TWI896060B - Rehabilitation assistance system - Google Patents

Abstract

A rehabilitation assistance system suitable for a patient undergoing rehabilitation includes a rehabilitation device, a sensing network, a sensing device and an interactive interface. The rehabilitation device is configured to drive hip and knee joints of the patient to perform flexion and extension movements. The sensing network includes an inertial sensing module configured to measure inertial sensing signals of the patient. The sensing device is configured to measure physiological signals of the patient. The interactive interface is coupled to the rehabilitation device, the sensing network and the sensing device, and is configured to receive and display the inertial sensing signals and the physiological signals, and includes a memory and a processor. The memory is configured to store the inertial sensing signals and the physiological signals. The processor is configured to receive control instructions from the patient and send rehabilitation instructions to the rehabilitation device according to the control instructions.

Description

Rehabilitation Assistance System

The present invention relates to an assistive system, and in particular to a rehabilitation assistive system.

Stroke patients experience significant impairments in limb control, body function, walking balance, and quality of life. Currently, most home rehabilitation programs focus on single-joint movements. In practice, these tedious and repetitive exercises often cause stroke patients to abandon their home rehabilitation program midway, hindering optimal rehabilitation effectiveness. Furthermore, traditional home rehabilitation programs are unable to automatically and fully collect information about stroke patients' movements and physiological status during rehabilitation, making it difficult for caregivers to monitor the entire rehabilitation process and for medical staff to assess the patient's rehabilitation progress in real time.

The purpose of this invention is to provide a rehabilitation assistance system to assist stroke patients in training the complete gait cycle during rehabilitation walking, thereby achieving lower limb walking rehabilitation and providing real-time monitoring of the patient's physiological status during rehabilitation.

One aspect of the present invention is to provide a rehabilitation assistance system for a user undergoing rehabilitation, comprising a rehabilitation device, a sensing network, a sensing device, and an interactive interface. The rehabilitation device is configured to move the user's hip and knee joints in flexion and extension movements. The sensing network includes an inertia sensing module configured to measure the user's inertia sensing signals. The sensing device is configured to measure the user's physiological signals. The interactive interface couples the rehabilitation device, the sensing network, and the sensing device, and is configured to receive and display the inertia sensing signals and physiological signals. The interactive interface includes a memory and a processor. The memory is configured to store the inertia sensing signals and physiological signals. The processor is configured to receive at least one control instruction from the user and, based on the at least one control instruction, send at least one rehabilitation instruction to the rehabilitation device.

In some embodiments, the at least one inertia sensing signal further includes a hip joint motion signal and a knee joint motion signal, and the processor is further configured to calculate the lower limb joint angle based on the hip joint motion signal and the knee joint motion signal using a lower limb joint angle measurement algorithm.

In some embodiments, the lower limb joint angle measurement algorithm is based on an extended Kalman filter (EKF), an unscented Kalman filter (UKF), a particle filter (PF), or a cubature Kalman filter (CKF) design, but is not limited thereto.

In some embodiments, the lower limb joint angle is a hip joint angle or a knee joint angle.

In some embodiments, the processor is further configured to control the rehabilitation device to stop moving when the hip joint angle is greater than an upper limit of the hip joint angle range or less than a lower limit of the hip joint angle range, and the processor is further configured to control the rehabilitation device to stop moving when the knee joint angle is greater than an upper limit of the knee joint angle range or less than a lower limit of the knee joint angle range.

In some embodiments, the lower limb joint angle measurement algorithm further includes a lower limb movement posture estimation algorithm and a lower limb joint angle estimation algorithm.

In some embodiments, the physiological signals further include skin temperature, heart rate, and blood oxygen concentration.

In some embodiments, the processor is further configured to process the physiological signal using a physiological emergency stop mechanism algorithm, and control the rehabilitation device to stop operating when it is determined that the physiological parameters of the physiological signal exceed the normal physiological parameter range.

In some embodiments, the at least one control command further includes one or more of a device height setting command, a step count setting command, a step length setting command, a step speed setting command, and a walking time setting command.

In some embodiments, the processor is further configured to store at least one inertial sensing signal and at least one physiological signal in a cloud database.

11: Thigh skeleton

12: Calf skeleton

13: Hip joint linear actuator

14: Knee joint stepping motor

15: Handrails

16: Fixing components

17: Drive device

100: Rehabilitation Assistance System

110: Rehabilitation Device

111: Thigh length adjustment device

120: Sensing Network

121: Calf length adjustment device

130: Sensing device

131: Hip joint actuator support frame

140:Interactive Interface

141: Knee joint motor support frame

142: Memory

144: Processor

152: Emergency stop button

153: Armrest height adjustment device

154: Armrest height actuator support frame

162: Thigh Movement Signal Sensor

163: Calf movement signal sensor device

171: DC deceleration motor

172: Drive wheel

173:Tugboat

200: Mechanical Devices

To facilitate a clearer understanding of the above and other objects, features, advantages, and embodiments of the present invention, the accompanying drawings are provided as follows: Figure 1 is a functional block diagram of a rehabilitation assistance system according to an embodiment of the present invention; Figure 2 is a schematic diagram of a mechanical device incorporating the rehabilitation assistance system according to an embodiment of the present invention; and Figure 3 is a schematic diagram of an operator using the mechanical device according to an embodiment of the present invention.

The following discusses embodiments of the present invention in detail. It will be appreciated that the embodiments provide numerous applicable concepts that can be implemented in a wide variety of specific contexts. The embodiments discussed and disclosed are for illustrative purposes only and are not intended to limit the scope of the present invention.

FIG1 is a functional block diagram of a rehabilitation assistance system 100 according to an embodiment of the present invention. The rehabilitation assistance system 100 is suitable for use by a user performing rehabilitation and includes a rehabilitation device 110, a sensor network 120, a sensor device 130, and an interactive interface 140. The interactive interface 140 further includes a memory 142 and a processor 144.

Figure 2 is a schematic diagram of a mechanical device 200 used in the rehabilitation assistance system 100 according to an embodiment of the present invention. The mechanical device 200 includes a rehabilitation device 110, a sensing network 120, and a sensing device 130.

The rehabilitation device 110 further includes a thigh frame 11, a thigh length adjustment device 111, a hip linear actuator 13, a hip actuator support frame 131, a calf frame 12, a calf length adjustment device 121, a knee stepper motor 14, and a knee motor support frame 141. It should be noted that the rehabilitation device 110 is symmetrical for both legs. The rehabilitation device 110 is configured to flex and extend the user's hip and knee joints. In one embodiment of the present invention, the rehabilitation device 110 utilizes a linear actuator and a stepper motor as its driving force.

The sensing network 120 is installed on one or more fixed elements 16 and includes one or more thigh motion signal sensing devices 162 and one or more calf motion signal sensing devices 163. Each thigh motion signal sensing device 162 and calf motion signal sensing device 163 includes a microcontroller, an inertia sensing module, and a first wireless radio frequency transmission module. The inertia sensing module is configured to measure the operator's inertia sensing signal, and the first wireless radio frequency transmission module is configured to transmit the measured inertia sensing signal.

Figure 3 is a schematic diagram of an operator using a mechanical device 200 according to an embodiment of the present invention. As shown in Figure 3 , the securing element 16 is secured to the operator's leg (thigh and/or calf), and its tightness can be adjusted appropriately. In some embodiments, the securing element 16 is a Velcro strap or a buckle strap.

It should be noted that inertial sensing signals include hip joint motion signals and knee joint motion signals.

Inertial sensing modules also include, but are not limited to, accelerometers, gyroscopes, and magnetometers.

The inertial sensing signal collected by the accelerometer in the sensing network 120 is an acceleration signal. Before being substituted into the lower limb joint angle measurement algorithm for calculation, this acceleration signal must first undergo a signal pre-processing process, including acceleration signal correction and rehabilitation movement noise filtering.

The inertial sensing signal collected by the gyroscope in the sensing network 120 is an angular velocity signal. Before being substituted into the lower limb joint angle measurement algorithm for calculation, this angular velocity signal must first undergo signal pre-processing, including angular velocity signal calibration and rehabilitation movement noise filtering.

The inertial sensing signal collected by the sensing network 120 via the magnetometer is the magnetometer signal. Before being substituted into the lower limb joint angle measurement algorithm for calculation, the magnetometer signal must first undergo signal pre-processing, including magnetometer signal calibration and rehabilitation movement noise filtering.

It should be further explained that the hip joint motion signals and knee joint motion signals include acceleration signals, angular velocity signals, and magnetometer signals.

The first wireless radio frequency transmission module is configured to transmit the operator's hip joint movement signal, knee joint movement signal, etc., but is not limited thereto.

The sensing device 130 is mounted on the armrest 15 and further includes an emergency stop button 152, an armrest height adjustment device 153, and an armrest height actuator support frame 154. The sensing device 130 is configured to measure the operator's physiological signals. Furthermore, the sensing device 130 includes a second wireless radio frequency transmission module configured to transmit these physiological signals. In one embodiment of the present invention, the sensing device 130 may be an infrared temperature sensor or a blood oxygen concentration, heart rate, or pulse sensor. It should be noted that the physiological signals include skin temperature, heart rate, and blood oxygen concentration. In other words, the second wireless radio frequency transmission module is configured to transmit the operator's skin temperature, heart rate, blood oxygen concentration, etc., but is not limited to these.

The mechanical device 200 further includes a drive device 17, which includes a DC reduction motor 171, one or more drive wheels 172 (e.g., the two drive wheels 172 shown in FIG. 2 ), and one or more tugs 173 (e.g., the ten tugs 173 shown in FIG. 2 ).

The interactive interface 140 is coupled to the rehabilitation device 110, the sensing network 120, and the sensing device 130. It is configured to receive and display inertial sensing signals and physiological signals, including but not limited to hip joint motion signals, knee joint motion signals, skin temperature, heart rate, and blood oxygen concentration.

In one embodiment of the present invention, the interactive interface 140 is further configured to allow the operator to adjust the height of the armrest device 15, the length of the thigh frame 11, and the length of the calf frame 12.

In another embodiment of the present invention, the interactive interface 140 is further configured to allow the operator to set the number of steps, set the step length, set the hip joint angle, and set the knee joint angle.

In some embodiments, the operator of the mechanical device 200 can set the hip and knee joint angles through the interactive interface 140. The microcontrollers of the thigh motion signal sensor 162 and calf motion signal sensor 163 in the sensing network 120 will drive the hip joint linear actuator 13 and knee joint stepping motor 14, respectively, based on the hip and knee joint angles during each gait cycle. This drives the operator's calf and thigh movements, completing walking motion rehabilitation throughout the entire gait cycle.

Regarding the actuation of the hip joint linear actuator 13, the present invention divides the complete gait cycle into six phases: Bipedal Support I (heel strike), Bipedal Support II (landing phase/foot strike), Single-Foot Support (mid-stance phase), Single-Foot Support (end-stance phase/heel-off), Bipedal Support II (pre-swing phase/toe-off), and Swing phase. Based on the specific human body conditions of these six phases, the hip joint angle is: Bipedal Support I (heel strike) (hip flexion 30°) The hip linear actuator 13 is driven by the following parameters: Bipedal support I (landing phase/foot landing) (hip flexion 30°); Single-leg support (mid-stance phase) (hip flexion 10°); Single-leg support (late stance phase/heel-off) (hip extension 10°); Bipedal support II (early swing phase/toe-off) (hip 0°); swing phase (hip flexion 30°).

In terms of driving the knee joint stepping motor 14, the present invention divides the complete gait cycle into six phases: double-foot support I (heel landing), double-foot support I (landing phase/foot landing), single-foot support (mid-stance phase), single-foot support (end-stance phase/heel off), double-foot support II (early swing phase/toe off) and swing phase, and according to the specific human hip joint angles of the six phases: double-foot support I (heel landing) (knee joint The following parameters are used to set the propulsion stroke of the knee stepper motor 14: Bipedal support I (landing phase/foot landing) (knee flexion 10°); Single-leg support (mid-stance phase) (knee 0°); Single-leg support (end-stance phase/heel-off) (knee 0°); Bipedal support II (early swing phase/toe-off) (knee flexion 35°); swing phase (knee 0°), thereby driving the knee stepper motor 14.

The interactive interface 140 further includes a memory 142 configured to store inertial sensing signals and physiological signals, including but not limited to hip joint motion signals, knee joint motion signals, skin temperature, heart rate, blood oxygen concentration, etc.

Memory 142 can be high-speed random access memory and may also include non-volatile memory, such as a hard drive, a plug-in hard drive, a smart media card (SMC), a secure digital (SD) card, a flash memory card, at least one magnetic disk memory device, a flash memory device, or other non-volatile solid-state memory device.

The interactive interface 140 further includes a processor 144 configured to receive one or more control instructions from the operator and send one or more rehabilitation instructions to the rehabilitation device 110 according to the one or more control instructions.

In one embodiment of the present invention, the one or more control instructions further include, but are not limited to, an instruction for setting device height, an instruction for setting step count, an instruction for setting stride length, an instruction for setting stride speed, and an instruction for setting walking time.

The processor 144 may be, but is not limited to, a central processing unit (CPU), a graphics processing unit (GPU), a microcontroller unit (MCU), a microprocessor, a system-on-chip (SoC), a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a programmable logic controller (PLC), or a combination of the foregoing.

After the sensor device 130 measures the operator's skin temperature, heart rate, blood oxygen concentration, and other physiological signals, the processor 144 feeds these physiological signals into a physiological emergency stop mechanism algorithm to determine the operator's physiological condition during rehabilitation, thus serving as the physiological emergency stop control mechanism for the rehabilitation device 110.

Specifically, during the operator's rehabilitation process, if the sensing device 130 detects an abnormal physiological signal from the operator, the processor 144 will issue a stop signal to control the rehabilitation device 110 to stop operating.

In one embodiment of the present invention, the processor 144 is further configured to process the physiological signal using a physiological emergency stop mechanism algorithm and control the rehabilitation device 110 to stop operating when it is determined that the physiological parameter of the physiological signal exceeds the normal physiological parameter range (i.e., the physiological parameter is greater than the upper limit of the normal physiological parameter range or less than the lower limit of the normal physiological parameter range).

Specifically, processor 144 uses skin temperature, heart rate, and blood oxygen concentration as input signals for the physiological emergency stop mechanism algorithm. The machine learning or deep learning neural network model within the physiological emergency stop mechanism algorithm determines whether one or more of these physiological signals are abnormal (i.e., whether the physiological parameters of the physiological signals exceed the normal physiological parameter range). If processor 144 determines that one or more of these physiological signals are abnormal, it controls rehabilitation device 110 to stop operating.

It should be noted that the physiological emergency stop mechanism algorithm is implemented using a neural network model architecture based on machine learning or deep learning, but is not limited to this.

After accessing the operator's hip and knee joint motion signals from memory 142, processor 144 substitutes the hip and knee joint motion signals into the lower limb joint angle measurement algorithm to calculate the lower limb joint angle.

It should be noted that the lower limb joint angle measurement algorithm is based on, but not limited to, an extended Kalman filter (EKF), an unscented Kalman filter (UKF), a particle filter (PF), or a cubature Kalman filter (CKF).

Lower limb joint angle measurement algorithms further include lower limb movement posture estimation algorithms, lower limb joint angle estimation algorithms, etc., but are not limited to these.

In one embodiment of the present invention, the lower limb joint angle is a hip joint angle or a knee joint angle.

Specifically, processor 144 first uses the lower limb posture estimation algorithm within the lower limb joint angle measurement algorithm to calculate the roll angle, pitch angle, and yaw angle of the thigh and calf bones in three-dimensional space. It then uses the lower limb joint angle estimation algorithm within the lower limb joint angle measurement algorithm to calculate the operator's hip and knee joint angles.

Specifically, during rehabilitation, when the sensing network 120 detects the operator's hip and knee joint motion signals and uses the lower limb joint angle measurement algorithm to calculate that the operator's hip and knee joint angles are abnormal, the processor 144 will issue a stop signal to control the rehabilitation device 110 to stop.

In one embodiment of the present invention, the processor 144 is further configured to control the rehabilitation device 110 to stop operating when the hip joint angle is greater than the upper limit of the hip joint angle range or less than the lower limit of the hip joint angle range.

In another embodiment of the present invention, the processor 144 is further configured to control the rehabilitation device 110 to stop moving when the knee joint angle is greater than the upper limit of the knee joint angle range or less than the lower limit of the knee joint angle range.

After measuring the operator's inertial sensing signals (e.g., hip joint motion signals, knee joint motion signals, etc.) and physiological signals (e.g., skin temperature, heart rate, blood oxygen concentration, etc.), processor 144 stores these inertial sensing signals and physiological signals in a cloud database.

The rehabilitation assistance system 100 also includes a monitoring platform configured to display real-time signals including hip joint angle, knee joint angle, skin temperature, blood oxygen concentration, and heart rate. This allows medical staff and the operator's family to access a cloud database to monitor the operator's rehabilitation status in real time.

In addition, the monitoring platform is configured to store the operator's historical rehabilitation records in a cloud database.

In one embodiment of the present invention, the rehabilitation assistance system 100 further includes an application that can be installed on a mobile device. This allows medical personnel and family members to use the application on their personal mobile devices to monitor the operator's hip joint angle, knee joint angle, skin temperature, blood oxygen concentration, heart rate, and other signals in real time while the operator performs rehabilitation exercises. The application can also be used to view the operator's complete rehabilitation history.

Continuing from the previous embodiment, the mobile device may be a smartphone, a smart bracelet, a tablet computer, etc., but is not limited thereto.

In summary, the rehabilitation assistance system of the present invention combines rehabilitation devices, a sensor network, sensor devices, and an interactive interface to assist stroke patients in training the complete gait cycle during rehabilitation walking, thereby achieving lower limb walking rehabilitation. Furthermore, medical staff and family members can monitor the patient's physiological status in real time during rehabilitation through a monitoring platform or mobile device application.

Although the present invention has been disclosed above through the use of embodiments, these are not intended to limit the scope of the present invention. Any person skilled in the art may make various changes, substitutions, and modifications without departing from the spirit and scope of the present invention. Therefore, the scope of protection of the present invention shall be determined by the scope of the patent application appended hereto.

100: Rehabilitation Assistance System

110: Rehabilitation Device

120: Sensing Network

130: Sensing device

140:Interactive Interface

142: Memory

144: Processor

Claims (5)

A rehabilitation assistance system, suitable for an operator performing rehabilitation, comprises: a rehabilitation device configured to drive a hip joint and a knee joint of the operator to perform a flexion movement and an extension movement; a sensing network comprising an inertia sensing module and a first wireless radio frequency transmission module, wherein the inertia sensing module is configured to measure the flexion movement and the extension movement to obtain at least one inertia sensing signal of the operator, and the first wireless radio frequency transmission module is configured to transmit the at least one inertia sensing signal; a sensing device configured to measure at least one physiological signal of the operator, the sensing device further comprising a second wireless radio frequency a transmission module configured to transmit the at least one physiological signal; an interactive interface coupled to the rehabilitation device, the sensing network, and the sensing device, the interactive interface configured to receive and display the at least one inertial sensing signal and the at least one physiological signal, comprising: a memory configured to store the at least one inertial sensing signal and the at least one physiological signal, wherein the at least one physiological signal further comprises a skin temperature, a heart rate value, and a blood oxygen concentration; and a processor configured to receive at least one control instruction from the operator and transmit at least one rehabilitation instruction to the rehabilitation device according to the at least one control instruction, wherein the at least one inertial sensing signal The sensing signal includes a hip joint motion signal and a knee joint motion signal, and the processor is further configured to calculate a lower limb joint angle according to the hip joint motion signal and the knee joint motion signal and using a lower limb joint angle measurement algorithm, wherein the lower limb joint angle is a hip joint angle or a knee joint angle, wherein the processor is further configured to control the rehabilitation device to stop moving when the hip joint angle is greater than an upper limit of a hip joint angle range or less than a lower limit of a hip joint angle range, and wherein the processor is further configured to control the rehabilitation device to stop moving when the knee joint angle is greater than a knee joint angle range. The rehabilitation device is controlled to stop moving when the knee angle value is less than an upper limit of a knee joint angle range or less than a lower limit of a knee joint angle range of the knee joint angle range, wherein the processor is further configured to process the physiological signal using a physiological emergency stop mechanism algorithm, and control the rehabilitation device to stop moving when it is determined that a physiological parameter of the physiological signal exceeds a normal physiological parameter range, wherein the physiological emergency stop mechanism algorithm includes at least one neural network model implemented by a machine learning method or a deep learning method, and the input signal of the physiological emergency stop mechanism algorithm includes at least one of the skin temperature, the heart rate value and the blood oxygen concentration. The rehabilitation assistive system as described in claim 1, wherein the lower limb joint angle measurement algorithm is based on an extended Kalman filter (EKF), an unscented Kalman filter (UKF), a particle filter (PF), or a cubature Kalman filter (CKF) design. The rehabilitation assistance system as described in claim 1, wherein the lower limb joint angle measurement algorithm further includes a lower limb movement posture estimation algorithm and a lower limb joint angle estimation algorithm. A rehabilitation assistance system as described in claim 1, wherein the at least one control instruction further includes one or more of a device height setting instruction, a step number setting instruction, a step length setting instruction, a step speed setting instruction, and a walking time setting instruction. The rehabilitation assistance system as described in claim 1, wherein the processor is further configured to store the at least one inertial sensing signal and the at least one physiological signal in a cloud database.