Optical tactile sensor, elastic body module manufacturing and information acquisition method
By using an optical design in the tactile sensor, including an elastomer, colored markers, and an opaque reflective layer, the problems of low accuracy and interference caused by the distribution of multiple sensitive elements are solved, achieving higher detection accuracy and adaptability.
Patent Information
- Application Number
- CN202010616930.5
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2020-06-30
- Publication Date
- 2024-11-22
- Estimated Expiration
- 2040-06-30
AI Technical Summary
Existing tactile sensors suffer from low accuracy and mutual interference due to the concentrated distribution of multiple sensitive elements.
An optical tactile sensor is used, including a sensor housing, an elastomer, a telescopic component, an illumination source, and an image acquisition component. By attaching colored markers and an opaque reflective layer to the elastomer, the image acquisition component collects the deformation information of the elastomer, avoiding mutual interference between multiple sensitive elements.
It improves the accuracy of tactile sensors, reduces mutual interference between components, expands the detection force range, and enhances adaptability and fit in complex environments.
Smart Images

Figure CN111761579B_ABST
Abstract
Description
Technical Field
[0001] The embodiments of the present application relate to sensor technology and artificial intelligence technology, and in particular to an optical tactile sensor, an elastomer module manufacturing method and information acquisition method. Background Art
[0002] Tactile sensors are sensors used in robots to mimic the sense of touch.
[0003] In related technologies, tactile sensors measure multi-dimensional contact force by integrating high-density electronic sensor devices in a small space. For example, tactile sensors use vertically crossed electrodes, that is, arrays, and determine the location of the force point by scanning the rows and columns of the capacitive array sensing units.
[0004] However, the tactile sensors in the above-mentioned related technologies have multiple sensitive elements that are centrally distributed and interfere with each other, resulting in low accuracy of the tactile sensors. Summary of the invention
[0005] The embodiment of the present application provides an optical tactile sensor, an elastic body module manufacturing method and information acquisition method, which improves the accuracy of the tactile sensor. The technical solution is as follows:
[0006] On the one hand, an embodiment of the present application provides an optical tactile sensor, the optical tactile sensor comprising: a sensor housing, an elastic body, and a telescopic component, an illumination light source, and an image acquisition component located inside the sensor housing;
[0007] The top of the elastic body is exposed from the sensor housing, and an opaque reflective layer is attached to the top of the elastic body; at least one colored marking point is attached to the first outer surface of the elastic body, and the first outer surface is the outer surface of the elastic body facing the opaque reflective layer;
[0008] The telescopic component is arranged close to the second outer surface of the elastic body, and the second outer surface is opposite to the first outer surface; the telescopic direction of the telescopic component is the same as the deformation direction of the elastic body;
[0009] The viewing angle of the image acquisition component includes the colored marking point, and the illumination light source is used to provide illumination conditions for the image acquisition component.
[0010] On the other hand, an embodiment of the present application provides a method for manufacturing an elastic body module, wherein the elastic body module is applied to an optical tactile sensor, and the method includes:
[0011] Filling the silicone mixture into the mold cavity of the elastomer mold and solidifying to obtain the elastomer;
[0012] Dipping a marking point drawing reagent onto the elastomer to obtain at least one colored marking point after solidification;
[0013] Covering the colored marking point with powder having a reflective effect to form an opaque reflective layer;
[0014] The silica gel mixture is covered on the top of the opaque reflective layer until the opaque reflective layer no longer floats, and the elastomer module is obtained after solidification.
[0015] On the other hand, an embodiment of the present application provides an information acquisition method based on an optical tactile sensor, wherein the optical tactile sensor is the optical tactile sensor as described in the above aspect, and the method includes:
[0016] Acquire images acquired by the image acquisition component; wherein the images include a first image acquired when the elastic body is not in contact with the object to be detected, and a second image set acquired when the elastic body is in contact with the object to be detected, wherein the second image set includes at least one second image;
[0017] determining information related to a contact force acting on the elastic body based on the first image and the at least one second image;
[0018] Eliminating the colored marking points contained in the second image to obtain a third image, wherein the third image is used to reflect the deformation information of the opaque reflective layer when the elastic body contacts the object to be detected;
[0019] Surface information of the object to be detected is obtained according to the third image.
[0020] On the other hand, an embodiment of the present application provides an information acquisition device based on an optical tactile sensor, wherein the optical tactile sensor is the optical tactile sensor as described in the above aspect, and the device includes:
[0021] An image acquisition module, used to acquire images acquired by the image acquisition component; wherein the images include a first image acquired when the elastic body is not in contact with the object to be detected, and a second image set acquired when the elastic body is in contact with the object to be detected, wherein the second image set includes at least one second image;
[0022] an information determination module, configured to determine information related to a contact force acting on the elastic body based on the first image and the at least one second image;
[0023] An image processing module, used for eliminating the colored marking points contained in the second image to obtain a third image, wherein the third image is used for reflecting the deformation information of the opaque reflective layer when the elastic body contacts the object to be detected;
[0024] The information determination module is further used to obtain surface information of the object to be detected based on the third image.
[0025] On the other hand, an embodiment of the present application provides a computer-readable storage medium, wherein the storage medium stores at least one instruction, at least one program, a code set, or an instruction set, and the at least one instruction, the at least one program, the code set, or the instruction set is loaded and executed by a processor to implement the information acquisition method based on an optical tactile sensor as described in the above aspects.
[0026] On the other hand, an embodiment of the present application provides a computer device, comprising a processor and a memory, wherein the memory stores at least one instruction, at least one program, a code set or an instruction set, and the at least one instruction, the at least one program, the code set or the instruction set is loaded and executed by the processor to implement the information acquisition method based on the optical tactile sensor as described in the above aspects.
[0027] In another aspect, a computer program product or a computer program is provided, the computer program product or the computer program comprising computer instructions, the computer instructions being stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computer device executes the information acquisition method based on the optical tactile sensor provided in various optional implementations of the above aspects.
[0028] The technical solution provided in the embodiments of the present application can bring the following beneficial effects:
[0029] By setting an image acquisition component inside the tactile sensor, the image acquisition component can be used to collect deformation information of the elastomer, and the deformation information of the elastomer includes deformation information of colored marking points and deformation information of the opaque reflective layer. The deformation information of the colored marking points is used to indicate relevant information of the contact force, and the deformation information of the opaque reflective layer is used to indicate surface information of the object to be detected. The embodiment of the present application uses an optical method, and there is no situation where multiple sensitive elements are concentratedly distributed, so there will be no mutual interference, thereby improving the accuracy of the tactile sensor. BRIEF DESCRIPTION OF THE DRAWINGS
[0030] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.
[0031] Figure 1 is a schematic diagram of a robot provided by an embodiment of the present application;
[0032] Figure 2 is a schematic diagram of the overall appearance of an optical tactile sensor provided by an embodiment of the present application;
[0033] Figure 3 is a cross-sectional schematic diagram of an optical tactile sensor provided by an embodiment of the present application;
[0034] Figure 4 is a schematic diagram of an optical tactile sensor provided by another embodiment of the present application;
[0035] Figure 5 is a schematic diagram of an elastomeric tray provided by an embodiment of the present application;
[0036] Figure 6 is a schematic diagram of a telescopic assembly base provided by an embodiment of the present application;
[0037] Figure 7 This is a connection diagram of a telescopic assembly provided by an embodiment of the present application;
[0038] Figure 8 is a schematic diagram of a sensor housing provided by an embodiment of the present application;
[0039] Fig. 9 is a schematic diagram of an illumination light source provided by an embodiment of the present application;
[0040] Fig.10 is a schematic diagram of an image acquisition component provided by an embodiment of the present application;
[0041] Fig.11 is a flow chart of a method for manufacturing an elastic body module provided by an embodiment of the present application;
[0042] Fig.12 This is a schematic diagram of the effect of an elastic body module provided by an embodiment of the present application;
[0043] Fig.13 is a flow chart of an information acquisition method provided by an embodiment of the present application;
[0044] Fig.14 is a flow chart of an information acquisition method provided by another embodiment of the present application;
[0045] Fig.15 is a schematic diagram of force performance of different contact forces provided by an embodiment of the present application;
[0046] Fig.16 is a schematic diagram of a third image provided by an embodiment of the present application;
[0047] Fig.17 is a block diagram of an information acquisition device provided by an embodiment of the present application;
[0048] Fig.18 It is a structural block diagram of a computer device provided by an embodiment of the present application. DETAILED DESCRIPTION
[0049] In order to make the objectives, technical solutions and advantages of the present application clearer, the implementation methods of the present application will be further described in detail below with reference to the accompanying drawings.
[0050] Artificial Intelligence (AI) is the theory, method, technology and application system that uses a machine controlled by a mathematical computer or a digital computer to simulate, extend and expand human intelligence, perceive the environment, acquire knowledge and use knowledge to obtain the best results. In other words, artificial intelligence is a comprehensive technology in computer science that attempts to understand the essence of intelligence and produce a new intelligent machine that can respond in a similar way to human intelligence. Artificial intelligence is to study the design principles and implementation methods of various intelligent machines so that machines have the functions of perception, reasoning and decision-making.
[0051] Artificial intelligence is a comprehensive discipline that covers a wide range of fields, including both hardware-level and software-level technologies. The basic technologies of artificial intelligence generally include sensors, dedicated artificial intelligence chips, cloud computing, distributed storage, big data processing technology, operation / interaction systems, mechatronics and other technologies. Artificial intelligence software technologies mainly include computer vision technology, speech processing technology, natural language processing technology, and machine learning / deep learning.
[0052] Sensors are mainly used for intelligent perception of the environment, actions, images, etc., and are important data inputs for artificial intelligence and human-computer interaction hardware.
[0053] Computer vision technology (CV) is a science that studies how to make machines "see". To put it more specifically, it refers to the use of cameras and computers to replace human eyes to identify, track and measure targets, and further perform graphic processing to make computer processing into images that are more suitable for human observation or transmission to instruments for detection. As a scientific discipline, computer vision studies related theories and technologies, and attempts to establish an artificial intelligence system that can obtain information from images or multi-dimensional data. Computer vision technology usually includes image processing, image recognition, image semantic understanding, image retrieval, OCR (Optical Character Recognition), video processing, video semantic understanding, video content / behavior recognition, three-dimensional object reconstruction, 3D technology, virtual reality, augmented reality, simultaneous positioning and mapping, and other technologies, as well as common biometric recognition technologies such as face recognition and fingerprint recognition.
[0054] Machine Learning (ML) is a multi-disciplinary subject that involves probability theory, statistics, approximation theory, convex analysis, algorithm complexity theory and other disciplines. It specializes in studying how computers simulate or implement human learning behavior to acquire new knowledge or skills and reorganize existing knowledge structures to continuously improve their performance. Machine learning is the core of artificial intelligence and the fundamental way to make computers intelligent. Its applications are spread across all areas of artificial intelligence. Machine learning and deep learning usually include artificial neural networks, belief networks, reinforcement learning, transfer learning, inductive learning, and teaching learning.
[0055] With the research and advancement of artificial intelligence technology, artificial intelligence technology has been studied and applied in many fields, such as common smart homes, smart wearable devices, virtual assistants, smart speakers, smart marketing, unmanned driving, automatic driving, drones, robots, smart medical care, smart customer service, etc. I believe that with the development of technology, artificial intelligence technology will be applied in more fields and play an increasingly important role.
[0056] With the continuous development of the robotics industry, more and more occasions require robots (robots are mechanical devices that automatically perform tasks and are controlled by computer programs or electronic circuits) to be able to stably grasp the objects to be detected. The optical tactile sensor provided in the embodiments of the present application, which involves sensor technology, computer vision technology of artificial intelligence, machine learning and other technologies, can be applied to robot scenes, for example, industrial robots, service robots, etc. Furthermore, the tactile sensor provided in the embodiments of the present application can be applied to scenes with higher and more delicate requirements for robot operation, such as household service robots, nursing robots in medical scenes, surgical operation robotic arms, finishing factory robots, etc. Tactile sensor technology simulates the skin perception function of humans, qualitatively and quantitatively perceives and feeds back the surface information of the object to be detected and the relevant information of the contact force acting on the contact surface. Computer vision technology can guide robots to manipulate objects, for example, lift, grab, and rotate objects.
[0057] like Figure 1 As shown, the robot 100 is provided with an optical tactile sensor 200. For example, the part of the robot 100 that needs to contact the object to be detected is provided with the optical tactile sensor 200. In a possible implementation, the robot 100 is also provided with a processing component 300, and data can be transmitted between the optical tactile sensor 200 and the processing component 300. The optical tactile sensor 200 sends the collected image to the processing component 300, so that the processing component 300 processes the collected image to obtain the surface information of the object to be detected and the relevant information of the contact force acting on the contact surface. The processing component 300 can issue an operation instruction based on the surface information of the object to be detected and the relevant information of the contact force, and the operation instruction is used to control the robot 100 to operate the object to be detected. In a possible implementation, the optical tactile sensor 200 sends the captured image to the server so that the server processes the captured image to obtain surface information of the object to be detected and relevant information of the contact force acting on the contact surface, and then the server sends the surface information of the object to be detected and relevant information of the contact force acting on the contact surface to the processing component 300 in the robot 100. Of course, in a possible implementation, a processing component can also be set inside the optical tactile sensor. For ease of introduction, the embodiment of the present application refers to the execution subject that processes the image captured by the optical tactile sensor as a computer device. The computer device can refer to a processing component set in the robot, or to a processing component inside the optical tactile sensor, or to a server, and the embodiment of the present application does not limit this.
[0058] The present application is described below through several embodiments.
[0059] Combined with reference Figure 2 and Figure 3 , which shows a schematic diagram of an optical tactile sensor provided in an embodiment of the present application. The optical tactile sensor 200 includes: a sensor housing 210, an elastic body 220, and a telescopic component 230, an illumination light source 240 and an image acquisition component 250 located inside the sensor housing 210.
[0060] The top of the elastic body 220 is exposed from the sensor housing 210 and an opaque reflective layer 260 is attached to the top of the elastic body 220. At least one colored marking point 270 is attached to the first outer surface of the elastic body 220, which is the outer surface of the elastic body 220 facing the opaque reflective layer 260.
[0061] The elastomer 220 is a transparent silicone elastomer, and the hardness of the elastomer 220 can be adjusted accordingly according to the use occasion of the optical tactile sensor 200 and the properties of the object to be detected. In a possible implementation, the elastomer 220 is made of a first silicone rubber composite material, a second silicone rubber composite material, and a silicone softener, and the first silicone rubber composite material and the second silicone rubber composite material have different compositions. The hardness of the elastomer 220 can be changed by adjusting the mass ratio of the first silicone rubber composite material, the second silicone rubber composite material, and the silicone softener.
[0062] The opaque reflective layer 260 refers to an opaque film with a reflective effect, and the opacity of the opaque reflective layer 260 can be set as needed. In a possible implementation, the opaque reflective layer 260 is made of an ultrafine aluminum powder layer. Aluminum powder is commonly known as "silver powder", and ultrafine aluminum powder is aluminum powder with a micron-level particle size or a nanometer-level particle size. Of course, in other possible implementations, the opaque reflective layer 260 can also be made of other fine powders with good reflective effects. By using fine powder to make the opaque reflective layer 260, there will be no situation where the powder can be clearly perceived in the image captured by the image acquisition component 250, and thus it will not affect the surface information of the object to be detected in the later stage.
[0063] The colored marking points 270 are colored marking points, and the color of the colored marking points 270 and the distribution position on the first outer surface of the elastic body 220 can be adjusted. For example, according to the size of the object to be detected or the contact mode of the object to be detected, the density of the colored marking points 270 or the color of the colored marking points 270 can be adjusted. In a possible implementation, the colored marking points 270 are made by mixing the third silicone rubber composite material, the fourth silicone rubber composite material, and the silica gel diluent, and then adding a coloring agent. The third silicone rubber composite material and the fourth silicone rubber composite material have different components.
[0064] Because the top of the elastic body 220 is exposed to the sensor housing 210, the elastic body 220 can contact the object to be detected. When the elastic body 220 contacts the object to be detected, the elastic body 220 is deformed. At this time, the opaque reflective layer 260 attached to the top of the elastic body 220 and the colored marking point 270 attached to the first outer surface of the elastic body 220 will also be deformed accordingly, and the deformation information of the colored marking point 270 and the deformation information of the opaque reflective layer 260 reflect the relevant information of the contact force and the surface information of the object to be detected.
[0065] The telescopic component 230 is disposed close to the second outer surface of the elastic body 220 , and the second outer surface is opposite to the first outer surface; the telescopic direction of the telescopic component 230 is the same as the deformation direction of the elastic body 220 .
[0066] The telescopic component 230 refers to a component that can be telescopic, and its telescopic direction is the same as the deformation direction of the elastic body 220. The deformation direction of the elastic body 220 refers to the vertical direction, and the vertical direction mentioned in the embodiment of the present application refers to the direction perpendicular to both the first outer surface and the second outer surface. Therefore, the telescopic component 230 is vertically arranged close to the second outer surface of the elastic body 220. When the elastic body 220 is deformed, the telescopic component 230 telescopes in the deformation direction of the elastic body 220.
[0067] The telescopic component 230 alleviates the deformation of the elastic body 220 when it contacts the object to be detected to a certain extent, expands the detection force range of the optical touch sensor 200, and makes the application scenarios of the optical touch sensor 200 wider. In addition, the telescopic component 230 increases the degree of freedom of the elastic body 220, so that the elastic body 220 can better adapt to the surface structure of the object to be detected, so that the elastic body 220 and the object to be detected have a better fit effect, which is helpful for the detection of the surface information of the object to be detected, and more degrees of freedom support the use of the optical touch sensor 200 in more complex environmental structures.
[0068] The viewing angle of the image acquisition component 250 includes a colored marking point 270 , and the illumination light source 240 is used to provide illumination conditions for the image acquisition component 250 .
[0069] The image acquisition component 250 refers to a component that can capture images. In a possible implementation, the image acquisition component 250 is a camera or other image sensing device, which is not limited in the present embodiment. The image acquisition component 250 is located below the elastic body 220 and can completely record the surface information of the elastic body 220. The surface information of the elastic body 220 includes at least one of the following: deformation information of the colored marking point 270 and deformation information of the opaque reflective layer 260.
[0070] The illumination light source 240 is located inside the optical tactile sensor 200, and provides effective illumination conditions for the image acquisition component 250, so that the image acquisition component 250 can receive the light reflected from the opaque reflective layer 260. In a possible implementation, the illumination light source 240 includes white mixed light and RGB (Red Green Blue) three-color light source.
[0071] To summarize, in the technical solution provided by the embodiment of the present application, an image acquisition component is arranged inside the tactile sensor, and the image acquisition component can be used to collect deformation information of the elastomer, and the deformation information of the elastomer includes deformation information of the colored marking points and deformation information of the opaque reflective layer, the deformation information of the colored marking points is used to indicate relevant information of the contact force, and the deformation information of the opaque reflective layer is used to indicate surface information of the object to be detected. The embodiment of the present application uses an optical method, and there is no situation where multiple sensitive elements are concentratedly distributed, so there will be no mutual interference, thereby improving the accuracy of the tactile sensor.
[0072] In addition, the telescopic component alleviates the deformation of the elastic body when it contacts the object to be detected to a certain extent, expands the detection force range of the optical tactile sensor, and makes the application scenarios of the optical tactile sensor wider.
[0073] In addition, the telescopic component increases the degrees of freedom of the elastomer, allowing the elastomer to better adapt to the surface structure of the object to be detected, making the elastomer fit better with the object to be detected, which helps to detect the surface information of the object to be detected, and more degrees of freedom support the use of optical tactile sensors in more complex environmental structures.
[0074] In an exemplary embodiment, Figure 4 As shown, the optical touch sensor 200 further includes: a telescopic assembly base 280 and an elastomeric tray 290 located inside the sensor housing 210 .
[0075] The elastic body 220 is disposed on the elastic body tray 290. Optionally, the elastic body 220 is disposed in the elastic body tray 290.
[0076] One end of the telescopic assembly 230 is connected to the bottom of the elastic body tray 290, and the other end of the telescopic assembly 230 is connected to the telescopic assembly base 280. The bottom of the elastic body tray 290 refers to the part of the elastic body tray 290 that is closest to the second outer surface of the elastic body 220.
[0077] The structure of the elastomeric tray 290 can be as follows Figure 5 As shown, Figure 5 (a) shows a front view of the elastomeric tray 290, Figure 5 (b) shows a top view of the elastomeric tray 290, Figure 5(c) shows a bottom view of the elastic tray 290. The cross-sectional shape of the elastic tray 290 is consistent with the cross-sectional shape of the elastic body 220. When the elastic body 220 is deformed, the elastic tray 290 moves in the deformation direction. In addition, a receiving groove is provided at the bottom of the elastic tray 290, and the receiving groove can be used to receive one end of the telescopic assembly 230.
[0078] The structure of the telescopic assembly base 280 can be as follows Figure 6 As shown, Figure 6 (a) and Figure 6 (c) shows a front view of the telescopic assembly base 280, Figure 6 (b) shows a bottom view of the telescopic assembly base 280 , on which a receiving groove is provided, which can be used to receive the other end of the telescopic assembly 230 .
[0079] In possible implementations, such as Figure 7 As shown, a first magnet 231 is provided at one end of the telescopic component 230, and a second magnet 291 is provided at the bottom of the elastomer tray 290. The magnetic properties of the first magnet 231 and the second magnet 291 are opposite, and the contact surface between the first magnet and the second magnet 231 is opposite magnetic attraction. One end of the telescopic component 230 is connected to the bottom of the elastomer 290 through the two magnets with opposite magnetic properties. Exemplarily, the first magnet 231 and the second magnet 291 can be fixed to one end of the telescopic component 230 and the bottom of the elastomer tray 290 respectively using glue.
[0080] The other end of the telescopic component 230 is provided with a third magnet 232, and the telescopic component base 280 is provided with a fourth magnet 281. The third magnet 232 and the fourth magnet 281 have opposite magnetic properties, and the contact surface between the third magnet 232 and the fourth magnet 281 is opposite magnetic attraction. The other end of the telescopic component 230 is connected to the telescopic component base 280 through the two magnets with opposite magnetic properties. Exemplarily, the third magnet 232 and the fourth magnet 281 can be fixed to the other end of the telescopic component 230 and the telescopic component base 280 respectively using glue.
[0081] Of course, in other possible implementations, one end of the telescopic component 230 can also be connected to the bottom of the elastomeric tray 290 in other ways, and the other end of the telescopic component 230 can also be connected to the telescopic component base 280 in other ways, and the embodiment of the present application is not limited to this.
[0082] The telescopic assembly base 280 is fixed on the sensor housing 210. In a possible implementation, the telescopic assembly base 280 is fixedly connected to the sensor housing 210 by screws, and at least one threaded hole may be provided in the contact area between the telescopic assembly base 280 and the sensor housing 210, and the threaded hole is used to fix the screw, so that the telescopic assembly base 280 is fixed on the sensor housing 210.
[0083] In a possible implementation, the telescopic component 230 includes at least one spring. The spring telescopes in the deformation direction of the elastic body 220 .
[0084] In a possible implementation, when the number of springs is greater than one, the springs are evenly distributed at the bottom of the elastic body 220. By evenly distributing the springs at the bottom of the elastic body 220, each spring can be subjected to a relatively uniform force.
[0085] In an exemplary embodiment, Figure 8 As shown, the sensor housing 210 is provided with a first receiving groove 211 on the housing portion located on the peripheral side of the elastic body 220, and the illumination light source 240 is provided in the first receiving groove 211; Figure 3 As shown, a second accommodating groove 212 is disposed at the bottom of the sensor housing 210 , and the image acquisition component 250 is disposed in the second accommodating groove 212 .
[0086] Take the illumination light source 240 as an RGB light source as an example for description. At this time, the illumination light source 240 can be respectively Fig. 9 The three LED (Light Emitting Diode) circuit boards shown: a blue LED circuit board, a red LED circuit board and a green LED circuit board are used as RGB light sources. The first receiving groove 211 includes three receiving grooves, which are respectively used to receive the above-mentioned blue LED circuit board, red LED circuit board and green LED circuit board, and the above-mentioned three receiving grooves are evenly distributed on the periphery of the elastomer 220.
[0087] Compared to the first outer surface of the elastic body 220, the bottom of the sensor housing 210 is closer to the second outer surface of the elastic body 220. Fig.10 As shown, at this time, the image acquisition component 250 can be placed flat in the second receiving groove 212.
[0088] Please refer to Fig.11 , which shows a flow chart of a method for manufacturing an elastic body module provided by an embodiment of the present application, the elastic body module can be applied to the optical tactile sensor introduced in the above embodiment, and the elastic body module includes the elastic body, colored marking points and opaque reflective layer described in the above embodiment. The method includes the following steps.
[0089] Step 1101, filling the silicone mixture into the mold cavity of the elastomer mold, and obtaining the elastomer after solidification.
[0090] In a possible implementation, the silicone mixture includes a first silicone rubber composite material, a second silicone rubber composite material, and a silicone softener, and the first silicone rubber composite material and the second silicone rubber composite material have different components. Exemplarily, the first silicone rubber composite material uses SMOOTH-ON's Solaris (A) reagent, the second silicone rubber composite material uses SMOOTH-ON's Solaris (B) reagent, and the silicone softener uses SMOOTH-ON's Slacker reagent.
[0091] In a possible implementation, the mass ratio of the first silicone rubber composite material, the second silicone rubber composite material and the silicone softener is the same, for example, the mass ratio of the first silicone rubber composite material, the second silicone rubber composite material and the silicone softener is 1:1:1.
[0092] In actual production, it is necessary to vacuum remove the bubbles in the silicone mixture, and then pour it into the mold cavity of the designed elastomer mold and wait for 6 hours (hours) for the elastomer to solidify.
[0093] Step 1102, dip a marking point drawing reagent onto the elastomer, and obtain at least one colored marking point after solidification.
[0094] In a possible implementation, the marking point drawing reagent includes a third silicone rubber composite material, a fourth silicone rubber composite material, a silicone diluent, and a coloring reagent, and the third silicone rubber composite material and the fourth silicone rubber composite material have different components. Exemplarily, the third silicone rubber composite material uses the Ecoflex-00110 (A) reagent of SMOOTH-ON, the fourth silicone rubber composite material uses the Ecoflex-00110 (B) reagent of SMOOTH-ON, and the coloring reagent uses the Slic-Pig coloring reagent of SMOOTH-ON. The transparency of the Ecoflex-00110 reagent is lower than that of the Solaris reagent and the hardness after solidification is greater than that of the Solaris reagent.
[0095] In a possible implementation, the mass ratio of the third silicone rubber composite material, the fourth silicone rubber composite material, and the silicone diluent is the same, for example, the mass ratio of the third silicone rubber composite material, the fourth silicone rubber composite material, and the silicone diluent is 1:1:1, and then an appropriate amount of coloring reagent is added to ensure that the marking point drawing reagent can have a clearly discernible coloring effect.
[0096] Dip a small amount of marking point drawing reagent onto the first outer surface of the elastomer, draw colored marking points of the desired shape and distribution density, and wait for 3-4 hours until the colored marking points solidify.
[0097] Step 1103, covering the colored marking points with powder having a reflective effect to form an opaque reflective layer.
[0098] In a possible implementation, the powder with a reflective effect includes ultrafine aluminum powder. The ultrafine aluminum powder is used to cover the elastomer with colored marking points with a spray gun or a brush until the elastomer no longer directly transmits light in the vertical direction, thereby obtaining an opaque reflective layer.
[0099] Step 1104, covering the opaque reflective layer with the silicone mixture until the opaque reflective layer no longer floats and solidifies to obtain an elastomer module.
[0100] Pour the silicone mixture for making the elastomer until it completely covers the opaque reflective layer, ensuring that the opaque reflective layer no longer floats, and wait for 6 hours for the silicone to solidify. At this point, the elastomer module is completed. The effect of the elastomer module can be seen as follows: Fig.12 shown.
[0101] In summary, in the technical solution provided in the embodiment of the present application, a marking point drawing reagent is dipped onto the elastomer, and at least one colored marking point is obtained after solidification, and the fit between the colored marking point and the elastomer is good.
[0102] In addition, compared with the laser coating method in the related art, the embodiment of the present application can change the color of the colored marking point according to the needs.
[0103] Please refer to Fig.13 , which shows a flow chart of an information acquisition method based on an optical tactile sensor provided by an embodiment of the present application. The optical tactile sensor is the optical tactile sensor 200 as described in the above embodiment. The method includes the following steps.
[0104] Step 1301, obtaining an image captured by an image acquisition component.
[0105] In an embodiment of the present application, the image includes a first image captured when the elastomer is not in contact with the object to be detected, and a second image set captured when the elastomer is in contact with the object to be detected, and the second image set includes at least one second image.
[0106] In a possible implementation, the image acquisition component records the entire contact process with the object to be detected to obtain a recorded video; the recorded video is sent to a computer device, and then the computer device extracts frames from the recorded video to obtain a first image and a second image set.
[0107] Step 1302: Determine information related to a contact force acting on an elastic body based on the first image and at least one second image.
[0108] Exemplarily, the contact force related information includes at least one of the following: the contact force action type and the contact force action magnitude. The contact force action type includes shear force, vertical force, torque force, etc.
[0109] Exemplarily, the image captured when the elastic body is not in contact with the object to be detected is used as the detection reference to determine the original center position coordinates of each colored marking point; each frame of the image during the contact process is compared in the order of image acquisition to determine the deformation center position coordinates of each colored marking point, thereby determining the type and magnitude of the contact force. In a possible implementation, the first image and at least one second image are processed by a contact force recognition model to obtain relevant information about the contact force. The contact force recognition model refers to a model for identifying relevant information about the contact force. The process of determining the relevant information about the contact force can be found in the following embodiments, which will not be introduced here.
[0110] Step 1303: Eliminate the colored marking points contained in the second image to obtain a third image.
[0111] In the embodiment of the present application, the third image is used to reflect the deformation information of the opaque reflective layer when the elastic body contacts the object to be detected.
[0112] Optionally, the computer device randomly extracts a second image from the second image set, eliminates the colored marking points contained therein, and obtains a third image.
[0113] Exemplarily, the colored marker points contained in the second image are eliminated by an image restoration algorithm to obtain a third image. In a possible implementation, the image restoration algorithm is selected according to the size of the colored marker points. For example, when the colored marker points are small, the image restoration algorithm can adopt a Gaussian filter method; when the colored marker points are large, the image restoration algorithm can adopt a TV (Total Variation) model, Context-Encoders, or Criminisi algorithm. Of course, other image restoration algorithms can also be used for processing, and the embodiments of the present application are not limited to this.
[0114] Step 1304: Obtain surface information of the object to be detected according to the third image.
[0115] Exemplarily, the surface information of the object to be detected includes at least one of the following: the material of the object to be detected, the cross-sectional profile of the object to be detected, and the surface protrusions of the object to be detected. The material of the object to be detected can reflect the texture of the object to be detected; the cross-sectional profile of the object to be detected can reflect the shape of the object to be detected; the surface protrusions of the object to be detected refer to whether the surface of the object to be detected is protruding, which can reflect the smoothness of the object to be detected.
[0116] The computer equipment obtains the surface information of the object to be detected, including the material of the object to be detected, the cross-sectional profile of the object to be detected, the surface protrusions of the object to be detected, etc., based on the deformation information of the opaque reflective layer through deep learning and other means.
[0117] In summary, in the technical solution provided in the embodiments of the present application, by simultaneously determining the relevant information of the contact force and the surface information of the object to be detected, the precision of the robot operation process can be increased and the overall operation effect can be improved.
[0118] In an exemplary embodiment, Fig.14 As shown, it shows a flowchart of an information acquisition method provided by another embodiment of the present application, and the method includes the following steps.
[0119] Step 1401, obtaining an image captured by an image acquisition component.
[0120] The images include a first image captured when the elastomer is not in contact with the object to be detected, and a second image set captured when the elastomer is in contact with the object to be detected, wherein the second image set includes at least one second image.
[0121] Step 1402, determining the original center position coordinates of each colored marking point in the first image, where the original center position coordinates refer to the center position of the colored marking point when the elastic body does not contact the object to be detected.
[0122] Optionally, the first image is input into a contact force recognition model, and the contact force recognition model can recognize each colored marking point in the first image and the original center position coordinates of the colored marking point.
[0123] Step 1403, determining the deformation center position coordinates of each colored marking point in each second image, where the deformation center position coordinates refer to the center position of the colored marking point when the elastic body contacts the object to be detected.
[0124] Optionally, the second image set is input into a contact force recognition model, and the contact force recognition model can recognize each colored marking point in the second image and the coordinates of the deformation center position of the colored marking point.
[0125] Step 1404, determining relevant information of the contact force according to the coordinates of each original center position and each deformation center position coordinates.
[0126] Optionally, step 1404 includes the following sub-steps:
[0127] 1. Taking the original center position coordinates as the vector starting point and the deformation center position coordinates as the vector end point, determine the target vector corresponding to each colored mark point in each second image.
[0128] 2. Determine the direction change information and size change information of the target vector according to the image acquisition sequence to obtain the relevant information of the contact force.
[0129] In the embodiment of the present application, the direction change information is used to indicate the type of contact force when the elastic body contacts the object to be detected, and the size change information is used to indicate the size of the contact force when the elastic body contacts the object to be detected.
[0130] like Fig.15 As shown, it is assumed that the computer device acquires images acquired by three image acquisition components, the first image is the first image 151, the second image and the third image are both second images 152, the original center position coordinates of each colored mark point in the first image 151 are used as the vector starting point, and the deformation center position coordinates of each colored mark point in the second image 152 are used as the vector end point, and the target vector corresponding to each colored mark point in each second image 152 is determined. Different types of contact forces have different effects, that is, the direction change information and magnitude change information of the vector are different. Fig.15 (a) shows the shear force behavior, Fig.15 (b) shows the force performance of the shear force and the vertical force acting together. Fig.15 (c) shows the force performance of the torque force. The contact force identification model can determine the contact force type and contact force size based on the direction change information and size change information of the target vector.
[0131] Before the contact force recognition model is put into practical application, the contact force recognition model needs to be trained. Optionally, the training process of the contact force recognition model is as follows: obtain a training data set, the training data set includes at least one training data and standard related information of the contact force corresponding to the training data, the training data includes a first sample image and a second sample image set, and the second sample image set includes at least one second sample image; input the first sample image and the second sample image set into the contact force recognition model to obtain prediction related information of the contact force corresponding to the training data; train the contact force recognition model according to the standard related information and the prediction related information.
[0132] Step 1405: Eliminate the colored marking points contained in the second image to obtain a third image.
[0133] In the embodiment of the present application, the third image is used to reflect the deformation information of the opaque reflective layer when the elastic body contacts the object to be detected.
[0134] like Fig.16 As shown, the colored marking points contained in the second image 152 are eliminated to obtain a third image 153.
[0135] Step 1406: Process the third image using a surface information recognition model to obtain surface information of the object to be detected.
[0136] In an embodiment of the present application, the surface information recognition model is a machine learning model used to recognize surface information of an object to be detected.
[0137] Different objects to be detected have different surface information and different deformations of the opaque reflective layer. The surface information recognition model analyzes and processes the deformation information of the opaque reflective layer to obtain the surface information of the object to be detected.
[0138] Optionally, before the third image is processed by the surface information recognition model to obtain the surface information of the object to be detected, the surface information recognition model needs to be trained, and the training process may include the following steps:
[0139] First, a training data set is obtained, where the training data set includes at least one sample image and standard surface information corresponding to the sample image.
[0140] Second, the sample image is input into the surface information recognition model to obtain the predicted surface information corresponding to the sample image.
[0141] Third, the surface information recognition model is trained according to the standard surface information and the predicted surface information to obtain a trained surface information recognition model.
[0142] The loss function of the surface information recognition model is determined according to the standard surface information and the predicted surface information, and the surface information recognition model is trained according to the loss function to obtain a trained surface information recognition model.
[0143] The following are device embodiments of the present application, which can be used to execute the method embodiments of the present application. For details not disclosed in the device embodiments of the present application, please refer to the method embodiments of the present application.
[0144] Please refer to Fig.17 , which shows a block diagram of an information acquisition device based on an optical tactile sensor provided by an embodiment of the present application. The optical tactile sensor is the optical tactile sensor as described in the above embodiment, and the device has the function of implementing the above method example, and the function can be implemented by hardware or by hardware executing corresponding software. The device 1700 may include: an image acquisition module 1710, an information determination module 1720 and an image processing module 1730.
[0145] An image acquisition module 1710 is used to acquire images acquired by the image acquisition component; wherein the images include a first image acquired when the elastic body is not in contact with the object to be detected, and a second image set acquired when the elastic body is in contact with the object to be detected, wherein the second image set includes at least one second image;
[0146] An information determination module 1720, configured to determine information related to a contact force acting on the elastic body based on the first image and the at least one second image;
[0147] An image processing module 1730 is used to eliminate the colored marking points contained in the second image to obtain a third image, wherein the third image is used to reflect the deformation information of the opaque reflective layer when the elastic body contacts the object to be detected;
[0148] The information determination module 1720 is further configured to obtain surface information of the object to be detected according to the third image.
[0149] In summary, in the technical solution provided in the embodiments of the present application, by simultaneously determining the relevant information of the contact force and the surface information of the object to be detected, the precision of the robot operation process can be increased and the overall operation effect can be improved.
[0150] In the exemplary embodiment, the information determination module 1720 includes: a coordinate determination unit and an information determination unit (not shown in the figure).
[0151] A coordinate determination unit, used to determine the original center position coordinates of each colored marking point in the first image, wherein the original center position coordinates refer to the center position of the colored marking point when the elastic body does not contact the object to be detected;
[0152] The coordinate determination unit is further used to determine the deformation center position coordinates of each colored marking point in each second image, wherein the deformation center position coordinates refer to the center position of the colored marking point when the elastic body contacts the object to be detected;
[0153] The information determination unit is used to determine the relevant information of the contact force according to each of the original center position coordinates and each of the deformation center position coordinates.
[0154] In an exemplary embodiment, the information determination unit is used to:
[0155] Taking the original center position coordinates as the vector starting point and the deformation center position coordinates as the vector end point, determining the target vector corresponding to each colored marking point in each second image;
[0156] Determine the direction change information and the size change information of the target vector according to the image acquisition sequence, and obtain the relevant information of the contact force;
[0157] The direction change information is used to indicate the type of contact force when the elastic body contacts the object to be detected, and the magnitude change information is used to indicate the magnitude of the contact force when the elastic body contacts the object to be detected.
[0158] In an exemplary embodiment, the information determination module 1720 is used to:
[0159] Processing the third image by using a surface information recognition model to obtain surface information of the object to be detected;
[0160] Among them, the surface information recognition model is a machine learning model used to identify the surface information of the object to be detected.
[0161] It should be noted that the device provided in the above embodiment, when implementing its functions, is only illustrated by the division of the above functional modules. In actual applications, the above functions can be assigned to different functional modules as needed, that is, the content structure of the device is divided into different functional modules to complete all or part of the functions described above. In addition, the device and method embodiments provided in the above embodiment belong to the same concept, and the specific implementation process is detailed in the method embodiment, which will not be repeated here.
[0162] Please refer to Fig.18 , which shows a structural block diagram of a computer device 1800 provided in one embodiment of the present application. The computer device 1800 may be Figure 1 The robot 100 introduced in the embodiment is used to implement the above-mentioned information acquisition method based on the optical tactile sensor.
[0163] Typically, the computer device 1800 includes a processor 1801 and a memory 1802 .
[0164] The processor 1801 may include one or more processing cores, such as a 4-core processor, an 8-core processor, etc. The processor 1801 may be implemented in at least one hardware form of DSP (Digital Signal Processing), FPGA (Field Programmable Gate Array), and PLA (Programmable Logic Array). The processor 1801 may also include a main processor and a coprocessor. The main processor is a processor for processing data in an awake state, also known as a CPU (Central Processing Unit); the coprocessor is a low-power processor for processing data in a standby state. In some embodiments, the processor 1801 may be integrated with a GPU (Graphics Processing Unit), which is responsible for rendering and drawing the content to be displayed on the display screen. In some embodiments, the processor 1801 may also include an AI (Artificial Intelligence) processor, which is used to process computing operations related to machine learning.
[0165] The memory 1802 may include one or more computer-readable storage media, which may be non-transitory. The memory 1802 may also include high-speed random access memory and non-volatile memory, such as one or more disk storage devices and flash memory storage devices.
[0166] In some embodiments, the computer device 1800 may also optionally include: a peripheral device interface 1803 and at least one peripheral device. The processor 1801, the memory 1802 and the peripheral device interface 1803 may be connected via a bus or a signal line. Each peripheral device may be connected to the peripheral device interface 1803 via a bus, a signal line or a circuit board. Specifically, the peripheral device may include: at least one of a display screen 1804, an audio circuit 1805, a communication interface 1806 and a power supply 1807.
[0167] Those skilled in the art will understand that Fig.18 The structure shown in the figure does not constitute a limitation on the computer device 1800, and the computer device 1800 may include more or less components than shown in the figure, or combine some components, or adopt a different arrangement of components.
[0168] In an exemplary embodiment, a computer device is also provided, the computer device comprising a processor and a memory, wherein the memory stores at least one instruction, at least one program, code set or instruction set. The at least one instruction, at least one program, code set or instruction set is configured to be executed by one or more processors to implement the above-mentioned information acquisition method based on the optical tactile sensor.
[0169] In an illustrative embodiment, a computer-readable storage medium is also provided, in which at least one instruction, at least one program, a code set or an instruction set is stored. When the at least one instruction, the at least one program, the code set or the instruction set is executed by a processor of a computer device, the above-mentioned information acquisition method based on an optical tactile sensor is implemented.
[0170] Optionally, the computer-readable storage medium may be a ROM (Read-Only Memory), a RAM (Random Access Memory), a CD-ROM (Compact Disc Read-Only Memory), a magnetic tape, a floppy disk, an optical data storage device, or the like.
[0171] In an exemplary embodiment, a computer program product or a computer program is also provided, the computer program product or the computer program includes computer instructions, and the computer instructions are stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computer device executes the information acquisition method based on the optical tactile sensor provided in the above various optional implementations.
[0172] It should be understood that the "multiple" mentioned in this article refers to two or more. "And / or" describes the association relationship of associated objects, indicating that three relationships may exist. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. The character " / " generally indicates that the objects associated before and after are in an "or" relationship. In addition, the step numbers described in this article only illustrate a possible execution sequence between the steps. In some other embodiments, the above steps may not be executed in the order of the numbers, such as two steps with different numbers are executed at the same time, or two steps with different numbers are executed in the opposite order to the diagram. The embodiments of the present application are not limited to this.
[0173] The above description is only an exemplary embodiment of the present application and is not intended to limit the present application. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present application shall be included in the protection scope of the present application.
Claims
1. An optical tactile sensor, characterized in that: The optical tactile sensor comprises: a sensor housing, an elastic body, and a telescopic component, an illumination light source and an image acquisition component located inside the sensor housing; The top of the elastic body is exposed from the sensor housing, and an opaque reflective layer is attached to the top of the elastic body; at least one colored marking point is attached to the first outer surface of the elastic body, and the first outer surface is the outer surface of the elastic body facing the opaque reflective layer; The telescopic component is arranged close to the second outer surface of the elastic body, and the second outer surface is opposite to the first outer surface; the telescopic direction of the telescopic component is the same as the deformation direction of the elastic body; The viewing angle of the image acquisition component includes the colored marking point, and the illumination light source is used to provide illumination conditions for the image acquisition component.
2. The optical tactile sensor according to claim 1, wherein: The telescoping assembly includes at least one spring.
3. The optical tactile sensor according to claim 2, wherein: When the number of the springs is greater than one, the springs are evenly distributed at the bottom of the elastic body.
4. The optical tactile sensor according to claim 1, wherein: The optical tactile sensor further includes: a telescopic assembly base and an elastomeric tray located inside the sensor housing; The elastic body is arranged on the elastic body tray; One end of the telescopic assembly is connected to the bottom of the elastic body tray, and the other end of the telescopic assembly is connected to the telescopic assembly base; The telescopic assembly base is fixed on the sensor housing.
5. The optical tactile sensor according to claim 4, characterized in that: A first magnet is disposed at one end of the telescopic assembly, and a second magnet is disposed at the bottom of the elastic body tray, wherein the first magnet has opposite magnetic properties to the second magnet; A third magnet is arranged at the other end of the telescopic component, and a fourth magnet is arranged on the base of the telescopic component. The magnetic properties of the third magnet and the fourth magnet are opposite.
6. The optical tactile sensor according to any one of claims 1 to 5, characterized in that: A first receiving groove is provided on the housing of the sensor housing located on the peripheral side of the elastic body, and the illumination light source is provided in the first receiving groove; A second accommodating groove is arranged at the bottom of the sensor housing, and the image acquisition component is arranged in the second accommodating groove.
7. A method for manufacturing an elastic body module, characterized in that: The elastic body module is applied to an optical tactile sensor, and the method comprises: Filling the silicone mixture into the mold cavity of the elastomer mold and solidifying to obtain the elastomer; Dipping a marking point drawing reagent onto the elastomer, and obtaining at least one colored marking point after solidification, wherein the transparency of the preparation material of the marking point drawing reagent is lower than the transparency of the preparation material of the silica gel mixture, and the hardness of the preparation material of the marking point drawing reagent after solidification is greater than the hardness of the preparation material of the silica gel mixture after solidification; Covering the colored marking point with powder having a reflective effect to form an opaque reflective layer; The silica gel mixture is covered on the top of the opaque reflective layer until the opaque reflective layer no longer floats, and the elastomer module is obtained after solidification.
8. The method according to claim 7, characterized in that The silicone mixture includes a first silicone rubber composite material, a second silicone rubber composite material and a silicone softener, and the first silicone rubber composite material and the second silicone rubber composite material have different components; The marking point drawing reagent comprises a third silicone rubber composite material, a fourth silicone rubber composite material, a silicone diluent, and a coloring reagent, wherein the third silicone rubber composite material and the fourth silicone rubber composite material have different components; The powder with reflective effect includes ultrafine aluminum powder.
9. An information acquisition method based on an optical tactile sensor, characterized in that: The optical tactile sensor is the optical tactile sensor according to any one of claims 1 to 6, and the method comprises: Acquire images acquired by the image acquisition component; wherein the images include a first image acquired when the elastic body is not in contact with the object to be detected, and a second image set acquired when the elastic body is in contact with the object to be detected, wherein the second image set includes at least one second image; determining information related to a contact force acting on the elastic body based on the first image and the at least one second image; Eliminating the colored marking points contained in the second image to obtain a third image, wherein the third image is used to reflect the deformation information of the opaque reflective layer when the elastic body contacts the object to be detected; Surface information of the object to be detected is obtained according to the third image.
10. The method according to claim 9, characterized in that Determining information related to the contact force acting on the elastic body according to the first image and the at least one second image includes: Determine the original center position coordinates of each colored marking point in the first image, wherein the original center position coordinates refer to the center position of the colored marking point when the elastic body does not contact the object to be detected; Determine the deformation center position coordinates of each colored marking point in each second image, wherein the deformation center position coordinates refer to the center position of the colored marking point when the elastic body contacts the object to be detected; The relevant information of the contact force is determined according to each of the original center position coordinates and each of the deformation center position coordinates.
11. The method according to claim 10, characterized in that Determining the relevant information of the contact force according to the original center position coordinates and the deformation center position coordinates includes: Taking the original center position coordinates as the vector starting point and the deformation center position coordinates as the vector end point, determining the target vector corresponding to each colored marking point in each second image; Determine the direction change information and the size change information of the target vector according to the image acquisition sequence, and obtain the relevant information of the contact force; The direction change information is used to indicate the type of contact force when the elastic body contacts the object to be detected, and the magnitude change information is used to indicate the magnitude of the contact force when the elastic body contacts the object to be detected.
12. The method according to any one of claims 9 to 11, characterized in that: The step of obtaining surface information of the object to be detected according to the third image includes: Processing the third image by using a surface information recognition model to obtain surface information of the object to be detected; Among them, the surface information recognition model is a machine learning model used to identify the surface information of the object to be detected.
13. An information acquisition device based on an optical tactile sensor, characterized in that: The optical tactile sensor is the optical tactile sensor according to any one of claims 1 to 6, and the device comprises: An image acquisition module, used to acquire images acquired by the image acquisition component; wherein the images include a first image acquired when the elastic body is not in contact with the object to be detected, and a second image set acquired when the elastic body is in contact with the object to be detected, wherein the second image set includes at least one second image; an information determination module, configured to determine information related to a contact force acting on the elastic body based on the first image and the at least one second image; An image processing module, used for eliminating the colored marking points contained in the second image to obtain a third image, wherein the third image is used for reflecting the deformation information of the opaque reflective layer when the elastic body contacts the object to be detected; The information determination module is further used to obtain surface information of the object to be detected based on the third image.
14. A computer device, characterized in that: The computer device includes a processor and a memory, wherein the memory stores at least one program, and the at least one program is loaded and executed by the processor to implement the information acquisition method based on the optical tactile sensor according to any one of claims 9 to 12.
15. A computer-readable storage medium, characterized in that: The storage medium stores at least one program, and the at least one program is loaded and executed by the processor to implement the information acquisition method based on the optical tactile sensor according to any one of claims 9 to 12.
