

Active resisted (Isometric) mode of exercise:

After choosing the movement type, and corresponding exercise type as active resisted - isometric, the caregiver sets the parameters like angle, repetitions, resistance and rate of movement. The IFMU (100) sends the corresponding selected commands to the main processor (62) in the control circuit (70) through the Bluetooth module (66) which further carries out the corresponding active resisted - isometric exercise control algorithm as shown in the flowchart in figure 18. In this mode, the user gains full control and starts strengthening their muscles with help of resistive exercises. However, the system (150) doesn’t allow any movement of the leg in order to strengthen the muscles. In this mode, no assistance is given but enough resistance is given to not allow any movement and complete effort is expected from the patient. Here the position and torque values are periodically (10 samples per second) read through the encoders (22, 24) and the torque sensors (32) in all the joints (J 1 , J2, J3) using the torque sensor drivers (TD1, TD2, TD3) and the encoder drivers (Ell, E12, E21, E22, E31, E32) through the data acquisition thread. The data acquisition thread then filters and converts the encoder and torque sensor values to meaningful position, velocity, acceleration and torque values. The safety thread in the microprocessor checks if the position, velocity, acceleration and torque values are within the limit. If not, the safety thread immediately sends a command to the motor drivers (MD1, MD2, MD3) to stop the motor (28) and alerts the caregiver through the IFMU (100). If the parameters are within the safety limit, the control thread checks if the position is close to the desired position. If yes, the control thread first decelerates the motor (28) to avoid any jittery stops towards the end of the repetition and further checks if the position is at desired position. If no, it goes to step 1. If yes, the control thread stops the motors (28), engages the brake (30) and starts measuring the amount of time since brake is engaged. The control thread further checks if the time measures if greater than the desired amount of holding time. If yes, it returns to home. If no, it goes to step 1. If no, it accelerates the motor (28) based on the speed compared with the desired speed of the system.

Active resisted (Isokinetic) mode of exercise:

After choosing the movement type, and corresponding exercise type as active resisted - isokinetic, the caregiver sets the parameters like angle, repetitions, resistance, rate of movement. The IFMU (100) sends the corresponding selected commands to the main processor (62) in the control circuit (70) through the Bluetooth module (66) which further carries out the corresponding active resisted - isokinetic exercise control algorithm as shown in the flowchart in figure 19. In this mode, the user gains full control and starts strengthening their muscles with help of resistive exercises. The system (150) restricts the movement of the leg in order to strengthen the muscles. In this mode, no is assistance given but varying resistance is given to achieve constant speed of movement and complete effort is expected from the patient. Here the position and torque values are periodically (10 samples per second) read through the encoders (22, 24) and the torque sensors (32) in all the joints (J 1 , J2, J3) using the torque sensor drivers (TD1, TD2, TD3) and the encoder drivers (Ell, E12, E21, E22, E31, E32) through the data acquisition thread. The data acquisition thread then filters and converts the encoder and torque sensor values to meaningful position, velocity, acceleration and torque values. The safety thread in the microprocessor checks if the position, velocity, acceleration and torque values are within the limit. If not, the safety thread immediately sends a command to the motor drivers (MD1, MD2, MD3) to stop the motor (28) and alerts the caregiver through the IFMU (100). If the parameters are within the safety limit, the control thread checks if the net torque on each joint (J 1 , J2, J3) is less than “Isokinetic Speed”. If no, the control thread first decelerates the motor (28) to avoid any jittery stops towards the end of the repetition and further checks if the position is at desired position. If yes, the control thread stops the motor. If no, it goes to step 1. If yes, the control thread checks if the position is at desired position. If no, the control thread accelerates the motor (28) in the desired direction. If yes, the control thread first decelerates the motor (28) to avoid any jittery stops towards the end of the repetition and further checks if the position is at desired position. If yes, the control thread stops the motor (28). If no, it goes to step 1.

Active mode of exercise:

After choosing the movement type, and corresponding exercise type as active, the caregiver sets the parameters like angle, repetitions, rate of movement. The IFMU (100) sends the corresponding selected commands to the main processor (62) in the control circuit (70) through the Bluetooth module (66) which further carries out the corresponding active exercise control algorithm as shown in the flowchart in figure 20. In this mode, the user gains full range control and overcomes simple gravitational force i.e. can move legs vertically up and down. The system (150) allows the patient to move their legs freely in all directions and do all movement exercises. In this mode, no assistance and no resistance are given and complete effort is expected from the patient. Here the position and torque values are periodically (10 samples per second) read through the encoders (22, 24) and the torque sensors (32) in all the joints (J 1 , J2, J3) using the torque sensor drivers (TD1, TD2, TD3) and the encoder drivers (Ell, E12, E21, E22, E31, E32) through the data acquisition thread. The data acquisition thread then filters and converts the encoder and torque sensor values to meaningful position, velocity, acceleration and torque values. The safety thread in the microprocessor checks if the position, velocity, acceleration and torque values are within the limit. If not, the safety thread immediately sends a command to the motor drivers (MD1, MD2, MD3) to stop the motor (28) and alerts the caregiver through the IFMU (100). If the parameters are within the safety limit, the control thread checks if the net torque on each joint (J 1 , J2, J3) is greater than ‘Modelled Gravitational Torque’. If no, the control thread first decelerates the motor (28) to avoid any jittery stops towards the end of the repetition and further checks if the position is at desired position. If yes, the control thread stops the motor (28). If no, it goes to step 1. If yes, the control thread checks if the position is at desired position. If no, the control thread accelerates the motor (28) in the desired direction. If yes, the control thread first decelerates the motor (28) to avoid any jittery stops towards the end of the repetition and further checks if the position is at desired position. If yes, the control thread stops the motor (28). If no, it goes to step 1.

Compound Movement

Compound movements are movements which require simultaneous movements of the joints. Figure 21 illustrates the steps involved in configuring compound movements in accordance with the present invention. In order to configure these movements, the system (150) needs to be first put on the “gravity eliminated mode” (Free drive Mode). This ensures that the system (150) doesn’t have its own weight and the caregiver can directly interact with the patient’s weight and forces through the system (150). Thereafter, the caregiver starts the recording by pressing the record button (34). While recording is ongoing, the system (150) measures the position, velocity, acceleration and torques continuously in periodic time samples and stores the data in the database (110). Once the movement is complete by the caregiver, he/she again presses the record button (34) to stop the recording. The movement is then displayed as a preview in the IFMU (100). The caregiver then selects the mode from anyone of passive, active, active resisted and like and sets the parameters to begin the exercise. Figure 22 shows the caregiver interacting with the system (150) and patient performing exercises, in accordance with the present invention.

Thus, in the compound movement the system (150) allows recording the physiotherapist’s movements during the therapy session and re-generates the optimized path-constrained trajectories thereof. The system (150) learns from the physiotherapist in the first session, then takes over the repetitive exercises and mimics the assisting and resisting patterns throughout the range of motion of the patient’s lower limb in sleeping, sitting, and standing positions. All this is done by gamifying the treatment and collecting real-time data of the patient's important parameters. However, it is understood here that the system (150) can be customized for upper limb movement types by changing the straps (44) connected to the adjustable links (54) or changing the adjustable links (54) connected to each joint (J 1, J2, J3).

Advantages of the invention

1. The system (150) and the method provide a motivational and gamified rehabilitation process to learn from the caregiver and mimic it with responsive real-time feedback of the patient's important parameters. 2. The system (150) and the method provide a fast, effective, and documented return to function while in turn reducing the efforts of the physiotherapists.

3. The system (150) and the method increase the efficiency and productivity of caregivers.

4. The system (150) and the method reduce the overall cost of providing physical rehabilitative healthcare.

5. The system (150) and the method provide personalized profiles for every patient with online follow-ups and reporting.

6. The system (150) provides portable treatment at the home with all possible comfort.

7. The system (150) and the method are further extendable to fitness centres, old age homes and bed ridden patients for exercise therapy.

8. The system (150) transforms the phsysiotherapy industry from a one-one industry to a one-many industry, where one physiotherapist can engage with multiple patients simultaneously.

9. The system (150) and the method provide better clinical outcome by providing the recommended levels of repetitions.

The foregoing objects of the invention are accomplished and the problems and shortcomings associated with prior art techniques and approaches are overcome by the present invention described in the present embodiment. Detailed descriptions of the preferred embodiment are provided herein; however, it is to be understood that the present invention may be embodied in various forms. Therefore, specific details disclosed herein are not to be interpreted as limiting, but rather as a basis for the claims and as a representative basis for teaching one skilled in the art to employ the present invention in virtually any appropriately detailed system, structure, or matter. The embodiments of the invention as described above and the methods disclosed herein will suggest further modification and alterations to those skilled in the art. Such further modifications and alterations may be made without departing from the scope of the invention.

Claims

Claims We claim,

1. An intelligent lower-limb orthosis system (150) for exercise therapy, the system (150) comprising: a height adjustment mechanism (20) positioned on a wheeled platform (10) for adjusting height thereof; a modular manipulator joint assembly (60) having at least three manipulator joints (J 1 , J2, J3) connected to each other through an adjustable link (54), the adjustable link (54) having straps (42) for connecting to human body and restricting any unwanted movement of legs in case of muscle stiffness of users, and a length adjuster, each manipulator joint (J 1 , J2, J3) having,

• a first encoder (22) positioned before a strain wave gear (26) and a second encoder (24) positioned after the strain wave gear (26), the encoders (22, 24) being configured to measure accurate position, velocities and accelerations to provide a feeling of natural assistance and resistance,

• at least one torque sensor (32) for detecting high torque values with very low precisions,

• a motor (28) having a rotor (28a) and a stator (28b),

• a joint printed circuit board (40) for distributing signals and power to individual elements thereof, and

• at least one fail-safe brake (30) for locking thereof;

• a control circuit (70) for controlling each joint of the three manipulator joints (J 1 , J2, J3) separately and simultaneously, the control circuit (70) having,

• a main processor (62) for executing all parallel threads, controlling algorithms and storing real-time data,

• a motor driver (MD1, MD2, MD3) for each motor (28) in corresponding joint (J 1 , J2, J3), the motor drivers (MD1, MD2, MD3) allowing the main processor (62) to control and maintain the speed and direction of the motors (28) by monitoring the exact position of the motor rotors (28a),

• brake drivers (BD1, BD2, BD3) being relay based circuits allowing the main processor (62) to brake individual joints (Jl, J2, J3) in case of any safety flags or during the time of active isometric strengthening exercises,

• torque sensor drivers (TD1, TD2, TD3) being amplifier circuits converting and amplifying the differential output from the torque sensors (32),

• encoder drivers (Ell, E12, E21, E22, E31, E32) being voltage divider circuits read the position data from each individual encoder (22, 24),

• joint connectors (J1C, J2C, J3C) for connecting a main control circuit to individual joint printed circuit boards (40), and

• a control panel driver (64) having respective voltage stepping-up or stepping down circuits; an intelligent fitness management unit (100) hosted by a screen element, the intelligent fitness management unit (100) configured on a portable device of a user/caregiver and used to configure the exercises for the user and to obtain real-time parameters, user-insights and storing the data in a server, wherein the exercises are selected from a passive exercise, an active assisted exercise, an active gravity eliminated exercise, an active exercise, an active resisted - isotonic exercise, an active resisted - isometric exercise, an active resisted - isokinetic exercise and a home mode exercise; and a database for storing gathered data from online and local databases.

2. The system (150) as claimed in claim 1, wherein the encoders (22, 24) are open optical incremental encoders.

3. The system (150) as claimed in claim 1, wherein the strain wave gears (26) are zero backlash high precision harmonic gears which maximize output torque and minimize size and weight.

4. The system (150) as claimed in claim 1, wherein the motors (28) are brushless direct current frameless torque motors with inbuilt hall effect sensors.

5. The system (150) as claimed in claim 1, wherein the length adjuster includes a mechanism for adjusting the height of the adjustable link (54), a knob (48) for changing the length of the adjustable link (54), a locking lever (50) for locking the set length and ensuring no backward movement and a display element (52) to display the current set length of the adjustable link (54).

6. The system (150) as claimed in claim 1, wherein the screen element (100) is connected to the system (150) through a movable arm (92), the movable arm (92) is a six degree of freedom movable arm which enables a screen to be viewed from any angle.

7. A method of performing exercise therapy, the method comprising the steps of: accessing a system (150) by a caregiver using login credentials, wherein the system (150) includes a modular manipulator joint assembly (60) having at least three manipulator joints (J 1 , J2, J3); setting movement types, exercises types, and parameters by the caregiver; recording multiple movements and exercises by the caregiver to create a session, wherein the exercises are selected from a passive exercise, an active assisted exercise, an active gravity eliminated exercise, an active exercise, an active resisted - isotonic exercise, an active resisted - isometric exercise, an active resisted - isokinetic exercise and a home mode exercise; accessing the system (150) by a user/patient by login into an intelligent fitness management unit (100), wherein the intelligent fitness management unit (100) is configured on a portable device of the user/patient; and selecting the required session and playing the session on the device by the user/patient.

8. The method as claimed in claim 7, wherein the parameters to be chosen for each exercise type includes angle, assistance, resistance, rate of movement (speed) and repetitions.

9. The method as claimed in claim 7, wherein after setting the movement types, exercises types, and parameters, the intelligent fitness management unit (100) sends the corresponding selected commands to a main processor (62) in a control circuit (70) through a Bluetooth module (66) for carrying out the selected exercise.

10. The method as claimed in claim 7, wherein position and torque values in the three manipulator joints (J 1 , J2, J3) are periodically read through encoders (22, 24) and torque sensors (32) using torque sensor drivers (TD1, TD2,

TD3) and encoder drivers (Ell, E12, E21, E22, E31, E32) through a data acquisition thread.

11. The method as claimed in claim 7, wherein in case of multiple joints movements a record button (34) is accessed by the caregiver to teach and record the movements to the system (150) during the therapy session and then the system (150) re-generates an optimized path-constrained trajectories thereof.