Optical fiber type underwater robot attitude sensing device and method

Abstract

The invention provides an optical fiber type underwater robot attitude sensing device and method. The device comprises a plurality of fiber bragg grating sensors, a base, flexible silica gel, an omnidirectional rotatable transmission shaft, a spring and a stress sensing ball, wherein the plurality of fiber bragg grating sensors are embedded in the flexible silica gel; the flexible silica gel is placed in the circular base and is used as a medium to transmit the force in the vertical direction of the stress sensing ball to the plurality of fiber bragg grating sensors; the base is separated from the lower rotary transmission shaft; the omni-directional rotatable transmission shaft, the spring and the stress sensing ball form an elastic linkage system. The device is installed on the upper surface of a robot, when the posture of the robot deviates, an elastic device formed by connecting a spring and a stress sensing ball slides on the whole flexible silica gel, the stress sensing ball extrudes the flexible silica gel, accordingly, the fiber Bragg wavelength changes, the position of the stress sensing ball can be obtained by adopting a posture analysis model based on deep learning, and the posture of the robot is analyzed. Therefore, different postures of the robot are sensed.

Description

Technical Field

[0001] The present invention relates to the field of touch-pressure sensing technology, and in particular to an optical fiber type underwater robot posture sensing device and method. Background Art

[0002] With the continuous advancement of science and technology, underwater robots play an important role in the fields of ocean exploration, seabed resource development, environmental monitoring, etc. However, due to the complex and changeable marine environment, natural factors such as water flow, ocean currents and undercurrents can easily cause the posture of underwater robots to shift, thus affecting their work efficiency and the accuracy of task execution.

[0003] Traditional attitude detection methods mainly rely on inertial sensors or gyroscopes. However, these devices are susceptible to interference in underwater environments and are difficult to accurately capture subtle attitude changes. At the same time, factors such as high pressure, high humidity and corrosiveness in underwater environments also pose severe challenges to the performance of these devices.

[0004] Prior art 1 [Patent No. CN202311343170.5, disclosing a flexible arm surface force and self-attitude sensing solution based on multiple fiber Bragg gratings] embeds multiple fiber Bragg gratings in the narrow gap between the airbags in the flexible arm. When the airbag expands, the fiber Bragg grating is stretched, and the stretching rate is associated with the attitude of the flexible arm to achieve attitude sensing of the flexible arm. However, this method can only sense the flexible arm and cannot be used to sense the overall attitude of the robot.

[0005] Prior art 2 [Patent No. CN201910128253.X, disclosing a fiber-based hand posture sensing glove] implants optical fibers into the gloves. When the finger joints move, the fiber gratings are deformed. By measuring the change in the central wavelength of the fiber gratings, the finger extension angle is calculated to sense the hand posture. However, this method relies on gloves and is also not applicable to the overall posture perception of robots.

[0006] Inertial sensors are usually composed of accelerometers, gyroscopes, and magnetometers. Accelerometers measure linear acceleration, gyroscopes measure angular velocity, and magnetometers provide heading references. By fusing and processing these sensor data, the attitude information of the object can be inferred. However, during long-term use of inertial sensors, sensor data will drift and accumulate errors, resulting in inaccurate attitude calculation results. At the same time, since the magnetometer in the inertial sensor is easily disturbed by the ambient magnetic field, the accuracy of attitude measurement is not high in areas with strong magnetic fields.

[0007] In addition, in a highly dynamic environment, the measurement accuracy and stability of inertial sensors will decrease, making it difficult to capture subtle changes in attitude. Gyroscopes use the principle of conservation of angular momentum to detect the angular velocity of an object to infer its attitude changes. However, gyroscopes will also drift over long periods of use, and sensor noise will also affect the accuracy of attitude calculations.

[0008] In addition, temperature changes will also affect the performance of the gyroscope, and temperature compensation is required to ensure measurement accuracy. Traditional attitude detection systems usually require multiple sensors to work together, the data fusion algorithm is complex, the system integration is difficult, and the operator experience is required to be high. Summary of the invention

[0009] According to the technical problems raised above, a fiber-optic underwater robot posture perception device and method are provided. The present invention is based on the principle that the fiber Bragg grating wavelength is shifted due to stress stimulation, and a deep learning model is used to establish the relationship between wavelength change and indentation position, sliding trajectory and posture change to perceive the posture of the underwater robot.

[0010] The technical means adopted by the present invention are as follows:

[0011] A fiber-optic underwater robot posture sensing device comprises: a plurality of fiber Bragg grating sensors, a base, a flexible silica gel, an omnidirectional rotatable transmission shaft, a spring and a stress sensing ball, wherein:

[0012] The multiple fiber Bragg grating sensors are embedded in the flexible silicone and are used to transmit in real time the fiber Bragg wavelength changes caused by the component force of the stress sensing ball in the vertical direction;

[0013] The flexible silica gel is placed in the circular base and directly contacts the stress sensing ball when in use, and acts as a medium to transmit the vertical force of the stress sensing ball to the multiple fiber Bragg grating sensors;

[0014] The omnidirectional rotatable transmission shaft is separated from the upper base and is used to drive the elastic device composed of the spring and the stress sensing ball to slide on the entire flexible silicone;

[0015] The spring is connected to the omnidirectional rotatable transmission shaft and the stress sensing ball, and is used to extend and retract to make the stress sensing ball slide when the posture of the underwater robot deviates, and then use the posture analysis model based on deep learning to obtain the position of the stress sensing ball, so as to sense the different postures of the robot;

[0016] The stress sensing ball is used to apply pressure to the flexible silicone.

[0017] Furthermore, the plurality of fiber Bragg grating sensors are provided in 19 pieces and are distributed in three fiber strings, wherein:

[0018] Nine fiber Bragg grating sensors are distributed in the outermost circle of optical fiber, six fiber Bragg grating sensors are distributed in the second circle of optical fiber, and four fiber Bragg grating sensors are distributed in the innermost circle of optical fiber; the distance between the fiber Bragg grating sensors is selected according to the size of the flexible silicone, and the arrangement method takes into account the cross-induction between multiple fiber Bragg grating sensors.

[0019] Furthermore, the optical fiber type underwater robot posture sensing device also includes a transparent protective dome, which is used to seal and protect the internal device, and is also used to prevent the stress sensing ball from escaping from the flexible silicone sensing range due to a large offset force.

[0020] Furthermore, the transparent protective dome is connected to the circular base by threads to achieve a stable connection and ensure waterproof performance.

[0021] Furthermore, the flexible silicone is polydimethylsiloxane and silicone resin, and a plurality of fiber Bragg grating sensors are located at half the thickness of the flexible silicone.

[0022] Furthermore, the spring is a linear compression spring, which provides an appropriate reaction force when the stress sensing ball slides, ensuring that the stress sensing ball is in good contact with the flexible silicone.

[0023] Furthermore, the stress sensing ball is formed by curing a mixture of epoxy resin and iron powder.

[0024] The present invention also provides an underwater robot posture perception method based on the optical fiber type underwater robot posture perception device, comprising:

[0025] S1. The underwater robot has posture deviation:

[0026] The optical fiber type underwater robot posture sensing device is loaded onto the underwater robot. When the underwater robot has posture deviation, the force in the deviation direction drives the omnidirectional rotatable transmission shaft and the elastic device composed of the spring and the stress sensing ball connected thereto to rotate. The spring is compressed to store the energy of the deviation process and provides an appropriate reaction force when the stress sensing ball slides, so that the stress sensing ball is in good contact with the flexible silica gel.

[0027] S2, Fiber Bragg Grating sensor transmits data:

[0028] The flexible silicone is compressed by the force in the vertical direction of the stress sensing ball, so that the grating area of ​​the multiple fiber Bragg grating sensors embedded in it is squeezed, the grating pitch changes, and the refractive index of the optical fiber changes. The fiber Bragg wavelength shifts, and the wavelength shift is used as input data and transmitted to the trained deep learning model for identifying the indentation position to predict the position. The deep learning model for identifying the indentation position is an MLPs classification model, which uses three hexagonal virtual grids to translate and superimpose on the flexible silicone for position segmentation and prediction. Each hexagonal grid consists of 37 hexagons, and the number of grids after the three virtual grids are translated and superimposed is 108. The position of the applied pressure is determined by the weighted centroid of each grid. Among them, the position recognition accuracy of a single hexagonal grid is 96.6%, 97.2% and 96.2% respectively, and the position recognition accuracy of a finer grid after superposition is 98.2%;

[0029] S3. Perceiving the underwater robot’s posture:

[0030] After the prediction is completed, the sliding trajectory of the stress sensing ball on the flexible silicone is obtained; the sliding trajectory is used as input data and transmitted to the posture analysis model to perceive the posture of the underwater robot.

[0031] Compared with the prior art, the present invention has the following advantages:

[0032] 1. The fiber-optic underwater robot posture sensing device provided by the present invention adopts a fiber Bragg grating with high sensitivity, fast response speed, high temperature resistance and anti-electromagnetic interference as a sensor, which is more suitable for complex and changeable underwater environments and can accurately sense the posture of the underwater robot.

[0033] 2. The optical fiber underwater robot posture sensing device provided by the present invention has the advantages of simple structure, accurate sensing, and simple sensing process.

[0034] Based on the above reasons, the present invention can be widely promoted in the fields of touch and pressure sensing. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0036] Figure 1 It is a schematic structural diagram of the optical fiber type underwater robot posture sensing device of the present invention.

[0037] Figure 2This is a distribution diagram of multiple fiber Bragg grating sensors in the fiber-optic underwater robot posture perception device of the present invention.

[0038] In the figure: 1. Multiple fiber Bragg grating sensors; 2. Base; 3. Flexible silicone; 4. Omnidirectional rotatable transmission shaft; 5. Spring; 6. Stress sensing ball; 7. Round base; 8. Fiber optic string; 9. Transparent protective dome. DETAILED DESCRIPTION

[0039] It should be noted that, in the absence of conflict, the embodiments of the present invention and the features in the embodiments can be combined with each other. The present invention will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.

[0040] In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. The following description of at least one exemplary embodiment is actually only illustrative and is by no means intended to limit the present invention and its application or use. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0041] It should be noted that the terms used herein are only for describing specific embodiments and are not intended to limit exemplary embodiments according to the present invention. As used herein, unless the context clearly indicates otherwise, the singular form is also intended to include the plural form. In addition, it should be understood that when the terms "comprising" and / or "including" are used in this specification, it indicates the presence of features, steps, operations, devices, components and / or combinations thereof.

[0042] Unless otherwise specifically stated, the relative arrangement of the parts and steps described in these embodiments, the numerical expressions and numerical values ​​do not limit the scope of the present invention. At the same time, it should be clear that, for ease of description, the sizes of the various parts shown in the drawings are not drawn according to the actual proportional relationship. The technology, methods and equipment known to ordinary technicians in the relevant field may not be discussed in detail, but in appropriate cases, the technology, methods and equipment should be regarded as part of the authorization specification. In all examples shown and discussed here, any specific value should be interpreted as merely exemplary, rather than as a limitation. Therefore, other examples of exemplary embodiments may have different values. It should be noted that similar numbers and letters represent similar items in the following drawings, so once an item is defined in one drawing, it does not need to be further discussed in subsequent drawings.

[0043] In the description of the present invention, it is necessary to understand that the directions or positional relationships indicated by directional words such as "front, back, up, down, left, right", "lateral, vertical, perpendicular, horizontal" and "top, bottom" are usually based on the directions or positional relationships shown in the drawings. They are only for the convenience of describing the present invention and simplifying the description. Unless otherwise specified, these directional words do not indicate or imply that the device or element referred to must have a specific direction or be constructed and operated in a specific direction. Therefore, they cannot be understood as limiting the scope of protection of the present invention: the directional words "inside and outside" refer to the inside and outside relative to the contours of each component itself.

[0044] For ease of description, spatially relative terms such as "above", "above", "on the upper surface of", "above", etc. may be used here to describe the spatial positional relationship between a device or feature and other devices or features as shown in the figure. It should be understood that spatially relative terms are intended to include different orientations of the device in use or operation in addition to the orientation described in the figure. For example, if the device in the accompanying drawings is inverted, the device described as "above other devices or structures" or "above other devices or structures" will be positioned as "below other devices or structures" or "below their position devices or structures". Thus, the exemplary term "above" can include both "above" and "below". The device can also be positioned in other different ways (rotated 90 degrees or in other orientations), and the spatially relative descriptions used here are interpreted accordingly.

[0045] In addition, it should be noted that the use of terms such as "first" and "second" to limit components is only for the convenience of distinguishing the corresponding components. If not otherwise stated, the above terms have no special meaning and therefore cannot be understood as limiting the scope of protection of the present invention.

[0046] like Figure 1 As shown, the present invention provides a fiber-optic underwater robot posture sensing device, comprising: a plurality of fiber Bragg grating sensors 1, a base 2, a flexible silica gel 3, an omnidirectional rotatable transmission shaft 4, a spring 5 and a stress sensing ball 6, wherein:

[0047] The multiple fiber Bragg grating sensors 1 are embedded in the flexible silicone 3 and are used to transmit in real time the fiber Bragg wavelength changes caused by the component force of the stress sensing ball 6 in the vertical direction;

[0048] The flexible silica gel 3 is placed in the circular base 7 and is in direct contact with the stress sensing ball 6 when in use, and acts as a medium to transmit the vertical force of the stress sensing ball 6 to the multiple fiber Bragg grating sensors 1;

[0049] The omnidirectional rotatable transmission shaft 4 is separated from the upper base 2 and is used to drive the elastic device composed of the spring 5 and the stress sensing ball 6 to slide on the entire flexible silicone 3;

[0050] The spring 5 is connected to the omnidirectional rotatable transmission shaft 4 and the stress sensing ball 6, and is used to extend and retract to make the stress sensing ball 6 slide when the underwater robot deviates from its posture, and then use the posture analysis model based on deep learning to obtain the position of the stress sensing ball 6, so as to sense different postures of the robot;

[0051] The stress sensing ball 6 is used to apply pressure to the flexible silica gel 3 .

[0052] When specifically implemented, as a preferred embodiment of the present invention, Figure 2 As shown, the plurality of fiber Bragg grating sensors 1 are provided in 19 pieces, which are distributed in three fiber strings 8, wherein:

[0053] Nine fiber Bragg grating sensors 1 are distributed in the outermost circle of optical fibers, six fiber Bragg grating sensors 1 are distributed in the second circle of optical fibers, and four fiber Bragg grating sensors 1 are distributed in the innermost circle of optical fibers; the distance between the fiber Bragg grating sensors 1 is selected according to the size of the flexible silicone 3, and the arrangement method takes into account the cross-induction between the multiple fiber Bragg grating sensors 1.

[0054] When implementing the invention, as a preferred embodiment of the invention, see Figure 1 The optical fiber type underwater robot posture sensing device also includes a transparent protective dome 9, which is used to seal and protect the internal device, and is also used to prevent the stress sensing ball 6 from escaping from the sensing range of the flexible silicone 3 due to a large offset force.

[0055] In specific implementation, as a preferred embodiment of the present invention, the transparent protective dome 9 and the circular base 7 are connected by threads to achieve a stable connection and ensure waterproof performance.

[0056] In specific implementation, as a preferred embodiment of the present invention, the flexible silicone 3 is polydimethylsiloxane and silicone resin, 16 mm thick, and a plurality of fiber Bragg grating sensors 1 are located at a position where the flexible silicone is 8 mm thick.

[0057] In specific implementation, as a preferred embodiment of the present invention, the spring 5 is a linear compression spring, which provides an appropriate reaction force when the stress sensing ball 6 slides, ensuring that the stress sensing ball 6 is in good contact with the flexible silicone 3.

[0058] In specific implementation, as a preferred embodiment of the present invention, the stress sensing ball 6 is formed by curing a mixture of epoxy resin and iron powder, and weighs 0.5 Newton.

[0059] The embodiment of the present invention further provides an underwater robot posture perception method implemented based on the optical fiber type underwater robot posture perception device, comprising:

[0060] S1. The underwater robot has posture deviation:

[0061] The optical fiber type underwater robot posture sensing device is loaded onto the underwater robot. When the underwater robot has posture deviation, the force in the deviation direction drives the omnidirectional rotatable transmission shaft 4 and the elastic device composed of the spring 5 and the stress sensing ball 6 connected thereto to rotate. The spring 5 compresses and stores the energy of the deviation process, and provides an appropriate reaction force when the stress sensing ball 6 slides, so that the stress sensing ball 6 is in good contact with the flexible silica gel 3.

[0062] S2, Fiber Bragg Grating sensor transmits data:

[0063] The flexible silicone 3 is compressed by the force in the vertical direction of the stress sensing ball 6, so that the grating area of ​​the multiple fiber Bragg grating sensors 1 embedded therein is squeezed, the grating pitch changes, and the refractive index of the fiber changes, and the fiber Bragg wavelength shifts. The wavelength shift is used as input data and transmitted to the trained deep learning model for identifying the indentation position to predict the position. The deep learning model for identifying the indentation position is an MLPs classification model, which uses three hexagonal virtual grids to translate and superimpose on the flexible silicone 3 for position segmentation and prediction. Each hexagonal grid consists of 37 hexagons. The number of grids after the three virtual grids are translated and superimposed is 108. The position of applying pressure is determined by the weighted centroid of each grid. Among them, the position recognition accuracy of a single hexagonal grid is 96.6%, 97.2% and 96.2% respectively, and the position recognition accuracy of a finer grid after superposition is 98.2%;

[0064] S3. Perceiving the underwater robot’s posture:

[0065] After the prediction is completed, the sliding trajectory of the stress sensing ball 6 on the flexible silicone 3 is obtained; the sliding trajectory is used as input data and transmitted to the posture analysis model to sense the posture of the underwater robot.

[0066] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or replace some or all of the technical features therein with equivalents. However, these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present invention.

Claims

1. A fiber-optic underwater robot posture sensing device, characterized in that: include: A plurality of fiber Bragg grating sensors (1), a base (2), a flexible silicone (3), an omnidirectional rotatable transmission shaft (4), a spring (5) and a stress sensing ball (6), wherein: The plurality of fiber Bragg grating sensors (1) are embedded in the flexible silicone rubber (3) and are used to transmit in real time the fiber Bragg wavelength change caused by the component force of the stress sensing ball (6) in the vertical direction; The flexible silica gel (3) is placed in the circular base (7) and is in direct contact with the stress sensing ball (6) when in use, and acts as a medium to transmit the vertical force of the stress sensing ball (6) to the plurality of fiber Bragg grating sensors (1); The omnidirectional rotatable transmission shaft (4) is separated from the upper base (2) and is used to drive the elastic device formed by the spring (5) and the stress sensing ball (6) to slide on the entire flexible silica gel (3); The spring (5) is connected to the omnidirectional rotatable transmission shaft (4) and the stress sensing ball (6), and is used to extend and retract to make the stress sensing ball (6) slide when the posture of the underwater robot deviates, and then use a posture analysis model based on deep learning to obtain the position of the stress sensing ball (6), so as to sense different postures of the robot; The stress sensing ball (6) is used to apply pressure to the flexible silica gel (3).

2. The optical fiber type underwater robot posture sensing device according to claim 1, characterized in that: The plurality of fiber Bragg grating sensors (1) are provided in a number of 19 and are distributed in three fiber strings (8), wherein: Nine fiber Bragg grating sensors (1) are distributed in the outermost circle of optical fibers, six fiber Bragg grating sensors (1) are distributed in the second circle of optical fibers, and four fiber Bragg grating sensors (1) are distributed in the innermost circle of optical fibers; the distance between the fiber Bragg grating sensors (1) is selected according to the size of the flexible silicone (3), and the arrangement method takes into account the cross-induction between the multiple fiber Bragg grating sensors (1).

3. The optical fiber type underwater robot posture sensing device according to claim 1, characterized in that: The optical fiber type underwater robot posture sensing device also includes a transparent protective dome (9) for sealing and protecting the internal device, and also for preventing the stress sensing ball (6) from escaping from the sensing range of the flexible silica gel (3) due to a large offset force.

4. The optical fiber type underwater robot posture sensing device according to claim 3, characterized in that: The transparent protective dome (9) and the circular base (7) are connected by threads to achieve a stable connection and ensure waterproof performance.

5. The optical fiber type underwater robot posture sensing device according to claim 1, characterized in that: The flexible silicone (3) is polydimethylsiloxane and silicone resin, and a plurality of fiber Bragg grating sensors (1) are located at half the thickness of the flexible silicone (3).

6. The optical fiber type underwater robot posture sensing device according to claim 1, characterized in that: The spring (5) is a linear compression spring, which provides appropriate elastic force when the stress sensing ball (6) slides, ensuring that the stress sensing ball (6) is in good contact with the flexible silica gel (3).

7. The optical fiber type underwater robot posture sensing device according to claim 1, characterized in that: The stress sensing ball (6) is formed by curing a mixture of epoxy resin and iron powder.

8. A method for underwater robot posture perception based on the optical fiber underwater robot posture perception device according to any one of claims 1 to 7, characterized in that: include: S1. The underwater robot has posture deviation: The optical fiber type underwater robot posture sensing device is mounted on the upper surface of the underwater robot. When the underwater robot has posture deviation, the force in the deviation direction drives the omnidirectional rotatable transmission shaft (4) and the elastic device composed of the spring (5) and the stress sensing ball (6) connected thereto to rotate. The spring (5) compresses and stores the energy of the deviation process and provides appropriate elastic force when the stress sensing ball (6) slides, so that the stress sensing ball (6) is in good contact with the flexible silica gel (3). S2, Fiber Bragg Grating sensor transmits data: The flexible silicone rubber (3) is compressed by the vertical force of the stress sensing ball (6), so that the grating area of ​​the multiple fiber Bragg grating sensors (1) embedded therein is squeezed, the grating pitch changes, and the refractive index of the optical fiber changes, and the fiber Bragg wavelength shifts. The wavelength shift is used as input data and transmitted to the trained deep learning model for identifying the indentation position to predict the position. The deep learning model for identifying the indentation position is an MLPs classification model, which uses three hexagonal virtual grids to be translated and superimposed on the flexible silicone rubber (3) for position segmentation and prediction. Each hexagonal grid consists of 37 hexagons. The number of grids after the three virtual grids are translated and superimposed is 108. The position of applying pressure is determined by the weighted centroid of each grid. Among them, the position recognition accuracy of a single hexagonal grid is 96.6%, 97.2% and 96.2% respectively, and the position recognition accuracy of a finer grid after superposition is 98.2%; S3. Perceiving the underwater robot’s posture: After the prediction is completed, the sliding trajectory of the stress sensing ball (6) on the flexible silicone (3) is obtained, and the sliding trajectory is used as input data and transmitted to the posture analysis model, so as to sense the posture of the underwater robot.

Images