Tactile positioning method, device and electronic equipment

Abstract

The present application discloses a tactile positioning method, device and electronic device, belonging to the technical field of tactile sensors. A positioning block group is provided on the surface of a target object, and the method comprises: when a manipulator contacts the target object, obtaining a first image corresponding to the target object, the first image comprising a plurality of target positioning points, the target positioning points being determined based on the positioning blocks in the positioning block group contacted by the manipulator; based on the first image, obtaining a second image comprising a plurality of reference points; based on the offset information between each of the target positioning points and the closest reference point, determining the contact position information of the manipulator contacting the target object. Based on the offset information between each of the target positioning points and the closest reference point, a decoding operation can be performed to determine the contact position information, without the need for comparison and matching with other feature information, which can improve the efficiency of tactile positioning and achieve rapid response of the manipulator.

Description

Technical Field

[0001] The present application belongs to the technical field of tactile sensors, and in particular, relates to a tactile positioning method, device and electronic equipment. Background Art

[0002] Vision-based tactile sensors (VBTS) can capture the texture of objects with pixel-level spatial resolution, which can even exceed the human tactile system. VBTS has been widely integrated into various types of robot grippers. Accurately identifying the position and direction of VBTS contacting an object helps improve the accuracy of robot operation, thereby enabling more precise manipulation of objects.

[0003] However, the current contact positioning of VBTS usually requires pre-calculation of the features of the object surface and matching the acquired texture features with the feature information in the feature library, which results in low efficiency of contact positioning. Summary of the invention

[0004] The present application aims to solve at least one of the technical problems existing in the prior art. To this end, the present application proposes a tactile positioning method, device and electronic device, which can improve the efficiency of tactile positioning and achieve rapid response of a manipulator.

[0005] In a first aspect, the present application provides a tactile positioning method, wherein a positioning block group is provided on the surface of a target object, and the method comprises:

[0006] When the manipulator contacts the target object, a first image corresponding to the target object is acquired, wherein the first image includes a plurality of target positioning points, and the target positioning points are determined based on the positioning blocks in the positioning block group that are contacted by the manipulator;

[0007] Based on the first image, acquiring a second image including a plurality of reference points;

[0008] Based on the offset information between each of the target positioning points and the closest reference point, the contact position information of the manipulator contacting the target object is determined.

[0009] According to the tactile positioning method of the present application, by setting a positioning block group on the surface of the target object, when the manipulator contacts the target object, a first image corresponding to the area on the surface of the target object contacted by the manipulator is obtained, and a reference point is determined according to the target positioning point corresponding to the positioning block in the first image to obtain a second image. Based on the offset information of each target positioning point and the closest reference point, a decoding operation is performed to determine the contact position information. There is no need to compare and match with other feature information, which can improve the efficiency of tactile positioning and achieve rapid response of the manipulator.

[0010] According to one embodiment of the present application, acquiring a second image including a plurality of reference points based on the first image includes:

[0011] Acquire a target direction of the first image, a target orthogonal point of the first image, and a target grid width of the first image;

[0012] Based on the target direction, the target orthogonal point and the target grid width, a target grid is established in the first image to obtain the second image, and the reference point is a grid point of the target grid.

[0013] According to an embodiment of the present application, acquiring the target direction of the first image, the target orthogonal point of the first image, and the target grid width of the first image includes:

[0014] Connect any two of the target positioning points to obtain a first baseline;

[0015] When the distance between each of the target positioning points and the first baseline meets a preset distance condition, determining the first baseline as the target baseline;

[0016] The direction of the target baseline is determined as the target direction.

[0017] According to an embodiment of the present application, acquiring the target direction of the first image, the target orthogonal point of the first image, and the target grid width of the first image includes:

[0018] Acquiring the target direction;

[0019] Determine a first coordinate value of the target direction based on a distance between each of the target positioning points and a corresponding first adjacent point, where the first adjacent point is another target positioning point adjacent to the target positioning point in the target direction;

[0020] Determine a second coordinate value in the first direction based on the distance between each of the target positioning points and the corresponding second adjacent point, where the second adjacent point is the other target positioning point adjacent to the target positioning point in the first direction;

[0021] Determining the target orthogonal point based on the first coordinate value and the second coordinate value;

[0022] Wherein, the target direction and the first direction intersect.

[0023] According to an embodiment of the present application, acquiring the target direction of the first image, the target orthogonal point of the first image, and the target grid width of the first image includes:

[0024] Acquire a first distance between each of the target positioning points and a corresponding third adjacent point, where the third adjacent point is the other target positioning point that is closest to the target positioning point in each direction;

[0025] The target grid width is determined based on each of the first distances.

[0026] According to an embodiment of the present application, the position of each positioning block in the positioning block group is determined by quasi-de Bruijn sequence coding, and the contact position information of the manipulator contacting the target object based on the offset information of each target positioning point and the closest reference point is determined, including:

[0027] Based on the offset information between each of the target positioning points and the closest reference point, the contact position information is determined by decoding the quasi-de Bruijn sequence.

[0028] According to an embodiment of the present application, determining the contact position information of the manipulator contacting the target object based on the offset information between each of the target positioning points and the closest reference point includes:

[0029] The contact position information is determined based on the offset information between each of the target positioning points and the closest reference point, the target direction of the first image, the reference contact direction of the manipulator, and the reference contact center of the manipulator.

[0030] According to an embodiment of the present application, when the manipulator contacts the target object, acquiring a first image corresponding to the target object includes:

[0031] When the manipulator contacts the target object, a third image corresponding to the target object is acquired, wherein the third image includes a plurality of target positioning blocks, and the target positioning blocks are determined based on the positioning blocks in the positioning block group that are contacted by the manipulator;

[0032] Performing binarization processing on the third image to obtain a binarized image corresponding to the third image;

[0033] Based on the binary image, the center point of the target positioning block is extracted as the target positioning point to obtain the first image.

[0034] In a second aspect, the present application provides a tactile positioning device, wherein a positioning block group is provided on the surface of a target object, and the device comprises:

[0035] an acquisition module, configured to acquire a first image corresponding to the target object when the manipulator contacts the target object, wherein the first image includes a plurality of target positioning points, and the target positioning points are determined based on the positioning blocks in the positioning block group that are contacted by the manipulator;

[0036] A first processing module, configured to acquire a second image including a plurality of reference points based on the first image;

[0037] The second processing module is used to determine the contact position information of the manipulator contacting the target object based on the offset information between each of the target positioning points and the closest reference point.

[0038] According to the tactile positioning device of the present application, by setting a positioning block group on the surface of the target object, when the manipulator contacts the target object, a first image corresponding to the area on the surface of the target object contacted by the manipulator is obtained, and a reference point is determined according to the target positioning point corresponding to the positioning block in the first image to obtain a second image. Based on the offset information of each target positioning point and the closest reference point, a decoding operation is performed to determine the contact position information, and there is no need to compare and match with other feature information, which can improve the efficiency of tactile positioning and achieve rapid response of the manipulator.

[0039] In a third aspect, the present application provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the tactile positioning method as described in the first aspect above when executing the computer program.

[0040] In a fourth aspect, the present application provides a non-transitory computer-readable storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the tactile positioning method as described in the first aspect above.

[0041] In a fifth aspect, the present application provides a computer program product, including a computer program, which, when executed by a processor, implements the tactile positioning method as described in the first aspect above.

[0042] Additional aspects and advantages of the present application will be given in part in the description below, and in part will become apparent from the description below, or will be learned through the practice of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] The above and / or additional aspects and advantages of the present application will become apparent and easily understood from the description of the embodiments in conjunction with the following drawings, in which:

[0044] Figure 1 is a structural schematic diagram of a tactile positioning module provided in an embodiment of the present application;

[0045] Figure 2 is a schematic flow chart of a method for preparing a tactile positioning module provided in an embodiment of the present application;

[0046] Figure 3 is a flow chart of a tactile positioning method provided in an embodiment of the present application;

[0047] Figure 4 is a schematic diagram of a second image provided in an embodiment of the present application;

[0048] Figure 5 is a schematic diagram of the structure of a tactile positioning device provided in an embodiment of the present application;

[0049] Figure 6 It is a schematic diagram of the structure of an electronic device provided in an embodiment of the present application.

[0050] Reference numerals:

[0051] Base 110, positioning block 120, acquisition module 510, first processing module 520, second processing module 530,

[0052] Electronic device 600 , processor 601 , memory 602 . DETAILED DESCRIPTION

[0053] The following will be combined with the drawings in the embodiments of the present application to clearly describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, rather than all the embodiments. All other embodiments obtained by ordinary technicians in this field based on the embodiments in the present application belong to the scope of protection of this application.

[0054] The terms "first", "second", etc. in the specification and claims of the present application are used to distinguish similar objects, and are not used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable under appropriate circumstances, so that the embodiments of the present application can be implemented in an order other than those illustrated or described here, and the objects distinguished by "first", "second", etc. are generally of one type, and the number of objects is not limited. For example, the first object can be one or more. In addition, "and / or" in the specification and claims represents at least one of the connected objects, and the character " / " generally indicates that the objects associated with each other are in an "or" relationship.

[0055] In conjunction with the accompanying drawings, the tactile positioning module, the preparation method of the tactile positioning module, the tactile positioning method, the tactile positioning device, the electronic device and the readable storage medium provided in the embodiments of the present application are described in detail through specific embodiments and their application scenarios.

[0056] like Figure 1 As shown, the tactile positioning module includes a base 110 and a positioning block group.

[0057] The base 110 is disposed on the surface of the target object, the positioning block group is disposed on the outer surface of the base 110 , and the positioning block group includes a plurality of positioning blocks 120 , and the plurality of positioning blocks 120 correspond to a plurality of positioning positions on the surface of the target object.

[0058] In this embodiment, the base 110 may be a component including a planar structure or a curved structure, and the base 110 may provide physical support for the positioning block group to ensure that the positions of the positioning blocks 120 in the positioning block group are fixed on the base 110 .

[0059] The positioning block group includes multiple positioning blocks 120, and the multiple positioning blocks 120 can be arranged on the base 110 according to a certain pattern. For example, the multiple positioning blocks 120 can form a matrix arrangement, a ring arrangement around the center point of the base 110, or a straight line arrangement, etc. The size, shape and material of the positioning blocks 120 at different positions can be different, thereby forming a texture effect.

[0060] The multiple positioning blocks 120 can also be arranged according to a set code, for example, they can be encoded by a quasi-de Bruijn sequence, and the multiple positioning blocks 120 are arranged according to the encoding result of the quasi-de Bruijn sequence. The multiple positioning blocks 120 can be visually arranged irregularly, thereby forming a texture effect.

[0061] The target object can be any object in production, life, medical and other scenarios. For example, the target object can be machine parts on a production line, bottled beverages, packaged foods, or surgical instruments.

[0062] In this embodiment, the base 110 is disposed on the surface of the target object, the positioning block group is disposed on the outer surface of the base 110, and the plurality of positioning blocks 120 correspond to a plurality of positioning positions on the surface of the target object.

[0063] The outer surface of the substrate 110 is used to install the positioning block group. The outer surface of the substrate 110 is provided with a positioning block group. The substrate 110 is set on the surface of the target object. The surface of the target object is attached with multiple positioning blocks 120 through the substrate 110 to form a three-dimensional texture on the surface of the target object.

[0064] Each positioning block 120 corresponds to a positioning position on the surface of the target object, and the positioning position is used to represent the position of the positioning block 120 on the target object.

[0065] In actual implementation, the target object may correspond to an object coordinate system, the origin of the object coordinate system may be the center or center of gravity of the target object, etc., and the positioning position may be expressed as a coordinate value in the object coordinate system.

[0066] In this embodiment, the tactile positioning module is used to contact the vision-based tactile sensors (VBTS) of the manipulator, and the vision-based tactile sensors are used to obtain the positioning block images of the contact positioning block group, and based on the positioning block images, determine the contact information of the vision-based tactile sensors contacting the target object.

[0067] Among them, the manipulator is a mechanical device that can imitate the functions of human hands. The manipulator can perform operations such as grasping, carrying, assembling and manipulating target objects. The visual tactile sensor is a sensor that obtains tactile information based on the captured image by photographing the surface of the object it touches. The tactile information may include the pressure applied by the visual tactile sensor on the object, the position where the visual tactile sensor touches the object, and the direction and angle at which the visual tactile sensor touches the object.

[0068] The visual tactile sensor may be disposed at a position where the manipulator is used to contact the target object. When the manipulator grasps the target object, the visual tactile sensor may contact all or part of the positioning block 120 on the target object.

[0069] When the visual tactile sensor contacts the positioning block 120 on the surface of the target object, it captures the area corresponding to the contacted positioning block 120 to obtain a positioning block image. The positioning block image includes the positioning block 120 contacted by the visual tactile sensor. The positioning block image can represent the arrangement of multiple positioning blocks 120 contacted by the visual tactile sensor.

[0070] In this embodiment, the contact information of the visual tactile sensor contacting the target object may be determined based on the arrangement of the plurality of positioning blocks 120 represented by the positioning block image.

[0071] Among them, the contact information may include contact position and contact direction. The contact position is the point or area on the target object where the visual tactile sensor contacts the contact position. The contact position can be expressed as a coordinate point or a group of coordinate points in the object coordinate system. The contact direction is the orientation or angle of the visual tactile sensor relative to the target object. The visual tactile sensor can correspond to a sensor reference direction, and the target object can correspond to an object reference direction. The contact direction can be expressed as the angle between the sensor reference direction and the object reference direction.

[0072] In actual implementation, the quasi-de Bruijn sequence can be used for encoding, and multiple positioning blocks 120 can be arranged according to the encoding result of the quasi-de Bruijn sequence. The arrangement of the multiple positioning blocks 120 represented by the positioning block image is decoded and calculated using the characteristics of the quasi-de Bruijn sequence to obtain the contact position, and the angle between the sensor reference direction and the object reference direction is calculated to obtain the contact direction.

[0073] According to the tactile positioning module provided in the embodiment of the present application, the base 110 is arranged on the surface of the target object, the positioning block group is arranged on the outer surface of the base 110, and the surface of the target object is attached with multiple positioning blocks 120 through the base 110, so that a three-dimensional texture is formed on the surface of the target object, so that the visual tactile sensor of the manipulator can identify the position and direction of contact with the target object in real time and accurately, thereby improving the accuracy of the manipulator in manipulating the object.

[0074] In some embodiments, the base 110 is detachably disposed on the surface of the target object.

[0075] In this embodiment, the substrate 110 is an independent component. The substrate 110 can be installed on the surface of the target object, and the substrate 110 installed on the surface of the target object can also be removed from the target object.

[0076] In actual implementation, glue can be set on the side of the substrate 110 facing away from the positioning block group, and the substrate 110 can be adhered to the surface of the target object through the glue. After the substrate 110 is adhered to the surface of the target object, multiple positioning blocks 120 are attached to the surface of the target object through the substrate 110 to form a three-dimensional texture.

[0077] It is understandable that the same substrate 110 can be repeatedly installed on the surfaces of different target objects, that is, after the substrate 110 is removed from the surface of one target object, it can be installed on the surface of another target object.

[0078] In this embodiment, the base 110 is detachably disposed on the surface of the target object, which can improve the flexibility of forming textures on the target object. The tactile positioning module can be reused, which can reduce costs and improve maintenance efficiency.

[0079] In some embodiments, the substrate 110 is made of a flexible material.

[0080] In this embodiment, the substrate 110 is made of a flexible material, and the substrate 110 has a certain elasticity and plasticity. The substrate 110 can adapt to the surfaces of target objects of different shapes and different curvatures.

[0081] Compared with the base 110 made of rigid material, the base 110 made of flexible material has better fit with the target object, and the position of the positioning block 120 can be better fixed, ensuring that the contact information obtained is more accurate.

[0082] In some embodiments, substrate 110 forms at least a portion of an outer shell of a target object.

[0083] In this embodiment, the substrate 110 is not an independent component, but all or part of the outer shell of the target object, that is, all or part of the outer shell of the target object serves as the substrate 110, and the positioning block group is arranged on the surface corresponding to the substrate 110 on the outer shell of the target object, and a plurality of positioning blocks 120 are attached to the corresponding area of ​​the substrate 110 of the target object to form a three-dimensional texture.

[0084] In this embodiment, the base 110 forms at least a part of the outer shell of the target object, and can provide more stable support for the positioning block 120. The position of the positioning block 120 on the surface of the target object is fixed, which can improve the accuracy of the contact information.

[0085] In some embodiments, the positioning block 120 is made of a rigid material.

[0086] In this embodiment, the positioning block 120 is made of a rigid material. When the positioning block 120 is subjected to pressure, it does not deform and maintains its shape and position unchanged, thereby improving the accuracy of the contact information.

[0087] In some embodiments, the positioning block 120 is detachably disposed on the outer surface of the base 110 .

[0088] In this embodiment, the positioning block 120 is an independent component, and the positioning block 120 can be mounted on the outer surface of the substrate 110 .

[0089] For example, the resistor can be mounted on the outer surface of the substrate 110 by surface mounting technology, welding technology, etc., and the resistor can be a 0201 resistor as the positioning block 120.

[0090] The 0201 resistor may be a resistor having a length of 0.02 inches and a width of 0.01 inches.

[0091] In some embodiments, the positioning block 120 forms a portion of the outer surface of the base 110 .

[0092] In this embodiment, mechanical processing such as engraving can be performed on the outer surface of the base 110 to obtain a positioning block 120 protruding from the outer surface of the base 110 , and the positioning block 120 forms a part of the outer surface of the base 110 .

[0093] It can be understood that the base 110 and the positioning block 120 can be both independent components, the positioning block 120 can be detachably provided on the outer surface of the base 110, and the side of the base 110 facing away from the positioning block 120 can be detachably provided on the surface of the target object; the base 110 can form at least a part of the outer shell of the target object, and the positioning block 120 can be detachably provided on the corresponding part of the base 110 of the outer shell of the target object; the positioning block 120 can form a part of the outer surface of the base 110, and the side of the base 110 facing away from the positioning block 120 can be detachably provided on the surface of the target object; the base 110 can form at least a part of the outer shell of the target object, and the positioning block 120 forms a part of the outer surface of the base 110, that is, the corresponding part of the base 110 of the target object is subjected to mechanical processing such as engraving, and the positioning block 120 forms a part of the outer surface of the target object.

[0094] In the description of the present application, it should be understood that the terms "center", "longitudinal", "lateral", "length", "width", "up", "down", "left", "right", "vertical", "horizontal", "inside", "outside", "clockwise", "counterclockwise" and the like indicating orientations or positional relationships are based on the orientations or positional relationships shown in the accompanying drawings, and are only for the convenience of describing the present application and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore should not be understood as a limitation on the present application.

[0095] In the description of this application, "first feature" or "second feature" may include one or more of the features.

[0096] In the description of the present application, “plurality” means two or more.

[0097] In the description of the present application, a first feature being “on” or “under” a second feature may include that the first and second features are directly in contact with each other, or may include that the first and second features are not in direct contact with each other but are in contact with each other via another feature therebetween.

[0098] In the description of the present application, “above”, “over” and “above” a first feature to a second feature includes the first feature being directly above and obliquely above the second feature, or simply means that the first feature is horizontally higher than the second feature.

[0099] The embodiment of the present application also provides a method for preparing a tactile positioning module, which can be used to prepare the above-mentioned tactile positioning module.

[0100] The method for preparing a tactile positioning module provided in an embodiment of the present application may be executed by an electronic device or a functional module or functional entity in the electronic device that can implement the method for preparing a tactile positioning module. The method for preparing a tactile positioning module provided in an embodiment of the present application is described below using an electronic device as an example of an execution subject.

[0101] like Figure 2 As shown, the method for preparing the tactile positioning module includes: step 210, step 220 and step 230.

[0102] Step 210 , generating a coding dot matrix, and based on the coding dot matrix, obtaining a processing file corresponding to the coding dot matrix through a rendering engine, wherein the processing file includes a plurality of identifiers for indicating the position of the positioning block 120 .

[0103] The coding dot matrix is ​​a dot matrix generated by a designed coding rule or an existing coding rule, and the coding dot matrix includes a plurality of coding points, and the plurality of coding points are arranged according to the coding rule.

[0104] In this embodiment, a coding point matrix is ​​generated by a designed coding rule or an existing coding rule. Each coding point in the coding point matrix can be in a different position. One coding point or a combination of multiple coding points can represent a position information.

[0105] In actual implementation, a programming language or software such as AutoCAD can be used to generate a coded dot matrix according to the coding rules.

[0106] In this embodiment, the rendering engine is an engine that can convert coded dot matrix into visual images, and the processing file can be a visual image corresponding to the coded dot matrix, wherein the rendering engine can be a built-in engine in the plate making design software, or the rendering engine can be a separate software program.

[0107] In this embodiment, the processing file includes multiple identifiers for indicating the position of the positioning block 120. The number of identifiers can be the same as the number of coding points. Multiple identifiers can form an identifier array, and the positions of the identifiers in the identifier array correspond one-to-one to the positions of the coding points in the coding point array.

[0108] In this embodiment, the processing file can be obtained through a printed circuit board (PCB) manufacturing process, and the processing file can be a layered board drawing; the processing file can also be obtained through a mechanical processing process, and the processing file can be a three-dimensional model or a computer-aided design (CAD) drawing.

[0109] Step 220 : Generate a processing file on the substrate 110 .

[0110] In this step, a pattern corresponding to the processing file is generated on the substrate 110 through steps such as etching, drilling, plating and silk-screen printing, so that the substrate 110 has a mark for indicating the position of the positioning block 120.

[0111] Step 230 : Install the positioning block 120 on the base 110 to mark the corresponding position.

[0112] In this step, the positioning block 120 is installed on the base 110 to mark the corresponding position. The positioning block group includes multiple positioning blocks 120. The arrangement of the multiple positioning blocks 120 is the same as the arrangement of the multiple coding points. The position of the positioning block 120 in the positioning block group corresponds one-to-one to the position of the coding point in the coding dot matrix.

[0113] In actual implementation, the positioning block 120 can be processed by standard process according to the mounting file corresponding to the processing file, and the positioning block 120 can be installed on the base 110 to mark the corresponding position.

[0114] According to the preparation method of the tactile positioning module provided in the embodiment of the present application, the base 110 is arranged on the surface of the target object, the positioning block group is arranged on the outer surface of the base 110, and the surface of the target object is attached with multiple positioning blocks 120 through the base 110, so that a three-dimensional texture is formed on the surface of the target object, so that the visual tactile sensor of the manipulator can identify the position and direction of contact with the target object in real time and accurately, thereby improving the accuracy of the manipulator in manipulating the object.

[0115] In some embodiments, generating a coded dot matrix includes:

[0116] Generate coded lattices through quasi-de Bruijn sequence.

[0117] Among them, Quasi-de Bruijn Sequence (QBS) is a type of DeBruijn sequence (DB sequence). The DeBruijn sequence consists of k different elements and contains all possible subsequences of length p. These subsequences appear once in the DeBruijn sequence. The DeBruijn sequence can be expressed as B(k, p), where k is the number of elements and p is the length of the subsequence.

[0118] For example, B(2, 3) represents the set of all possible subsequences of length 3 consisting of element 0 and element 1.

[0119] The quasi-de Bruijn sequence may be a truncated de Bruijn sequence. The quasi-de Bruijn sequence may not include all possible subsequences of length k, but the characteristic that the subsequence appears only once is maintained. The position can be efficiently found through the subsequence according to specific needs.

[0120] In this embodiment, a plurality of subsequences are generated by a quasi-de Bruijn sequence, and digital arrays including the number 0 and the number 1 are obtained in the X direction and the Y direction respectively, each number in the digital array corresponds to an initial point, and an initial dot matrix is ​​obtained. According to the number corresponding to each initial point in the initial dot matrix and the position thereof, an offset direction is assigned to each initial point, and the offset direction may include up, down, left, and right, or include east (East, E), west (W), south (South, S), and north (North, N). The initial point is moved by an offset distance in the corresponding offset direction to obtain a coded point, and each initial point is moved accordingly to generate a coded dot matrix.

[0121] The offset distance may be a preset distance, and the offset distance between the encoding point and the corresponding initial point is smaller than the distance between the encoding point and other initial points.

[0122] In actual implementation, a low-order QBS can be used. For example, a 4-order QBS can be used to generate a coding dot matrix. The generated coding dot matrix is ​​sparser, which is conducive to visual tactile sensor recognition.

[0123] In some embodiments, after the positioning block 120 is mounted on the base 110 and marked at a corresponding position, the method further includes:

[0124] The surface of the base 110 facing away from the positioning block 120 is detachably disposed on the surface of the target object.

[0125] In this embodiment, the substrate 110 is a component independent of the target object. Glue can be provided on a side of the substrate 110 away from the positioning block group. After the substrate 110 is installed, the plurality of positioning blocks 120 can be glued to the surface of the target object.

[0126] In some embodiments, the base 110 is made of a flexible material, the positioning block 120 is made of a rigid material, and the positioning block 120 is installed on the base 110 to mark the corresponding position, including:

[0127] Through the flexible printed circuit board manufacturing process, the rigid positioning block 120 is installed on the flexible substrate 110 to mark the corresponding position.

[0128] In this embodiment, a flexible textured tape (GelLocator), that is, a flexible and adhesive substrate 110, can be manufactured through a flexible printed circuit (FPC) manufacturing process. After the coding dot matrix is ​​calculated, the required processing file is automatically drawn by the rendering engine, and a corresponding mounting file is generated. Combined with the surface mounting technology (SMT), the factory uses a standard process to process and mount 0201 resistors to form a three-dimensional texture.

[0129] In some embodiments, the substrate 110 forms at least a portion of a housing of a target object, and generating a processing file on the substrate 110 includes:

[0130] The processing file is generated on the shell of the target object at a portion corresponding to the substrate 110 .

[0131] In this embodiment, the substrate 110 is not a component independent of the target object, but is all or part of the outer shell of the target object, that is, all or part of the outer shell of the target object serves as the substrate 110, and a processing file is generated on the outer shell of the target object corresponding to the part of the substrate 110 through steps such as etching, drilling, plating and silk screen printing. The target object may have a mark for indicating the position of the positioning block 120, and the positioning block 120 is installed at a position on the target object corresponding to the mark.

[0132] The embodiment of the present application also provides a tactile positioning method.

[0133] The tactile positioning method may be applied to a terminal, and may be specifically executed by hardware or software in the terminal, which includes but is not limited to a desktop computer.

[0134] In the following embodiments, a terminal including a display is described. However, it should be understood that the terminal may include one or more other physical user interface devices such as a physical keyboard, a mouse and a joystick.

[0135] The tactile positioning method provided in the embodiment of the present application can be executed by an electronic device or a functional module or functional entity in the electronic device that can implement the tactile positioning method. The electronic device mentioned in the embodiment of the present application includes but is not limited to a computer, etc. The tactile positioning method provided in the embodiment of the present application is described below using an electronic device as an example of an execution subject.

[0136] In this embodiment, a positioning block group is provided on the surface of the target object.

[0137] like Figure 3 As shown, the tactile positioning method includes: step 310, step 320 and step 330.

[0138] Step 310 : When the manipulator contacts the target object, a first image corresponding to the target object is acquired, where the first image includes a plurality of target positioning points, and the target positioning points are determined based on the positioning block 120 in the positioning block group that is contacted by the manipulator.

[0139] In this embodiment, a visual tactile sensor can be provided on the manipulator. When the manipulator contacts the target object, the visual tactile sensor contacts the target object. The visual tactile sensor can photograph the area corresponding to the contacted positioning block 120 to obtain a positioning block image, which includes the positioning block 120 contacted by the visual tactile sensor.

[0140] The positioning block 120 in the positioning block image is subjected to feature point extraction and other processing to obtain a first image.

[0141] In this embodiment, the target positioning point may be determined based on the positioning block 120 contacted by the manipulator. For example, the target positioning point may be the center point of the positioning block 120 contacted by the manipulator.

[0142] Step 320: Based on the first image, obtain a second image including a plurality of reference points.

[0143] Among them, the second image is an image including multiple reference points, and the second image may also include multiple target positioning points. Multiple reference points can be determined in the first image to obtain the second image. The reference points are points used to calculate the offset information of the target positioning points. The positions of the reference points can be the corresponding positions when there is no offset of the target positioning points.

[0144] In this embodiment, the second image can be obtained by determining evenly and regularly distributed reference points in the first image based on the arrangement characteristics of multiple target positioning points in the first image, for example, based on the arrangement direction of the overall target positioning points, the distance between the target positioning points, and other characteristics.

[0145] Step 330: Determine contact position information of the manipulator contacting the target object based on the offset information between each target positioning point and the closest reference point.

[0146] In this embodiment, the second image includes multiple target positioning points and multiple reference points. Each target positioning point may correspond to a closest reference point, that is, a reference point with the closest distance. The offset information may include the direction in which the target positioning point is offset relative to the reference point. The offset information may be expressed as east, west, south, north, or up, down, left, right, etc.

[0147] In this embodiment, the contact position information can be determined based on the offset information corresponding to a target positioning point or the offset information corresponding to multiple target positioning points. The contact position information includes the contact position where the manipulator contacts the target object. The contact position information is used to characterize the point or area where the manipulator contacts the target object. The contact position information may include a coordinate point or a group of coordinate points in the object coordinate system.

[0148] In this embodiment, the correspondence between the offset of the target positioning point relative to the closest reference point and the contact position represented by the target positioning point can be preset, and the contact position information can be obtained according to the offset information through the preset correspondence.

[0149] In this embodiment, when the positioning block group is determined by the encoding rule, the offset information can be decoded by the decoding rule corresponding to the encoding rule to obtain the contact position information.

[0150] According to the tactile positioning method provided in the embodiment of the present application, by setting a positioning block group on the surface of the target object, when the manipulator contacts the target object, a first image corresponding to the area on the surface of the target object contacted by the manipulator is obtained, and a reference point is determined according to the target positioning point corresponding to the positioning block 120 in the first image to obtain a second image. Based on the offset information of each target positioning point and the closest reference point, a decoding operation is performed to determine the contact position information. There is no need to compare and match with other feature information, which can improve the efficiency of tactile positioning and achieve rapid response of the manipulator.

[0151] In some embodiments, based on the first image, acquiring a second image including a plurality of reference points comprises:

[0152] Acquire a target direction of the first image, a target orthogonal point of the first image, and a target grid width of the first image;

[0153] Based on the target direction, the target orthogonal point and the target grid width, a target grid is established in the first image to obtain the second image, and the reference point is a grid point of the target grid.

[0154] In this embodiment, the positioning block group may correspond to a positioning block group reference direction. For example, the positioning block group as a whole may form a rectangle. The positioning block group reference direction may be the direction of the short side of the positioning block group rectangle. The positioning block group reference direction may be the same as the object reference direction.

[0155] The target direction is used to indicate the reference direction of the positioning block group in the first image, the target orthogonal point is a coordinate point in the first image, and the target grid width is a width value.

[0156] In this embodiment, a direction mark can be set in the positioning block group, and the direction mark is used to mark the reference direction of the positioning block group. The first image correspondingly includes the direction mark, and the target direction can be obtained according to the direction mark; or a plurality of candidate directions are randomly determined, and according to the arrangement characteristics of each target positioning point, a direction that is most consistent with the overall arrangement direction of the plurality of target positioning points is selected from the plurality of candidate directions as the target direction.

[0157] In this embodiment, a target positioning point may be arbitrarily selected in the first image as the target orthogonal point, or a target positioning point may be selected in the first image as the target orthogonal point according to features such as the distance between target positioning points.

[0158] In this embodiment, the target grid width may be obtained according to the resolution of the visual tactile sensor, etc.

[0159] In this embodiment, after obtaining the target direction, the target orthogonal point and the target grid width, grid lines can be drawn in the target direction and in a direction orthogonal to the target direction in the first image. The target orthogonal point is used as a grid point, and the distance between two adjacent grid lines is the target grid width. A target grid is established in the first image to obtain a second image, in which each grid point of the target grid corresponds to a reference point.

[0160] In some embodiments, obtaining a target direction of the first image, a target orthogonal point of the first image, and a target grid width of the first image includes:

[0161] Connect any two target positioning points to obtain the first baseline;

[0162] When the distance from each target positioning point to the first baseline meets a preset distance condition, the first baseline is determined as the target baseline;

[0163] The direction of the target baseline is determined as the target direction.

[0164] The first baseline is a line determined by any two target positioning points, the first image may correspond to multiple first baselines, and the target baseline is a first baseline whose distance from each target positioning point to the first baseline meets a preset distance condition.

[0165] The preset distance condition is a pre-set condition, and the preset distance condition may be a condition corresponding to the distance from each target positioning point to the first baseline.

[0166] In this embodiment, for a first baseline, when the distances from each target positioning point to the first baseline meet a preset distance condition, the first baseline is determined as the target baseline.

[0167] For example, when the distance from each target positioning point to the first baseline meets the following preset distance conditions, the first baseline is determined as the target baseline:

[0168]

[0169] in, m is any positive integer including 0, n is 0, 1, or 2, Indicates the distance from the target positioning point to the first baseline. is the target grid width, is a set value, which can be .

[0170] In some embodiments, obtaining a target direction of the first image, a target orthogonal point of the first image, and a target grid width of the first image includes:

[0171] Get the target direction;

[0172] Determine a first coordinate value of the target direction based on the distance between each target positioning point and the corresponding first adjacent point, where the first adjacent point is other target positioning points adjacent to the target positioning point in the target direction;

[0173] Determine a second coordinate value in the first direction based on the distance between each target positioning point and the corresponding second adjacent point, where the second adjacent point is other target positioning points adjacent to the target positioning point in the first direction;

[0174] Determining a target orthogonal point based on the first coordinate value and the second coordinate value;

[0175] The target direction and the first direction intersect, the target direction can be expressed as the x direction, and the first direction can be expressed as the y direction.

[0176] In this embodiment, the first coordinate value may be a value in the x direction, and the second coordinate value may be a value in the y direction.

[0177] In this embodiment, each target positioning point can correspond to a coordinate value in the y direction , in the y direction n The target positioning points meet In the case of ,in, For Sort and remove duplicate values ​​to obtain the first n +1 target location and n- 1 target positioning point can be n The first adjacent point corresponding to the target positioning point, Can indicate the n The target positioning point and n- 1 The distance between target positioning points, Can indicate the n +1 target location and n The distance between the target locations.

[0178] In this embodiment, the first coordinate value may be determined by determining the second coordinate value.

[0179] It can be understood that after obtaining the first coordinate value in the x direction and the second coordinate value in the y direction, the determined coordinate point is used as the target orthogonal point.

[0180] In some embodiments, obtaining a target direction of the first image, a target orthogonal point of the first image, and a target grid width of the first image includes:

[0181] Obtaining a first distance between each target positioning point and a corresponding third adjacent point, where the third adjacent point is another target positioning point that is closest to the target positioning point in each direction;

[0182] Based on the respective first distances, a target grid width is determined.

[0183] In this embodiment, the first distance Can include , and Several situations:

[0184]

[0185] in, is the target grid width, is a set value, which can be .

[0186] In most first distances In the case of nearby, calculate multiple first distances The mean and standard deviation , filter multiple first distances by standard deviation, and then calculate the filtered multiple first distances The mean of :

[0187]

[0188] in, is the filtered multiple first distances The mean of is the number of the first distance after filtering, let , then the target grid width is

[0189]

[0190] In some embodiments, the position of each positioning block 120 in the positioning block group is determined by quasi-de Bruijn sequence coding, and the contact position information of the manipulator contacting the target object is determined based on the offset information of each target positioning point and the closest reference point, including:

[0191] Based on the offset information between each target positioning point and the closest reference point, the contact position information is determined through quasi-De Bruijn sequence decoding.

[0192] In actual implementation, decoding can be performed through the microdot pattern processing library (py-microdots) based on the characteristics of the quasi-de Bruijn sequence.

[0193] For example, if n=4, the observed symbol matrix is ​​first separated into 4 components consisting of 0 elements and 1 elements in the X and Y directions. 4 Matrix.

[0194] For a certain direction, such as the X direction, all columns in the Y direction are part of the quasi-de Bruijn sequence. The position of each column in the original quasi-de Bruijn sequence can be found through the observed part, which is recorded as a0, a1, a2, a3.

[0195] According to the coding rules, the position difference di=(a i+1 -a i ) also forms a quasi-de Bruijn sequence, so the position of the observed part in the X direction, that is, the number of columns, can be found through the difference subsequence of length 3. Figure 4As shown, the points where the dotted lines intersect are reference points, and the solid circles are target positioning points. Each target positioning point is marked with offset information of N, S, W or E. It can be decoded through the microdot pattern processing library (py-microdots) based on the offset information and the characteristics of the quasi-de Bruijn sequence.

[0196] In this embodiment, the position of the target positioning point in the object coordinate system is:

[0197]

[0198] in,( i , j ) is the row and column position of the decoded center reference point, W is the grid width w The corresponding physical size, is the offset distance, is the displacement factor in the x direction corresponding to the target positioning point, is the displacement factor in the y direction corresponding to the target positioning point. The relationship between the offset information and the displacement factor is shown in Table 1.

[0199] Table 1

[0200]

[0201] In some embodiments, based on the offset information between each target positioning point and the closest reference point, determining the contact position information of the manipulator contacting the target object includes:

[0202] Contact position information is determined based on the offset information of each target positioning point from the closest reference point, the target direction of the first image, the reference contact direction of the manipulator, and the reference contact center of the manipulator.

[0203] The reference contact direction is a sensor reference direction corresponding to the visual tactile sensor of the manipulator, the reference contact direction may be preset, and the reference contact center of the manipulator may be the center of a contact plane of the visual tactile sensor for contacting the target object.

[0204] In this embodiment, the centers corresponding to the multiple target positioning points in the first image may deviate from the reference contact center, and there may be an angle between the target direction and the reference contact direction.

[0205] In this embodiment, an initial contact position information can be determined through the offset information, and the initial contact position information is calibrated according to the deviation between the centers corresponding to multiple target positioning points and the reference contact center and the angle between the target direction and the reference contact direction to obtain more accurate contact position information.

[0206] In some embodiments, when the manipulator contacts the target object, acquiring a first image corresponding to the target object includes:

[0207] When the manipulator contacts the target object, a third image corresponding to the target object is acquired, where the third image includes a plurality of target positioning blocks, and the target positioning block is determined based on the positioning block 120 in the positioning block group that is contacted by the manipulator;

[0208] performing binarization processing on the third image to obtain a binarized image corresponding to the third image;

[0209] Based on the binary image, the center point of the target positioning block is extracted as the target positioning point to obtain a first image.

[0210] The target positioning block is the positioning block 120 touched by the manipulator, the third image may be the positioning block image, and the binarized image is the image obtained by binarizing the third image.

[0211] In actual implementation, the texture depth image of the target object surface can be obtained through VBTS, and a uniform depth map, ie, the third image, can be obtained by using high-pass filtering.

[0212] In this embodiment, the contour of the target positioning block is extracted from the binary image, the center point of the target positioning block is calculated as the target positioning point, and the center point is retained, and other parts of the target positioning block are removed to obtain the first image.

[0213] The tactile positioning method provided in the embodiment of the present application can be executed by a tactile positioning device. In the embodiment of the present application, the tactile positioning device executing the tactile positioning method is taken as an example to illustrate the tactile positioning device provided in the embodiment of the present application.

[0214] The embodiment of the present application also provides a tactile positioning device.

[0215] A positioning block group is arranged on the surface of the target object.

[0216] like Figure 5 As shown, the tactile positioning device comprises:

[0217] An acquisition module 510, configured to acquire a first image corresponding to the target object when the manipulator contacts the target object, wherein the first image includes a plurality of target positioning points, and the target positioning points are determined based on the positioning block 120 in the positioning block group that is contacted by the manipulator;

[0218] A first processing module 520 is used to acquire a second image including a plurality of reference points based on the first image;

[0219] The second processing module 530 is used to determine the contact position information of the manipulator contacting the target object based on the offset information between each target positioning point and the closest reference point.

[0220] According to the tactile positioning device provided in the embodiment of the present application, by setting a positioning block group on the surface of the target object, when the manipulator contacts the target object, a first image corresponding to the area on the surface of the target object contacted by the manipulator is obtained, and a reference point is determined according to the target positioning point corresponding to the positioning block 120 in the first image to obtain a second image. Based on the offset information between each target positioning point and the closest reference point, a decoding operation is performed to determine the contact position information, and there is no need to compare and match with other feature information, which can improve the efficiency of tactile positioning and achieve rapid response of the manipulator.

[0221] In some embodiments, the first processing module 520 is used to obtain the target direction of the first image, the target orthogonal point of the first image, and the target grid width of the first image;

[0222] Based on the target direction, the target orthogonal point and the target grid width, a target grid is established in the first image to obtain the second image, and the reference point is a grid point of the target grid.

[0223] In some embodiments, the first processing module 520 is used to connect any two target positioning points to obtain a first baseline;

[0224] When the distance from each target positioning point to the first baseline meets a preset distance condition, the first baseline is determined as the target baseline;

[0225] The direction of the target baseline is determined as the target direction.

[0226] In some embodiments, the first processing module 520 is used to obtain the target direction;

[0227] Determine a first coordinate value of the target direction based on the distance between each target positioning point and the corresponding first adjacent point, where the first adjacent point is other target positioning points adjacent to the target positioning point in the target direction;

[0228] Determine a second coordinate value in the first direction based on the distance between each target positioning point and the corresponding second adjacent point, where the second adjacent point is other target positioning points adjacent to the target positioning point in the first direction;

[0229] Determining a target orthogonal point based on the first coordinate value and the second coordinate value;

[0230] Wherein, the target direction and the first direction intersect.

[0231] In some embodiments, the first processing module 520 is used to obtain a first distance between each target positioning point and a corresponding third adjacent point, where the third adjacent point is another target positioning point that is closest to the target positioning point in each direction;

[0232] Based on the respective first distances, a target grid width is determined.

[0233] In some embodiments, the position of each positioning block 120 in the positioning block group is determined by quasi-de Bruijn sequence encoding, and the second processing module 530 is used to determine the contact position information based on the offset information between each target positioning point and the closest reference point by quasi-de Bruijn sequence decoding.

[0234] In some embodiments, the second processing module 530 is used to determine the contact position information based on the offset information between each target positioning point and the closest reference point, the target direction of the first image, the reference contact direction of the manipulator and the reference contact center of the manipulator.

[0235] In some embodiments, the acquisition module 510 is used to acquire a third image corresponding to the target object when the manipulator contacts the target object, the third image including a plurality of target positioning blocks, and the target positioning block is determined based on the positioning block 120 contacted by the manipulator in the positioning block group;

[0236] performing binarization processing on the third image to obtain a binarized image corresponding to the third image;

[0237] Based on the binary image, the center point of the target positioning block 120 is extracted as the target positioning point to obtain a first image.

[0238] The tactile positioning device in the embodiment of the present application can be an electronic device, or a component in the electronic device, such as an integrated circuit or a chip. The electronic device can be a terminal, or other devices other than a terminal. For example, the electronic device can be an ultra-mobile personal computer (UMPC), a netbook, etc., or a server, a personal computer (PC), etc., which is not specifically limited in the embodiment of the present application.

[0239] The tactile positioning device in the embodiment of the present application may be a device having an operating system. The operating system may be an Android operating system, an IOS operating system, or other possible operating systems, which are not specifically limited in the embodiment of the present application.

[0240] The tactile positioning device provided in the embodiment of the present application can achieve Figure 3 To avoid repetition, the various processes implemented by the method embodiment are not described here.

[0241] In some embodiments, Figure 6As shown, an embodiment of the present application further provides an electronic device 600, including a processor 601, a memory 602, and a computer program stored in the memory 602 and executable on the processor 601. When the program is executed by the processor 601, the various processes of the preparation method of the tactile positioning module and the tactile positioning method embodiment described above are implemented, and the same technical effect can be achieved. To avoid repetition, it will not be described here.

[0242] The embodiment of the present application also provides a non-transitory computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the preparation method of the tactile positioning module and each process of the tactile positioning method embodiment described above are implemented, and the same technical effect can be achieved. To avoid repetition, it will not be repeated here.

[0243] The processor is the processor in the electronic device described in the above embodiment. The readable storage medium includes a computer readable storage medium, such as a computer read-only memory ROM, a random access memory RAM, a magnetic disk or an optical disk.

[0244] The embodiment of the present application further provides a computer program product, including a computer program, which, when executed by a processor, implements the preparation method of the tactile positioning module and the tactile positioning method.

[0245] The processor is the processor in the electronic device described in the above embodiment. The readable storage medium includes a computer readable storage medium, such as a computer read-only memory ROM, a random access memory RAM, a magnetic disk or an optical disk.

[0246] An embodiment of the present application further provides a chip, which includes a processor and a communication interface, wherein the communication interface is coupled to the processor, and the processor is used to run programs or instructions to implement the various processes of the above-mentioned preparation method of the tactile positioning module and the tactile positioning method embodiment, and can achieve the same technical effect. To avoid repetition, it will not be repeated here.

[0247] It should be understood that the chip mentioned in the embodiments of the present application can also be called a system-level chip, a system chip, a chip system or a system-on-chip chip, etc.

[0248] It should be noted that, in this article, the terms "comprise", "include" or any other variant thereof are intended to cover non-exclusive inclusion, so that the process, method, article or device including a series of elements includes not only those elements, but also includes other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise one..." do not exclude the presence of other identical elements in the process, method, article or device including the element. In addition, it should be pointed out that the scope of the methods and devices in the embodiments of the present application is not limited to performing functions in the order shown or discussed, and may also include performing functions in a substantially simultaneous manner or in reverse order according to the functions involved, for example, the described method may be performed in an order different from that described, and various steps may also be added, omitted, or combined. In addition, the features described with reference to certain examples may be combined in other examples.

[0249] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present application, or the part that contributes to the prior art, can be embodied in the form of a computer software product, which is stored in a storage medium (such as ROM / RAM, a disk, or an optical disk), and includes a number of instructions for a terminal (which can be a mobile phone, a computer, a server, or a network device, etc.) to execute the methods described in each embodiment of the present application.

[0250] The embodiments of the present application are described above in conjunction with the accompanying drawings, but the present application is not limited to the above-mentioned specific implementation methods. The above-mentioned specific implementation methods are merely illustrative and not restrictive. Under the guidance of the present application, ordinary technicians in this field can also make many forms without departing from the purpose of the present application and the scope of protection of the claims, all of which are within the protection of the present application.

[0251] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "illustrative embodiments", "examples", "specific examples", or "some examples" means that the specific features, structures, materials, or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present application. In this specification, the schematic representation of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials, or characteristics described may be combined in any one or more embodiments or examples in a suitable manner.

[0252] Although the embodiments of the present application have been shown and described, those skilled in the art will appreciate that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present application, and that the scope of the present application is defined by the claims and their equivalents.

Claims

1. A tactile positioning method, characterized in that: A positioning block group is provided on the surface of the target object, and the method comprises: When the manipulator contacts the target object, a first image corresponding to the target object is acquired, wherein the first image includes a plurality of target positioning points, and the target positioning points are determined based on the positioning blocks in the positioning block group that are contacted by the manipulator; Based on the first image, acquiring a second image including a plurality of reference points; Determining contact position information of the manipulator contacting the target object based on the offset information between each of the target positioning points and the closest reference point; The position of each positioning block in the positioning block group is determined by quasi-de Bruijn sequence coding, and the contact position information of the manipulator contacting the target object is determined based on the offset information of each target positioning point and the closest reference point, including: Based on the offset information between each of the target positioning points and the closest reference point, the contact position information is determined by decoding the quasi-de Bruijn sequence.

2. The tactile positioning method according to claim 1, characterized in that: The step of acquiring a second image including a plurality of reference points based on the first image comprises: Acquire a target direction of the first image, a target orthogonal point of the first image, and a target grid width of the first image; Based on the target direction, the target orthogonal point and the target grid width, a target grid is established in the first image to obtain the second image, and the reference point is a grid point of the target grid.

3. The tactile positioning method according to claim 2, characterized in that: The acquiring the target direction of the first image, the target orthogonal point of the first image, and the target grid width of the first image includes: Connect any two of the target positioning points to obtain a first baseline; When the distance between each of the target positioning points and the first baseline meets a preset distance condition, determining the first baseline as the target baseline; The direction of the target baseline is determined as the target direction.

4. The tactile positioning method according to claim 2, characterized in that: The acquiring the target direction of the first image, the target orthogonal point of the first image, and the target grid width of the first image includes: Acquiring the target direction; Determine a first coordinate value of the target direction based on a distance between each of the target positioning points and a corresponding first adjacent point, where the first adjacent point is another target positioning point adjacent to the target positioning point in the target direction; Determine a second coordinate value in the first direction based on the distance between each of the target positioning points and the corresponding second adjacent point, where the second adjacent point is the other target positioning point adjacent to the target positioning point in the first direction; Determining the target orthogonal point based on the first coordinate value and the second coordinate value; Wherein, the target direction and the first direction intersect.

5. The tactile positioning method according to claim 2, characterized in that: The acquiring the target direction of the first image, the target orthogonal point of the first image, and the target grid width of the first image includes: Acquire a first distance between each of the target positioning points and a corresponding third adjacent point, where the third adjacent point is the other target positioning point that is closest to the target positioning point in each direction; The target grid width is determined based on each of the first distances.

6. The tactile positioning method according to any one of claims 1 to 5, characterized in that: The step of determining the contact position information of the manipulator contacting the target object based on the offset information between each of the target positioning points and the closest reference point comprises: The contact position information is determined based on the offset information between each of the target positioning points and the closest reference point, the target direction of the first image, the reference contact direction of the manipulator, and the reference contact center of the manipulator.

7. The tactile positioning method according to any one of claims 1 to 5, characterized in that: The step of acquiring a first image corresponding to the target object when the manipulator contacts the target object comprises: When the manipulator contacts the target object, a third image corresponding to the target object is acquired, wherein the third image includes a plurality of target positioning blocks, and the target positioning blocks are determined based on the positioning blocks in the positioning block group that are contacted by the manipulator; Performing binarization processing on the third image to obtain a binarized image corresponding to the third image; Based on the binary image, the center point of the target positioning block is extracted as the target positioning point to obtain the first image.

8. A tactile positioning device, characterized in that: A positioning block group is provided on the surface of the target object, and the device comprises: an acquisition module, configured to acquire a first image corresponding to the target object when the manipulator contacts the target object, wherein the first image includes a plurality of target positioning points, and the target positioning points are determined based on the positioning blocks in the positioning block group that are contacted by the manipulator; A first processing module, configured to acquire a second image including a plurality of reference points based on the first image; A second processing module, configured to determine contact position information of the manipulator contacting the target object based on offset information between each of the target positioning points and the closest reference point; The position of each positioning block in the positioning block group is determined by quasi-de Bruijn sequence encoding. The second processing module is used to determine the contact position information by quasi-de Bruijn sequence decoding based on the offset information between each target positioning point and the closest reference point.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the program, the tactile positioning method according to any one of claims 1 to 7 is implemented.

Images