Prosthetic movement intention recognition method and device based on source-end fusion

Abstract

The present invention discloses a method and device for recognizing prosthetic movement intention based on source-end fusion, which is to collect ground support reaction force distribution through a pressure sensor arranged on the sole of the prosthetic foot, judge the gait cycle, and calculate the walking speed; distinguish the road conditions of flat ground, going up stairs, going up slope, going down stairs, and going down slope by data collected by an acceleration sensor arranged at the position of the prosthetic knee joint; distinguish the road conditions of going up stairs, going up slope, going down stairs, and going down slope by combining the angle sensor data arranged at the position of the prosthetic ankle joint, and finally the processor judges the movement intention of the amputee according to the walking speed and road conditions. The processor of the present invention controls the prosthesis to change the action according to the walking speed and road conditions, and helps the prosthesis to accurately make the corresponding action, so that the amputee does not need to use his own strength to change the prosthetic action, which can make the amputee more labor-saving in the process of using the prosthesis, and can also make the gait of the prosthesis more natural.

Description

Technical Field

[0001] The present invention relates to the field of information processing technology, and in particular to a method and device for identifying prosthetic movement intention based on source-end fusion. Background Art

[0002] With the development of society and the improvement of living standards, amputees have higher and higher requirements for intelligent prostheses. Simple walking and standing can no longer meet the requirements of amputees. Amputees also need intelligent prostheses to recognize their movement intentions and adjust their gait according to different walking speeds and different road conditions. In order to achieve the intelligent prosthesis being able to adjust the gait according to the walking speed and road conditions, the intelligent prosthesis must be able to recognize information such as walking speed and road conditions, and accurately identify the movement intention of the amputee. Therefore, the recognition of movement intention is of great significance to improving the performance of intelligent prostheses.

[0003] At present, the main method of motion intention recognition is to use gyroscopes and accelerometers to calculate and analyze motion intention. The main method is to install gyroscopes and accelerometers in the residual limb cavity of the intelligent prosthesis, install pressure switch sensors on the soles of the feet, distinguish the support phase and swing phase of the gait cycle through the switch signal of the pressure sensor, test the angular velocity of the thigh residual limb through the gyroscope, calculate the hip joint angle according to the angular velocity, test the acceleration of the thigh residual limb through the accelerometer, and match the tested pressure, hip joint angle, angular velocity, acceleration and other data with the data model library established in the early stage through the sensor fusion algorithm and hidden Markov model to judge the road condition and identify the movement intention of the amputee. However, the method of using gyroscopes and accelerometers to calculate and analyze motion intention requires the collected data to be calculated and analyzed by the sensor fusion algorithm and hidden Markov model to obtain the possibility of each road condition, and then determine the road condition with the highest possibility as the current road condition. This method cannot determine the accurate road condition 100%. Due to the limitations of the algorithm, the accuracy of judgment can only reach 90%. Moreover, this recognition method requires the establishment of a complex database in the early stage, and the sensor data also needs to be processed and calculated in a complex manner during the later use. The algorithm is complex and prone to misjudgment. Summary of the invention

[0004] In view of the defects of the above-mentioned prior art, the present invention provides a prosthetic movement intention recognition method and device based on source-end fusion, which can accurately judge the amputee's movement intention during the amputee's movement process, control the intelligent prosthesis to move according to the amputee's movement intention, and make the wearer of the intelligent prosthesis more comfortable and the gait more natural.

[0005] The method for identifying prosthetic movement intention based on source-end fusion provided by the present invention is improved in that the method includes a processor collecting ground support reaction force distribution through a pressure sensor arranged on the sole of the prosthetic limb, judging the gait cycle, and calculating the walking speed; distinguishing between flat ground, going up stairs, going up slopes, going down stairs, and going down slope road conditions through data collected by an acceleration sensor arranged at the position of the prosthetic knee joint; distinguishing between going up stairs, going up slopes, going down stairs, and going down slopes in combination with data from an angle sensor arranged at the position of the prosthetic ankle joint; and finally, the processor judging the amputee's movement intention based on the walking speed and road conditions.

[0006] The distinguishing road conditions of going up stairs, going up a slope, going down stairs and going down a slope includes:

[0007] Stair climbing: the knee joint moves upward in the direction of gravity, the acceleration data is positive, and the ankle joint angle is 0±8° in the middle of the gait cycle;

[0008] Going down stairs: the knee joint moves downward in the direction of gravity, the acceleration data is negative, and the ankle joint angle is <-10° in the late stage of the gait cycle;

[0009] Uphill: The knee joint moves upward in the direction of gravity, the acceleration data is positive, the ankle joint angle is >20° in the middle of the gait cycle;

[0010] Downhill slope: The knee joint moves downward in the direction of gravity, the acceleration data is negative, and the ankle angle is >0° in the late gait cycle.

[0011] The formula for calculating the pace includes:

[0012]

[0013] In the formula, is the pace; is the cadence; is the step length.

[0014] The processor controls the prosthesis to change its movement according to the walking speed and road conditions.

[0015] The pressure sensor includes a first pressure sensor and a second pressure sensor, which are used to collect the ground support reaction force of the forefoot and the rear foot of the artificial foot.

[0016] The device of the present invention is based on the above-mentioned intention recognition method, and its improvement lies in that it comprises a first pressure sensor, a second pressure sensor, an acceleration sensor and an angle sensor respectively connected to the processor;

[0017] The processor is arranged in the middle part of the prosthesis;

[0018] The first pressure sensor is arranged on the forefoot of the artificial foot matched with the artificial limb;

[0019] The second pressure sensor is arranged at the rear heel of the artificial foot matched with the artificial limb;

[0020] The acceleration sensor is arranged at the position of the prosthetic knee joint;

[0021] The angle sensor is arranged at the bare joint position of the artificial foot.

[0022] The processor includes a clock circuit and a reset circuit respectively connected to the STM32F103VET6 main control chip; the main control chip is used to control the action of the prosthesis, the clock circuit is used to provide a time reference for the circuit, and the reset circuit is used to perform initialization settings when the prosthesis is abnormal and restore the prosthesis to normal;

[0023] The first pressure sensor includes a first thin film pressure sensor, which is used to convert the ground support reaction force data collected by the forefoot into a first voltage signal output and transmit it to the main control chip;

[0024] The second pressure sensor includes a second thin film pressure sensor, which is used to convert the ground support reaction force data collected by the heel into a second voltage signal output and transmit it to the main control chip;

[0025] The acceleration sensor includes a three-axis acceleration sensor, which is used to convert the acceleration data of the knee joint in the gravity direction into a third voltage signal output and transmit it to the main control chip;

[0026] The angle sensor includes an anisotropic magnetoresistive angle sensor, which is used to convert the angle data of the ankle joint into a fourth voltage signal output and transmit it to the main control chip.

[0027] In the technical solution of the present invention, the road condition pace can be determined and the movement intention can be identified through simple threshold judgment, which overcomes the shortcomings of the method of using gyroscopes and acceleration sensors to calculate and analyze movement intentions, such as complex data processing, complex calculations, and low judgment accuracy. BRIEF DESCRIPTION OF THE DRAWINGS

[0028] Figure 1 It is a flow chart of a method for recognizing prosthetic movement intention based on source-end fusion according to an embodiment of the present invention;

[0029] Figure 2 Schematic diagram of a prosthetic movement intention recognition device according to an embodiment of the present invention; in the figure, 1 represents an acceleration sensor, 2 represents an angle sensor, and 3 represents a pressure sensor;

[0030] Figure 3The following is a schematic diagram of ankle joint angle change curves under different road conditions during the gait cycle of an embodiment of the present invention. In the figure, the solid line represents flat ground, the dotted line represents climbing stairs, the dotted line represents descending stairs, the dotted horizontal line represents ascending a slope, and the double-dot horizontal line represents descending a slope. DETAILED DESCRIPTION

[0031] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below with reference to the accompanying drawings and preferred embodiments. However, it should be noted that many details listed in the specification are only for the purpose of enabling the reader to have a thorough understanding of one or more aspects of the present invention, and these aspects of the present invention can be implemented even without these specific details.

[0032] The method for prosthetic movement intention recognition based on source-end fusion proposed in this embodiment has a flow chart as shown in FIG. Figure 1 As shown, the processor analyzes the distribution of ground support reaction force through a pressure sensor set on the sole of the prosthetic limb, determines the gait cycle, and calculates the walking speed; distinguishes between flat ground, climbing stairs, climbing slopes, descending stairs, and descending slopes through data collected by an acceleration sensor set at the position of the prosthetic knee joint; distinguishes between climbing stairs, climbing slopes, descending stairs, and descending slopes in combination with data from an angle sensor set at the position of the prosthetic ankle joint. Finally, the processor determines the amputee's movement intention based on the walking speed and road conditions.

[0033] Correspondingly, the device proposed in this embodiment according to the above method includes a first pressure sensor, a second pressure sensor, an acceleration sensor and an angle sensor respectively connected to the processor; Figure 2 As shown:

[0034] The processor is arranged in the middle part of the prosthesis; the processor comprises an STM32F103VET6 main control chip, a clock circuit composed of a crystal oscillator and a reset circuit; and is mainly used to control the prosthesis to perform corresponding actions.

[0035] The first pressure sensor is arranged at the forefoot of the artificial foot matched with the artificial limb, and specifically comprises a first thin film pressure sensor, which is used to convert the ground support reaction force data collected by the forefoot into a first voltage signal output, and transmit it to the main control chip;

[0036] The second pressure sensor is arranged at the rear heel of the artificial foot matched with the artificial limb, and specifically comprises a second thin film pressure sensor, which is used to convert the ground support reaction force data collected by the rear heel into a second voltage signal output, and transmit it to the main control chip;

[0037] The acceleration sensor is arranged at the position of the prosthetic knee joint, and specifically comprises a three-axis acceleration sensor, which is used to convert the acceleration data of the knee joint in the gravity direction into a third voltage signal output, and transmit it to the main control chip;

[0038] The angle sensor is arranged at the bare joint position of the artificial foot, and includes an anisotropic magnetoresistive angle sensor, which is used to convert the angle data of the ankle joint into a fourth voltage signal output and transmit it to the main control chip.

[0039] The processor controls the prosthesis to change its movements according to the walking speed and road conditions, helping the prosthesis to accurately make corresponding movements, so that the amputee does not need to use force to change the movement of the prosthesis, which can save the amputee more effort in the process of using the prosthesis and make the gait of the prosthesis more natural.

[0040] Specific:

[0041] Differentiate road conditions including:

[0042] Flat ground: The displacement of the knee joint in the direction of gravity changes very little (the change is less than 0.1), and the acceleration is close to 0 (the absolute value of the acceleration is less than 0.2);

[0043] Stair climbing: the knee joint moves upward in the direction of gravity, the acceleration data is positive, and the ankle joint angle is 0±8° in the middle of the gait cycle;

[0044] Going down stairs: the knee joint moves downward in the direction of gravity, the acceleration data is negative, and the ankle joint angle is <-10° in the late stage of the gait cycle;

[0045] Uphill: The knee joint moves upward in the direction of gravity, the acceleration data is positive, the ankle joint angle is >20° in the middle of the gait cycle;

[0046] Downhill slope: the knee joint moves downward in the direction of gravity, the acceleration data is negative, and the ankle joint angle is >0° in the late stage of the gait cycle;

[0047] like Figure 3 As shown in the ankle joint angle curves of different road conditions, it can be seen that in the late 90%-100% of the gait cycle, the ankle joint angle when going down stairs is always <-10°, and the ankle joint angle when going down a slope is always >0°. If the angle is not within the range of this embodiment, the main control chip will perform a secondary judgment until the angle is within the range of this embodiment and then make corresponding control.

[0048] The above is only a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principle of the present invention. These improvements and modifications should also be regarded as the scope of protection of the present invention.

Claims

1. A method for recognizing prosthetic movement intention based on source-end fusion, characterized in that: The method includes a processor collecting ground support reaction force distribution through a pressure sensor arranged on the sole of the prosthesis, judging the gait cycle, and calculating the walking speed; distinguishing the road conditions of flat ground, climbing stairs, climbing slopes, descending stairs, and descending slopes through data collected by an acceleration sensor arranged at the position of the prosthesis knee joint; distinguishing the road conditions of climbing stairs, climbing slopes, descending stairs, and descending slopes by combining data from an angle sensor arranged at the position of the prosthesis ankle joint, and finally the processor judging the movement intention of the amputee according to the walking speed and road conditions; The processor controls the prosthesis to change its movements according to the walking speed and road conditions, and helps the prosthesis to accurately make corresponding movements, so that the amputee does not need to use his / her own strength to change the movement of the prosthesis, which can make the amputee more labor-saving during the use of the prosthesis and make the gait of the prosthesis more natural; The road conditions of distinguishing between going up stairs, going up a slope, going down stairs and going down a slope include: Stair climbing: the knee joint moves upward in the direction of gravity, the acceleration data is positive, and the ankle joint angle is 0±8° in the middle of the gait cycle; Going down stairs: the knee joint moves downward in the direction of gravity, the acceleration data is negative, and the ankle joint angle is <-10° in the late stage of the gait cycle; Uphill: The knee joint moves upward in the direction of gravity, the acceleration data is positive, the ankle joint angle is >20° in the middle of the gait cycle; Downhill slope: The knee joint moves downward in the direction of gravity, the acceleration data is negative, and the ankle angle is >0° in the late gait cycle.

2. The method according to claim 1, characterized in that The formula for calculating your pace includes: ， In the formula, is the pace; is the cadence; is the step length.

3. The method according to claim 2, characterized in that The processor controls the prosthesis to change its movement according to the walking speed and road conditions.

4. The method according to claim 1, characterized in that The pressure sensor comprises a first pressure sensor and a second pressure sensor, which are used to collect the ground support reaction force of the forefoot and the rear foot of the artificial foot.

5. A device based on the intention recognition method according to any one of claims 1 to 4, characterized in that: It includes a first pressure sensor, a second pressure sensor, an acceleration sensor and an angle sensor respectively connected to the processor; The processor is arranged in the middle part of the prosthesis; The first pressure sensor is arranged on the forefoot of the artificial foot matched with the artificial limb; The second pressure sensor is arranged at the rear heel of the artificial foot matched with the artificial limb; The acceleration sensor is arranged at the position of the prosthetic knee joint; The angle sensor is arranged at the bare joint position of the artificial foot.

6. The device according to claim 5, characterized in that The processor includes a clock circuit and a reset circuit respectively connected to the STM32F103VET6 main control chip; the main control chip is used to control the action of the prosthesis, the clock circuit is used to provide a time reference, and the reset circuit is used to perform initialization settings when the prosthesis is abnormal; The first pressure sensor includes a first thin film pressure sensor, which is used to convert the ground support reaction force data collected by the forefoot into a first voltage signal output and transmit it to the main control chip; The second pressure sensor includes a second thin film pressure sensor, which is used to convert the ground support reaction force data collected by the heel into a second voltage signal output and transmit it to the main control chip; The acceleration sensor includes a three-axis acceleration sensor, which is used to convert the acceleration data of the knee joint in the gravity direction into a third voltage signal output and transmit it to the main control chip; The angle sensor includes an anisotropic magnetoresistive angle sensor, which is used to convert the angle data of the ankle joint into a fourth voltage signal output and transmit it to the main control chip.

Images