Method, device and system for generating calibration track of force / touch sensor

Abstract

The embodiment of the invention belongs to the technical field of force sensor calibration, and relates to a calibration track generation method of a force / touch sensor, which comprises the following steps: acquiring a calibration grid corresponding to a force / touch sensor to be calibrated; wherein the calibration grid is a calibration grid constructed based on the bottom of the force / touch sensor; mapping the calibration grid to the surface of the force / touch sensor; determining a plurality of calibration contact points based on the calibration grid; and based on the plurality of calibrated contact points, generating a motion instruction of the actuator to instruct the actuator to be in press contact with the plurality of calibrated contact points on the surface of the real force / touch sensor in sequence. The embodiment of the invention further relates to a related device, system and the like. According to the technical scheme, the calibration track of the force / touch sensor can be effectively generated.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of force detection, and in particular to a calibration track generation method, device and system for a force / tactile sensor. BACKGROUND

[0002] With the rapid development of intelligent robots, the important role of force / tactile sensors in intelligent control of robots is increasingly prominent. In order to enable force / tactile sensors to obtain more abundant force / tactile information and enable intelligent robots to perceive objects in complex environments, in recent years, force / tactile sensors have been developing towards array type and flexibility, so that they can better adapt to external installation and contact environment, and realize sensitive detection of force / tactile information such as contact force, contact position, contact surface stiffness and texture characteristics.

[0003] After the design and processing of the force / tactile sensor are completed, in order to determine the input-output relationship and then decouple and solve various input-output characteristics, a calibration test needs to be performed. However, the existing calibration method usually results in low measurement accuracy of the calibrated force / tactile sensor. SUMMARY

[0004] The purpose of the embodiments of the present application is to propose a calibration track generation method, device and system for a force / tactile sensor, so as to effectively generate a calibration track for the force / tactile sensor.

[0005] In a first aspect, the embodiments of the present application provide a calibration track generation method for a force / tactile sensor, which adopts the technical scheme as follows:

[0006] A calibration track generation method for a force / tactile sensor is applied to a calibration system, the system comprising an actuator, a fixing device and a controller; the fixing device is used for fixing a force / tactile sensor to be calibrated; the force / tactile sensor comprises a plurality of sensing units arranged in an array; the calibration track generation method for the force / tactile sensor comprises the following steps:

[0007] Obtaining a calibration grid corresponding to the force / tactile sensor to be calibrated; wherein the calibration grid is a calibration grid constructed based on the bottom of the force / tactile sensor;

[0008] Mapping the calibration grid to the surface of the force / tactile sensor;

[0009] Determining a plurality of calibration contact points on the surface of the force / tactile sensor based on the calibration grid;

[0010] Generating a movement instruction of the actuator based on the plurality of calibration contact points, so as to instruct the actuator to sequentially press and contact the plurality of calibration contact points on the surface of the real force / tactile sensor.

[0011] Further, in one embodiment, before the step of constructing the calibration grid corresponding to the force / tactile sensor to be calibrated, the method further comprises the following step:

[0012] constructing the calibration grid based on the sensing portions of the plurality of sensing units arranged in an array; wherein the sensing portions are arranged on the bottom of the force / tactile sensor.

[0013] Further, in one embodiment, the step of constructing the calibration grid corresponding to the force / tactile sensor based on the sensing portions of the plurality of sensing units arranged in an array comprises the following steps:

[0014] constructing a bounding box of the calibration grid based on the sensing portions of the plurality of sensing units arranged in an array;

[0015] constructing the calibration grid based on the bounding box and the arrangement of the sensing portions of the plurality of sensing units.

[0016] Further, in one embodiment, the step of constructing a bounding box of the calibration grid based on the sensing portions of the plurality of sensing units arranged in an array comprises the following steps:

[0017] extracting the center of the sensing portion of the sensing unit located at the corner point;

[0018] drawing a circle with the center of the sensing portion of each of the sensing units located at the corner point as the center and the detection range of each of the corresponding sensing units as the radius;

[0019] forming an outer box enclosing all the circles;

[0020] taking the outer box as the bounding box of the calibration grid.

[0021] Further, in one embodiment, the step of determining a plurality of calibration contact points on the surface of the force / tactile sensor based on the calibration grid comprises the following steps:

[0022] inserting an insertion point based on the corner point of each of the unit grids in the calibration grid according to a preset rule;

[0023] taking the corner point of each of the unit grids and the insertion point as the calibration contact point; or,

[0024] taking the corner point of each of the unit grids as the calibration contact point.

[0025] Further, in one embodiment, the step of mapping the calibration grid to the surface of the force / tactile sensor comprises the following steps:

[0026] obtaining a 3D model of the force / tactile sensor;

[0027] mapping the calibration grid to the surface of the 3D model of the force / tactile sensor; or,

[0028] sending a projection instruction to a projector to project the calibration grid to a surface of the force / tactile sensor.

[0029] Further, in one embodiment, the generating the motion instruction of the actuator based on the plurality of calibration contact points comprises the following steps:

[0030] obtaining a connection trajectory sequentially connecting the plurality of calibration contact points;

[0031] generating the motion instruction based on the connection trajectory.

[0032] In a second aspect, embodiments of the present application provide a calibration trajectory generation device of a force / tactile sensor, the device comprising:

[0033] a grid obtaining module configured to obtain a calibration grid corresponding to the force / tactile sensor to be calibrated; wherein the calibration grid is a calibration grid constructed based on a bottom of the force / tactile sensor;

[0034] a grid mapping module configured to map the calibration grid to a surface of the force / tactile sensor;

[0035] a contact determining module configured to determine a plurality of calibration contact points on the surface of the force / tactile sensor based on the calibration grid;

[0036] a trajectory generating module configured to generate a motion instruction of an actuator based on the plurality of calibration contact points, so as to instruct the actuator to sequentially press against the plurality of calibration contact points on the surface of the real force / tactile sensor.

[0037] In a third aspect, embodiments of the present application provide a calibration system, the system comprising an actuator, a fixing device and a controller; the force / tactile sensor comprises a plurality of sensing units arranged in an array;

[0038] the fixing device is configured to fix the force / tactile sensor to be calibrated;

[0039] the controller is in communication connection with the actuator;

[0040] the controller is configured to implement the steps of the calibration trajectory generation method of the force / tactile sensor according to any one of the above.

[0041] Further, in one embodiment, the actuator comprises an actuator body and a pressing actuator arranged at an execution end of the actuator body;

[0042] the pressing actuator comprises a mounting disc and a pressure head extending from the mounting disc away from the execution end of the actuator body;

[0043] The free end of the pressure head forms an arc surface; and / or, the diameter of the pressure head is 4mm-6mm.

[0044] Fourthly, embodiments of this application provide a computer device, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps of the above-described method for generating calibration trajectories of a force / tactile sensor.

[0045] Fifthly, embodiments of this application provide a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the steps of the above-described method for generating calibration trajectories of a force / tactile sensor.

[0046] Compared with the prior art, the embodiments of this application have the following main advantages:

[0047] This application embodiment maps a calibration grid constructed based on the bottom of the force / tactile sensor onto the surface of the force / tactile sensor; determines multiple calibration contact points based on the calibration grid; and generates motion commands for the actuator based on the multiple calibration contact points to instruct the actuator to press and contact the multiple calibration contact points on the surface of the tactile sensor in sequence. This allows for the rapid and efficient generation of the calibration trajectory of the force / tactile sensor even when the surface of the tactile sensor has an irregular shape, thereby improving the measurement accuracy of the calibrated force / tactile sensor. Attached Figure Description

[0048] To more clearly illustrate the solutions in this application, the accompanying drawings used in the description of the embodiments of this application will be briefly introduced below. Obviously, the accompanying drawings described below are some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0049] Figure 1 This is an architecture diagram of one embodiment of the calibration system to which this application can be applied.

[0050] Figure 2 This is a three-dimensional structural schematic diagram of an embodiment of the pressing actuator of the calibration system of this application.

[0051] Figure 3 Based on Figure 5 The diagram shows a planar structure of an embodiment of a force / tactile sensor where the bottom is formed into a circle based on the sensing portion of the sensing unit located at the corner.

[0052] Figure 4 Based on Figure 5A plan view of a force / tactile sensor according to an embodiment of the present application.

[0053] Figure 5 A perspective view of a force / tactile sensor according to an embodiment of the present application.

[0054] Figure 6 A plan view of a force / tactile sensor according to an embodiment of the present application. Figure 5 A plan view of a force / tactile sensor according to an embodiment of the present application.

[0055] Figure 7 A plan view of a force / tactile sensor according to an embodiment of the present application. Figure 6 A plan view of a force / tactile sensor according to an embodiment of the present application.

[0056] Figure 8 A plan view of a force / tactile sensor according to an embodiment of the present application. Figure 7 A plan view of a force / tactile sensor according to an embodiment of the present application.

[0057] Figure 9 A perspective view of a force / tactile sensor according to another embodiment of the present application.

[0058] Figure 10 A front view of a force / tactile sensor according to an embodiment of the present application. Figure 9 A front view of a force / tactile sensor according to an embodiment of the present application.

[0059] Figure 11 A flow chart of a method for generating a calibration track of a force / tactile sensor according to an embodiment of the present application.

[0060] Figure 12 A block diagram of an apparatus for generating a calibration track of a force / tactile sensor according to an embodiment of the present application.

[0061] Figure 13 A block diagram of a computer device according to an embodiment of the present application. DETAILED DESCRIPTION

[0062] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs; the terminology used in the description herein is for describing particular embodiments only and is not intended to be limiting of the application; the description herein and the claims of the application and the above description of the drawings herein is not intended to be complete descriptions of all features of the application; the terminology used herein is intended to be interpreted broadly according to the principles of the application; the phraseology and terminology used herein is for the purpose of description and not of limitation; terms such as "including" as used herein are used greedly to mean "including, but not limited to"; and the singular forms "a", "an" and "the" include plural references unless the context clearly dictates otherwise.

[0063] Reference to“an embodiment” herein means that a particular feature, structure, or characteristic described in connection with the embodiment can be included in at least one embodiment of the application. The appearances of the phrase“in an embodiment” in various places in the specification are not necessarily all referring to the same embodiment, nor are they necessarily all directed to the same embodiment, or to a single alternative embodiment. One of ordinary skill in the art will readily recognize from the disclosure herein a wide number of variations, alternatives, and equivalents in the application.

[0064] For those skilled in the art to better understand the technical solutions of the present application, the technical solutions in the embodiments of the present application will be described clearly and completely in conjunction with the drawings.

[0065] As shown in Figure 1 , Figure 1 is an architecture diagram of one embodiment of the calibration system to which the present application can be applied.

[0066] The embodiment of the present application provides a calibration system 100 for calibrating a force / tactile sensor 200, which comprises an actuator 110, a fixing device 130 and a controller 140.

[0067] The controller 130 is in wired or wireless communication connection with the actuator 110, etc.

[0068] It should be noted that the above wireless connection mode can include but is not limited to 3G / 4G / 5G connection, WiFi connection, Bluetooth connection, WiMAX connection, Zigbee connection, UWB (ultra wideband) connection, and other now known or future developed wireless connection modes.

[0069] Force / tactile sensor

[0070] Among them, the force / tactile sensor (which can be simply referred to as“sensor”) refers to an array force sensor and / or a tactile sensor. The array force / tactile sensor comprises a plurality of arrayed sensor units, so as to realize the sensing of multi-point force distribution information. Generally, each sensor unit comprises a collection part and a sensing part arranged correspondingly. The collection part is used for collecting force / tactile related signals; the sensing part is used for generating force / tactile information based on the collected signals.

[0071] The force / tactile sensor described in the embodiment of the present application can be but is not limited to: capacitive, inductive, photoelectric, Hall, piezoresistive, piezoelectric, visual.

[0072] Specifically, the force sensor can be but is not limited to: one-dimensional or multi-dimensional force sensor, used for measuring pressure or three-dimensional force data, etc.

[0073] The tactile sensor can measure contact force information of the object. The contact force information includes, but is not limited to, arrayed multi-dimensional contact force information, surface deformation information, temperature information, texture information, etc. The contact surface of the tactile sensor and the object is usually flexible and has good elasticity. The implementation of the tactile sensor includes a flexible contact surface, a sensing circuit, a computing device, and a contact force information analysis algorithm. Compared with a conventional force sensor, the tactile sensor can more sensitively perceive various forces from multiple dimensions, such as being able to perceive dense tangential frictional forces. The tactile sensor can be applied in various fields as needed. For example, the tactile sensor can be placed in a dexterous hand or other gripping manipulator, and used to measure contact force information under the premise of cooperating with the dexterous hand to realize the gripping function, so as to realize gripping of objects with different shapes and softness.

[0074] Actuator

[0075] The manipulator 110 includes a manipulator body and a pressing manipulator (such as a pressure head) arranged at the execution end of the manipulator body to apply a force for sensor calibration to the surface of the force / tactile sensor.

[0076] Specifically, the manipulator body can be, but is not limited to, a robot (such as a mechanical arm or a humanoid robot), an XYZ platform, or a manipulator including an XYZ platform.

[0077] For the convenience of understanding, as shown in Figure 1 The embodiments of the present application mainly take the manipulator body as a mechanical arm 111 as an example for detailed description, and the execution end of the mechanical arm 111 is provided with a pressing manipulator 112.

[0078] As shown in Figure 2 , Figure 2 is a perspective structural schematic view of one embodiment of the pressing manipulator of the calibration system of the present application.

[0079] In one embodiment, the pressing manipulator 112 described in the embodiments of the present application can include a mounting disc 1121 and a pressure head 1122 extending away from the execution end of the manipulator body by the mounting disc.

[0080] In one embodiment, the free end of the pressure head 1122 is arc-shaped, so as to reduce the occurrence of damage to the surface of the sensor 200 by the free end of the pressure head during the process of applying a calibration force to the sensor 200.

[0081] The mounting disc 1121 is used to fix the pressure head 1122 to the execution end of the manipulator body.

[0082] In one embodiment, the mounting disc can be provided with a mounting hole, so as to be fixedly connected with the execution end of the actuator body by means of a fixing bolt, a fixing pin or the like. In addition, any other structure or method available now or to be developed in the future can be adopted to realize the fixed connection between the pressing actuator and the execution end of the actuator body, such as: fixed connection by means of a cooperating bayonet and a clamping groove; fixed connection by means of adhesive bonding; or pre-fabricated as a whole.

[0083] In one embodiment, the diameter of the pressing head is 4mm to 6mm.

[0084] In the embodiments of the present application, the pressing head with the above diameter can reduce the situation that the contact area with the sensor surface is too large during the calibration experiment due to the too large diameter of the pressing head, so that the strain of the sensor surface is reduced when pressed with the same force, and the displacement signal detected is weakened. In addition, the situation that the sensor is pierced due to the too small contact area with the sensor surface during the calibration experiment due to the too small diameter of the pressing head can also be reduced.

[0085] It should be noted that the pressing head is usually made of rigid (and insulating or non-magnetic, etc.) materials such as aluminum alloy and ABS engineering plastic, so as to prevent interference with the sensor to be calibrated, thereby reducing the calibration accuracy of the sensor.

[0086] Fixing device

[0087] Specifically, the fixing device 130 can be various devices capable of fixing the sensor. For example, the fixing device 130 can include a workbench 131 and a fixing clamp 132. The fixing clamp 132 is arranged on the workbench 131, and the sensor 200 to be calibrated is fixed in position by the fixing clamp 132.

[0088] Specifically, the clamp can adopt any structure available now or to be developed in the future which can fix the sensor.

[0089] Controller

[0090] The controller 130 is configured to execute the steps of the calibration trajectory generation method of the force / tactile sensor according to the embodiments of the present application.

[0091] The force / tactile sensor calibration track generation method provided by the embodiment of the present application can be applied to a personal computer (PC), an industrial personal computer (IPC), a mobile terminal, a server, a system including a terminal and a server, and is implemented through interaction of the terminal and the server, a programmable logic controller (PLC), a field-programmable gate array (FPGA), a digital signal processor (DSP), a microcontroller unit (MCU) or the like, and the like. The controller generates program instructions and the like according to a pre-fixed program and / or in combination with data signals and the like collected by an external actuator and the like. Specifically, the force / tactile sensor calibration track generation method can be applied to a computer device as shown in FIG. 15. Figure 13

[0092] Based on the calibration system described in the above embodiment, the present embodiment provides a force / tactile sensor calibration track generation method, which is generally executed by the controller 130. Accordingly, the force / tactile sensor calibration track generation device described in the following embodiment is generally provided in the controller 130.

[0093] As shown in FIG. 16, Figure 11 Figure 11 is a flowchart of an embodiment of the force / tactile sensor calibration track generation method of the present application. The force / tactile sensor calibration track generation method can include the following method steps.

[0094] In step 210, a calibration grid corresponding to the force / tactile sensor to be calibrated is obtained. The calibration grid is a calibration grid constructed based on the bottom of the force / tactile sensor.

[0095] In step 220, the calibration grid is mapped to the surface of the force / tactile sensor.

[0096] In step 230, based on the calibration grid, a plurality of calibration contact points on the surface of the force / tactile sensor are determined.

[0097] In step 240, based on the plurality of calibration contact points, movement instructions of the actuator are generated to instruct the actuator to sequentially press and contact the plurality of calibration contact points on the surface of the real force / tactile sensor.

[0098] ​​The embodiment of the present application maps the calibration grid constructed based on the force / tactile sensor bottom to the surface of the force / tactile sensor; determines a plurality of calibration contact points based on the calibration grid; generates a motion instruction of the actuator based on the plurality of calibration contact points to instruct the actuator to sequentially press against the plurality of calibration contact points on the surface of the tactile sensor, so that even if the surface shape of the force / tactile sensor is irregular, an effective calibration grid can still be quickly and efficiently generated on the surface of the force / tactile sensor based on subsequent calibration grid mapping, thereby improving the efficiency and accuracy of calibration.

[0099] In addition, by mapping the calibration grid to the surface of the force / tactile sensor, determining a plurality of calibration contact points based on the calibration grid, and then generating a motion instruction of the actuator based on the plurality of calibration contact points to instruct the actuator to sequentially press against the plurality of calibration contact points on the surface of the tactile sensor, the efficiency, accuracy, range, time, etc. of the calibration method are effectively improved compared with the traditional manual and single-point pressing calibration, and the pressing trajectory can be more accurately and uniformly generated on the effective area of the sensor surface.

[0100] For the convenience of understanding, the above method steps are further described in detail as follows.

[0101] In step 210, a calibration grid corresponding to the force / tactile sensor to be calibrated is obtained; wherein the calibration grid is a calibration grid constructed based on the bottom of the force / tactile sensor.

[0102] In one embodiment, the controller obtains the calibration grid pre-constructed and stored from the memory or server according to a preset address.

[0103] In one embodiment, before step 210, the calibration trajectory generation method of the force / tactile sensor according to the embodiment of the present application can further include the following method steps:

[0104] In step 250, a calibration grid is constructed based on the sensing part of the arrayed plurality of sensing units; wherein the sensing part is arranged at the bottom of the force / tactile sensor.

[0105] As shown in Figure 9 and Figure 10 , the force / tactile sensor is a front view as shown in Figure 9 is a perspective structural schematic diagram of another embodiment of the force / tactile sensor of the present application; Figure 10 is a front view of the force / tactile sensor as shown in Figure 9

[0106] ​For example, the force / tactile sensor 200 according to the embodiment of the present application generally comprises a bottom 210 (including a circuit board 211 and a plurality of sensor unit chips 212 (i.e. "sensing part") arranged in an array on the circuit board) and a data acquisition structure 220 (including a deformation layer 222 and a plurality of permanent magnets 221 (i.e. "acquisition part") arranged in an array on the deformation layer), wherein the surface of the deformation layer 222 is also the surface of the sensor according to the embodiment of the present application; each sensor chip and a permanent magnet are arranged correspondingly to form a sensor unit, and a plurality of sensor units are arranged in an array.

[0107] In the embodiment of the present application, the sensor surface formed by the deformation layer and the like is generally irregular in shape according to actual needs, and therefore the calibration grid is generally constructed based on the bottom of the tactile sensor.

[0108] In the embodiment of the present application, the calibration grid corresponding to the force / tactile sensor is constructed based on the bottom of the force / tactile sensor, so that even if the surface of the force / tactile sensor is irregular in shape, the calibration grid can still be effectively generated on the surface of the force / tactile sensor based on subsequent grid mapping.

[0109] In one embodiment, the step 250 can comprise the following method steps:

[0110] The step 251 constructs a boundary box of the calibration grid based on the sensing part of the plurality of sensor units arranged in an array.

[0111] The step 252 constructs the calibration grid based on the boundary box and the arrangement of the sensing part of the plurality of sensor units.

[0112] Specifically, the controller can construct the calibration grid based on the boundary box and the array arrangement of the sensing part of the sensor unit on the bottom.

[0113] It should be noted that in addition to the method for generating the calibration grid described in the steps 251 to 252 of the above embodiment, the calibration grid can also be constructed based on the bottom of the sensor by using any other existing or future developed method, for example, a cell can be generated directly based on the arrangement of each sensor unit and the detection range parameter of each unit, and a plurality of cells constitute the calibration grid as a whole.

[0114] In the embodiment of the present application, the boundary box of the calibration grid is constructed based on the bottom of the sensor, and the calibration grid is constructed based on the boundary box and the arrangement of the sensor unit, so that the calibration grid can be generated more accurately and quickly.

[0115] In one embodiment, the step 251 can comprise the following method steps:

[0116] Step 2511: Obtain the center of the sensing part of the sensing unit located at the corner point.

[0117] In one embodiment, the controller can retrieve the center coordinate parameters of the sensing part of the sensing unit corresponding to the preset code of the sensing part (e.g., the sensing chip) of the transmitting unit located at the corner of the bottom of the sensor from the memory or server according to the preset address.

[0118] Step 2512: Draw a circle with the center of the sensing part of each corner sensing unit as the center and the detection range of the sensing unit as the radius.

[0119] In one implementation, the controller can retrieve the pre-stored detection range parameters (e.g., 3-5 times the diameter of the permanent magnet) of the sensing part of each sensing unit from the memory or server according to a preset address; and draw a circle with the detection range as the radius and the center of the sensing unit located at the corner as the center.

[0120] like Figure 3 As shown, it is based on Figure 5 The diagram shows a planar structure of an embodiment of a force / tactile sensor where the bottom is formed into a circle based on the sensing portion of the sensing unit located at the corner.

[0121] For example, there are four corner sensing units 230 at the bottom of the sensor. Four circles are drawn with the center of the sensing part of the four corner sensing units 230 as the center and the detection range of the sensing unit as the radius.

[0122] Step 2513 forms the circumscribed frame that surrounds all the circles.

[0123] like Figure 4 As shown, Figure 4 Based on Figure 5 The diagram shows a planar structure of an embodiment of a force / tactile sensor, where the bottom is formed by the sensing portion of the sensing unit located at the corner point, creating an externally circumscribed rectangular frame.

[0124] For example, four circles are formed around the sensing portion of the sensing unit 230 located at the corner, generating its circumscribed rectangle 240. Specifically, this can be done manually or automatically by the controller based on a preset program.

[0125] Step 2514 uses the external bounding box as the bounding box of the calibration mesh.

[0126] The embodiment of the present application draws a circle with the center of the sensing part of the sensing unit located at the corner point as the center and the detection range of the sensing unit as the radius, forms an outer tangent frame of all the circles corresponding to the sensing unit located at the corner point, fully considers the detection range of the sensing unit located at the boundary, and determines the boundary frame of the calibration grid based on the same, so that the effective detection area on the sensor surface can be better determined, and the detection precision is improved.

[0127] It should be noted that, in addition to the above method for determining the boundary frame, the embodiment of the present application can also use various existing or future developed methods to determine the boundary frame, such as: determining an initial frame by connecting the centers of the sensing units in the outermost circle, and then expanding the detection range to generate the boundary frame; or a neural network-based method, such as: directly generating a boundary frame based on the input center coordinates of the sensing part of each sensing unit in the outermost circle or the center coordinates of the sensing part of the sensing unit located at the corner point.

[0128] In one embodiment, the step 252 of constructing the calibration grid based on the boundary frame and the arrangement of the sensing units can include the following method steps:

[0129] Figure 6 is based on Figure 5 A planar structure schematic diagram of one embodiment of a bottom of a force / tactile sensor after forming a calibration grid is shown in FIG. 8.

[0130] For example, a tactile sensor including 3*5 sensing units is taken as an example, and a calibration grid including 3*5 unit cells can be formed based on the boundary frame.

[0131] The step 220 maps the calibration grid to the surface of the force / tactile sensor.

[0132] In one embodiment, the step 220 can include the following method steps:

[0133] The step 221 acquires a 3D model of the force / tactile sensor.

[0134] The step 223 maps the calibration grid to the surface of the 3D model of the force / tactile sensor.

[0135] In one embodiment, the controller can acquire a 3D model (such as a CAD model or a point cloud model) of the force / tactile sensor pre-generated and stored or generated in real time from the storage or the server according to a preset address; map the calibration grid to the surface of the 3D model of the force / tactile sensor, so as to obtain a virtual surface of the force / tactile sensor after the calibration grid is mapped.

[0136] The embodiment of the present application maps the calibration grid based on the 3D model of the force / tactile sensor, avoids the error caused by data conversion in the method of projecting an image onto a real object and then generating a trajectory based on the collected image, and improves the efficiency.

[0137] As shown in Figure 5 , Figure 5 is a three-dimensional structural schematic diagram of an embodiment of the present application after the surface of the force / tactile sensor is mapped with the calibration grid.

[0138] For example, after the calibration grid is mapped, the calibration grid can be formed on the surface of the sensor 200.

[0139] In another embodiment, the step 220 can include the following method steps:

[0140] The step 222 sends a projection instruction to the projector to project the calibration grid onto the surface of the force / tactile sensor.

[0141] In an embodiment, the controller can also send the calibration grid image to the real image projector corresponding to the real sensor setting according to a preset address, so as to project the calibration grid onto the surface of the sensor through the image projector; and the corresponding motion instruction can also be generated based on the image collected by the image sensor after the surface of the sensor is mapped with the calibration grid.

[0142] The step 230 determines a plurality of calibration contact points on the surface of the force / tactile sensor based on the calibration grid.

[0143] It should be noted that based on the above embodiment, the "plurality of calibration contact points on the surface of the force / tactile sensor" in the above embodiment can refer to the surface of the virtual 3D model of the force / tactile sensor or the surface of the real force / tactile sensor.

[0144] In an embodiment, the step 230 can include the following method steps:

[0145] The step 231 inserts a point based on the corner point of each unit grid in the calibration grid according to a preset rule;

[0146] The step 233 takes the corner point and the inserted point of each unit grid as the calibration contact point.

[0147] As shown in Figure 7 , Figure 7 is a planar structural schematic diagram of an embodiment after the contact points are formed based on the calibration grid shown in Figure 6 .

[0148] Continuing with the above example, if the 4 corner points of each unit grid, the midpoints of the adjacent two corner points, and the center point (i.e. the interpolation point) of each unit grid are taken as the calibration contact points, then a total of 7*11=77 contact points are generated in this example.

[0149] It should be noted that the preset rule for inserting the interpolation points can be arbitrarily set as needed, such as: the preset rule for inserting 2 points at each adjacent two corner points can be preset.

[0150] In another embodiment, step 230 can include the following method steps:

[0151] Step 232 takes the corner points of each unit grid in the calibration grid as the calibration contact points.

[0152] It should be noted that in addition to the method for determining the calibration contact points described in steps 231 and 233, more or fewer contact points can also be used as needed, such as: when the sensor surface area is relatively small, only the corner points of each unit grid can be used as the contact points, all of which are within the scope of the present application.

[0153] In addition, in addition to the generation methods of the multiple calibration contact points listed in the above embodiments, various existing or future developed methods can also be used, such as: based on a neural network, the calibration grid can be taken as the input of the contact point recognition network, and the multiple calibration contact points of the surface of the force / tactile sensor can be directly output.

[0154] Step 240 generates the motion instructions of the actuator based on the multiple calibration contact points, to instruct the actuator to sequentially press the multiple calibration contact points of the surface of the real force / tactile sensor.

[0155] In one embodiment, step 240 can include the following method steps:

[0156] Step 241 obtains the coordinates of the multiple calibration contact points in the actuator coordinate system.

[0157] In one embodiment, step 241 can include the following method steps:

[0158] Step 2411 determines the coordinates of each contact point in the tactile sensor coordinate system in combination with the 3D model of the tactile sensor.

[0159] Step 2422 converts the coordinates of each contact point in the tactile sensor coordinate system to the actuator coordinate system.

[0160] In this embodiment, based on the coordinates of each contact point in the tactile sensor coordinate system, and combined with the coordinate transformation relationship between the force / tactile sensor and the actuator, the coordinates of each contact point in the tactile sensor coordinate system can be transformed to the actuator coordinate system.

[0161] In one embodiment, before step 2422, the following method steps may also be included:

[0162] Construct a coordinate system for the force / tactile sensor.

[0163] For example, such as Figure 5 As shown, taking the calibration trajectory generation of a 3*5 sensor array as an example, a three-dimensional rectangular coordinate system can be established with the center of the short side of the lower surface of the sensor flexible layer as the origin, the direction of the short side as the X-axis, the length direction as the Y-axis, and the height direction as the Z-axis.

[0164] Establish the coordinate transformation relationship between force / tactile sensors and actuators.

[0165] Specifically, since the coordinate system of the tactile sensor is fixed, the transformation relationship between the coordinate system of the tactile sensor and the coordinate system of the robot can be pre-built, so that the coordinates of each contact point in the coordinate system of the tactile sensor can be transformed into the coordinate system of the actuator.

[0166] Step 242: Obtain the connection trajectory of sequentially connecting multiple calibrated contact points.

[0167] In one embodiment, prior to step 241, the connection trajectory of each contact point can be connected sequentially in a manner either manually or automatically by the controller according to preset rules.

[0168] like Figure 8 As shown, Figure 8 Based on Figure 7 The diagram shows a planar structure of one embodiment after the contact points form a connection trajectory.

[0169] For example, it can be done according to Figure 8 As shown, a serpentine connection trajectory sequentially connects each contact point.

[0170] Step 243 generates motion commands based on the coordinates of the contact point in the actuator coordinate system and the connection trajectory.

[0171] For example, taking the actuator as a robotic arm, trajectory planning can be performed based on each contact point and connection trajectory, and then combined with the pressing force parameters, motion commands for each joint of the robotic arm can be generated based on inverse kinematics equations, etc.

[0172] The embodiment of the present application can more accurately generate the pressing track uniformly on the effective area of the sensor surface by obtaining the coordinates of the plurality of calibration contact points in the actuator coordinate system, generating the motion instruction of the actuator based on the coordinates of the calibration contact points in the actuator coordinate system and the connection track.

[0173] It should be noted that in addition to the method steps described in the above embodiments, the embodiment of the present application can implement the method steps of "generating the motion instruction of the actuator based on the plurality of calibration contact points" described in step 240 above based on various methods that exist now or will be developed in the future, such as: the motion instruction can be generated based on a neural network model. For example, the plurality of calibration contact points can be used as the input of a pre-trained instruction recognition model, so as to output the connection track or the motion instruction.

[0174] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by a computer program instructing related hardware, and the computer program can be stored in a computer-readable storage medium. When the program is executed, it can include the processes of the above-mentioned embodiments of each method. The storage medium can be a non-volatile storage medium such as a magnetic disk, an optical disk, a read-only memory (ROM), or a random access memory (RAM).

[0175] It should be understood that although each step in the flowchart of the accompanying drawings is displayed in sequence according to the direction of the arrow, these steps are not necessarily executed in sequence according to the direction of the arrow. Unless otherwise stated herein, the execution of these steps is not strictly limited in sequence, and they can be executed in other orders. Moreover, at least part of the steps in the flowchart of the accompanying drawings can include multiple sub-steps or multiple stages, which are not necessarily executed at the same time, but can be executed at different times, and the execution sequence is not necessarily sequential, but can be executed alternately or alternately with at least part of other steps or other steps, sub-steps or stages.

[0176] Further referring to Figure 12 , as an implementation of the method shown in Figure 11 , the present application provides an embodiment of a calibration track generation device for a force / tactile sensor, which corresponds to the method embodiment shown in Figure 11 .

[0177] As shown in Figure 12 , the calibration track generation device 300 for the force / tactile sensor described in the embodiment can include:

[0178] The grid acquisition module 310 is configured to acquire a calibration grid corresponding to the force / tactile sensor to be calibrated, wherein the calibration grid is a calibration grid constructed based on the bottom of the force / tactile sensor.

[0179] The grid mapping module 320 is configured to map the calibration grid to the surface of the force / tactile sensor.

[0180] The contact determination module 330 is configured to determine a plurality of calibration contact points on the surface of the force / tactile sensor based on the calibration grid.

[0181] The trajectory generation module 340 is configured to generate a motion instruction of the actuator based on the plurality of calibration contact points, so as to instruct the actuator to sequentially press against the plurality of calibration contact points on the surface of the real force / tactile sensor.

[0182] In an embodiment, the calibration trajectory generation apparatus 300 of the force / tactile sensor can further include:

[0183] The grid construction module is configured to construct the calibration grid corresponding to the force / tactile sensor based on the sensing portions of the plurality of sensor units arranged in an array, wherein the sensing portions are arranged on the bottom of the force / tactile sensor.

[0184] Further, in an embodiment, the grid construction module can include:

[0185] The boundary construction submodule is configured to construct a boundary box of the calibration grid based on the sensing portions of the plurality of sensor units arranged in an array.

[0186] The grid construction submodule is configured to construct the calibration grid based on the boundary box and the arrangement of the sensing portions of the plurality of sensor units.

[0187] Further, in an embodiment, the boundary construction submodule can include:

[0188] The center extraction unit is configured to extract the center of the sensing portion of the sensor unit located at the corner point.

[0189] The circle drawing unit is configured to draw a circle with the center of the sensing portion of each of the sensor units located at the corner point as the center and the detection range of each of the corresponding sensor units as the radius.

[0190] The bounding box generation unit is configured to form an enclosing box surrounding all the circles.

[0191] The bounding box determination unit takes the enclosing box as the boundary box of the calibration grid.

[0192] In an embodiment, the contact determination module 330 can include:

[0193] The insertion point insertion submodule is configured to insert an insertion point based on a corner point of each unit grid in the calibration grid according to a preset rule.

[0194] The first determination submodule is configured to take the corner point and the insertion point of each unit grid as the calibration contact point.

[0195] In an embodiment, the contact determination module 330 can include:

[0196] The second determination submodule is configured to take the corner point of each unit grid in the calibration grid as the calibration contact point.

[0197] In an embodiment, the grid mapping module 320 can include:

[0198] The model acquisition submodule is configured to acquire a 3D model of the force / tactile sensor.

[0199] The grid mapping submodule is configured to map the calibration grid to a surface of the 3D model of the force / tactile sensor.

[0200] In an embodiment, the grid mapping module 320 can include:

[0201] The instruction sending submodule is configured to send a projection instruction to the projector to project the calibration grid to the surface of the force / tactile sensor.

[0202] In an embodiment, the trajectory generation module 340 can include:

[0203] The trajectory acquisition submodule is configured to acquire a connection trajectory sequentially connecting a plurality of calibration contact points.

[0204] The instruction generation submodule is configured to generate a motion instruction based on the connection trajectory.

[0205] To solve the above technical problems, the embodiments of the present application further provide a computer device. For details, please refer to Figure 13 , Figure 13 The figure is a basic structure block diagram of the computer device of the present embodiment.

[0206] The computer device can be a terminal or a server.

[0207] The computer device 6 comprises a memory 61, a processor 62, and a network interface 63 which are communicatively connected by a system bus. It should be noted that only the computer device 6 with components 61-63 is shown in the figure, but it should be understood that not all of the shown components are required to be implemented, and more or fewer components can be alternatively implemented. Among them, those skilled in the art can understand that the computer device herein is a device capable of automatically performing numerical calculation and / or information processing according to pre-set or stored instructions, and its hardware includes but is not limited to microprocessors, application specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), digital signal processors (DSPs), embedded devices, etc.

[0208] The computer device can be a desktop computer, a notebook computer, a palm computer, a cloud server, and the like. The computer device can interact with the user through a keyboard, a mouse, a remote controller, a touchpad, a voice control device, and the like.

[0209] The memory 61 comprises at least one type of readable storage medium, including a flash memory, a hard disk, a multimedia card, a card-type memory (e.g., an SD or DX memory, etc.), a random access memory (RAM), a static random access memory (SRAM), a read-only memory (ROM), an electrically erasable programmable read-only memory (EEPROM), a programmable read-only memory (PROM), a magnetic memory, a magnetic disk, an optical disk, and the like. In some embodiments, the memory 61 can be an internal storage unit of the computer device 6, such as a hard disk or a memory of the computer device 6. In other embodiments, the memory 61 can also be an external storage device of the computer device 6, such as a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, and the like. Of course, the memory 61 can also include both the internal storage unit and the external storage device of the computer device 6. In the present embodiment, the memory 61 is generally used to store an operating system and various application software installed in the computer device 6, such as program codes of the force / tactile sensor calibration trajectory generation method, and the like. In addition, the memory 61 can also be used to temporarily store various data that have been output or will be output.

[0210] The processor 62 may, in some embodiments, be a central processing unit (CPU), a controller, a microcontroller, a microprocessor, or other data processing chip. The processor 62 is generally used to control the overall operation of the computer device 6. In the present embodiment, the processor 62 is configured to run program code stored in the memory 61 or process data, such as program code of the force / tactile sensor calibration trajectory generation method.

[0211] The network interface 63 may include a wireless network interface or a wired network interface, and is generally used to establish a communication connection between the computer device 6 and other electronic devices.

[0212] The present application also provides another embodiment, i.e., a computer readable storage medium storing a force / tactile sensor calibration trajectory generation program, which can be executed by at least one processor to enable the at least one processor to perform the steps of the force / tactile sensor calibration trajectory generation method as described above.

[0213] From the above description of the embodiments, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software and a general hardware platform, and of course, can also be implemented by hardware, but in many cases, the former is a better embodiment. Based on such understanding, the technical solutions of the present application can be embodied in the form of a software product, which is stored in a storage medium (such as a ROM / RAM, a magnetic disk, or an optical disk) and includes a plurality of instructions for enabling a terminal device (which can be a mobile phone, a computer, a server, an air conditioner, or a network device) to perform the methods described in the various embodiments of the present application.

[0214] Obviously, the above-described embodiments are only some embodiments of the present application, rather than all embodiments of the present application, and the preferred embodiments of the present application are given in the drawings, but do not limit the patent scope of the present application. The present application can be implemented in many different forms, and conversely, the purpose of providing these embodiments is to make the disclosure of the present application more thorough and comprehensive. Although the present application has been described in detail with reference to the foregoing embodiments, those skilled in the art can still modify the technical solutions described in the foregoing specific embodiments, or make equivalent replacements to some technical features. Any equivalent structure made by referring to the contents of the specification and drawings, directly or indirectly applied to other related technical fields, is also within the scope of the patent protection of the present application.

Claims

1. A method for generating a calibration trajectory of a force / tactile sensor, applied to a calibration system, the system comprising an actuator, a fixing device and a controller; the fixing device is used to fix the force / tactile sensor to be calibrated; the force / tactile sensor comprises a plurality of sensing units arranged in an array, characterized in that, The calibration trajectory generation method of the force / tactile sensor comprises the following steps: Obtain the calibration grid corresponding to the force / tactile sensor to be calibrated; wherein the calibration grid is a calibration grid constructed based on the bottom of the force / tactile sensor; Map the calibration grid to the surface of the force / tactile sensor; Based on the calibration grid, determine a plurality of calibration contact points on the surface of the force / tactile sensor; Based on the plurality of calibration contact points, generate movement instructions for the actuator to indicate that the actuator sequentially presses the plurality of calibration contact points on the surface of the real force / tactile sensor.

2. The method of claim 1, wherein, Before the step of obtaining the calibration grid corresponding to the force / tactile sensor to be calibrated, the following step is further included: Construct the calibration grid based on the sensing part of the arrayed plurality of sensing units; wherein the sensing part is arranged on the bottom of the force / tactile sensor.

3. The method of claim 2, wherein, The step of constructing the calibration grid corresponding to the force / tactile sensor based on the sensing part of the arrayed plurality of sensing units comprises the following steps: Construct the bounding box of the calibration grid based on the sensing part of the arrayed plurality of sensing units; Construct the calibration grid based on the bounding box and the arrangement mode of the sensing part of the plurality of sensing units.

4. The method of claim 3, wherein The step of constructing the bounding box of the calibration grid based on the sensing part of the arrayed plurality of sensing units comprises the following steps: Extract the center of the sensing part of the sensing unit located at the corner point; Draw a circle with the center of the sensing part of each of the sensing units located at the corner point as the center and the detection range of each of the corresponding sensing units as the radius; Form an inscribed frame surrounding all the circles; Take the inscribed frame as the bounding box of the calibration grid.

5. The method of claim 1 or 2, wherein The step of determining a plurality of calibration contact points on the surface of the force / tactile sensor based on the calibration grid comprises the following steps: According to a preset rule, insert an insertion point based on the corner point of each unit grid in the calibration grid; Take the corner point of each unit grid and the insertion point as the calibration contact point; Or, Take the corner point of each unit grid as the calibration contact point.

6. The method of claim 1 or 2, wherein The step of mapping the calibration grid to the surface of the force / tactile sensor comprises the following steps: Obtain the 3D model of the force / tactile sensor; Map the calibration grid to the surface of the 3D model of the force / tactile sensor; or Send a projection instruction to the projector to project the calibration grid onto the surface of the force / tactile sensor.

7. The method of claim 1 or 2, wherein The step of generating movement instructions for the actuator based on the plurality of calibration contact points comprises the following steps: Obtain a connection trajectory sequentially connecting the plurality of calibration contact points; Generate the movement instructions based on the connection trajectory.

8. A calibration trajectory generation device for a force / tactile sensor, characterized by, The device comprises: A grid acquisition module for obtaining a calibration grid corresponding to a force / tactile sensor to be calibrated; wherein the calibration grid is a calibration grid constructed based on the bottom of the force / tactile sensor; A grid mapping module for mapping the calibration grid to the surface of the force / tactile sensor; A contact determination module for determining a plurality of calibration contact points on the surface of the force / tactile sensor based on the calibration grid; A trajectory generation module is configured to generate movement instructions of the actuator based on the plurality of calibration contact points, so as to instruct the actuator to sequentially press against the plurality of calibration contact points on the surface of the real force / tactile sensor.

9. A calibration system characterized by, The system comprises an actuator, a fixing device and a controller; the force / tactile sensor comprises a plurality of sensing units arranged in an array; The fixing device is configured to fix the force / tactile sensor to be calibrated; The controller is in communication connection with the actuator; The controller is configured to implement the steps of the method for generating calibration trajectories of the force / tactile sensor according to any one of claims 1 to 7.

10. The calibration system of claim 9, wherein, The actuator comprises an actuator body and a pressing actuator arranged at an execution end of the actuator body; The pressing actuator comprises a mounting disc and a pressing head extending away from the execution end of the actuator body by the mounting disc; A free end of the pressing head forms a curved surface; and / or, a diameter of the pressing head is 4mm-6mm.

Images