Core removing robot control system and control method

Abstract

The invention is suitable for the technical field of intelligent robot control, and provides a denucleating robot control system and method.The system comprises a visual recognition unit, a motion planning unit, a tactile feedback unit, a control unit and a denucleating robot body, and the denucleating robot body comprises a cutter body assembly integrated with a pressure sensor. According to the system, a pressure sensor is directly integrated into a transmission chain through an innovative cutter body structural design, so that real-time force feedback is realized; the visual identification unit adopts a multi-stage image processing flow, so that the accuracy of identifying feature information is improved; according to the control method of the kernel removing robot, judgment is carried out based on multi-parameter threshold values, and high-precision action control is achieved. The coring robot control system provided by the invention has the advantages of high efficiency, flexible action, high precision and the like, and can be widely applied to the fields of industry, medical treatment and the like.

Description

Technical Field

[0001] This application belongs to the technical field of intelligent robot control, and particularly relates to a pit-removing robot control system and a control method. Background Art

[0002] With the continuous development of industries such as food processing, the demand for pit-removing automation is increasing day by day. Most traditional pit-removing processes rely on manual operations, which are not only inefficient but also difficult to ensure the consistency and hygiene standards of pit-removing. Therefore, pit-removing robots have emerged.

[0003] A pit-removing robot is an intelligent device that can simulate humans for recognition, positioning, decision-making, planning, and pit-removing operations. Its working principle usually involves multiple links such as image recognition, expert analysis, path planning, solution decision-making, motion choreography, motion control, external perception, real-time control, and power drive. Existing pit-removing robots often rely on fixed preset templates or simple image matching algorithms when identifying the types, sizes, and shapes of items to be pit-removed. This method is significantly inferior to manual processing in terms of recognition ability, operation accuracy, and pit-removing effect when dealing with items to be pit-removed with large differences in shape and size. In addition, when existing pit-removing robots control the movement of the robotic arm, they usually adopt fixed movement trajectories and speed parameters. This control method is difficult to achieve flexible and precise pit-removing intelligent operations when facing items to be pit-removed with different shapes and sizes.

[0004] Furthermore, existing pit-removing robot control systems usually lack real-time tactile feedback capabilities when performing fine operation tasks, resulting in the inability to adjust actions in a timely manner according to changes in contact forces in complex environments. Especially in fields such as medical treatment and precision machining, traditional robot control systems are difficult to achieve precise force control and real-time action adjustment. In addition, the coordination efficiency between visual processing and motion control of existing robot control systems is relatively low, affecting the overall operation accuracy.

[0005] Therefore, how to improve the intelligence and operation effect of pit-removing robots has become an urgent problem to be solved. Summary of the Invention

[0006] The embodiments of this application provide a pit-removing robot control system and a control method, aiming to improve the intelligence and operation effect of pit-removing robots, and at the same time solve technical problems such as the lack of real-time tactile feedback in intelligent robot control systems, low coordination efficiency between vision and motion control, and poor adaptability to fine operations.

[0007] In a first aspect, the embodiments of this application provide a pit-removing robot control system, including a visual recognition unit, a motion planning unit, a tactile feedback unit, a control unit, and a pit-removing robot body. The pit-removing robot body includes a tool body assembly integrated with a pressure sensor.

[0008] The visual recognition unit is configured to obtain a target image of the item to be pitted and determine feature information of the target pit based on the target image, where the target pit is the pit of the item to be pitted, and the feature information is used to characterize the external shape feature of the target pit;

[0009] The motion planning unit is configured to determine motion parameters of the pitting robot body based on the target image and the feature information, where the motion parameters include a motion route, a motion strategy, an entry point, and a departure point;

[0010] The control unit is configured to control the action of the tool body assembly based on the motion parameters;

[0011] The tactile feedback unit is configured to, during the action of the tool body assembly, collect a pressure value of the tool body assembly through the pressure sensor and calculate the cumulative extension length and the pressure change rate of the tool body assembly, and adjust the action of the tool body assembly based on the pressure value, the cumulative extension length, and the pressure change rate.

[0012] In a possible implementation manner, the tool body assembly includes a push rod assembly, a gear transmission mechanism, a tool handle, a blade, a pressure sensing assembly, a mounting seat, a thrust connection nut, and a connection screw;

[0013] The push rod assembly is internally provided with a rack, and a servo motor or a steering gear pulls or pushes the tool body assembly by driving the gear transmission mechanism, and the tool handle is connected to the blade; the pressure sensing assembly includes a bearing, a pressure sensor, and a washer, the tool handle serially connects the bearing, the pressure sensor, and the washer through the connection screw, and the pressure sensor is combined with the thrust connection nut through the mounting seat.

[0014] In a possible implementation manner, the visual recognition unit is further configured to:

[0015] Perform visual processing operations on the target image, where the visual processing operations include any one or more of image correction, color layer separation, binary processing, and graphic morphology processing.

[0016] In a second aspect, an embodiment of the present application provides a control method for a pitting robot, which is applied to a pitting robot control system as described in the first aspect or any possible implementation manner, and the method includes:

[0017] Obtain a target image of the item to be pitted;

[0018] Based on the target image, determine feature information of the target pit, where the target pit is the pit of the item to be pitted, and the feature information is used to characterize the external shape feature of the target pit;

[0019] Based on the target image and the feature information, determine the motion parameters of the pit-removing robot body;

[0020] Based on the motion parameters, control the servo motor or the steering gear to step one step, and after waiting for a preset time interval, collect the pressure value and the cumulative extended length of the tool body assembly, and calculate the pressure change rate;

[0021] Based on the pressure value, the cumulative extended length, the pressure change rate and the multi-parameter threshold, adjust the action of the tool body assembly.

[0022] In a possible implementation manner, the multi-parameter threshold includes a maximum allowable pressure value, a maximum pressure change rate and a maximum extended length;

[0023] The adjusting the action of the tool body assembly based on the pressure value, the cumulative extended length, the pressure change rate and the multi-parameter threshold includes:

[0024] When any one or more of the pressure value, the cumulative extended length and the pressure change rate are greater than or equal to the corresponding maximum allowable pressure value, the maximum extended length and the maximum pressure change rate, end the step-in insertion mode and process of the tool body assembly, and start the next cleaning action.

[0025] In a possible implementation manner, the determining the motion parameters of the pit-removing robot body based on the target image and the feature information includes:

[0026] Based on the feature information, determine the shape information, position information, size information and feature point information of the target pit;

[0027] Based on the shape information, position information, size information and feature point information of the target pit, determine the number of cutting times, the cutting positions and the tool-using directions;

[0028] Based on the feature point information and the target image, determine the local images corresponding to the respective cutting positions;

[0029] Based on the feature information and the local images corresponding to the respective cutting positions, determine the cutting types and the tool-using directions corresponding to the respective cutting positions.

[0030] In a possible implementation manner, the determining the number of cutting times, the cutting positions and the tool-using directions based on the shape information, position information, size information and feature point information of the target pit includes:

[0031] Based on the shape information and the size information, determine the segmentation information of the target pit;

[0032] Based on the segmentation information, determine the number of cutting times;

[0033] Based on the shape information, the position information, the feature point information, and the segmentation information, determine the cutting positions and the cutting directions corresponding to each of the cutting times.

[0034] In a possible implementation, before determining the local images corresponding to each of the cutting positions based on the feature point information and the target image, the method further includes:

[0035] Calculate the distance between any two of the cutting positions;

[0036] When the distance between any two of the cutting positions is less than a preset distance threshold, optimize the cutting positions and the cutting times.

[0037] In a possible implementation, before determining the local images corresponding to each of the cutting positions based on the feature point information and the target image, the method further includes:

[0038] Obtain nuclear removal target information, where the nuclear removal target information is used to indicate the nuclear removal fineness requirement of the item to be nuclear removed;

[0039] Determine the nuclear removal mode of the item to be nuclear removed based on the nuclear removal target information, and different nuclear removal modes correspond to different nuclear removal fineness;

[0040] Calculate the distance between any two of the cutting positions;

[0041] Optimize the cutting positions and the cutting times based on the nuclear removal mode and the distance between any two of the cutting positions.

[0042] In a possible implementation, the determining the cutting type and the cutting direction corresponding to each of the cutting positions based on the feature information and the local images corresponding to each of the cutting positions includes

[0043] Based on the feature information and each of the local images, determine the local feature information of the target nucleus in each of the local images, where the local feature information includes any one or more of local position information, local shape information, local size information, local angle information, local color information, and local depth information;

[0044] Based on the local feature information of the target nucleus in each of the local images, determine the cutting type and the cutting direction corresponding to each of the cutting positions.

[0045] In a third aspect, an embodiment of the present application provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, where when the processor executes the computer program, the method described in the second aspect or any one of its implementations is implemented.

[0046] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium storing a computer program, which when executed by a processor implements the method as described in the second aspect or any one of its implementation manners.

[0047] In a fifth aspect, an embodiment of the present application provides a computer program product including a computer program, which when executed by a processor implements the steps of the method as described in the second aspect or any one of its implementation manners.

[0048] The beneficial effects of the embodiment of the present application compared with the prior art are as follows: The system includes a visual recognition unit, a motion planning unit, a tactile feedback unit, a control unit, and a pit-removing robot body. The pit-removing robot body includes a cutter body assembly integrated with a pressure sensor. Through the innovative design of the cutter body structure, the system directly integrates the pressure sensor into the transmission chain to achieve real-time force feedback. The visual recognition unit adopts a multi-level image processing process to improve the accuracy of identifying feature information. The control method of the pit-removing robot is based on multi-parameter thresholds for judgment to achieve high-precision motion control. The pit-removing robot control system provided by the present application has the advantages of high efficiency, flexible movement, and high precision, and can be widely applied to industrial, medical, and other fields.

[0049] It can be understood that the control method, electronic device, computer-readable storage medium, and computer program product of the pit-removing robot provided by the embodiment of the present application have the same beneficial effects as the above-mentioned pit-removing robot control system, which will not be elaborated here. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] To more clearly illustrate the technical solutions in the embodiments of the present application, the following will briefly introduce the drawings required for use in the embodiments or the description of the prior art. Obviously, the following drawings are only some embodiments of the present application. For those of ordinary skill in the art, without creative efforts, other drawings can be obtained based on these drawings.

[0051] Figure 1 It is a schematic diagram of the architecture of a pit-removing robot control system provided by an embodiment of the present application;

[0052] Figure 2 It is a schematic diagram of the architecture of another pit-removing robot control system provided by an embodiment of the present application;

[0053] Figure 3 It is a schematic flowchart of a visual processing process provided by an embodiment of the present application;

[0054] Figure 4Schematic diagram of a tool body component provided by an embodiment of the present application;

[0055] Figure 5 Flow schematic diagram of a tactile feedback control method provided by an embodiment of the present application;

[0056] Figure 6 Flow schematic diagram of a control method for a pit-removing robot provided by an embodiment of the present application;

[0057] Figure 7 Schematic diagram of the structure of an electronic device provided by an embodiment of the present application. Detailed implementation manners

[0058] In the following description, specific details such as specific system architectures and technologies are presented for the purpose of illustration rather than limitation, so as to thoroughly understand the embodiments of the present application. However, those skilled in the art should clearly understand that the present application can also be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to avoid unnecessary details from interfering with the description of the present application.

[0059] It should be understood that when used in the specification and appended claims of the present application, the term "comprising" indicates the presence of the described features, wholes, steps, operations, elements, and / or components, but does not exclude the presence or addition of one or more other features, wholes, steps, operations, elements, components, and / or their combinations.

[0060] It should also be understood that the term "and / or" used in the specification and appended claims of the present application refers to any combination and all possible combinations of one or more of the associated listed items, and includes these combinations.

[0061] As used in the specification and appended claims of the present application, the term "if" can be interpreted as "when", "once", "in response to determining", or "in response to detecting" according to the context. Similarly, the phrase "if determined" or "if [the described condition or event] is detected" can be interpreted as meaning "once determined", "in response to determining", "once [the described condition or event] is detected", or "in response to detecting [the described condition or event]" according to the context.

[0062] In addition, in the description of the specification and appended claims of the present application, the terms "first", "second", "third", etc. are only used for distinguishing descriptions and cannot be understood as indicating or implying relative importance.

[0063] References to "one embodiment" or "some embodiments" etc. described in the specification of this application mean that specific features, structures, or characteristics described in connection with that embodiment are included in one or more embodiments of this application. Thus, statements such as "in one embodiment", "in some embodiments", "in other some embodiments", "in still other embodiments", etc. that appear in different places in this specification do not necessarily all refer to the same embodiment, but mean "one or more but not all embodiments", unless otherwise specifically emphasized in other ways. The terms "comprising", "including", "having" and their variants all mean "including but not limited to", unless otherwise specifically emphasized in other ways.

[0064] For ease of understanding, the technical solution of this application will be introduced in detail below in conjunction with the accompanying drawings.

[0065] Figure 1 It is a schematic diagram of the architecture of a pit-removing robot control system provided in an embodiment of this application. Figure 2 It is another schematic diagram of the architecture of a pit-removing robot control system provided in an embodiment of this application, as Figure 1 and Figure 2 shown, the pit-removing robot control system includes a pit-removing robot body, a control unit, a communication unit, a host system, a motion control system, a vision processing system, a tactile perception system, a software process control system, a network communication module, etc. Among them, the vision processing system includes a vision recognition unit, the host system includes a motion planning unit, the tactile perception system includes a tactile feedback unit, and the pit-removing robot body includes a tool body assembly integrated with a pressure sensor.

[0066] Specifically, the pit-removing robot control system is composed of parts such as a pit-removing robot body, control, communication, host, vision, software (including an expert library and a motion model library), etc., and completes processes such as recognition, judgment, analysis, path planning, motion choreography, motion control, external perception, decision-making, etc., becoming a subject that can work autonomously.

[0067] In specific implementation, the vision recognition unit is used to obtain a target image of the item to be pit-removed, and determine the feature information of the target pit based on the target image. The target pit is the pit of the item to be pit-removed, and the feature information is used to characterize the external shape features of the target pit; the motion planning unit is used to determine the motion parameters of the pit-removing robot body based on the target image and the feature information; the control unit is used to control the action of the tool body assembly based on the motion parameters; the tactile feedback unit is used to collect the pressure value of the tool body assembly through the pressure sensor during the action of the tool body assembly, calculate the cumulative extension length and the pressure change rate of the tool body assembly, and adjust the action of the tool body assembly based on the pressure value, the cumulative extension length, and the pressure change rate.

[0068] As an example, after obtaining the target image, the control system of the pit-removing robot can calculate characteristic information such as the workload of the execution process, the movement position, and the graphic feature points (such as boundaries, starting points, ending points, centers, midlines, inflection points, widths, angles, convex points, concave points, quantities) based on the position information and shape information (such as straight, crescent-shaped, S-shaped, length, width, turning positions, etc.) in the image. Then, according to the task objectives, functions, and algorithms, it generates motion parameters such as the motion target position, motion route, speed, acceleration, action cut-in points, action times, action types (such as stabbing, picking, gouging, cutting, slicing, prying, shaving, tool setting, resetting, etc.), motion correction, and coordinate correction to process the target pit. During the processing, the tactile feedback unit monitors the action process, judges the changes in force and material, and timely aborts and adjusts the processing actions to complete a reasonable and proper processing process.

[0069] The technical solution provided by this application, through the innovative design of the tool body structure, directly integrates the pressure sensor into the transmission chain to achieve real-time force feedback; the visual recognition unit adopts a multi-level image processing process to improve the accuracy of recognizing characteristic information; the control method of the pit-removing robot is based on multi-parameter thresholds for judgment to achieve high-precision motion control.

[0070] Figure 3 It is a schematic flowchart of a visual processing process provided by an embodiment of this application. On the basis of the above embodiments, this embodiment further explains and optimizes the technical solution. Specifically, in this embodiment, as Figure 3 shown, the steps in the figure are executed by the visual recognition unit for performing visual processing operations on the target image. The visual processing operations include any one or more of image correction, color layer separation, binarization processing, and graphic morphology processing.

[0071] It should be noted that the steps in the process are not necessarily in the order shown in the figure, and can be interspersed and appear multiple times, still constituting the embodiments of the present invention; after processing the target image multiple times and performing arithmetic operations to merge into the final target image, it also constitutes the embodiments of the present invention.

[0072] Figure 4 It is a schematic diagram of a tool body assembly provided by an embodiment of this application. On the basis of the above embodiments, this embodiment further explains and optimizes the technical solution. Specifically, in this embodiment, as Figure 2 and Figure 4 shown, the tool body assembly is composed of a push rod assembly 1 (with an internal rack 2), a gear transmission mechanism, a tool handle assembly 9 (connected to the blade 10), a pressure sensing assembly (including a bearing 6, a pressure sensor 7, and a washer 8), a mounting seat 4, a thrust connecting nut 3, and a connecting screw 5. The servo drive system (servo motor, stepper motor, or servo) drives the tool body assembly to move.

[0073] Specifically, a rack 2 is built into the push rod assembly 1. A servo motor or a steering gear drives a driving gear transmission mechanism to pull or push the tool body assembly, and the tool handle 9 is connected to the blade 10; the pressure sensing assembly includes a bearing 6, a pressure sensor 7 and a washer 8. The tool handle 9 connects the bearing 6, the pressure sensor 7 and the washer 8 in series through a connecting screw 5, and the pressure sensor 7 is combined with a thrust connecting nut 3 through a mounting seat 4.

[0074] It should be noted that Figure 4 changing the connection structure to make the pressure sensor sense force during both the pushing and pulling of the tool body, or connecting or paralleling sensors specifically for sensing forces in the pulling and pressing directions in the tool body assembly, both constitute embodiments of the present invention.

[0075] As an example, the pit-removing robot control system uses a servo motor to drive the gear transmission mechanism of the tool body assembly in the pit-removing robot body. The pressure sensor is connected in series in the tool body transmission chain. The vision processing system executes the Figure 3 image processing process as shown, and the control host processes visual and tactile data in real time. In the vision processing stage, the target image is obtained through the vision processing system and image preprocessing is performed to identify the characteristic information (such as boundaries, positions, starting points, ending points, centers, etc.) of the target pit in the target image. Then, motion parameters are generated based on the target image and the characteristic information; in the motion control stage, the motion planning unit plans the motion path according to the motion parameters, selects a processing scheme or action type according to the expert library, drives the tool body assembly to perform a predetermined action, and monitors the tactile feedback in real time through the tactile feedback unit; in the tactile feedback stage, as Figure 5 shown, the servo motor or the steering gear is driven to step one step based on the motion parameters. After each step, wait for a detection period, collect the pressure value through the pressure sensor in the tool body assembly and calculate the pressure change rate, and count the cumulative extended length of the tool body; when one or more of the pressure value, the cumulative extended length, and the pressure change rate are greater than or equal to the corresponding preset thresholds, end the step-by-step insertion mode and process of the tool body assembly, and start the next cleaning action.

[0076] Among them, Figure 5 the control method shown endows the pit-removing robot control system with an excellent operation mode, making it more direct to obtain perception data, timely in information processing, avoiding large errors, making the motion control more accurate, having quite good real-time performance, and realizing high-precision and real-time force feedback control; improving the coordination efficiency of vision recognition and motion control, realizing the synchronization of the data transfer analysis judgment decision-making process and motion, timely in information processing, and advanced in technology; enhancing the operation adaptability and safety in complex environments; the tactile feedback mechanism has a compact structure, is suitable for a variety of application scenarios, and has a highly intelligent independent decision-making ability.

[0077] Figure 6The flowchart shows a control method for a pit-removing robot provided by an embodiment of the present application. Based on the above embodiment, the technical solution is further described and optimized in this embodiment. Specifically, in this embodiment, as Figure 6 shown, it is applied to a pit-removing robot control system such as Figure 1 or Figure 2 shown. For the sake of convenience of description, only the parts related to this embodiment are shown. The method provided by this embodiment includes the following steps:

[0078] S610. Obtain the target image of the item to be pitted.

[0079] Specifically, the item to be pitted can be an item that needs to be pitted in the fields of food, agriculture, medicinal materials, industry, medical treatment, etc., including but not limited to betel nuts, hawthorns, jujubes, olives, and croton.

[0080] In a specific implementation, the target image of the item to be pitted is collected through an image acquisition device such as a camera. The target image should contain the complete image of the item to be pitted.

[0081] S620. Based on the target image, determine the feature information of the target pit. The target pit is the pit of the item to be pitted, and the feature information is used to characterize the external shape feature of the target pit.

[0082] In a possible implementation manner, as Figure 3 shown, first perform a visual processing operation on the target image to highlight the target pit part in the target image, and then determine the feature information of the target pit based on the target image after the visual processing operation. Among them, the visual processing operation includes any one or more of image correction, color layer separation and extraction, image binarization, and graphic morphology processing.

[0083] As an example, the image correction operation on the target image includes the correction of any one or more of the brightness, exposure, resolution, and color temperature of the target image.

[0084] As an example, the graphic morphology processing includes image modification, target highlighting, impurity filtering, and target image modification and restoration, etc. Among them, the image modification includes operations such as supplementation, rounding, connection, and separation; the target highlighting includes operations such as shape comparison, area calculation, position division, and feature recognition; the impurity filtering includes removing or weakening the graphics outside the target pit to highlight the target pit; the target graphic modification and restoration includes operations such as scaling, supplementation, rounding, connection, and separation.

[0085] It should be noted that the steps in the visual processing operation can be executed in different orders, and the steps can be interspersed or appear multiple times; or multiple visual processing operations can be performed on the same target image, and the images obtained after each visual processing operation are calculated and combined to obtain the final processed image, and then the characteristic information of the target nucleus is determined based on the final processed image.

[0086] Exemplarily, the characteristic information includes any one or more of the boundary, starting point, ending point, center, midline, inflection point, width, angle, convex point, concave point, and quantity of the target nucleus.

[0087] In a specific implementation, the position information and shape information, etc. of the target nucleus in the target image after the visual processing operation are used to calculate the characteristic points of the target nucleus in the image through various image processing algorithms, and the characteristic information is constructed.

[0088] S630. Based on the target image and the characteristic information, determine the motion parameters of the de-nucleation robot body.

[0089] Specifically, the motion parameters of the de-nucleation robot body include but are not limited to the motion route, motion strategy, entry point, and exit point. The motion strategy includes the number of knife insertions, motion sequence, knife insertion position for each knife insertion, knife insertion type, and knife use direction, etc. Among them, the knife insertion type includes but is not limited to stabbing, picking, gouging, cutting, slicing, prying, and shaving.

[0090] In a possible implementation manner, step S630 may optionally include: determining the shape information, position information, size information, and characteristic point information of the target nucleus based on the characteristic information; determining the number of knife insertions, knife insertion positions, and knife use directions based on the shape information, position information, size information, and characteristic point information of the target nucleus; determining the local images corresponding to each knife insertion position based on the characteristic point information and the target image; determining the knife insertion type and knife use direction corresponding to each knife insertion position based on the characteristic information and the local images corresponding to each knife insertion position.

[0091] Among them, determining the number of knife insertions, knife insertion positions, and knife use directions based on the shape information, position information, size information, and characteristic point information of the target nucleus may optionally include: determining the segmentation information of the target nucleus based on the shape information and size information; determining the number of knife insertions based on the segmentation information; determining the knife insertion positions and knife use directions corresponding to each number of knife insertions based on the shape information, position information, characteristic point information, and segmentation information.

[0092] In one embodiment, the feature information includes information such as the contour, position, starting point, and ending point of the target nucleus. The determined shape information of the target nucleus includes the shape of the target nucleus (such as S-shaped or straight-line-shaped, etc.), the dimension information includes the area or width of the target nucleus, etc., and the feature point information includes the starting point, ending point, center, convex point, concave point, inflection point, etc. Then, based on the contour, position, shape type, starting point, and ending point of the target nucleus in the feature information, the starting coordinates, feature points, segmentation information, angle, stroke length, and width of the target nucleus in the target image are determined; based on the shape type, area, segmentation information, stroke length, position, and angle of the target nucleus, the number of cutting operations is determined.

[0093] In a specific implementation, based on the information such as the boundary, width, starting point, and ending point of the target nucleus in the feature information, the target nucleus is segmented, and the feature points of the target nucleus are determined (for example, the feature points can be the starting point, ending point, or midpoint of each segment). It is judged whether the distance between two adjacent feature points is less than the first preset distance threshold. If so, the number of cutting operations is one cut; if not, the distance to the next adjacent feature point is further determined.

[0094] As an example, when the distance between two adjacent feature points is greater than or equal to the first preset distance threshold, the number of cutting operations is appropriately increased according to the integrity of the processing, and the newly added cutting positions correspondingly become part of the motion parameters. Similarly, when the distance between two adjacent feature points is less than the second preset distance threshold, the cutting points are cancelled or merged for optimization, and the first preset distance threshold is greater than the second preset distance threshold.

[0095] In a possible implementation manner, the segmentation information includes the number of segments, the starting point, ending point, or midpoint of each segment, and the segment length of each segment. The cutting position and the cutting direction corresponding to each cutting operation are determined by the center, convex point, concave point, inflection point, width of the target nucleus in the feature point information, and the segment length of each segment in the segmentation information.

[0096] As an example, the shape of the target nucleus obtained by processing the target image through an image processing algorithm is classified. When the nucleus is straight, the cutting direction can be to cut alternately from left to right, and the removal directions are opposite and staggered, or it can be to cut at intervals in the same direction until it is completely removed properly; when the nucleus is crescent-shaped, the cutting direction can be carried out at intervals in the same side in sequence; when the nucleus is S-shaped, the cutting strategy is to divide the outer shape into several small crescent shapes according to the inflection points, process each segment according to the crescent shape, and then combine them into the cutting scheme for the entire S-shaped nucleus.

[0097] As an example, when the length of the above-mentioned profile segmentation is too long, in order to achieve proper processing, a cutting point can be added at the middle position, and the cutting direction is arranged based on the above-mentioned scheme; similarly, when the length of the above-mentioned profile segmentation is too short, especially when the distance between two inflection points is too short, the number of cutting operations can be appropriately reduced and the strategy can be optimized to reduce the processing actions and processes while ensuring proper processing, so as to improve efficiency.

[0098] As an example, when the distance of the middle feature point from the starting point or the ending point is too long, a cutting point can be added in the middle to ensure proper processing.

[0099] Preferably, after determining the number of cutting operations and the cutting positions of the item to be pitted, pit removal target information is obtained, and the pit removal target information is used to indicate the pit removal fineness requirement of the item to be pitted; based on the pit removal target information, the pit removal mode of the item to be pitted is determined, and different pit removal modes correspond to different pit removal fineness; the distance between any two cutting positions is calculated; based on the pit removal mode and the distance between any two cutting positions, the cutting positions and the number of cutting operations are optimized.

[0100] Specifically, the pit removal fineness requirements of the item to be pitted indicated by the pit removal target information include rough, medium, and fine, and the corresponding pit removal modes are fast mode, medium mode, and fine mode respectively.

[0101] In specific implementation, if the pit removal fineness requirement of the item to be pitted indicated by the pit removal target information is fine, the pit removal mode adopted by the pit removal robot is the fine mode, and at this time, the number of cutting operations and the cutting positions of the item to be pitted are not optimized; if the pit removal fineness requirements of the item to be pitted indicated by the pit removal target information are rough and medium, the pit removal modes adopted by the pit removal robot are the fast mode and the medium mode respectively. At this time, when the number of cutting operations of the item to be pitted is greater than or equal to two, the method of optimizing the cutting positions and the number of cutting operations by the distance between the cutting positions is adopted, which will not be elaborated here.

[0102] In a possible implementation manner, based on the feature information and the local images corresponding to each cutting position, the cutting type and the cutting direction corresponding to each cutting position are determined, and the options may include: based on the feature information, the local feature information of the target pit in each local image is determined, and the local feature information includes any one or more of local position information, local shape information, local size information, local angle information, local color information, and local depth information; based on the local feature information of the target pit in each local image, the cutting type and the cutting direction corresponding to each cutting position are determined.

[0103] In specific implementation, after determining the cutting position of each cutting operation, in the target image, the cutting type corresponding to each cutting position is determined through the feature point information, segmentation information, size information, etc. of the target pit.

[0104] As an example, the shape of the target nucleus in the corresponding local image is determined by the boundary of the target nucleus in the local shape information. When the width of the target nucleus in the local size information is greater than or equal to the blade width, for high efficiency, a simple and direct stabbing and picking action is usually adopted; on the contrary, if the width is less than the blade width, a treatment of stabbing and then gouging is usually adopted.

[0105] As another example, if the width of the target nucleus in the local size information is small, even in the shape of a slit, the cutting type is selected as stabbing, prying and then gouging.

[0106] As still another example, when the material of the target nucleus in the local image is relatively hard, during the stabbing process of the tool body, a certain amplitude of reciprocating rotation is added, and a prying and loosening action is attached during stabbing to make the stabbing smoother.

[0107] As yet another example, when the local color information in the local feature information shows that the color of the target nucleus is deep, indicating the center of the nucleus, then stabbing and picking is better; when the color is light, indicating the edge of the nucleus, stabbing and prying is better.

[0108] As still another example, when the local depth information in the local feature information shows that the depth of the target nucleus is relatively deep, such as a depression, gouging or prying is better; when the depth is shallow (protrusion), such as protruding from the surface of the areca nut peel, cutting or slicing is better.

[0109] It should be noted that the first preset distance threshold, the second preset distance threshold, etc. in this embodiment can be custom-set according to the actual situation, and this application does not limit this.

[0110] S640, control the servo motor or the steering gear to step one step based on the motion parameters, and after waiting for a preset time interval, collect the pressure value and the cumulative extension length of the tool body assembly, and calculate the pressure change rate.

[0111] S650, adjust the action of the tool body assembly based on the pressure value, the cumulative extension length, the pressure change rate and the multi-parameter threshold.

[0112] Specifically, the multi-parameter threshold includes the maximum allowable pressure value, the maximum pressure change rate and the maximum extension length; then when any one or more of the pressure value, the cumulative extension length and the pressure change rate is greater than or equal to the corresponding maximum allowable pressure value, the maximum extension length and the maximum pressure change rate, end the step-by-step insertion mode and process of the tool body assembly, and start the next cleaning action.

[0113] In specific implementation, such as Figure 5As shown in the figure, first, based on the determined motion parameters such as the number of cutting operations, cutting positions, and cutting types, the tool body is controlled to align with the cutting point first, and then enters the piercing process. For each step of forward extension of the tool body, the motor is controlled to step once; after waiting for a preset time interval, the pressure value and the cumulative extension length of the tool body in the pit-removing robot at the current moment are obtained; when the pressure value is greater than or equal to the maximum allowable pressure value and / or the cumulative extension length is greater than or equal to the maximum extension length, the driving control motor stops operating; if the pressure value is less than the maximum allowable pressure value and the cumulative extension length is less than the maximum extension length, the control motor in the pit-removing robot is controlled to perform the next operation step based on the motion parameters.

[0114] As an example, after controlling the control motor in the pit-removing robot to step forward once based on the motion parameters, the pressure value and the cumulative extension length of the tool body in the pit-removing robot at the current moment are collected, and the pressure change rate is calculated based on the pressure value. When any one of the pressure value, the cumulative extension length, and the pressure change rate reaches the corresponding preset threshold, the driving control motor stops operating; if none of the pressure value, the total extension length value, and the pressure change rate reaches the corresponding preset threshold, the pit-removing robot continues to perform the pit-removing operation based on the motion parameters.

[0115] The technical solution provided in this embodiment determines the feature information used to characterize the external shape features of the target nucleus in the item to be pitted based on the target image of the item to be pitted; determines the motion parameters of the pit-removing robot body based on the target image and the feature information used to characterize the external shape features of the target nucleus; and then controls the pit-removing robot to perform the pit-removing operation on the item to be pitted based on the motion parameters. For items to be pitted with different external shape features such as the size and shape of the nucleus, different motion parameters are used to control the pit-removing robot to perform the pit-removing operation according to the external shape features of its nucleus. Compared with using the same motion parameters or several preset fixed motion parameters to control the pit-removing robot to perform the pit-removing operation on all types of items to be pitted, the adaptability of the motion parameters to the items to be pitted is improved, and thus the pit-removing accuracy of the pit-removing robot is improved.

[0116] In addition, the pit-removing robot control system with tactile sensation endows the pit-removing robot with the ability of real-time control during operation, and has the ability to change the action process in a timely manner during the processing. Cooperating with the decision-making function or expert system of the pit-removing robot, it can handle more complex processes and is an essential part of the intelligent control solution. The tactile feedback control method provided in this application obtains perception data more directly, processes information in a timely manner, avoids large errors, has accurate motion control, has quite good real-time performance, and realizes high-precision and real-time force feedback control.

[0117] Figure 7 This is a schematic structural diagram of an electronic device provided in an embodiment of the present application. As Figure 7 shown, the electronic device 7 in this embodiment includes: at least one processor 70 (Figure 7 only one is shown), a memory 71, and a computer program 72 stored in the memory 71 and executable on at least one processor 70. When the processor 70 executes the computer program 72, the steps in the above Figure 6 method embodiments are implemented.

[0118] The electronic device 7 may be a computing device such as an industrial control computer, an embedded system, a workstation, a desktop computer, a notebook, a palm computer, and a cloud server. The electronic device 7 may include, but is not limited to, a processor 70 and a memory 71. Those skilled in the art can understand that Figure 7 merely examples of the electronic device 7, which do not constitute a limitation on the electronic device 7, may include more or fewer components than shown in the figure, or combine certain components, or different components. For example, it may also include input / output devices, network access devices, etc.

[0119] The processor 70 may be a central processing unit (CPU). The processor 40 may also be other general-purpose processors, digital signal processors (DSPs), application specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.

[0120] In some embodiments, the memory 71 may be an internal storage unit of the electronic device 7, such as the hard disk or memory of the electronic device 7. In other embodiments, the memory 71 may also be an external storage device of the electronic device 7, such as a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, etc. equipped on the electronic device 7. Further, the memory 71 may also include both the internal storage unit and the external storage device of the electronic device 7. The memory 71 is used to store an operating system, application programs, a boot loader, data, and other programs, such as the program code of a computer program. The memory 71 may also be used to temporarily store data that has been output or will be output.

[0121] The embodiments of the present application also provide a computer-readable storage medium. The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps in the above-mentioned method embodiments can be implemented.

[0122] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, to implement all or part of the processes in the above-mentioned method embodiments of the present application, a computer program can be used to instruct relevant hardware to complete. The computer program can be stored in a computer-readable storage medium. When the computer program is executed by a processor, the steps in the above-mentioned method embodiments can be implemented. Among them, the computer program includes computer program code, and the computer program code can be in the form of source code, object code, executable file or some intermediate form, etc. The computer-readable medium can at least include: any entity or device that can carry the computer program code to an electronic device, a recording medium, a computer memory, a read-only memory (ROM, Read-Only Memory), a random access memory (RAM, Random Access Memory), an electrical carrier signal, a telecommunication signal, and a software distribution medium. For example, a USB flash drive, a mobile hard disk, a magnetic disk or an optical disc, etc.

[0123] A computer-readable storage medium provided by the embodiments of the present application has the same beneficial effects as the above-mentioned control method of a core-removing robot.

[0124] The embodiments of the present application provide a computer program product. The computer program product includes a computer program, and when the computer program is executed by a processor, the steps in the above-mentioned method embodiments can be implemented.

[0125] A computer program product provided by the embodiments of the present application has the same beneficial effects as the above-mentioned control method of a core-removing robot.

[0126] In the above embodiments, the descriptions of the various embodiments have their own emphases. For the parts not detailed or recorded in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0127] Those of ordinary skill in the art can realize that the units and algorithm steps of the examples described in combination with the embodiments disclosed herein can be implemented by electronic hardware, or by a combination of computer software and electronic hardware. Whether these functions are executed in a hardware or software manner depends on the specific application and design constraints of the technical solution. A professional technician can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of the present application.

[0128] In the embodiments provided in the present application, it should be understood that the disclosed device / equipment and method can be implemented in other ways. For example, the device / equipment embodiments described above are only illustrative. For example, the division of the modules or units is only a logical function division. In actual implementation, there may be other division methods. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the displayed or discussed coupling or direct coupling or communication connection between each other can be through some interfaces. The indirect coupling or communication connection of the device or unit can be in electrical, mechanical or other forms.

[0129] The units described as separate components may or may not be physically separated. The components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0130] The above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them; although the present application has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that: they can still modify the technical solutions recorded in the foregoing embodiments, or perform equivalent replacements for some of the technical features; and these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the various embodiments of the present application, and should all be included in the protection scope of the present application.

Claims

1. A control system for a pit-removing robot, characterized in that It includes a visual recognition unit, a motion planning unit, a tactile feedback unit, a control unit and a pit-removing robot body. The pit-removing robot body includes a tool body assembly integrated with a pressure sensor. The visual recognition unit is used to obtain a target image of the item to be pitted and determine the characteristic information of the target pit based on the target image. The target pit is the pit of the item to be pitted, and the characteristic information is used to characterize the external shape characteristics of the target pit. The motion planning unit is used to determine the motion parameters of the pit-removing robot body based on the target image and the characteristic information. The motion parameters include a motion route, a motion strategy, an entry point and a departure point. The control unit is used to control the action of the tool body assembly based on the motion parameters. The tactile feedback unit is used to collect the pressure value of the tool body assembly through the pressure sensor during the action of the tool body assembly, calculate the cumulative extension length and the pressure change rate of the tool body assembly, and adjust the action of the tool body assembly based on the pressure value, the cumulative extension length and the pressure change rate.

2. The system according to claim 1, wherein The tool body assembly includes a push rod assembly, a gear transmission mechanism, a tool handle, a blade, a pressure sensing assembly, a mounting seat, a thrust connection nut and a connection screw. The push rod assembly is internally provided with a rack. A servo motor or a steering gear pulls or pushes the tool body assembly by driving the gear transmission mechanism. The tool handle is connected to the blade. The pressure sensing assembly includes a bearing, a pressure sensor and a washer. The tool handle connects the bearing, the pressure sensor and the washer in series through the connection screw. The pressure sensor is combined with the thrust connection nut through the mounting seat.

3. The system according to claim 1, characterized in that, The visual recognition unit is further used for: Performing a visual processing operation on the target image. The visual processing operation includes any one or more of image correction, color layer separation, binarization processing, and graphic morphology processing.

4. A control method for a pit-removing robot, characterized in that, Applied to the pit-removing robot control system according to any one of claims 1 to 3, the method includes: Obtaining a target image of the item to be pitted; Based on the target image, determining the characteristic information of the target pit. The target pit is the pit of the item to be pitted, and the characteristic information is used to characterize the external shape characteristics of the target pit; Based on the target image and the characteristic information, determining the motion parameters of the pit-removing robot body; Based on the motion parameters, controlling the servo motor or the steering gear to step one step, and after waiting for a preset time interval, collecting the pressure value and the cumulative extension length of the tool body assembly, and calculating the pressure change rate; Based on the pressure value, the cumulative extension length, the pressure change rate and multi-parameter thresholds, adjusting the action of the tool body assembly.

5. The method according to claim 4, characterized in that, The multi-parameter thresholds include a maximum allowable pressure value, a maximum pressure change rate and a maximum extension length; The adjusting the action of the tool body assembly based on the pressure value, the cumulative extension length, the pressure change rate and the multi-parameter thresholds includes: When any one or more of the pressure value, the cumulative extension length, and the pressure change rate are greater than or equal to the corresponding maximum allowable pressure value, the maximum extension length, and the maximum pressure change rate, the step insertion mode and process of the tool body assembly are ended, and the next cleaning action is started.

6. The method according to claim 4, characterized in that Based on the target image and the feature information, determine the motion parameters of the nuclear removal robot body, including: Based on the feature information, determine the shape information, position information, size information, and feature point information of the target nucleus; Based on the shape information, position information, size information, and feature point information of the target nucleus, determine the number of knife insertions, the knife insertion positions, and the knife use directions; Based on the feature point information and the target image, determine the local images corresponding to each of the knife insertion positions; Based on the feature information and the local images corresponding to each of the knife insertion positions, determine the knife types and the knife use directions corresponding to each of the knife insertion positions.

7. The method according to claim 6, characterized in that, The determination of the number of knife insertions, the knife insertion positions, and the knife use directions based on the shape information, position information, size information, and feature point information of the target nucleus includes: Based on the shape information and the size information, determine the segmentation information of the target nucleus; Based on the segmentation information, determine the number of knife insertions; Based on the shape information, the position information, the feature point information, and the segmentation information, determine the knife insertion positions and the knife use directions corresponding to each of the numbers of knife insertions.

8. The method according to claim 6, characterized in that Before determining the local images corresponding to each of the knife insertion positions based on the feature point information and the target image, the method further includes: Calculate the distance between any two of the knife insertion positions; When the distance between any two of the knife insertion positions is less than a preset distance threshold, optimize the knife insertion positions and the number of knife insertions.

9. The method according to claim 6, wherein Before determining the local images corresponding to each of the knife insertion positions based on the feature point information and the target image, the method further includes: Obtain nuclear removal target information, where the nuclear removal target information is used to indicate the nuclear removal fineness requirement of the item to be nuclear removed; Based on the nuclear removal target information, determine the nuclear removal mode of the item to be nuclear removed, and different nuclear removal modes correspond to different nuclear removal finenesses; Calculate the distance between any two of the knife insertion positions; Based on the nuclear removal mode and the distance between any two of the knife insertion positions, optimize the knife insertion positions and the number of knife insertions.

10. The method according to claim 6, wherein The determination of the knife types and the knife use directions corresponding to each of the knife insertion positions based on the feature information and the local images corresponding to each of the knife insertion positions includes Based on the feature information and each of the local images, determine the local feature information of the target nucleus in each of the local images, where the local feature information includes any one or more of local position information, local shape information, local size information, local angle information, local color information, and local depth information; Based on the local feature information of the target nucleus in each of the local images, determine the knife types and the knife use directions corresponding to each of the knife insertion positions.

Images