Wireless transmission wearable glove and dexterous hand synchronous control method

Abstract

The application discloses a wireless transmission wearable glove and dexterous hand synchronous control method, relates to the dexterous hand synchronous technical field, and comprises the following steps: constructing a real-time detection distance based on real-time detection data; obtaining a screening distance threshold based on a first number of hand shaking conditions; judging whether the real-time detection distance is initial abnormal data based on the screening distance threshold; constructing an adjacent fluctuation difference value based on the real-time detection data; obtaining a first fluctuation threshold and a second fluctuation threshold based on the first number of hand shaking conditions; judging that the initial abnormal data is final abnormal data based on the first fluctuation threshold and the second fluctuation threshold; and controlling the dexterous hand based on the real-time detection data and the final abnormal data; the application is used to solve the problem that the existing dexterous hand synchronous control technology fails to set a suitable control hand natural shaking judgment method, leading to inaccurate control hand shaking judgment.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of dexterous hand synchronous control, in particular to a wireless transmission wearable glove and dexterous hand synchronous control method. BACKGROUND

[0002] In the current deep integration of human-computer interaction and robot technology, the wireless transmission wearable glove and dexterous hand synchronous control technology captures human hand movements in real time and accurately maps them to the mechanical end effector, while simultaneously feeding back interactive force and tactile information. Existing wearable gloves integrate multiple bend sensors, IMU sensors, and pressure sensors, and the dexterous hand synchronous control is based on data from multiple sensors.

[0003] However, based on the wearable glove and dexterous hand synchronous control, the human hand control is based on the natural physiological tremor of the human hand, which is related to age, fatigue, or tension. At this time, the hand tremor is purposeless, so the dexterous hand controlled at this time will also exhibit these meaningless tremors, making the dexterous hand unstable. For example, the patent application with publication number CN109514521A discloses a human hand coordinated dexterous hand servo operation system and method based on multi-information fusion. This scheme fails to judge the natural tremor of the hand, and the dexterous hand controlled at this time will also exhibit these meaningless tremors, making the dexterous hand unstable. The existing dexterous hand synchronous control technology fails to set a suitable natural tremor judgment method for the control hand, resulting in inaccurate tremor judgment for the control hand. SUMMARY

[0004] The present application aims to at least partially solve one of the technical problems in the prior art. Real-time detection distance is constructed based on real-time detection data. Filter distance threshold is obtained based on the first number of hand shaking conditions. It is determined whether the real-time detection distance is initial abnormal data based on the filter distance threshold. Adjacent fluctuation difference is constructed based on real-time detection data. First fluctuation threshold and second fluctuation threshold are obtained based on the first number of hand shaking conditions. It is determined whether the initial abnormal data is final abnormal data based on the first fluctuation threshold and the second fluctuation threshold. The dexterous hand is controlled based on the real-time detection data and the final abnormal data, to solve the problem that the existing dexterous hand synchronous control technology fails to set a suitable natural tremor judgment method for the control hand, resulting in inaccurate tremor judgment for the control hand.

[0005] To achieve the above-mentioned purpose, the present application provides a wireless transmission wearable glove and dexterous hand synchronous control method, comprising the following steps:

[0006] Install a bend angle sensor on the wearable glove, labeled as a real-time angle sensor. Obtain detection data based on the real-time angle sensor, labeled as real-time detection data.

[0007] constructing a real-time detection distance based on the real-time detection data;

[0008] acquiring a screening distance threshold based on the first number of hand-shaking conditions;

[0009] determining whether the real-time detection distance is initial abnormal data based on the screening distance threshold;

[0010] constructing an adjacent fluctuation difference value based on the real-time detection data;

[0011] acquiring a first fluctuation threshold and a second fluctuation threshold based on the first number of hand-shaking conditions;

[0012] determining that the initial abnormal data is final abnormal data based on the first fluctuation threshold and the second fluctuation threshold; and controlling the dexterous hand based on the real-time detection data and the final abnormal data.

[0013] Further, a bending angle sensor is installed on the wearable glove, which is marked as a real-time angle sensor; detection data is acquired based on the real-time angle sensor, which is marked as real-time detection data, including the following sub-steps:

[0014] The real-time angle sensor is installed at the joint of each finger on the wearable glove, and when the data detected by the real-time angle sensor changes, the real-time detection data is then acquired through the real-time angle sensor.

[0015] Further, constructing a real-time detection distance based on the real-time detection data includes the following sub-steps:

[0016] A plane rectangular coordinate system is established, which is marked as a two-dimensional projection coordinate system; a side view of the wearable glove is acquired, each segment of the fingers of the wearable glove is regarded as a line segment, which is marked as a contrast line segment, and the real-time detection data is regarded as a corresponding bending angle; the side view of the form of the wearable glove is drawn in the two-dimensional projection coordinate system;

[0017] The end point of the contrast line segment corresponding to the change in the real-time detection data is acquired, which is marked as a change end point; the change end point before the change in the real-time detection data is acquired, which is marked as a starting end point;

[0018] The change end point when the real-time detection data changes is acquired, which is marked as a process end point;

[0019] The distance from the process end point to the starting end point is acquired, which is marked as a process detection distance;

[0020] The maximum value of the process detection distance is acquired, which is marked as a real-time detection distance.

[0021] Further, acquiring a screening distance threshold based on the first number of hand-shaking conditions includes the following sub-steps:

[0022] The real-time detection distance is acquired under the first number of hand jitter conditions, and is marked as a historical detection distance;

[0023] The range of the historical detection distance is acquired, and the range of the historical detection distance is represented as N1 to N2; N1 to N2 is evenly divided into q1 equal interval ranges, which are marked as distance segmentation ranges; the range length of each distance segmentation range is (N2-N1) ÷ q1; the minimum value and the maximum value of each distance segmentation range are N1+[(N2-N1) ÷ q1]×w1 and N1+[(N2-N1) ÷ q1]×(w1+1) respectively; wherein w1 is a positive integer from 0 to q1-1.

[0024] The number of historical detection distances in each distance segmentation range is counted, which is marked as a range distance number;

[0025] The distance number threshold is calculated as E1=z1×(T1 ÷ q1); wherein E1 is the distance number threshold; z1 is the distance number proportion; T1 is the sum of all range distance numbers;

[0026] The range distance number less than the distance number threshold is marked as an abnormal distance number.

[0027] Further, acquiring the screening distance threshold based on the first number of hand jitter conditions further includes the following sub-steps:

[0028] The range distance numbers are sorted from left to right according to the minimum values of the corresponding distance segmentation ranges from small to large;

[0029] It is judged whether the rightmost range distance number is an abnormal distance number, if not, the judgment is directly stopped; if yes, the abnormal distance number is deleted, and then it is judged whether the rightmost range distance number is an abnormal distance number, if yes, the deletion and judgment are continued, until the rightmost range distance number is not an abnormal distance number, and then the judgment is stopped; after the judgment is stopped, the maximum value of the distance segmentation range corresponding to the rightmost range distance number is acquired, which is marked as a screening distance threshold.

[0030] Further, judging whether the real-time detection distance is initial abnormal data based on the screening distance threshold includes the following sub-steps:

[0031] It is judged whether the real-time detection distance is less than or equal to the screening distance threshold, if yes, the real-time detection data is marked as initial abnormal data; if not, the real-time detection data is directly used to synchronously control the dexterous hand.

[0032] Further, constructing an adjacent fluctuation difference value based on the real-time detection data includes the following sub-steps:

[0033] The endpoints of the adjacent control line segments corresponding to the change of the real-time detection data are acquired, which are marked as adjacent endpoints;

[0034] Obtain the distance between the change endpoint and the adjacent endpoint before the change of the real-time detection data, and mark it as the influence distance;

[0035] Obtain the distance between the change endpoint and the adjacent endpoint when the real-time detection data changes, and mark it as the process distance;

[0036] Obtain the absolute value of the difference between the process distance and the influence distance when the real-time detection data changes, and mark it as the process fluctuation value;

[0037] Obtain the sum of the process fluctuation values, and mark it as the adjacent fluctuation difference value.

[0038] Further, obtaining the first fluctuation threshold and the second fluctuation threshold based on the first number of hand-shaking conditions comprises the following sub-steps:

[0039] Obtain the adjacent fluctuation difference value in the first number of hand-shaking conditions, and mark it as the historical fluctuation difference value;

[0040] Obtain the range of the historical fluctuation difference value, and represent the range of the historical fluctuation difference value as M1 to M2; evenly divide M1 to M2 into q2 equal intervals, and mark the interval as the difference value division range; the range length of each difference value division range is (M2-M1) ÷ q2; the minimum value and the maximum value of each difference value division range are M1+[(M2-M1) ÷ q2]×w2 and M1+[(M2-M1) ÷ q2]×(w2+1) respectively; wherein w2 is a positive integer from 0 to q2-1.

[0041] Count the number of historical fluctuation difference values in each difference value division range, and mark it as the difference value division number;

[0042] Calculate the difference value number threshold as E2=z2×(T2 ÷ q2); wherein E2 is the difference value number threshold; z2 is the difference value number proportion; T2 is the sum of all difference value division numbers;

[0043] Mark the difference value division numbers less than the difference value number threshold as the abnormal difference value number.

[0044] Further, obtaining the first fluctuation threshold and the second fluctuation threshold based on the first number of hand-shaking conditions further comprises the following sub-steps:

[0045] Sort the difference value division numbers from left to right in ascending order according to the minimum values of the corresponding difference value division ranges;

[0046] determining whether the leftmost difference value segmentation number is an abnormal difference value number, if not, directly stopping the determination, if yes, deleting the abnormal difference value number, and then continuing to determine whether the leftmost difference value segmentation number is an abnormal difference value number, if yes, continuing to delete and determine, until the leftmost difference value segmentation number is not an abnormal difference value number, and then stopping; after stopping, obtaining the minimum value of the difference value segmentation range corresponding to the leftmost difference value segmentation number, and marking it as the first fluctuation threshold value;

[0047] determining whether the rightmost difference value segmentation number is an abnormal difference value number, if not, directly stopping the determination, if yes, deleting the abnormal difference value number, and then continuing to determine whether the rightmost difference value segmentation number is an abnormal difference value number, if yes, continuing to delete and determine, until the rightmost difference value segmentation number is not an abnormal difference value number, and then stopping; after stopping, obtaining the maximum value of the difference value segmentation range corresponding to the rightmost difference value segmentation number, and marking it as the second fluctuation threshold value.

[0048] Further, judging the initial abnormal data as the final abnormal data based on the first fluctuation threshold value and the second fluctuation threshold value; and controlling the dexterous hand based on the real-time detection data and the final abnormal data includes the following sub-steps:

[0049] determining whether the adjacent fluctuation difference value is between the first fluctuation threshold value and the second fluctuation threshold value, if yes, regarding the initial abnormal data as the final abnormal data, if not, not regarding the initial abnormal data as the final abnormal data;

[0050] if the final abnormal data appears, the real-time detection data is not used for synchronous control of the dexterous hand, if the final abnormal data does not appear, the real-time detection data is used for synchronous control of the dexterous hand.

[0051] The present application has the following advantages: the present application constructs a real-time detection distance based on real-time detection data, obtains a screening distance threshold value based on a first number of hand shake conditions, judges whether the real-time detection distance is initial abnormal data based on the screening distance threshold value, constructs an adjacent fluctuation difference value based on the real-time detection data, obtains a first fluctuation threshold value and a second fluctuation threshold value based on the first number of hand shake conditions, judges the initial abnormal data as the final abnormal data based on the first fluctuation threshold value and the second fluctuation threshold value, and controls the dexterous hand based on the real-time detection data and the final abnormal data, which has the advantages of setting a suitable natural hand shake judgment method and threshold value setting, improving the accuracy of hand shake judgment, and increasing the stability of the dexterous hand.

[0052] The present application constructs a real-time detection distance and an adjacent fluctuation difference value, which has the advantages of quickly and accurately judging whether it is a natural hand shake, improving the accuracy of hand shake judgment, and increasing the stability of the dexterous hand. BRIEF DESCRIPTION OF DRAWINGS

[0053] Figure 1 Flow chart of steps of the method of the present application;

[0054] Figure 2 Schematic diagram of the process of detecting distance of the present application;

[0055] Figure 3 Schematic diagram of the influence of distance and process distance of the present application. DETAILED DESCRIPTION

[0056] The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative work fall within the scope of protection of the present application.

[0057] Embodiment 1, please refer to Figure 1 As shown in the figure, the present application provides a wireless transmission wearable glove and dexterous hand synchronous control method, comprising the following steps:

[0058] Step S1, installing a bending angle sensor on the wearable glove, marked as a real-time angle sensor; obtaining detection data based on the real-time angle sensor, marked as real-time detection data; step S1 comprises the following sub-steps:

[0059] Step S101, installing a real-time angle sensor at the joint of each finger on the wearable glove, when the data detected by the real-time angle sensor changes, then obtaining real-time detection data through the real-time angle sensor; further judging whether it is an involuntary hand tremor based on the angle change detected by the installed real-time angle sensor.

[0060] Step S2, constructing a real-time detection distance based on the real-time detection data; step S2 comprises the following sub-steps:

[0061] Step S201, establishing a plane rectangular coordinate system, marked as a two-dimensional projection coordinate system; obtaining a side view of the wearable glove, regarding each segment of the finger of the wearable glove as a line segment, marked as a contrast line segment; regarding the real-time detection data as the corresponding bending angle, drawing the side view of the form of the wearable glove in the two-dimensional projection coordinate system; constructing the contrast line segment for convenient data analysis;

[0062] Step S202, obtaining the end point of the contrast line segment corresponding to the change of the real-time detection data, marked as a change end point; the change end point is the end point of the fingertip, when the finger unconsciously trembles, the tremor amplitude of the fingertip of the finger is the largest, therefore, the change end point is constructed to facilitate the identification of the involuntary tremor of the finger;

[0063] Step S203, obtaining the change endpoint before the change of the real-time detection data, marked as the starting endpoint; the starting endpoint is the starting point when the finger moves;

[0064] Step S204, obtaining the change endpoint when the real-time detection data changes, marked as the process endpoint;

[0065] Step S205, obtaining the distance from the process endpoint to the starting endpoint, marked as the process detection distance; wherein the process detection distance is the amplitude of the finger tip when the finger is shaking;

[0066] Step S206, obtaining the maximum value of the process detection distance, marked as the real-time detection distance; the real-time detection distance can be the maximum amplitude of the finger movement within a short time of 1s; if the hand is unconsciously shaking, the shaking amplitude is small, and the real-time detection distance is also small, so the real-time detection distance can be used to judge whether the hand is shaking;

[0067] In practical application, please refer to Figure 2 , the process detection distance is drawn.

[0068] Step S3, obtaining the screening distance threshold based on the first number of hand shaking conditions; step S3 includes the following sub-steps:

[0069] Step S301, obtaining the real-time detection distance under the first number of hand shaking conditions, marked as the historical detection distance; the first number of ranges for obtaining the historical detection distance, i.e. the range distribution of hand shaking; therefore, the first number should not be too small, for example, the first data is 200;

[0070] Step S302, obtaining the range of the historical detection distance, representing the range of the historical detection distance as N1 to N2; dividing N1 to N2 into q1 equal intervals, marked as the distance segmentation range; the range length of each distance segmentation range is: (N2-N1) ÷ q1; the minimum value and the maximum value of each distance segmentation range are: N1+[(N2-N1) ÷ q1]×w1 and N1+[(N2-N1) ÷ q1]×(w1+1); wherein w1 is a positive integer from 0 to q1-1; dividing q1 distance segmentation ranges is to obtain the distribution of the historical detection distance, therefore, q1 should not be too small, for example, q1 is 10;

[0071] In practical application, the range of the historical detection distance is 2.2mm to 12.2mm; 2.2mm to 12.2mm is evenly divided into 10 distance segmentation ranges, which are: 2.2 to 3.2, 3.2 to 4.2,..., 11.2 to 12.2; the minimum value and the maximum value of each distance segmentation range, for example, the minimum value and the maximum value of the distance segmentation range when w1 is 0 are 2.2 and 3.2 respectively.

[0072] Step S303, count the number of historical detection distances in each distance segmentation range, marked as range distance number;

[0073] Step S304, calculate the distance number threshold value as: E1=z1x(T1÷q1); wherein E1 is the distance number threshold value; z1 is the distance number proportion; T1 is the sum of all range distance numbers; the distance number threshold value is to obtain a smaller range distance number, therefore z1 is set smaller, for example, z1 is 0.1;

[0074] Step S305, mark the range distance number smaller than the distance number threshold value as an abnormal distance number;

[0075] Step S306, sort the range distance numbers in ascending order from left to right according to the minimum value of the corresponding distance segmentation range;

[0076] Step S307, judge whether the rightmost range distance number is an abnormal distance number, if not, stop judging directly; if yes, delete this abnormal distance number, and then continue to judge whether the rightmost range distance number is an abnormal distance number, if yes, continue to delete and judge, until the rightmost range distance number is not an abnormal distance number, then stop; after stopping, obtain the maximum value of the distance segmentation range corresponding to the rightmost range distance number, marked as the screening distance threshold value; the screening distance threshold value is to exclude individual too large historical detection distances, and then obtain an accurate historical detection distance range; the accurate historical detection distance range is the range of the historical detection distance of hand jitter;

[0077] In actual application, the sum of all range distance numbers is 200, the distance number threshold value is calculated as: E1=0.1x(200÷10)=2; mark the range distance number smaller than 2 as an abnormal distance number; sort the range distance numbers in ascending order from left to right according to the minimum value of the corresponding distance segmentation range as: 2, 5,..., 3, 1; after deleting the abnormal distance number, the arrangement order is: 2, 5,..., 3; the maximum value of the distance segmentation range corresponding to the rightmost abnormal distance number 3 is 11.2, so the screening distance threshold value is 11.2.

[0078] Step S4, judge whether the real-time detection distance is initial abnormal data based on the screening distance threshold value; step S4 includes the following sub-steps:

[0079] Step S401, determine whether the real-time detection distance is less than or equal to the screening distance threshold, if yes, mark the real-time detection data as initial abnormal data; if not, directly use the real-time detection data to control the dexterous hand in synchronization; because the involuntary shaking of the hand is generally small in amplitude, that is, the screening distance threshold determines whether it is small shaking, if yes, further determination is needed, if not, directly use the real-time detection data to control the dexterous hand in synchronization;

[0080] In actual application, for example, the real-time detection distance 21.2 is greater than 11.2, which indicates that it is not hand shaking, and the real-time detection data is directly used to control the dexterous hand in synchronization.

[0081] Step S5, construct the adjacent fluctuation difference value based on the real-time detection data; step S5 includes the following sub-steps:

[0082] Step S501, obtain the end points of the adjacent control line segments corresponding to the change of the real-time detection data, and mark them as adjacent end points; for example, the adjacent control line segments of the middle finger are the index finger;

[0083] Step S502, obtain the distance between the change end point before the change of the real-time detection data and the adjacent end point, and mark it as the influence distance;

[0084] Step S503, obtain the distance between the change end point when the real-time detection data changes and the adjacent end point, and mark it as the process distance;

[0085] Step S503, obtain the absolute value of the difference between the process distance and the influence distance when the real-time detection data changes, and mark it as the process fluctuation value; because the shaking of a certain finger is isolated, and each finger is linked when using the hand, the process fluctuation value can be set to further determine whether it is the involuntary shaking of the finger;

[0086] Step S504, obtain the sum of the process fluctuation values, and mark it as the adjacent fluctuation difference value; it can be the fluctuation value between all fingers within a short time of 1s; here, the collection times can be set to 6 times within 1s for convenience; because the shaking of a certain finger is isolated, and each finger is linked when using the hand, the adjacent fluctuation difference value will be different;

[0087] In actual application, please refer to Figure 3 The schematic diagram of the influence distance and the process distance is shown.

[0088] Step S6, obtain the first fluctuation threshold and the second fluctuation threshold based on the first number of hand shaking conditions; step S6 includes the following sub-steps:

[0089] Step S601, obtain the adjacent fluctuation difference value under the first number of hand shaking conditions, and mark it as the historical fluctuation difference value; the first number is 200;

[0090] Step S602, the range of historical fluctuation difference value is obtained, and the range of historical fluctuation difference value is represented as M1 to M2; M1 to M2 is evenly divided into q2 equal intervals, and the range is marked as a difference value segmentation range; the range length of each difference value segmentation range is (M2-M1) ÷ q2; the minimum value and the maximum value of each difference value segmentation range are M1+[(M2-M1) ÷ q2]×w2 and M1+[(M2-M1) ÷ q2]×(w2+1) respectively; wherein w2 is a positive integer from 0 to q2-1; q2 difference value segmentation ranges are obtained in order to observe the range of historical fluctuation difference value, and q2 is not too small, for example, q2 is 10;

[0091] In practical application, the range of historical fluctuation difference value is 6.3 to 36.3; 6.3 to 36.3 is evenly divided into 10 difference value segmentation ranges, which are 6.3 to 9.3, 9.3 to 12.3,..., 33.3 to 36.3; for example, when w2 is 0, the minimum value and the maximum value of the difference value segmentation range are 6.3 and 9.3 respectively.

[0092] Step S603, the number of historical fluctuation difference values in each difference value segmentation range is counted, and the number is marked as a difference value segmentation number;

[0093] Step S604, the difference value number threshold is calculated as E2=z2×(T2 ÷ q2); wherein E2 is the difference value number threshold; z2 is the difference value number proportion; T2 is the sum of all difference value segmentation numbers; the difference value number threshold filters out smaller difference value segmentation numbers, and therefore z2 is not too large, for example, z2 is 0.1;

[0094] Step S605, the difference value segmentation number smaller than the difference value number threshold is marked as an abnormal difference value number;

[0095] Step S606, the difference value segmentation numbers are sorted from left to right according to the minimum value of the corresponding difference value segmentation range from small to large;

[0096] Step S607, it is judged whether the leftmost difference value segmentation number is an abnormal difference value number, if not, the judgment is directly stopped; if yes, the abnormal difference value number is deleted, and then it is continued to judge whether the leftmost difference value segmentation number is an abnormal difference value number, if yes, the deletion and judgment are continued, and the judgment is stopped until the leftmost difference value segmentation number is not an abnormal difference value number; after the judgment is stopped, the minimum value of the difference value segmentation range corresponding to the leftmost difference value segmentation number is obtained, and the minimum value is marked as a first fluctuation threshold; the first fluctuation threshold is a deletion of individual smaller historical fluctuation difference value, and then an accurate distribution range of historical fluctuation difference value is obtained;

[0097] Step S608, it is judged whether the difference value segmentation number on the right side is an abnormal difference value number, if not, it is directly stopped judging, if yes, the abnormal difference value number is deleted, then it is continued to judge whether the difference value segmentation number on the right side is an abnormal difference value number, if yes, it is continued to delete and judge, until the difference value segmentation number on the right side is not an abnormal difference value number, then it is stopped; after stopping, the maximum value of the difference value segmentation range corresponding to the difference value segmentation number on the right side is obtained, which is marked as a second fluctuation threshold; the second fluctuation threshold is to delete individual larger historical fluctuation difference values, and then the distribution range of accurate historical fluctuation difference values is obtained; the distribution range of historical fluctuation difference values is the data distribution range of hand jitter;

[0098] In actual application, the sum of all difference value segmentation numbers is 200, then the difference value number threshold is calculated as: E2=0.1×(200÷10)=2; the difference value segmentation number less than 2 is marked as an abnormal difference value number; the difference value segmentation numbers are sorted from left to right according to the minimum value of the corresponding difference value segmentation range from small to large as: 1, 3,..., 4, 1; the sorting of the abnormal difference value numbers is: 3,..., 4; the minimum value of the difference value segmentation range corresponding to the leftmost difference value segmentation number 3 is 9.3, then the first fluctuation threshold is 9.3; the maximum value of the difference value segmentation range corresponding to the rightmost difference value segmentation number 4 is 33.3, then the second fluctuation threshold is 33.3.

[0099] Step S7, the initial abnormal data is judged as the final abnormal data based on the first fluctuation threshold and the second fluctuation threshold; the control of the dexterous hand is performed based on the real-time detection data and the final abnormal data; step S7 includes the following sub-steps:

[0100] Step S701, it is judged whether the adjacent fluctuation difference value is between the first fluctuation threshold and the second fluctuation threshold, if yes, the initial abnormal data is recognized as the final abnormal data; if not, the initial abnormal data is not recognized as the final abnormal data; because in a certain finger jitter is isolated, and each finger is linked when using the hand, therefore, if the adjacent fluctuation difference value is too small, or too large, it is possible that the finger is actively moved, otherwise, it can be further judged as the finger is unconsciously jittered;

[0101] Step S702, if the final abnormal data appears, the real-time detection data is not used to perform synchronous control on the dexterous hand; if the final abnormal data does not appear, the real-time detection data is used to perform synchronous control on the dexterous hand; the final abnormal data is that both conditions are met, that is, it is determined that the hand is unconsciously jittered, if the final abnormal data does not appear, the real-time detection data is used to perform synchronous control on the dexterous hand;

[0102] In actual application, for example, the adjacent fluctuation difference is 2.1, which is not between the first fluctuation threshold 9.3 and the second fluctuation threshold 33.3, and the initial abnormal data is not recognized as the final abnormal data; and the real-time detection data is used to control the dexterous hand synchronously.

[0103] In embodiment 2, the application further provides an electronic device, which can include a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory can communicate with each other through the communication bus. The memory stores computer readable instructions, and the processor can call the instructions in the memory. When the computer readable instructions are executed by the processor, the steps in the wireless transmission wearable glove and dexterous hand synchronous control method are run to realize the following functions: installing a bending angle sensor on the wearable glove, which is marked as a real-time angle sensor; obtaining detection data based on the real-time angle sensor, which is marked as real-time detection data; constructing a real-time detection distance based on the real-time detection data; obtaining a screening distance threshold based on the first number of hand shake conditions; judging whether the real-time detection distance is initial abnormal data based on the screening distance threshold; constructing an adjacent fluctuation difference based on the real-time detection data; obtaining a first fluctuation threshold and a second fluctuation threshold based on the first number of hand shake conditions; judging whether the initial abnormal data is final abnormal data based on the first fluctuation threshold and the second fluctuation threshold; and controlling the dexterous hand based on the real-time detection data and the final abnormal data.

[0104] In addition, the logical instructions in the memory described above can be implemented in the form of a software functional unit and sold or used as an independent product, which can be stored in a computer readable storage medium. Based on this understanding, the technical solutions of the application essentially or the parts that contribute to the prior art or parts of the technical solutions can be embodied in the form of a software product, which is stored in a storage medium and includes a plurality of instructions for causing a computer device (which can be a personal computer, a server or a network device, etc.) to execute all or part of the steps of the method described in the embodiments of the application. The aforementioned storage medium includes a U disk, a mobile hard disk, a read-only memory (ROM, Read-Only Memory), a random access memory (RAM, Random Access Memory), a magnetic disk or an optical disk and various program code storage media.

[0105] In embodiment 3, the application further provides a computer program product, which comprises a computer program stored on a computer readable storage medium, and the computer program comprises program instructions, when the program instructions are executed by a computer, the computer can execute a wireless transmission wearable glove and dexterous hand synchronous control method provided by each method, the method comprises: installing a bending angle sensor on the wearable glove, marked as a real-time angle sensor; obtaining detection data based on the real-time angle sensor, marked as real-time detection data; constructing a real-time detection distance based on the real-time detection data; obtaining a screening distance threshold based on the first number of hand shaking conditions; determining whether the real-time detection distance is initial abnormal data based on the screening distance threshold; constructing an adjacent fluctuation difference value based on the real-time detection data; obtaining a first fluctuation threshold and a second fluctuation threshold based on the first number of hand shaking conditions; determining that the initial abnormal data is the final abnormal data based on the first fluctuation threshold and the second fluctuation threshold; and controlling the dexterous hand based on the real-time detection data and the final abnormal data.

[0106] In embodiment 4, the application further provides a computer readable storage medium, and the application provides a storage medium, which stores a computer program, when the computer program is executed by a processor, the steps of the wireless transmission wearable glove and dexterous hand synchronous control method are run to realize the following functions: installing a bending angle sensor on the wearable glove, marked as a real-time angle sensor; obtaining detection data based on the real-time angle sensor, marked as real-time detection data; constructing a real-time detection distance based on the real-time detection data; obtaining a screening distance threshold based on the first number of hand shaking conditions; determining whether the real-time detection distance is initial abnormal data based on the screening distance threshold; constructing an adjacent fluctuation difference value based on the real-time detection data; obtaining a first fluctuation threshold and a second fluctuation threshold based on the first number of hand shaking conditions; determining that the initial abnormal data is the final abnormal data based on the first fluctuation threshold and the second fluctuation threshold; and controlling the dexterous hand based on the real-time detection data and the final abnormal data.

[0107] Through the description of the above embodiments, the embodiments of the application can be provided as a method, a system or a computer program product. Based on such understanding, the above technical solutions can be embodied in the form of a software product, which can be stored in a computer readable storage medium, such as ROM / RAM, a magnetic disk, an optical disk, etc., and includes a plurality of instructions to make a computer device (which can be a personal computer, a server, or a network device, etc.) execute the method described in each embodiment or some parts of the embodiment.

[0108] In the embodiments of the present application, it should be understood that the disclosed system or method can be implemented in other ways. The embodiments described above are only illustrative, for example, the division of modules or units is only a logical function division, and other division manners can be used in actual implementation, for example, a plurality of modules or units can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the coupling or direct coupling or communication connection between the displayed or discussed each other can be through some communication interface, the indirect coupling or communication connection between the system, the module and the unit can be electrical, mechanical or other forms.

[0109] Finally, it should be noted that: the above embodiments are only used to illustrate the technical solutions of the present application, and not to limit them; although the present application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that: it can still modify the technical solutions recorded in the foregoing embodiments, or make equivalent replacement for part of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A wireless transmission wearable glove and dexterous hand synchronous control method, characterized in that, The method comprises the following steps: installing a bending angle sensor on a wearable glove, marked as a real-time angle sensor; obtaining detection data based on the real-time angle sensor, marked as real-time detection data; constructing a real-time detection distance based on the real-time detection data; obtaining a screening distance threshold based on the first number of hand shake conditions; judging whether the real-time detection distance is initial abnormal data based on the screening distance threshold; constructing an adjacent fluctuation difference value based on the real-time detection data; obtaining a first fluctuation threshold and a second fluctuation threshold based on the first number of hand shake conditions; judging whether the initial abnormal data is final abnormal data based on the first fluctuation threshold and the second fluctuation threshold; controlling the dexterous hand based on the real-time detection data and the final abnormal data.

2. The wireless transmission wearable glove and dexterous hand synchronous control method of claim 1, wherein, installing a bending angle sensor on a wearable glove, marked as a real-time angle sensor; obtaining detection data based on the real-time angle sensor, marked as real-time detection data comprises the following sub-steps: installing a real-time angle sensor at the joint of each finger on the wearable glove; when the data detected by the real-time angle sensor changes, then obtaining real-time detection data through the real-time angle sensor.

3. The wireless transmission wearable glove and dexterous hand synchronous control method of claim 2, wherein, constructing a real-time detection distance based on the real-time detection data comprises the following sub-steps: establishing a plane rectangular coordinate system, marked as a two-dimensional projection coordinate system; obtaining a side view of the wearable glove, regarding each segment of the fingers of the wearable glove as a line segment, marked as a contrast line segment; regarding the real-time detection data as a corresponding bending angle, and drawing the side view of the form of the wearable glove in the two-dimensional projection coordinate system; obtaining the end point of the contrast line segment corresponding to the change in the real-time detection data, marked as a change end point; obtaining the change end point before the change in the real-time detection data, marked as a starting end point; obtaining the change end point when the real-time detection data changes, marked as a process end point; obtaining the distance from the process end point to the starting end point, marked as a process detection distance; obtaining the maximum value of the process detection distance, marked as a real-time detection distance.

4. The wireless transmission wearable glove and dexterous hand synchronous control method of claim 3, wherein, obtaining a screening distance threshold based on the first number of hand shake conditions comprises the following sub-steps: obtaining a real-time detection distance under the first number of hand shake conditions, marked as a historical detection distance; obtaining the range of the historical detection distance, representing the range of the historical detection distance as N1 to N2; evenly dividing N1 to N2 into q1 equal intervals, marked as distance segmentation ranges; the range length of each distance segmentation range is (N2-N1) ÷ q1; the minimum value and the maximum value of each distance segmentation range are N1+[(N2-N1) ÷ q1]×w1 and N1+[(N2-N1) ÷ q1]×(w1+1) respectively; wherein w1 is a positive integer from 0 to q1-1; counting the number of historical detection distances in each distance segmentation range, marked as range distance number; calculating the distance number threshold as E1=z1×(T1 ÷ q1); wherein E1 is the distance number threshold; z1 is the distance number proportion; T1 is the total sum of all range distance numbers; marking the range distance number less than the distance number threshold as abnormal distance number.

5. The wireless transmission wearable glove and dexterous hand synchronous control method of claim 4, wherein, obtaining a screening distance threshold based on the first number of hand shake conditions further comprises the following sub-steps: Sort the range distance numbers from left to right according to the minimum value of the corresponding distance segmentation range from small to large; Determine whether the range distance number on the right side is an abnormal distance number. If not, stop determining directly. If yes, delete the abnormal distance number, and then continue to determine whether the range distance number on the right side is an abnormal distance number. If yes, continue to delete and determine until the range distance number on the right side is not an abnormal distance number, and then stop. After stopping, obtain the maximum value of the distance segmentation range corresponding to the range distance number on the right side, and mark it as a screening distance threshold.

6. The wireless transmission wearable glove and dexterous hand synchronous control method of claim 5, wherein, The method for determining whether the real-time detection distance is initial abnormal data based on the screening distance threshold comprises the following sub-steps: Determine whether the real-time detection distance is less than or equal to the screening distance threshold. If yes, mark the real-time detection data as initial abnormal data. If not, directly use the real-time detection data to control the dexterous hand synchronously.

7. The wireless transmission wearable glove and dexterous hand synchronous control method of claim 6, wherein, The method for constructing an adjacent fluctuation difference value based on the real-time detection data comprises the following sub-steps: Obtain the end points of the adjacent control line segment corresponding to the change of the real-time detection data, and mark them as adjacent end points. Obtain the change end point before the change of the real-time detection data, that is, the distance between the starting end point and the adjacent end point, and mark it as an influence distance. Obtain the change end point when the real-time detection data changes, that is, the distance between the process end point and the adjacent end point, and mark it as a process distance. Obtain the absolute value of the difference between the process distance and the influence distance when the real-time detection data changes, and mark it as a process fluctuation value. Obtain the sum of the process fluctuation value, and mark it as an adjacent fluctuation difference value.

8. The wireless transmission wearable glove and dexterous hand synchronous control method of claim 7, wherein, The method for obtaining a first fluctuation threshold and a second fluctuation threshold based on the first number of hand jitter conditions comprises the following sub-steps: Obtain the adjacent fluctuation difference value under the first number of hand jitter conditions, and mark it as a historical fluctuation difference value. Obtain the range of the historical fluctuation difference value, and express the range of the historical fluctuation difference value as M1 to M2. Divide M1 to M2 into q2 equal intervals, and mark them as difference segmentation ranges. The range length of each difference segmentation range is (M2-M1) ÷ q2. The minimum value and the maximum value of each difference segmentation range are M1+[(M2-M1) ÷ q2]×w2 and M1+[(M2-M1) ÷ q2]×(w2+1) respectively, where w2 is a positive integer from 0 to q2-1. Statistically obtain the number of historical fluctuation difference values in each difference segmentation range, and mark it as a difference segmentation number. Calculate the difference number threshold as E2=z2×(T2 ÷ q2), where E2 is the difference number threshold, z2 is the difference number proportion, and T2 is the sum of all difference segmentation numbers. Mark the difference segmentation numbers less than the difference number threshold as abnormal difference numbers. The method for obtaining a first fluctuation threshold and a second fluctuation threshold based on the first number of hand jitter conditions further comprises the following sub-steps:

9. The wireless transmission wearable glove and dexterous hand synchronous control method of claim 8, wherein, Sort the difference segmentation numbers from left to right according to the minimum value of the corresponding difference segmentation range from small to large; ​ determining whether the leftmost difference value segmentation number is an abnormal difference value number, if not, directly stopping the determination; if yes, deleting the abnormal difference value number, and then continuing to determine whether the leftmost difference value segmentation number is an abnormal difference value number, if yes, continuing to delete and determine, until the leftmost difference value segmentation number is not an abnormal difference value number to stop; after stopping, obtaining the minimum value of the difference value segmentation range corresponding to the leftmost difference value segmentation number, and marking it as the first fluctuation threshold; determining whether the rightmost difference value segmentation number is an abnormal difference value number, if not, directly stopping the determination; if yes, deleting the abnormal difference value number, and then continuing to determine whether the rightmost difference value segmentation number is an abnormal difference value number, if yes, continuing to delete and determine, until the rightmost difference value segmentation number is not an abnormal difference value number to stop; after stopping, obtaining the maximum value of the difference value segmentation range corresponding to the rightmost difference value segmentation number, and marking it as the second fluctuation threshold.

10. The wireless transmission wearable glove and dexterous hand synchronous control method of claim 9, wherein, determining whether the initial abnormal data is the final abnormal data based on the first fluctuation threshold and the second fluctuation threshold; controlling the dexterous hand based on the real-time detection data and the final abnormal data includes the following sub-steps: determining whether the adjacent fluctuation difference value is between the first fluctuation threshold and the second fluctuation threshold, if yes, regarding the initial abnormal data as the final abnormal data; if not, regarding the initial abnormal data as not the final abnormal data; if the final abnormal data appears, the real-time detection data is not used for synchronous control of the dexterous hand; if the final abnormal data does not appear, the real-time detection data is used for synchronous control of the dexterous hand.

Images