Grip force measurement method using robotic hand, robotic hand, and storage medium

Abstract

Embodiments of the present application relate to a hand grip measurement method using a robot dexterous hand, a dexterous hand and a storage medium. The method comprises: in response to detecting that the dexterous hand makes a handshake with a target object, collecting hand grip distribution data of the target object via a flexible electronic skin; judging whether the handshake posture of the target object is correct based on the hand grip distribution data; in response to determining that the handshake posture of the target object is correct, collecting real-time hand grip numerical value of the target object via a pressure sensor and collecting real-time hand grip distribution data of the target object via the flexible electronic skin; and evaluating the handshake state of the target object and the strength state of the hand muscles based on the real-time hand grip numerical value and / or the real-time hand grip distribution data of the target object. Thus, the hand grip distribution and change of the measured person can be accurately perceived, and the handshake posture can be distinguished.

Description

Technical Field

[0001] Embodiments of the present invention relate to the field of robotics, and more specifically to a method for measuring grip strength using a robotic dexterous hand, the dexterous hand, a computing device, and a storage medium. Background Technology

[0002] As the population ages, grip strength, a key indicator for assessing motor function, sarcopenia, rehabilitation outcomes, and physical frailty in the elderly, is crucial for clinical diagnosis and health management if it can be measured consistently, accurately, and conveniently. Furthermore, grip strength measurement is also a critical indicator for hospital patients, such as those recovering from stroke.

[0003] Traditional grip strength measurement techniques generally employ spring-type or electronic grip dynamometers, which have several drawbacks: For example, the initial resistance is high, making it difficult for elderly individuals with hand weakness, arthritis, or hemiplegia to overcome the initial resistance and complete effective measurements; furthermore, these grip dynamometers only output a single peak grip strength value and cannot automatically collect multi-dimensional data such as grip strength changes and hand pressure distribution, resulting in insufficient data dimensions for medical grip strength assessment; and finally, they require on-site guidance from professionals to determine grip posture, making home-based self-testing difficult. Moreover, traditional robotic hands are mostly rigid structures lacking grip strength measurement and grip posture recognition functions, making them unsuitable for grip strength measurement.

[0004] In summary, traditional grip strength measurement methods and robotic hands have the following shortcomings: they cannot accurately sense the distribution and changes in grip strength in the subject's hand, and they do not support handshake posture identification. They cannot sense minute forces, such as a few tenths of a gram, and therefore cannot provide accurate assessment for some patients in the early stages of rehabilitation. Summary of the Invention

[0005] To address the aforementioned problems, this invention provides a method for measuring grip strength using a robot's dexterous hand, the dexterous hand itself, a computing device, and a storage medium. This method can accurately sense the pressure distribution and changes in the hand of the person being tested and supports handshake posture recognition.

[0006] According to a first aspect of the present invention, a method for measuring grip force using a robotic dexterous hand is provided. The dexterous hand is equipped with a flexible electronic skin and one or more pressure sensors. The flexible electronic skin covers the dexterous hand. The method includes: in response to detecting a handshake between the dexterous hand and a target object, acquiring grip force distribution data of the target object via the flexible electronic skin; determining whether the handshake posture of the target object is correct based on the grip force distribution data; in response to determining that the handshake posture of the target object is correct, acquiring real-time grip force values ​​of the target object via the pressure sensors and acquiring real-time grip force distribution data of the target object via the flexible electronic skin; and evaluating the handshake state and hand muscle strength state of the target object based on the real-time grip force values ​​and / or real-time grip force distribution data of the target object.

[0007] In some embodiments, determining whether the handshake posture of the target object is correct based on grip force distribution data includes: determining the contact state between the target object and the web of the dexterous hand, and determining the contact area between the target object and the dexterous hand based on the grip force distribution data; and determining that the handshake posture of the target object is correct in response to determining that the web of the target object and the dexterous hand are in contact, and that the contact area between the target object and the dexterous hand is greater than or equal to a predetermined contact area threshold.

[0008] In some embodiments, the grip force measurement method for utilizing the dexterous hand of a robot further includes: in response to determining that the target object has a handshake posture error, generating handshake posture adjustment information about the target object based on grip force distribution data, so that the target object can adjust its handshake posture.

[0009] In some embodiments, assessing the handshake state and hand muscle strength state of the target object based on the target object's real-time grip strength value and / or real-time grip strength distribution data further includes: generating a time-series change curve of the target object's grip strength based on the target object's real-time grip strength value, so as to determine the target object's peak grip strength and / or average grip strength; and assessing the target object's hand muscle strength state based on the target object's age, gender, and the target object's peak grip strength and / or average grip strength.

[0010] In some embodiments, the flexible electronic skin includes a pressure sensor array comprising multiple sensing units. Assessing the handshake state and hand muscle strength state of the target object based on real-time grip force values ​​and / or real-time grip force distribution data further includes: calculating the pressure value of each of the multiple sensing units for electrical signals from the sensing units based on a predetermined calibration relationship to obtain real-time grip force distribution data of the target object; and generating a grip force distribution heatmap of the target object based on the real-time grip force distribution data, calculating the contact area between the target object and the dexterous hand during grip force measurement, the maximum pressure point, and the pressure change gradient, in order to identify the handshake state of the target object, which includes at least: normal, weak, and abnormal force exertion.

[0011] In some embodiments, the method for measuring grip strength using a robot's dexterous hand further includes: storing grip strength measurement data for a predetermined duration for a target object; uploading the grip strength measurement data for the target object to a health monitoring platform and / or the main control system of a robot equipped with a dexterous hand; and triggering an early warning message and / or feeding back an early warning message to the robot's control system in response to determining that the target object's handshake state and / or the strength state of its hand muscles meet predetermined conditions.

[0012] According to a second aspect of the invention, a dexterous hand is provided, configured in a robot, the dexterous hand being controlled by any of the methods of the first aspect for measuring grip force of a robot dexterous hand. The dexterous hand includes: a bionic hand body including a palm and multiple fingers, each finger including multiple movable joints; a flexible electronic skin including a flexible base layer, a pressure sensor array, and an encapsulation layer, the flexible electronic skin covering the dexterous hand and configured to sense the handshake posture and grip force distribution of a target object; one or more pressure sensors configured between the fingers of the dexterous hand for detecting grip force values ​​between adjacent fingers; a data acquisition module configured to acquire grip force distribution data about the target object via the flexible electronic skin; and a data processing module configured to process the grip force distribution data to confirm the handshake state and hand muscle strength state of the target object.

[0013] In some embodiments, the pressure sensor is configured with a rigid support, and when the pressure sensor is positioned on a finger, it protrudes from the flexible electronic skin surface of the dexterous hand.

[0014] In some embodiments, the dexterous hand further includes: a communication module configured to communicate with the robot's main control system; a storage module configured to store grip force distribution data of the target object within a predetermined time period; and an early warning module configured to trigger an early warning message and / or feed back an early warning message to the robot's control system in response to determining that the handshake state and / or the strength state of the hand muscles of the target object meet predetermined conditions.

[0015] In some embodiments, the flexible substrate layer includes: a biomimetic fingertip microstructure having a surface texture that mimics the skin texture of a human hand; and the surface of the flexible substrate layer being treated with a skin-friendly modification and an antibacterial treatment.

[0016] In some embodiments, the flexible substrate layer is also configured to adapt to the bending of the palm and the flexion and extension of the fingers of a dexterous hand.

[0017] In some embodiments, the pressure sensor array is a piezoresistive flexible array sensor, including a predetermined number of sensing units to form a distributed tactile sensing network covering multiple areas of a dexterous hand.

[0018] In some embodiments, the multiple regions of a dexterous hand include at least: the fingertips, the palmar surface, the thenar eminence, and the web between the thumb and index finger.

[0019] In some embodiments, the pressure sensor array is further configured to: employ a matrix scanning wiring method so that the row and column lines of the pressure sensor array are interleaved; and employ a flexible conductive material for wiring the pressure sensor array.

[0020] According to a third aspect of the invention, a computing device is provided, the computing device comprising: at least one processing unit; at least one memory coupled to the at least one processing unit and storing instructions for execution by the at least one processing unit, the instructions, when executed by the at least one processing unit, causing the device to perform the steps of the method according to the first aspect.

[0021] According to a fourth aspect of the present invention, a computer-readable storage medium is provided, on which a computer program is stored, which, when executed by a machine, implements the method according to the first aspect.

[0022] As described above, the shortcomings of traditional grip strength measurement methods for dexterous hands are that they cannot accurately perceive the pressure distribution and changes in the subject's hand and do not support grip posture identification.

[0023] To at least partially address one or more of the aforementioned problems and other potential issues, exemplary embodiments of the present invention propose a dexterous hand and a grip force measurement method using a robotic dexterous hand. The dexterous hand provided by the present invention is equipped with a flexible electronic skin and one or more pressure sensors. The flexible electronic skin covers the dexterous hand. The grip force measurement method using the robotic dexterous hand includes: detecting a handshake between the dexterous hand and a target object; collecting grip force distribution data of the target object via the flexible electronic skin; determining whether the handshake posture of the target object is correct based on the grip force distribution data; and, in response to determining that the handshake posture of the target object is correct, collecting real-time grip force values ​​of the target object via pressure sensors and real-time grip force distribution data of the target object via the flexible electronic skin. Thus, the dexterous hand collects grip force distribution data and determines the correctness of the handshake posture through the flexible electronic skin, supporting handshake posture discrimination. Furthermore, under the premise of correct posture, dynamic grip force distribution data is collected, thereby accurately sensing the pressure distribution and changes in the hand of the person being tested, ensuring measurement standardization and improving the accuracy of grip force measurement.

[0024] Simultaneously, based on the target object's real-time grip strength value and / or real-time grip strength distribution data, the target object's handshake state and hand muscle strength state can be assessed. Thus, by combining the target object's real-time grip strength value and grip strength distribution data, a comprehensive and objective assessment of the target object's handshake state and hand muscle strength state can be achieved, providing a reliable basis for the target object's muscle strength assessment and health screening.

[0025] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of the present invention, nor is it intended to limit the scope of the invention. Other features of the invention will become readily apparent from the following description. Attached Figure Description

[0026] The above and other features, advantages, and aspects of the various embodiments of the present invention will become more apparent from the accompanying drawings and the following detailed description. In the drawings, the same or similar reference numerals denote the same or similar elements.

[0027] Figure 1 A schematic diagram of a dexterous hand for implementing a grip strength measurement method using a robotic dexterous hand according to an embodiment of the present invention is shown.

[0028] Figure 2 A schematic diagram of the data processing module of the dexterous hand according to an embodiment of the present invention is shown.

[0029] Figure 3 A flowchart of a grip strength measurement method using a robotic dexterous hand according to an embodiment of the present invention is shown.

[0030] Figure 4A flowchart illustrating a method for acquiring real-time grip force distribution data of a target object according to an embodiment of the present invention is shown.

[0031] Figure 5 A flowchart of a method for processing grip strength measurement data of a target object according to an embodiment of the present invention is shown.

[0032] Figure 6 A block diagram of an electronic device according to an embodiment of the present invention is shown. Detailed Implementation

[0033] The following description, in conjunction with the accompanying drawings, illustrates exemplary embodiments of the present invention, including various details to aid understanding. These details should be considered merely exemplary. Therefore, those skilled in the art will recognize that various changes and modifications can be made to the embodiments described herein without departing from the scope and spirit of the invention. Similarly, for clarity and brevity, descriptions of well-known functions and structures are omitted in the following description.

[0034] The term "comprising" and its variations as used herein signify open inclusion, i.e., "including but not limited to". Unless otherwise stated, the term "or" means "and / or". The term "based on" means "at least partially based on". The terms "one example embodiment" and "one embodiment" mean "at least one example embodiment". The term "another embodiment" means "at least one additional embodiment". The terms "first", "second", etc., may refer to different or the same objects. Other explicit and implicit definitions may also be included below.

[0035] Figure 1 A schematic diagram of a dexterous hand 100 for implementing a grip strength measurement method utilizing a robotic dexterous hand according to an embodiment of the present invention is shown. Figure 1 As shown, the dexterous hand 100 includes a bionic hand body 110, flexible electronic skin (not shown in the figure), the flexible electronic skin covering the bionic hand body 110, and one or more pressure sensors (such as...). Figure 1 The pressure sensor 150 is illustrated. The dexterous hand 100 can be configured on the robot.

[0036] The bionic hand 110 includes a palm and multiple fingers, each finger having multiple movable joints. Figure 1 The diagram also shows the structure of the bionic hand 110, with the red circled part representing multiple movable joints.

[0037] The flexible electronic skin includes a flexible substrate, a pressure sensor array, and an encapsulation layer. The flexible electronic skin covers a dexterous hand and is configured to sense the handshake posture and grip force distribution of a target object.

[0038] In some embodiments, the flexible substrate layer includes a biomimetic fingertip microstructure, the surface of which is provided with a texture that mimics the skin of a human hand. Thus, through the biomimetic fingertip microstructure and the simulated human skin texture, the contact stability with the target object's hand skin can be improved, slippage reduced, and the foreign body sensation during contact decreased. For example, if the target object is an elderly person, it can be adapted to the characteristics of elderly people's sensitive skin and easily dry hands.

[0039] In some embodiments, the surface of the flexible substrate layer is treated with a skin-friendly modification. This increases comfort upon skin contact, avoids skin damage to the target object due to friction, and is suitable for the delicate physiological characteristics of the target object's (e.g., the elderly) hands.

[0040] Regarding the encapsulation layer, its surface undergoes antibacterial treatment, such as using a medical-grade antibacterial coating, to inhibit bacterial growth. This allows it to be adapted to the sensitive and easily infected skin characteristics of target groups (such as the elderly), enabling direct contact with the skin of target groups (such as the elderly) and supporting gentle disinfection, thus meeting the hygiene requirements of elderly care settings.

[0041] In some embodiments, the flexible substrate is also configured to adapt to the flexion and extension of the palm and fingers of a dexterous hand, and is made of a self-healing material. Thus, the flexible substrate possesses excellent stretchability, bendability, tear resistance, and self-healing properties, perfectly adapting to the movement trajectories of finger flexion and extension and palm bending of a dexterous hand, improving long-term reliability and reducing maintenance costs.

[0042] In some embodiments, the flexible electronic skin is integrally formed with the curved surfaces of the fingers and palm of the dexterous hand 100 through a molding / bonding process, thereby achieving a tight fit without loosening, without affecting the joint movement and motion precision of the dexterous hand, and can accurately adapt to the handshake posture of the target object.

[0043] One or more pressure sensors are configured between the fingers of a dexterous hand to detect the grip force between adjacent fingers; and the pressure sensors are configured with rigid supports (e.g., pressure sensor 150 is configured with rigid support 120), protruding from the flexible electronic skin surface of the dexterous hand when configured on the fingers. Figure 1 The pressure sensor 150 is positioned between the index and middle fingers of the dexterous hand 100. Alternatively, the pressure sensor can also be positioned between other fingers, such as the middle and ring fingers.

[0044] In some embodiments, the pressure sensor array is a piezoresistive flexible array sensor, including a predetermined number of sensing units to form a distributed tactile sensing network covering multiple areas of a dexterous hand. For example, the pressure sensor array may consist of N rows × M columns of sensing units to form a high-density distributed tactile sensing network, and may be optimized for the grip strength range of a target object (e.g., an elderly person) to avoid insufficient accuracy due to excessive measurement range.

[0045] For example, by adjusting the grip strength range of the pressure sensor array, the initial resistance to measurement can be made much lower than that of conventional grip strength meters (such as spring-type grip strength meters). Even a small grip force can trigger the Dexterous Hand 100 to measure grip strength, making it suitable for target individuals with weak grip strength, upper limb hemiplegia, arthritis, or other similar symptoms. Therefore, this solution can solve the problem that traditional grip strength meters cannot measure the grip strength of people with weak grip strength.

[0046] In some embodiments, the multiple regions of a dexterous hand include at least: the fingertips, the palmar surface, the thenar eminence, and the web between the thumb and index finger. For example Figure 1 The pressure sensor array 130 is distributed in the fingertips, palmar surface, and thenar eminence. For example, please refer to... Figure 1 The blue dot matrix illustrates the pressure sensor array of the dexterous hand, distributed across the five fingers (thumb, index finger, middle finger, ring finger, and little finger) and palm of the dexterous hand 100. It focuses on covering the main contact areas (such as fingertips, palm, and thenar eminence) when the target object (e.g., the elderly) shakes hands, thereby ensuring the accuracy of grip force distribution detection. It can clearly identify the differences in force exerted by each finger and palm when the target object shakes hands, so as to assess the target object's handshake state and the strength of the hand muscles.

[0047] In some embodiments, the pressure sensor array is further configured to: employ a matrix scanning wiring method so that the row and column lines of the pressure sensor array are interleaved; and employ a flexible conductive material for wiring the pressure sensor array.

[0048] Regarding the matrix scanning wiring method, i.e., the row / column line intersection, it can reduce the number of wires, thus adapting to the narrow internal space of the dexterous hand; for example, the wiring and flexible connectors are integrated inside the joints of the dexterous hand 100, thereby avoiding interference with the flexion and extension movements of the dexterous hand, and also facilitating later maintenance. In addition, the wiring uses flexible conductive materials, such as conductive silver paste, which allows the wiring to adhere tightly to the flexible substrate layer, thus not affecting the flexion and extension movements of the dexterous hand.

[0049] In some embodiments, the dexterous hand 100 further includes a force buffer module configured to trigger a grip force feedback signal in response to detecting that the grip force value of the target object exceeds a preset grip force safety threshold, so as to control the dexterous hand to reduce the grip force, thereby avoiding pressure on the target object's hand and preventing injury caused by the target object's weak hand muscles. The preset grip force safety threshold may be preset, for example, based on the target object's age, physical condition, and / or gender.

[0050] The Dexterous Hand 100 also includes a data acquisition module (not shown in the figure), which is configured to acquire grip force distribution data about the target object via a flexible electronic skin.

[0051] For example, the data acquisition module integrates a low-noise amplifier, an analog-to-digital converter (ADC), and a scanning drive circuit. It is configured to optimize amplifier gain and reduce noise interference when the handshake force of the target object is weak and the signal is susceptible to interference, so as to ensure accurate acquisition of weak pressure signals and reduce the signal interference rate to below 5%.

[0052] The Dexterous Hand 100 also includes a data processing module (not shown in the figure), configured to process grip force distribution data to determine the target object's handshake state and hand muscle strength. Regarding handshake state, this includes, for example, the handshake posture and force exertion, such as incorrect handshake posture, normal handshake force, excessive force, uneven force, etc.

[0053] For example, the data processing module uses a low-power embedded processor (e.g., a microcontroller unit (MCU) or a system-on-chip (SoC)) to meet the low-power requirements of the robot equipped with Dexterity Hand 100. The data processing module completes pressure distribution reconstruction, contact point localization, pressure gradient calculation, and timing filtering. At the same time, it integrates an age-appropriate data processing algorithm, which can automatically identify the handshake state of the target object (e.g., the elderly), such as normal handshake, weak handshake, and abnormal force exertion. It can also calculate the average, peak, and rate of change of the target object's grip force to assess the strength state of the target object's hand muscles.

[0054] For example, the Dexterous Hand 100 supports adjusting the sensitivity of the pressure sensor and data processing module and the grip strength warning threshold of the Dexterous Hand 100 based on the target object's age, physical condition, and hand size, through the data processing module and / or the main control system of the robot equipped with the Dexterous Hand, thereby supporting personalized adaptation and being able to adapt to target objects of different ages and health conditions.

[0055] The Dexterous Hand 100 also includes a communication module configured to communicate with the robot's main control system. For example, the communication module enables the Dexterous Hand 100 to wirelessly communicate (e.g., Bluetooth / Ethernet) with the main control system of a robot equipped with a dexterous hand, a health monitoring platform, etc., thereby uploading data to the target object's health record, realizing long-term tracking and health trend analysis of the target object's grip strength data, and supporting data export for easy viewing by medical personnel.

[0056] The dexterous hand 100 also includes a storage module configured to store grip force distribution data of a target object over a predetermined period of time. For example, with its built-in small storage unit, the dexterous hand 100 can store at least 30 days of grip force distribution data of a target object.

[0057] The dexterous hand 100 also includes an early warning module, which is configured to trigger an early warning message and / or send an early warning message to the robot's control system in response to determining that the handshake state and / or the strength state of the hand muscles of the target object meet predetermined conditions.

[0058] Regarding the predetermined conditions for the target object's handshake state and / or hand muscle strength state, for example, if the target object's grip strength is abnormal (such as a continuous decrease in grip strength, uneven finger force, sudden pressure changes during handshake, etc.), when the target object's grip strength is abnormal, the early warning module will report the abnormal grip strength of the target object to the main control system of the robot equipped with the dexterous hand. This can be done through methods such as voice prompts and / or background notifications, thereby prompting medical staff, the target object, and / or related personnel (such as relatives and friends) to pay attention to the target object's hand health status, and providing assistance for the early screening of potential health problems (such as sarcopenia, etc.) of the target object.

[0059] Regarding the data processing module, it may have one or more processing units, such as dedicated processing units including graphics processing units (GPUs), field programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), general-purpose computing on graphics processing units (GPGPUs), and general-purpose processing units such as CPUs. Additionally, one or more virtual machines may run on each data processing module 200. In some embodiments, the data processing module 200 includes, for example, a grip force measurement activation module 210, a handshake posture determination module 220, a grip force distribution data acquisition module 230, and a grip force measurement result module 240.

[0060] The grip force measurement activation module 210 is used to collect grip force distribution data of the target object via a flexible electronic skin in response to the detection of a handshake between a dexterous hand and the target object.

[0061] The handshake posture judgment module 220 is used to determine whether the handshake posture of the target object is correct based on the grip force distribution data.

[0062] The grip force distribution data acquisition module 230 is used to acquire the real-time grip force value of the target object via a pressure sensor and the real-time grip force distribution data of the target object via a flexible electronic skin in response to determining that the handshake posture of the target object is correct.

[0063] The grip strength measurement result module 240 is used to assess the handshake state and hand muscle strength state of the target object based on the real-time grip strength value and / or real-time grip strength distribution data of the target object.

[0064] Figure 3 A flowchart of a method 300 for measuring grip strength using a robot's dexterous hand, according to an embodiment of the present invention, is shown. Method 300 can be performed by, for example... Figure 2 The data processing module 200 shown can be executed, or it can be... Figure 1 The dexterous hand shown is 100. Figure 6 The method is performed at the illustrated electronic device 600. It should be understood that method 300 may also include additional steps not shown and / or the steps shown may be omitted, and the scope of the invention is not limited in this respect.

[0065] In step 302, if the data processing module 200 detects that the dexterous hand shakes hands with the target object, it collects the grip force distribution data of the target object via the flexible electronic skin.

[0066] Once the robot equipped with the dexterous hand is started, it first performs initialization calibration to power on the electronic skin system, complete the zero-point compensation and sensitivity calibration of the pressure sensor and pressure sensor array, and set the grip strength warning threshold and force buffer parameters in combination with the target object's age, gender, and physical parameters to ensure that the detection accuracy is adapted to the physiological characteristics of the target object (e.g., Zhang San, male, 60 years old, 70 kg, no underlying diseases).

[0067] After initial calibration is completed, the dexterous hand is triggered to enter the grip force measurement mode by contact. For example, the target object actively shakes hands with the dexterous hand, and the robot controls the dexterous hand to actively shake hands with the target object. When the contact area of ​​the flexible electronic skin is subjected to pressure, the pressure sensing unit deforms, the resistance changes linearly, and the signal acquisition is triggered. The grip force distribution data of the target object is collected through the flexible electronic skin.

[0068] In step 304, the data processing module 200 determines whether the handshake posture of the target object is correct based on the grip force distribution data.

[0069] In some embodiments, determining whether the handshake posture of the target object is correct based on grip force distribution data includes: the data processing module 200 determining the contact state between the target object and the web of the dexterous hand, and determining the contact area between the target object and the dexterous hand based on the grip force distribution data; and if the data processing module 200 determines that the target object is in contact with the web of the dexterous hand, and the contact area between the target object and the dexterous hand is greater than or equal to a predetermined contact area threshold, determining that the handshake posture of the target object is correct.

[0070] For example, if the predetermined contact area threshold is 60%, when the contact area between the target object and the dexterous hand is 50% and the target object is in contact with the web of the dexterous hand, the target object's handshake posture is determined to be incorrect; when the contact area between the target object and the dexterous hand is 80% and the target object is not in contact with the web of the dexterous hand, the target object's handshake posture is determined to be incorrect; when the contact area between the target object and the dexterous hand is 70% and the target object is in contact with the web of the dexterous hand, the target object's handshake posture is determined to be correct.

[0071] For example, in some embodiments, the data processing module 200 also combines the data collected by the robot's vision sensor to determine whether the handshake posture of the target object is correct, and to guide the target object to adjust the handshake posture.

[0072] Therefore, the above scheme determines whether the handshake posture is correct by using both the contact state of the thumb and forefinger and the contact area, making the judgment of handshake posture standardized and quantifiable, avoiding measurement deviations caused by arbitrary postures, and ensuring the consistency and comparability of data from different target objects and multiple measurements.

[0073] In some embodiments, if the data processing module 200 determines that the target object's handshake posture is incorrect, it generates handshake posture adjustment information based on grip force distribution data so that the target object can adjust its handshake posture. For example, it may prompt the target object to grip deeper and make firm contact between its own thumb and forefinger and the forefinger of its dexterous hand; or it may prompt the target object to move its hand upwards slightly.

[0074] Therefore, the above solution can automatically generate posture adjustment information when the target object makes a handshake error, and interact with the target object to guide the target object to adjust the handshake posture. Standardized measurement can be completed without the participation of professional personnel, which lowers the threshold for grip strength measurement and improves the success rate and convenience of the target object (such as the elderly) to conduct self-testing of grip strength.

[0075] In step 306, if the data processing module 200 determines that the handshake posture of the target object is correct, it collects the real-time grip force value of the target object via the pressure sensor and the real-time grip force distribution data of the target object via the flexible electronic skin.

[0076] Regarding the acquisition of grip force distribution data from the target subject via flexible electronic skin, the process includes: the scanning drive circuit of the pressure sensor array sequentially selects and reads the electrical signals of each sensing unit in a matrix manner, row by row and column by column. For example, it focuses on acquiring signals from core contact areas such as the fingertips, palm, and thenar eminence of the dexterous hand. Considering the slow handshake movements of the target subject (such as the elderly), the scanning frequency is optimized to ensure complete capture of dynamic pressure changes. Then, the front-end circuit of the data acquisition module converts the analog signals into digital signals. A low-noise filtering algorithm filters out environmental interference signals, retaining the true pressure signal of the target subject's (such as the elderly) handshake, ensuring data accuracy.

[0077] The following will combine Figure 4 The detailed method for collecting real-time grip force distribution data of the target object will not be elaborated here.

[0078] In step 308, the data processing module 200 evaluates the handshake state and hand muscle strength state of the target object based on the real-time grip force value and / or real-time grip force distribution data of the target object.

[0079] In some embodiments, the data processing module 200 generates a time-series variation curve of the grip force of the target object based on the real-time grip force value of the target object, so as to determine the peak grip force and / or the average grip force of the target object.

[0080] Regarding the peak grip force of the target object, for example, it is tested using pressure sensor 150. Pressure sensor 150 is a high-precision pressure sensor, whose measurement accuracy is higher than that of a pressure sensor array. The pressure sensor array mounted on the flexible electronic skin can collect grip force distribution data, while the precise grip force value is collected by pressure sensor 150. Pressure sensor 150 is installed using a rigid support and protrudes slightly from the surface of the flexible electronic skin after installation, ensuring direct and accurate force transmission, avoiding interference from flexible deformation in the measurement, and significantly improving the accuracy and stability of grip force value detection.

[0081] Therefore, the above solution adopts a dual-sensor design. The pressure sensor placed between the fingers of the dexterous hand obtains accurate grip force values, thereby ensuring the accuracy of the peak grip force of the target object; while the pressure sensor array on the flexible electronic skin completes the collection of relative grip force distribution data, realizing functions such as handshake posture judgment, force uniformity judgment, and handshake contact surface identification. The two types of sensors work together to complete the collection of grip force data of the target object, thereby obtaining grip force data at each stage of the grip force measurement process, and realizing a comprehensive assessment of the strength state of the hand muscles of the target object.

[0082] In some embodiments, the data processing module 200 assesses the strength status of the target object's hand muscles based on the target object's age, gender, and the target object's peak and / or average grip strength.

[0083] Therefore, the above scheme obtains the peak and mean values ​​by generating a grip strength time-series change curve, and combines factors such as age and gender to conduct hand muscle strength assessment for the target subjects, making the assessment results more consistent with individual physiological characteristics and improving the scientific nature and medical reference value of hand muscle strength status assessment.

[0084] Once the grip strength measurement of the target subject is completed, the dexterous hand ends the handshake with the target subject, the electronic skin system automatically resets, clears temporary data, and enters standby mode, waiting for the next grip strength measurement to be triggered. At the same time, it completes the data storage of the target subject's grip strength measurement for subsequent health analysis.

[0085] In the above solution, the dexterous hand provided by the embodiments of the present invention collects grip force distribution data through flexible electronic skin and judges whether the handshake posture is correct, making the handshake posture judgment standard, quantifiable and intelligent; and, under the premise that the handshake posture is correct, dynamic grip force distribution data is collected, thereby accurately sensing the hand pressure distribution and changes of the tested person (target object), which not only ensures the standardization of measurement, but also improves the accuracy of grip force measurement.

[0086] Furthermore, it can assess the target's handshake state and hand muscle strength based on the target's real-time grip strength values ​​and / or real-time grip strength distribution data. Thus, by combining the target's real-time grip strength values ​​and grip strength distribution data, it can comprehensively and objectively assess the target's handshake state and hand muscle strength, providing a reliable basis for the target's muscle strength assessment and health screening.

[0087] Figure 4 A flowchart of a method 400 for providing support to a target object according to an embodiment of the present invention is shown. Method 400 may be performed by, for example... Figure 1 The data processing module 200 shown can be executed, or it can be... Figure 1 The dexterous hand 100 shown is in Figure 6The method is performed at the illustrated electronic device 600. It should be understood that method 400 may also include additional steps not shown and / or the steps shown may be omitted, and the scope of the invention is not limited in this respect.

[0088] In step 402, the data processing module 200 calculates the pressure value of each of the multiple sensing units based on a predetermined calibration relationship for the electrical signal from the sensing unit, so as to obtain real-time grip force distribution data of the target object.

[0089] In step 404, the data processing module 200 generates a grip force distribution heatmap of the target object based on the real-time grip force distribution data of the target object, calculates the contact area between the target object and the dexterous hand, the maximum pressure point and the pressure gradient in the grip force measurement, so as to identify the handshake state of the target object. The handshake state includes at least: normal, weak and abnormal force exertion.

[0090] For example, pressure data from the entire handshake process of the target object is continuously collected by each sensing unit in the pressure sensor array, recording the time-series change curve of the target object's grip force and tracking the migration of the target object's handshake contact area. Furthermore, when the target object's grip force is detected to exceed a warning threshold, a force buffering mode is triggered, and the data processing module 200 controls the dexterous hand to reduce the grip force; and when an abnormal handshake state is detected, a warning message is triggered.

[0091] Regarding the force buffer mode, in response to detecting that the target object's grip force exceeds a preset safe grip force threshold (i.e., a warning threshold), a grip force feedback signal is triggered to control the dexterous hand to reduce grip force, thereby avoiding pressure on the target object's hand and preventing injury caused by the target object's weak hand muscles. The preset safe grip force threshold may be based on, for example, the target object's age, physical condition, and / or gender.

[0092] Therefore, the above solution achieves high-precision distribution detection through a pressure sensor array, generates a heat map and calculates the contact area, maximum pressure point and pressure gradient, and can accurately identify the uniformity of force application, abnormal force application and weakness state, realize multi-dimensional judgment of handshake state, and improve the comprehensiveness of the assessment of the hand muscle strength state of the target object.

[0093] Figure 5 A flowchart of a method 500 for processing grip strength measurement data of a target object according to an embodiment of the present invention is shown. Method 500 may be performed by, for example... Figure 1 The data processing module 200 shown can be executed, or it can be... Figure 1 The dexterous hand 100 shown is in Figure 6The method is performed at the illustrated electronic device 600. It should be understood that method 500 may also include additional steps not shown and / or the steps shown may be omitted, and the scope of the invention is not limited in this respect.

[0094] In step 502, the data processing module 200 stores grip strength measurement data for the target object over a predetermined period of time.

[0095] In step 504, the data processing module 200 uploads grip strength measurement data of the target object to the health monitoring platform and / or the main control system of the robot equipped with a dexterous hand.

[0096] In step 506, if the data processing module 200 determines that the handshake state and / or the strength state of the hand muscles of the target object meet the predetermined conditions, it triggers an early warning message and / or sends an early warning message back to the robot's control system.

[0097] For example, data such as the grip force distribution, grip force timing data, and handshake state recognition results of the target object are stored in the storage module (such as the built-in storage unit) and uploaded to the robot's main control system and health monitoring platform, and linked to the target object's health record; at the same time, the target object's handshake state is fed back to the control system on the dexterous hand so as to adjust the dexterous hand's grip force and posture to ensure comfortable interaction.

[0098] Therefore, the above solution enables local storage, remote uploading, and abnormal early warning of grip strength data of the target subject, which can support long-term health tracking and remote monitoring of the target subject. It can provide timely alerts when risks such as decreased hand muscle strength or abnormal grip force occur, thereby improving the timeliness and practicality of grip strength measurement.

[0099] Figure 6 A schematic step diagram of an example electronic device 600 that can be used to implement embodiments of the contents of this specification is shown. For example, as Figure 1 The data processing module 200 shown can be implemented by the electronic device 600. As shown, the electronic device 600 includes a central processing unit (CPU) 601, which can perform various appropriate actions and processes according to computer program instructions stored in read-only memory (ROM) 602 or loaded from storage unit 608 into random access memory (RAM) 603. The random access memory 603 can also store various programs and data required for the operation of the electronic device 600. The CPU 601, ROM 602, and RAM 603 are interconnected via a bus 604. An input / output (I / O) interface 605 is also connected to the bus 604.

[0100] Multiple components in electronic device 600 are connected to input / output interface 605, including: input unit 606, such as keyboard, mouse, microphone, etc.; output unit 607, such as various types of monitors, speakers, etc.; storage unit 608, such as disk, optical disk, etc.; and communication unit 609, such as network card, modem, wireless transceiver, etc. Communication unit 609 allows device 600 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0101] The various processes and handling described above, such as methods 300 to 500, can be executed by the central processing unit 601. For example, in some embodiments, methods 300 to 500 may be implemented as computer software programs tangibly contained in a machine-readable medium, such as storage unit 608. In some embodiments, part or all of the computer program may be loaded and / or installed on device 600 via read-only memory 602 and / or communication unit 609. When the computer program is loaded into random access memory 603 and executed by the central processing unit 601, one or more actions of methods 300 to 500 described above can be performed.

[0102] This invention relates to methods, apparatus, systems, electronic devices, computer-readable storage media, and / or computer program products. The computer program product may include computer-readable program instructions for performing various aspects of the invention.

[0103] Computer-readable storage media can be tangible devices capable of holding and storing instructions for use by an instruction execution device. Computer-readable storage media can be, for example—but not limited to—electrical storage devices, magnetic storage devices, optical storage devices, electromagnetic storage devices, semiconductor storage devices, or any suitable combination of the foregoing. More specific examples (a non-exhaustive list) of computer-readable storage media include: portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), static random access memory (SRAM), portable compact disc read-only memory (CD-ROM), digital multifunction disc (DVD), memory sticks, floppy disks, mechanical encoding devices, such as punch cards or recessed protrusions storing instructions thereon, and any suitable combination of the foregoing. The computer-readable storage media used herein are not to be construed as transient signals themselves, such as radio waves or other freely propagating electromagnetic waves, electromagnetic waves propagating through waveguides or other transmission media (e.g., light pulses through fiber optic cables), or electrical signals transmitted through wires.

[0104] The computer-readable program instructions described herein can be downloaded from computer-readable storage media to various computing / processing devices, or downloaded via a network, such as the Internet, local area network, wide area network, and / or wireless network, to an external computer or external storage device. The network may include copper transmission cables, fiber optic transmission, wireless transmission, routers, firewalls, switches, gateway computers, and / or edge computing devices. A network adapter card or network interface in each computing / processing device receives the computer-readable program instructions from the network and forwards them to computer-readable storage media within the respective computing / processing device.

[0105] The computer program instructions used to perform the operations of this invention may be assembly instructions, instruction set architecture (ISA) instructions, machine instructions, machine-dependent instructions, microcode, firmware instructions, state setting data, or source code or object code written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Smalltalk, C++, etc., and conventional procedural programming languages ​​such as the "C" language or similar programming languages. The computer-readable program instructions may be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving a remote computer, the remote computer may be connected to the user's computer via any type of network—including a local area network (LAN) or a wide area network (WAN)—or may be connected to an external computer (e.g., via the Internet using an Internet service provider). In some embodiments, electronic circuitry, such as programmable logic circuitry, field-programmable gate arrays (FPGAs), or programmable logic arrays (PLAs), is personalized by utilizing state information from the computer-readable program instructions. This electronic circuitry can execute the computer-readable program instructions to implement various aspects of the invention.

[0106] Various aspects of the present invention are described herein with reference to flowchart illustrations and / or step diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It should be understood that each step in the flowchart illustrations and / or step diagrams, as well as combinations of steps in the flowchart illustrations and / or step diagrams, can be implemented by computer-readable program instructions.

[0107] These computer-readable program instructions can be provided to a processing unit of a general-purpose computer, a special-purpose computer, or other programmable data processing apparatus to produce a machine such that, when executed by the processing unit of the computer or other programmable data processing apparatus, they create means for implementing the functions / actions specified in one or more steps of the flowchart and / or diagram of steps. These computer-readable program instructions can also be stored in a computer-readable storage medium that causes a computer, programmable data processing apparatus, and / or other device to operate in a particular manner. Thus, the computer-readable medium storing the instructions comprises an article of manufacture that includes instructions for implementing aspects of the functions / actions specified in one or more steps of the flowchart and / or diagram of steps.

[0108] Computer-readable program instructions may also be loaded onto a computer, other programmable data processing apparatus, or other device to cause a series of operational steps to be performed on the computer, other programmable data processing apparatus, or other device to produce a computer-implemented process, thereby causing the instructions executed on the computer, other programmable data processing apparatus, or other device to perform the functions / actions specified in one or more steps of a flowchart and / or a diagram of steps.

[0109] The flowcharts and step diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of the present invention. In this regard, each step in the flowchart or step diagram may represent a module, segment, or part of an instruction, which contains one or more executable instructions for implementing the specified logical function. In some alternative implementations, the functions indicated in the step may occur in a different order than those indicated in the drawings. For example, two consecutive step steps may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each step in the step diagram and / or flowchart, and combinations of steps in the step diagram and / or flowchart, can be implemented using a dedicated hardware-based system that performs the specified function or action, or using a combination of dedicated hardware and computer instructions.

[0110] The various embodiments of the present invention have been described above. These descriptions are exemplary and not exhaustive, nor are they limited to the disclosed embodiments. Many modifications and variations will be apparent to those skilled in the art without departing from the scope and spirit of the described embodiments. The terminology used herein is chosen to best explain the principles, practical application, or technical improvements to the embodiments in the market, or to enable others skilled in the art to understand the embodiments disclosed herein.

Claims

1. A grip force measurement method using a robot dexterous hand, characterized by, The dexterous hand is equipped with a flexible electronic skin and one or more pressure sensors, the flexible electronic skin covering the dexterous hand, and the method includes: In response to the detection of a handshake between the dexterous hand and the target object, grip force distribution data of the target object is collected via the flexible electronic skin; Based on the grip force distribution data collected and calculated by a flexible electronic skin pressure sensor array covering the surface of the robot's dexterous hand, the system determines whether the handshake posture of the target object is correct. This includes: determining the contact state between the target object and the web of the dexterous hand, and determining the contact area between the target object and the dexterous hand, based on the grip force distribution data; and determining that the target object is in contact with the web of the dexterous hand and the contact area between the target object and the dexterous hand is greater than or equal to a predetermined contact area threshold, thus determining that the handshake posture of the target object is correct. In response to determining that the handshake posture of the target object is correct, the real-time grip force value of the target object is collected via the pressure sensor, and the real-time grip force distribution data of the target object is collected via the flexible electronic skin, so as to perform handshake posture judgment, force uniformity judgment, and handshake contact surface identification; and Based on the real-time grip force value and / or real-time grip force distribution data of the target object, assess the handshake state and hand muscle strength state of the target object, including: generating a grip force distribution heatmap of the target object based on the real-time grip force distribution data of the target object, calculating the contact area between the target object and the dexterous hand, the maximum pressure point and the pressure change gradient during grip force measurement, so as to identify the handshake state of the target object, the handshake state including at least: normal, weak and abnormal force exertion; The one or more pressure sensors are configured between the fingers of the dexterous hand to detect the grip force between adjacent fingers; The flexible electronic skin primarily collects signals from the fingertips, palmar surfaces, and thenar eminence of each finger of the dexterous hand; and In response to determining that the handshake state and / or the strength state of the hand muscles of the target object meet predetermined conditions, an early warning message is triggered and / or the early warning message is fed back to the control system of the robot; wherein, the predetermined conditions include one or more of the following: continuous decrease in grip strength, uneven finger force, and sudden change in pressure during handshake.

2. The method according to claim 1, characterized in that, Also includes: In response to determining that the target object's handshake posture is incorrect, handshake posture adjustment information is generated based on the grip force distribution data so that the target object can adjust its handshake posture.

3. The method according to claim 1, characterized in that, Assessing the handshake state and hand muscle strength of the target subject based on real-time grip force values ​​and / or real-time grip force distribution data also includes: Based on the real-time grip strength values ​​of the target object, a time-series curve of grip strength variation is generated to determine the peak and / or average grip strength of the target object; and Assess the strength status of the target's hand muscles based on the target's age, gender, and peak and / or mean grip strength.

4. The method according to claim 1, characterized in that, The flexible electronic skin includes a pressure sensor array, which comprises multiple sensing units. Based on real-time grip force values ​​and / or real-time grip force distribution data of the target object, the assessment of the target object's handshake state and hand muscle strength state further includes: Based on a predetermined calibration relationship, the pressure value of each of the plurality of sensing units is calculated for the electrical signal from the sensing unit in order to obtain real-time grip force distribution data of the target object.

5. The method according to claim 1, characterized in that, The method further includes: Store grip strength measurement data for a predetermined period of time for the target object; Upload grip strength measurement data of the target object to the health monitoring platform and / or the main control system of the robot equipped with the dexterous hand; and In response to determining that the handshake state and / or the strength state of the hand muscles of the target object meet predetermined conditions, an early warning message is triggered and / or the early warning message is fed back to the control system of the robot.

6. A dexterous hand, characterized in that, The dexterous hand is configured on the robot, and the dexterous hand is controlled by the grip strength measurement method of any one of claims 1 to 5, wherein the dexterous hand comprises: The bionic hand consists of a palm and multiple fingers, each finger having multiple movable joints; A flexible electronic skin, comprising a flexible substrate layer, a pressure sensor array, and an encapsulation layer, covers the dexterous hand and is configured to sense the handshake posture and grip force distribution of a target object; One or more pressure sensors are configured between the fingers of the dexterous hand to detect the grip force between adjacent fingers; The data acquisition module is configured to acquire grip force distribution data about the target object via flexible electronic skin; The data processing module is configured to process the grip force distribution data in order to confirm the handshake state and hand muscle strength state of the target object. The flexible electronic skin covers multiple areas of the dexterous hand, including at least: the fingertips, the palmar surface, the thenar eminence, and the web between the thumb and index finger.

7. The dexterous hand according to claim 6, characterized in that, The pressure sensor is equipped with a rigid support and protrudes from the flexible electronic skin surface of the dexterous hand when it is mounted on a finger.

8. The dexterous hand according to claim 6, characterized in that, Also includes: A communication module is configured to communicate with the robot's main control system; The storage module is configured to store grip force distribution data of the target object over a predetermined period of time; as well as The early warning module is configured to trigger an early warning message and / or feed back the early warning message to the robot's control system in response to determining that the handshake state and / or the strength state of the hand muscles of the target object meet predetermined conditions.

9. The dexterous hand according to claim 6, characterized in that, The flexible substrate layer includes: Bionic fingertip microstructure, wherein the surface of the bionic fingertip microstructure is provided with skin texture simulating that of a human hand; and The surface of the flexible substrate layer is treated with a skin-friendly modification.

10. The dexterous hand according to claim 6, characterized in that, The flexible substrate layer is also configured to adapt to the palm bending and finger flexion and extension of the dexterous hand.

11. The dexterous hand according to claim 6, characterized in that, The pressure sensor array is a piezoresistive flexible array sensor, comprising a predetermined number of sensing units to form a distributed tactile sensing network covering multiple areas of the dexterous hand.

12. The dexterous hand according to claim 11, characterized in that, The pressure sensor array is also configured to: A matrix scanning wiring method is adopted to allow for the cross-distribution of row and column lines in the pressure sensor array; and The pressure sensor array is wired using a flexible conductive material.

13. A computing device, comprising: At least one processing unit; At least one memory coupled to the at least one processing unit and storing instructions for execution by the at least one processing unit, the instructions, when executed by the at least one processing unit, causing the device to perform the steps of the method according to any one of claims 1 to 5.

14. A computer-readable storage medium having a computer program stored thereon, the computer program implementing the method according to any one of claims 1 to 5 when executed by a machine.

Images