A finger joint angle detection mechanism and a three-dimensional model construction method

Abstract

This invention discloses a finger joint angle detection mechanism and a method for constructing a 3D model of an object; belonging to the field of exoskeletons for human finger joints, it consists of a fabric substrate, a data storage module, a displacement sensor, and a transmission mechanism, including five sets of three-segment skeletons. The thumb skeleton includes a fingertip joint rod, a root joint rod, a back-of-hand rod, and a wrist rod; the other finger skeletons include a fingertip joint rod, a middle joint rod, a root joint rod, and a back-of-hand rod. Each pair of skeleton segments is connected by a transmission mechanism and a cylindrical pin. The glove does not affect the natural movement of the human hand, and when collecting finger joint data through grasping or other methods, it ensures flexible hand movement, and the range of joint bending angles is unrestricted. When the human hand wears the glove to grasp an object, the bending angles of each finger joint are collected and converted into bending angle images. A convolutional neural network is used to fuse the bending angle images with multi-angle captured object images to achieve accurate 3D reconstruction of the object.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of human finger joint exoskeletons; in particular to a finger joint angle detection mechanism and an object three-dimensional model construction method. BACKGROUND

[0002] The finger joint angle is one of the important parameters of human hand movement; it can provide information about finger movement control and coordination; therefore it has wide application in the fields of medical treatment, rehabilitation and motion control. Traditional finger joint angle measurement methods include X-ray measurement, magnetic resonance imaging, motion capture and other technologies; but these methods have the disadvantages of being expensive, complex, inefficient, radioactive and the like; they are not suitable for real-time and portable measurement. In order to overcome these shortcomings; some researchers have begun to explore the use of data gloves to measure finger joint angles. Data gloves are usually composed of multiple sensors and controllers; they can measure information such as finger posture and motion trajectory. Among them; the sensors usually use inertial measurement units (IMU), pressure sensors, stretch sensors and the like.

[0003] Using data gloves to measure finger joint angles has the advantages of being real-time, portable, non-radioactive and the like; it is suitable for medical rehabilitation, gesture recognition, virtual reality and other application scenarios. However; traditional glove measurement methods usually require the use of expensive sensors; and cannot provide high-precision data.

[0004] Current methods for three-dimensional reconstruction of objects mostly rely only on visual images; which cannot provide complete information about the object. Finger joint angle information can make up for the missing or ambiguous information in visual images; and can make the model more fully understand the properties of the object. Therefore; an efficient, accurate and low-cost finger joint angle detection mechanism and object three-dimensional model construction method are needed. SUMMARY

[0005] In view of the deficiencies of the prior art; the present application proposes a finger joint angle detection mechanism and an object three-dimensional model construction method; a new exoskeleton data glove; which accurately measures the bending angle of the human finger joint by combining a transmission mechanism with a displacement sensor; and proposes an object three-dimensional model construction method that fuses tactile interaction data and object image data; to generate a virtual object with the same size and shape characteristics as the real object; and to achieve accurate three-dimensional reconstruction of the object.

[0006] The purpose of the present application can be achieved by the following technical solutions:

[0007] The first aspect of the application discloses a finger joint angle detection mechanism, which comprises joint rods connected in sequence; one of the joint rods is rotationally connected with a connecting rod; the other joint rod is fixedly installed with a displacement sensor; the joint rod installed with the displacement sensor is provided with a linearly movable transmission rod; the transmission rod is connected with a sliding rod of the displacement sensor.

[0008] In some embodiments, the joint rod installed with the displacement sensor is provided with a track hole; the transmission rod is slidingly connected with the track hole.

[0009] In some embodiments, a data storage module is further included; the data storage module comprises a shell, a rechargeable battery, a toggle switch, an initialization button and a control circuit board; the shell is fixedly installed on the outside with the toggle switch and the initialization button; the inside of the shell is provided with the control circuit board and the rechargeable battery; the displacement sensor, the rechargeable battery, the toggle switch and the initialization button are electrically connected with the control circuit board; the displacement sensor is connected in series with a resistor to a circuit loop, the toggle switch is turned on, the rechargeable battery supplies power to the entire circuit, and the control circuit board collects the current passing through the displacement sensor.

[0010] In some embodiments, the finger joint angle detection mechanism is provided with at least one set of the joint rods connected in sequence; each set has at least two joint rods.

[0011] In some embodiments, each set of the joint rods connected in sequence is provided with four joint rods.

[0012] In some embodiments, a flexible substrate is included, which can be made of fabric, rubber or other flexible materials; the flexible substrate is fixedly installed with the data storage module and at least one set of the joint rods connected in sequence; the joint rods are fixedly connected with the flexible substrate.

[0013] In some embodiments, the flexible substrate is provided with five sets of the joint rods connected in sequence.

[0014] In some embodiments, the inside of the shell is provided with a vibration motor.

[0015] In some embodiments, the flexible substrate is in the shape of a glove.

[0016] The second aspect of the application further discloses a three-dimensional model construction method of an object comprising the finger joint angle detection mechanism disclosed in the first aspect, which comprises the following steps:

[0017] Fixing and installing a joint rod on each finger joint position of the operator's hand, keeping the fingers in a straight state, and setting the displacement sensor to zero; the operator performs object top gripping and side gripping respectively; each gripping action is kept still for a few seconds;

[0018] After initialization, the initial position of the displacement sensor slide rod is recorded, and the current data of the angle detection circuit in the control circuit board is recorded during the gripping process; according to the current-resistance relationship curve of the angle detection circuit and the resistance-displacement characteristic curve of the displacement sensor, the measured current value is converted into the displacement of the displacement sensor; the joint angle data between the two joint rods is calculated according to the cosine formula; the angle information calculation process is as follows:

[0019] For the joint angle between the two adjacent joint rods, the distance between the rotating connections of the finger joint rod in the initial state is L0, and the distance between the rotating connections of the connecting rod is L1;

[0020] When bending the fingers, the joint rod moves with the fingers, and the current sequence I0 obtained by gripping is recorded; after median filtering and smoothing processing, the current sequence I is obtained; according to the current-resistance relationship curve of the angle detection circuit, a group of resistance value sequence R x is obtained; according to the resistance-displacement characteristic curve of the displacement sensor, the position of the displacement sensor slide rod is obtained;

[0021] In the case of a joint angle of 180°, the initial position of the displacement sensor slide rod is X0, and the position of the displacement sensor slide rod after the finger is bent is X1;

[0022] The displacement of the displacement sensor slide rod is Δx=(X1-X0), and the lengths of the three sides of the triangle composed of the two joint rods and the connecting rod are L0; L1; L0+L1-(X1-X0);

[0023] According to the cosine law, the joint angle θ is:

[0024]

[0025] Integrate and save the joint angle data to the storage unit;

[0026] After the gripping is completed, the data acquisition is ended; the stored series of joint angle data is converted into a two-dimensional image as a tactile data set; the object is photographed from multiple angles using a camera to establish an appearance image data set of the object; based on the tactile data set and the visual data set, the Concatenate method is used for visual-tactile feature fusion of the object to obtain a new feature vector; the feature vector is input into the convolutional neural network for multiple training to obtain a finger three-dimensional model containing size information, and the generated model is optimized, adjusted and corrected to realize precise three-dimensional model reconstruction of the object.

[0027] The beneficial effects of this invention are:

[0028] This invention uses a displacement sensor as the sensor to detect changes in angle; it is less expensive than similar data gloves on the market; and it is easier to install.

[0029] This invention uses a lever structure to connect the movements on both sides of the joint; it converts the bending motion of the finger into the displacement motion of the displacement sensor slider; thus making the measurement of finger joint angle data simpler and more accurate.

[0030] The device of the present invention can measure a range of finger joint angles that exceeds the range of actual finger joint angle data; it can measure the angle of every joint on the hand; and it also adds angle information between the thumb metacarpal bone and the wrist; enriching the data of finger joint angles; and ensuring that the collected data has a high degree of integrity.

[0031] The three-dimensional shape reconstruction method proposed in this invention integrates tactile interaction data and object image data; it can generate virtual objects with the same size and shape features as real objects; and it can achieve accurate three-dimensional reconstruction of objects.

[0032] The device and method designed in this invention have the characteristics of low power consumption, compact structure, high wearing comfort, high precision even after long-term use, feedback reminders during interaction, and simple operation. They can be widely used in multiple application fields such as robotics, human-computer tactile interaction, and virtual reality. Attached Figure Description

[0033] The invention will now be further described with reference to the accompanying drawings.

[0034] Figure 1 This is a schematic diagram of the overall structure of the joint angle detection mechanism;

[0035] Figure 2 A side view of a single finger joint angle detection mechanism;

[0036] Figure 3 A schematic diagram of a two-joint rod transmission structure for the smallest unit;

[0037] Figure 4 This is a schematic diagram of the data storage module structure;

[0038] Figure 5 A flowchart of the algorithm for 3D model reconstruction using precise joint angle data acquisition and visual-tactile modal data fusion.

[0039] Reference numerals: 1. Finger tip joint rod; 2. Middle finger joint rod; 3. Finger root joint rod; 4. Back of hand rod; 5. Wrist rod; 6. Finger tip sleeve; 7. Connecting rod; 8. Displacement sensor; 9. Transmission rod; 10. Base; 11. Fabric backing; 13. Joint rod; 14. Cylindrical pin; 12. Data storage module; 1201. Housing; 1202. Rechargeable battery; 1203. Toggle switch; 1204. Initialization button; 1205. Cover; 1206. Vibration motor; 1207. Control circuit board. Detailed Implementation

[0040] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0041] In the description of this invention, it should be understood that the terms "opening", "upper", "lower", "thickness", "top", "middle", "length", "inner", "around", etc., which indicate orientation or positional relationship, are only for the convenience of describing this invention and simplifying the description, and do not indicate or imply that the components or elements referred to must have a specific orientation, or be constructed and operated in a specific orientation; therefore, they should not be construed as limitations on this invention.

[0042] In the description of this specification, the references to terms such as "an embodiment," "example," "specific example," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of the invention. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples.

[0043] This application discloses a joint angle detection mechanism; it includes joint rods 13 connected in sequence; one of two adjacent joint rods 13 is rotatably connected to a connecting rod 7; the other joint rod 13 is fixedly mounted with a displacement sensor 8; the joint rod 13 with the displacement sensor 8 is provided with a linearly movable transmission rod 9; the transmission rod 9 is connected to the slide rod of the displacement sensor 8; and it is used to convert the bending motion of the joint rod 13 into the translational motion of the connecting rod 7.

[0044] In use, the joint rod 13 is fixed to the corresponding finger joint. The fixing method can be to tie it directly to the finger or to tie the joint rod 13 to the glove and then put on the glove. By recording the translation distance of the connecting rod 7 and combining the relationship between the initial positions of the joint rod 13, the connecting rod 7, and the transmission rod 9, the bending angle of the finger can be calculated.

[0045] The linear movement of the transmission rod 9 can be achieved by having a track hole provided in the joint rod 13 on which the displacement sensor 8 is installed; the transmission rod 9 is slidably connected to the track hole; the linear movement of the transmission rod 9 can also be achieved by setting the connecting rod 7 as a telescopic rod structure, connecting the fixed end of the telescopic rod to the joint rod 13, and rotatably connecting the telescopic end of the telescopic rod to the connecting rod 7; the linear movement of the transmission rod 9 can also be achieved by installing an optical axis on the joint rod 13, the optical axis being slidably connected to the slider, and the transmission rod 9 being installed on the slider; the linear movement of the transmission rod 9 includes, but is not limited to, the methods mentioned above.

[0046] In some embodiments, a data storage module 12 is also included; the data storage module 12 includes a housing 1201, a rechargeable battery 1202, a toggle switch 1203, an initialization button 1204, and a control circuit board 1207; the toggle switch 1203 and the initialization button 1204 are fixedly installed on the outside of the housing 1201; the control circuit board 1207 and the rechargeable battery 1202 are disposed inside the housing 1201; the displacement sensor 8, the rechargeable battery 1202, the toggle switch 1203, and the initialization button 1204 are all electrically connected to the control circuit board 1207; the displacement sensor 8 is connected in series with a resistor in the circuit loop, when the toggle switch 1203 is turned on, the rechargeable battery 1202 supplies power to the entire circuit, the control circuit board 1207 collects the current passing through the displacement sensor 8, and when the initialization button 1204 is pressed, the displacement of the displacement sensor 8 corresponding to the current detected at this moment is set to 0.

[0047] In some embodiments, the knuckle angle detection mechanism is provided with at least one set of joint rods 13 that are rotatably connected in sequence; wherein each set has at least two joint rods 13.

[0048] In some embodiments, a flexible substrate is included; a data storage module 12 and at least one set of rotatable joint rods 13 are fixedly mounted on the flexible substrate; the joint rods 13 are fixedly connected to the flexible substrate.

[0049] The second aspect of this application also discloses a method for constructing a three-dimensional model of an object, including a knuckle angle detection mechanism as disclosed in the first aspect, comprising the following steps:

[0050] A joint rod 13 is fixedly installed at each finger joint of the operator's hand, with the fingers in a straight position and the displacement sensor 8 set to zero; the operator performs a top grip and a side grip on the object respectively; each gripping action is held still for a few seconds;

[0051] After initialization, the initial position of the slider of displacement sensor 8 is recorded. During the gripping process, the current data of the angle detection circuit in the control circuit board 1207 is recorded. Based on the current-resistance relationship curve of the angle detection circuit and the resistance-displacement characteristic curve of displacement sensor 8, the measured current value is converted into the displacement of displacement sensor 8. The joint angle data between the two joint rods 13 is calculated according to the cosine formula. The angle information calculation process is as follows:

[0052] For the joint angle between two adjacent joint rods 13, in the initial state, the distance between the rotational connection points of the joint rods 13 is L0, and the distance between the rotational connection points at both ends of the connecting rod 7 is L1.

[0053] When the finger is bent, joint rod 13 follows the finger's movement, recording the current sequence I0 obtained from grasping; after median filtering and smoothing, the current sequence I is obtained; based on the current-resistance relationship curve of the angle detection circuit, a set of resistance value sequences R is obtained. x The position of the slider of displacement sensor 8 is obtained based on the resistance-displacement characteristic curve of displacement sensor 8.

[0054] When the joint angle is 180°, the initial position of the slider of displacement sensor 8 is X0, and the position of the slider of displacement sensor 8 after the finger is bent is X1.

[0055] The displacement of the slider of displacement sensor 8 is Δx=(X1-X0), then the three side lengths of the triangle formed by the two joint rods 13 and the connecting rod 7 are L0; L1; L0+L1-(X1-X0);

[0056] The joint angle θ can be obtained using the law of cosines.

[0057] The following description, in conjunction with the accompanying drawings and embodiments, provides a further explanation of the knuckle angle detection mechanism provided by the present invention.

[0058] like Figure 1 , Figure 2 , Figure 3 As shown, a joint angle detection mechanism and a method for reconstructing a three-dimensional object model include two parts: the design of an exoskeleton glove and the method for reconstructing a three-dimensional model.

[0059] The data glove includes fingertip joint 1, middle finger joint 2, base finger joint 3, back of hand joint 4, wrist joint 5, fingertip sleeve 6, connecting rod 7, displacement sensor 8, transmission rod 9, base 10, fabric substrate 11, and data storage module 12. The joints are connected by cylindrical pins 14.

[0060] The data acquisition module 12 includes a housing 1201, a cover 1205, a toggle switch 1203, and an initialization button 1204;

[0061] For the four fingers other than the thumb, the left end of the fingertip sleeve 6 is fixed to the fingertip joint rod 1. The right end of the fingertip joint rod 1 has two connecting holes. The left connecting hole is connected to the left connecting hole of the middle joint rod 2 via a cylindrical pin 14, and the right connecting hole is connected to the connecting rod 7 via a cylindrical pin 14. The other side of the connecting rod 7 is connected to the transmission rod 9 via a cylindrical pin 14, and the cylindrical pin 14 is restricted in the track hole of the middle joint rod 2, so that it can only slide along the direction of the middle joint rod 2. This structure is used to convert the bending motion of the fingertip joint rod 1 into the translational motion of the cylindrical pin 14 at the right end of the connecting rod 7. The transmission rod 9 is fixed to the slide rod of the displacement sensor 8. The displacement sensor 8 is welded to the base 10 according to the circuit relationship and fixed to the right side of the middle joint rod 2. The connection between the middle joint rod 2 and the root joint rod 3, and the connection between the root joint rod 3 and the back of the hand rod 4 are in the same way as the connection between the fingertip joint rod 1 and the middle joint rod 2. All the joint rods are fixed above the fabric substrate.

[0062] For the thumb, since it only has two phalanges, its connection method differs from the other four fingers. The fingertip joint rod 1 is directly connected to the finger root joint rod 3, and the finger root joint rod 3 is directly connected to the back of the hand rod 4 using the aforementioned connection method. An angular relationship is added between the back of the hand rod 4 and the wrist rod 5: the back of the hand rod 4 and the wrist rod 5 are connected by placing the connecting rod 7 and the displacement sensor 8 on two different sides of the wrist rod 5, allowing the connecting rod 7 to move on the other side of the wrist rod 5. This allows the measurement of an angle greater than 180 degrees between the thumb metacarpal and carpal bones. The wrist rod 5 is then fixed to the side of the data module acquisition module's housing 1202. The fingertip joint rod, finger root joint rod, and back of the hand rod are then fixed above the fabric substrate 11.

[0063] like Figure 4 As shown, the outer shell is fixed above the wrist of the fabric substrate 11. The outer shell 1201 has an opening at the top and a rechargeable battery 1202 and a control circuit board 1207 are provided inside the outer shell. A toggle switch 1203 and an initialization button 1204 are provided on the right end of the outer shell.

[0064] like Figure 5 As shown, the method for data acquisition and three-dimensional shape reconstruction of a finger joint angle detection glove is characterized by the following steps:

[0065] Step 1: The operator puts on a data glove on their right hand, turns on the toggle switch 1203, and the glove begins to detect the knuckle angle. With both fingers straight, the operator presses the initialization button 1204 to set the knuckle angle to zero at this moment.

[0066] Step 2: The operator grips the object from the top and the side, holding each grip for a few seconds. The vibration motor 1206 provides a vibration prompt. Release the object to be tested. One gripping operation is completed. Wait a few seconds before performing the next gripping operation.

[0067] Step 3: After initialization, record the initial position of the displacement sensor 8 slider. During the gripping process, record the current data of the control circuit board in the data storage module. Based on the current-resistance relationship curve of the angle detection circuit and the resistance-displacement characteristic curve of the displacement sensor, convert the measured current value into the displacement of the displacement sensor. Calculate the joint angle data between the two links using the cosine formula. The angle calculation process is as follows:

[0068] (A) Regarding the joint angle between the fingertip joint rod 1 and the middle joint rod 2, in the initial state, the distance between the two connecting holes on the right side of the fingertip joint rod 1 is L0, and the distance between the connecting holes at both ends of the connecting rod 7 is L1;

[0069] (B) When the finger is bent, the lever follows the finger's movement; the current sequence I0 obtained from grasping is recorded, and after median filtering and smoothing, the current sequence I is obtained; based on the current-resistance relationship curve of the angle detection circuit, a set of resistance value sequences R is obtained. x The position of the displacement sensor slider is obtained based on the resistance-displacement characteristic curve of the displacement sensor.

[0070] (C) When the joint angle is 180°, the initial position of the slider of displacement sensor 8 is X0, and the position of the slider of displacement sensor after the finger is bent is X1.

[0071] (D) The displacement of the slide rod of displacement sensor 8 is Δx=(X1-X0), then the three side lengths of the triangle formed by fingertip rod 1, middle rod 2, and connecting rod 7 are L0, L1, and L0+L1-(X1-X0) respectively.

[0072] (E) By the law of cosines, the joint angle θ can be obtained as:

[0073]

[0074] Step 4: Integrate the joint angle data and save it to the storage unit;

[0075] Step 5: After the grip is complete, turn off the toggle switch 1203 to end the data acquisition.

[0076] Step 6: Convert the stored series of joint angle data into two-dimensional images as a tactile dataset; use a camera to photograph the object from multiple angles to create an object appearance image dataset; based on the tactile dataset and the visual dataset, use the Concatenate method to fuse the visual and tactile features of the object to obtain a new feature vector; input the feature vector into a convolutional neural network for multiple training iterations to obtain a three-dimensional model containing object size information, and optimize, adjust, and correct the generated model to achieve accurate three-dimensional model reconstruction of real-world objects.

[0077] The foregoing has shown and described the basic principles, main features, and advantages of the present invention. Those skilled in the art should understand that the present invention is not limited to the above embodiments; the embodiments and descriptions in the specification are merely illustrative of the principles of the invention; various changes and modifications can be made to the invention without departing from its spirit and scope; all such changes and modifications fall within the scope of the claimed invention.

Claims

1. A knuckle angle detection mechanism, characterized in that, It includes joint rods (13) that are rotatably connected in sequence; one of the two adjacent joint rods (13) is rotatably connected to a connecting rod (7); the other joint rod (13) is fixedly mounted with a displacement sensor (8); the joint rod (13) with the displacement sensor (8) is provided with a transmission rod (9) that can move linearly at one end; the transmission rod (9) is connected to the slide rod of the displacement sensor (8); It also includes a data storage module (12); the data storage module (12) includes a housing (1201), a rechargeable battery (1202), a toggle switch (1203), an initialization button (1204), and a control circuit board (1207); the toggle switch (1203) and the initialization button (1204) are fixedly installed on the outside of the housing (1201); the control circuit board (1207) and the rechargeable battery (1202) are arranged inside the housing (1201); the displacement sensor (8), the rechargeable battery (1202), the toggle switch (1203), and the initialization button (1204) are all electrically connected to the control circuit board (1207); the displacement sensor (8) is connected in series with a resistor in the circuit loop, the toggle switch (1203) is turned on, the rechargeable battery (1202) supplies power to the entire circuit, and the control circuit board (1207) collects the current passing through the displacement sensor (8); The method for constructing a 3D model of the object for the knuckle angle detection mechanism includes the following steps: A joint rod (13) is fixedly installed at each finger joint of the operator's hand, the fingers are in a straight position, and the displacement sensor (8) is set to zero; the operator performs a top grip and a side grip on the object respectively; each gripping action is held still for a few seconds; After initialization, the initial position of the slider of the displacement sensor (8) is recorded. During the gripping process, the current data of the angle detection circuit in the control circuit board (1207) is recorded. According to the current-resistance relationship curve of the angle detection circuit and the resistance-displacement characteristic curve of the displacement sensor (8), the measured current value is converted into the displacement of the displacement sensor (8). The joint angle data between the two joint rods (13) is calculated according to the cosine formula. The angle information calculation process is as follows: For the joint angle between two adjacent joint rods (13), in the initial state, the distance between the rotational connection points of the joint rods (13) is L0, and the distance between the rotational connection points of the two ends of the connecting rod (7) is L1. When the finger is bent, the joint rod (13) follows the finger movement, and the current sequence I0 obtained by grasping is recorded; after median filtering and smoothing, the current sequence I is obtained; according to the current-resistance relationship curve of the angle detection circuit, a set of resistance value sequence R is obtained. x The position of the slider of the displacement sensor (8) is obtained based on the resistance-displacement characteristic curve of the displacement sensor (8). When the joint angle is 180°, the position of the slider of the displacement sensor (8) at the initial moment is X0, and the position of the slider of the displacement sensor (8) after the finger is bent is X1. The displacement of the slider of the displacement sensor (8) is Δx=(X1-X0), then the three sides of the triangle formed by the two joint rods (13) and the connecting rod (7) are L0; L1; L0+L1-(X1-X0); The joint angle θ can be obtained from the law of cosines as: The joint angle data is integrated and saved to the storage unit; Once the grasping is complete, data acquisition ends. The stored series of joint angle data are converted into two-dimensional images as a tactile dataset. The object is photographed from multiple angles using a camera to create an image dataset of the object's appearance. Based on the tactile and visual datasets, the object's visual and tactile features are fused using the Concatenate method to obtain new feature vectors. These feature vectors are then input into a convolutional neural network for multiple training iterations to obtain a three-dimensional model of the object containing size information. The generated model is then optimized, adjusted, and corrected to achieve accurate three-dimensional model reconstruction of the object.

2. The knuckle angle detection mechanism according to claim 1, characterized in that, The joint rod (13) on which the displacement sensor (8) is installed is provided with a track hole; the transmission rod (9) is slidably connected to the track hole.

3. The knuckle angle detection mechanism according to claim 1, characterized in that, The knuckle angle detection mechanism is provided with at least one set of the joint rods (13) that are rotatably connected in sequence; wherein each set has at least two joint rods (13).

4. The knuckle angle detection mechanism according to claim 3, characterized in that, Each set of sequentially rotatably connected joint rods (13) is provided with 4 joint rods (13).

5. The knuckle angle detection mechanism according to claim 3, characterized in that, It includes a flexible substrate; the data storage module (12) and at least one set of joint rods (13) rotatably connected in sequence are fixedly mounted on the flexible substrate; the joint rods (13) are fixedly connected to the flexible substrate.

6. The knuckle angle detection mechanism according to claim 5, characterized in that, The flexible substrate is provided with 5 sets of joint rods (13) that are rotatably connected in sequence.

7. The knuckle angle detection mechanism according to claim 1, characterized in that, A vibration motor (1206) is installed inside the outer casing (1201).

8. The knuckle angle detection mechanism according to claim 5, characterized in that, The flexible substrate is glove-shaped.

Images