An agv trolley of a collaborative robot and a control method thereof

Abstract

The application discloses an AGV trolley of a cooperative robot and a control method thereof, and belongs to the technical field of AGV transportation. The AGV trolley comprises a trolley main body, a mechanical arm arranged on one side of the trolley main body, and an obstacle removing portion arranged at the bottom end of the trolley main body. The trolley main body comprises a camera module, an image processing module, a substance state judging module, a first control module and a second control module. When the AGV trolley encounters obstacles covering a preset route during movement, the image of the obstacles on the preset route is acquired first, and it is judged according to the obstacle image whether the obstacles are in a solid state or a liquid state. If the obstacles are in the solid state, the mechanical arm is driven to remove the obstacles from the preset route. If the obstacles are in the liquid state, the obstacle removing portion is driven to remove the obstacles on the preset route. In this way, the obstacles do not need to be avoided, and the influence of subsequent obstacles on the movement of the AGV trolley is avoided.

Description

Technical Field

[0001] This invention belongs to the field of AGV transportation technology, specifically, it relates to a collaborative robot AGV vehicle and its control method. Background Technology

[0002] AGV (Automated Guided Vehicle) is an automated logistics device typically used for material handling and transportation in industrial, manufacturing, and warehousing sectors. AGVs can move, navigate, and operate autonomously according to predetermined routes and tasks without human intervention. In existing technologies, AGVs are generally equipped with obstacle avoidance sensors and communication modules. The communication module is connected to the control console, and if an obstacle appears on the predetermined route, it can notify the control console for handling.

[0003] For example, patent application publication number CN113734721A discloses a heavy-duty AGV operating vehicle for intelligent logistics. The heavy-duty AGV operating vehicle for intelligent logistics includes a vehicle body, a load-bearing device, an obstacle avoidance sensor, and a WIFI module. Although the above-mentioned heavy-duty AGV operating vehicle for intelligent logistics prevents collisions during vehicle operation through obstacle avoidance sensors and sends information to the control console through the WIFI module to remind staff to handle the situation, the following processing still exists.

[0004] While the aforementioned heavy-duty AGV for intelligent logistics can prevent collisions during operation through obstacle avoidance sensors, it is generally only applicable when solid obstacles appear on the predetermined route. When liquid obstacles cover the predetermined route, if the AGV continues to travel on the covered route, it is prone to veer off course. Furthermore, since factories are mostly made of metal, veer-off course can affect signal transmission, making it difficult to promptly notify the control console for handling. The obstacle will continue to have an adverse effect on the AGV. Summary of the Invention

[0005] The purpose of this section is to outline some aspects of embodiments of the present invention and to briefly describe some preferred embodiments. Simplifications or omissions may be made in this section, as well as in the abstract and title of this application, to avoid obscuring the purpose of these documents; however, such simplifications or omissions should not be construed as limiting the scope of the invention.

[0006] To solve the above problems, the present invention adopts the following technical solution.

[0007] An AGV (Automated Guided Vehicle) for collaborative robots includes a vehicle body, a robotic arm on one side of the vehicle body, and an obstacle removal unit at the bottom of the vehicle body. The vehicle body includes a camera module, an image processing module, a material state discrimination module, a first control module, and a second control module.

[0008] The camera module is used to acquire images of obstacles along a preset route;

[0009] The image processing module preprocesses the obstacle images;

[0010] The matter state discrimination module inputs the obstacle image into the matter state discrimination model and outputs the matter state category.

[0011] The first control module determines and generates a first control command or detection command based on the material state category.

[0012] The robotic arm can remove obstacles on a preset route according to the first control command or perform ultrasonic detection on the surface of the obstacle according to the detection command to obtain the surface information of the obstacle.

[0013] The second control module generates obstacle state coefficients based on obstacle surface information, compares the obstacle state coefficients with state coefficient thresholds, and determines whether to generate a second control command or a third control command.

[0014] The obstacle removal unit removes obstacles on a preset route according to a second or third control command.

[0015] Preferably, the preprocessing includes noise reduction, contrast enhancement, and image segmentation, and the material state categories include solid state and liquid state.

[0016] Preferably, the training process of the material state discrimination model is as follows: acquire i sets of data, where i is a positive integer greater than 1, the data includes obstacle images and material state categories, use the obstacle images and material state categories as sample sets, divide the sample sets into training sets and test sets, construct a classifier, use the obstacle images in the training set as input data, use the material state categories in the training set as output data, train the classifier to obtain an initial classifier, use the test set to test the initial classifier, and output a classifier that meets the preset accuracy as the material state discrimination model.

[0017] Preferably, the logic for generating the first control command and the detection command is as follows:

[0018] If the state of matter is solid, then the first control command is generated;

[0019] If the state of matter is liquid, a detection command is generated.

[0020] Preferably, the robotic arm includes a robotic arm body, an electric suction cup, and an ultrasonic detector. One end of the robotic arm body is equipped with an electric suction cup and an ultrasonic detector. The robotic arm moves to the area where the obstacle is located according to the detection command and acquires the surface information of the obstacle.

[0021] Preferably, the obstacle surface information includes obstacle surface density, obstacle surface viscosity, and echo amplitude, and the obstacle state coefficient generation formula is:

[0022] ;

[0023] in, For obstacle state coefficients, The surface density of the obstacle, The viscosity of the obstacle surface. Echo amplitude, This represents the number of ultrasonic tests performed. All are weighting coefficients, and All are greater than 0.

[0024] Preferably, the logic for determining whether to generate a second or third control instruction is as follows:

[0025] If the obstacle state coefficient is less than the state coefficient threshold, a second control command is generated;

[0026] If the obstacle state coefficient is greater than or equal to the state coefficient threshold, a third control command is generated.

[0027] Preferably, the obstacle removal unit includes a main housing, a drive motor, a receiving housing, an electric slide rail, a support member, and an adsorption member. The main housing is fixedly connected to the bottom of the trolley body. The drive motor is fixedly installed inside the main housing. The output end of the drive motor is fixedly connected to the receiving housing. The inner wall of the receiving housing is provided with an electric slide rail. A support member is provided on one side of the electric slide rail. The electric slide rail drives the support member to move up and down. Multiple adsorption members are provided at the bottom of the support member.

[0028] Preferably, the second control command includes an extension command and a descent command;

[0029] The drive motor moves the receiving box according to the extension command until the receiving box is completely moved out of the main box.

[0030] The electric slide rail moves the support downwards according to the descent command until the bottom of the suction component contacts the ground.

[0031] Preferably, the bottom end of the support is also provided with multiple liquid storage boxes, which are spaced apart from the adsorption element at the bottom end of the support, and the bottom end of the liquid storage box is provided with multiple heating nozzles.

[0032] Preferably, the third control command includes an extension command, a descent command, and a heating command;

[0033] The drive motor moves the receiving box according to the extension command until the receiving box is completely moved out of the main box.

[0034] The electric slide rail moves the support downwards according to the descent command until the bottom of the suction component contacts the ground.

[0035] Heated nozzles spray heated mist onto the surface of obstacles according to heating instructions.

[0036] Preferably, the method for the robotic arm to remove the obstacle includes:

[0037] The obstacle images acquired by the camera module are mapped onto a pre-built 3D coordinate system;

[0038] The obstacle image acquired by the camera module is processed in grayscale to obtain the grayscale value of each pixel in the obstacle image;

[0039] The difference between the gray value of each pixel and the gray value of its neighboring pixels is obtained sequentially. The edge pixels of the regions with a difference less than a preset difference threshold are connected to obtain y regions to be snapped, where y is a positive integer greater than or equal to 1.

[0040] Traverse the pixels of the area to be adsorbed, and draw a circle with the smallest adsorption radius of the electric suction cup as the center of the traversed pixels. The minimum adsorption area is obtained. The minimum adsorption radius is the radius of the obstacle that the electric suction cup can adsorb.

[0041] The region whose edge line of the minimum adsorption region lies within the region to be adsorbed is marked as the adsorption region;

[0042] The pixel corresponding to the smallest adsorption area within the adsorption area is taken as the center, and the coordinates of the pixel corresponding to the center are taken as the adsorption coordinates. The robotic arm aligns the center of the electric suction cup with the adsorption coordinates, picks up the obstacle, and then moves it out of the preset route.

[0043] A control method for an AGV (Automated Guided Vehicle) is provided, based on the aforementioned collaborative robot AGV, the method comprising:

[0044] Used to acquire images of obstacles along a preset route;

[0045] Preprocess the obstacle images;

[0046] The obstacle image is input into the matter state discrimination model, and the matter state category is output.

[0047] Based on the material state category, determine whether to generate the first control command or detection command;

[0048] According to the first control command, the obstacle on the preset route is moved out, or according to the detection command, the surface of the obstacle is ultrasonically detected to obtain the surface information of the obstacle;

[0049] Based on the obstacle surface information, an obstacle state coefficient is generated. The obstacle state coefficient is compared with the state coefficient threshold to determine whether to generate a second or third control command.

[0050] Remove obstacles on the preset route according to the second or third control command.

[0051] Beneficial effects

[0052] Compared with the prior art, the beneficial effects of the present invention are as follows:

[0053] (1) When the AGV in this invention encounters an obstacle covering the preset route during its movement, it first acquires an image of the obstacle on the preset route, determines whether the obstacle is in a solid state or a liquid state based on the obstacle image, and generates different instructions according to the different obstacle state categories. If the obstacle is in a solid state, it drives the robotic arm to remove the obstacle from the preset route. If the obstacle is in a liquid state, it drives the obstacle removal unit to remove the obstacle on the preset route. In this way, it is not necessary to avoid the obstacle, and it also avoids the subsequent obstacles from affecting the movement of the AGV.

[0054] (2) When the obstacle is in a liquid state, it is also necessary to determine whether the surface of the obstacle has solidified. If no solidification occurs, a second control command is generated, and the adsorption component only needs to wipe the obstacle during the AGV's movement. If solidification occurs, a third control command is generated, and the surface of the obstacle needs to be heated first to change the surface of the obstacle from a solidified state to a liquid state, so that the adsorption component can more easily wipe the solidified obstacle. Attached Figure Description

[0055] Figure 1 This is a schematic diagram of the overall structure of the AGV (Automated Guided Vehicle).

[0056] Figure 2 This is a system schematic diagram of the main body of the vehicle;

[0057] Figure 3 This is a schematic diagram of the robotic arm.

[0058] Figure 4 This is a side view of the AGV (Automated Guided Vehicle).

[0059] Figure 5 This is a schematic diagram of the obstacle removal unit.

[0060] Figure 6 This is a front sectional view of the obstacle removal section;

[0061] Figure 7 for Figure 5 Enlarged structural diagram at point A;

[0062] Figure 8 A schematic diagram of an AGV (Automated Guided Vehicle) driving a robotic arm.

[0063] Figure 9 This is a schematic diagram of an AGV being blocked by a solid obstacle while it is moving.

[0064] Figure 10 A schematic diagram of an AGV (Automated Guided Vehicle) moving a solid obstacle off its preset route;

[0065] Figure 11 A schematic diagram of the obstacle removal unit driven by the AGV trolley during operation;

[0066] Figure 12 This is a schematic diagram of an AGV being blocked by a liquid obstacle while it is moving.

[0067] Figure 13 A schematic diagram of an AGV clearing liquid obstacles on a preset route;

[0068] Figure 14 This is a schematic diagram of the AGV (Automated Guided Vehicle) control method.

[0069] The correspondence between the labels and component names in the attached figures is as follows:

[0070] 10. Car body; 11. Camera module; 12. Image processing module; 13. Material state discrimination module; 14. First control module; 15. Second control module; 20. Robotic arm; 21. Robotic arm body; 22. Electric suction cup; 23. Ultrasonic detector; 30. Obstacle removal unit; 31. Main box; 32. Drive motor; 33. Receiving box; 34. Electric slide rail; 35. Support component; 36. Adsorption component; 37. Liquid storage box; 38. Heating nozzle. Detailed Implementation

[0071] To make the above-mentioned objects, features and advantages of the present invention more apparent and understandable, the specific embodiments of the present invention will be described in detail below with reference to the accompanying drawings.

[0072] Many specific details are set forth in the following description in order to provide a full understanding of the invention. However, the invention may also be practiced in other ways different from those described herein, and those skilled in the art can make similar extensions without departing from the spirit of the invention. Therefore, the invention is not limited to the specific embodiments disclosed below.

[0073] Secondly, the term "an embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The phrase "in one embodiment" appearing in different places throughout this specification does not necessarily refer to the same embodiment, nor is it a single embodiment or an embodiment selectively excluded from other embodiments.

[0074] Example 1

[0075] This embodiment provides an AGV (Automated Guided Vehicle) for a collaborative robot, such as... Figure 1 and Figure 2 As shown, it includes a car body 10, a robotic arm 20 is provided on one side of the car body 10, and an obstacle removal part 30 is provided at the bottom of the car body 10. The car body 10 includes a camera module 11, an image processing module 12, a material state discrimination module 13, a first control module 14, and a second control module 15.

[0076] S10: Camera module 11, used to acquire images of obstacles on a preset route;

[0077] Specifically, since the AGV car achieves automatic navigation by detecting the preset route on the road and following the preset route, when an obstacle covers the preset route, the AGV car stops moving and obtains an image of the obstacle covering the preset route through the camera module 11. The obstacle can be a solid obstacle or a liquid obstacle, and the camera module 11 is preferably a camera.

[0078] S20: Image processing module 12, preprocesses the obstacle image;

[0079] It should be noted that the preprocessing includes noise reduction, contrast enhancement and image segmentation. When the camera module 11 acquires images of obstacles covering the preset route, the complexity of the environment may cause interference from other objects in the directly acquired images, so the directly acquired images need to be segmented.

[0080] S30: Matter state discrimination module 13 inputs the obstacle image into the matter state discrimination model and outputs the matter state category;

[0081] Specifically, the material state categories include solid state and liquid state. The training process of the material state discrimination model is as follows: obtain i sets of data, where i is a positive integer greater than 1. The data includes obstacle images and material state categories. Use the obstacle images and material state categories as a sample set. Divide the sample set into a training set and a test set. Construct a classifier. Use the obstacle images in the training set as input data and the material state categories in the training set as output data. Train the classifier to obtain an initial classifier. Test the initial classifier using the test set. Output a classifier that meets the preset accuracy as the material state discrimination model. The classifier is preferably one of the Naive Bayes model or the Support Vector Machine model.

[0082] S40: The first control module 14 determines and generates a first control command or detection command based on the material state category;

[0083] Furthermore, the logic for generating the first control command and detection command is as follows:

[0084] If the state of matter is solid, then the first control command is generated;

[0085] If the state of matter is liquid, a detection command is generated.

[0086] S50: Robotic arm 20, which moves obstacles on a preset route according to the first control command or performs ultrasonic detection on the surface of obstacles according to the detection command to obtain obstacle surface information.

[0087] It is understandable that, such as Figure 3 As shown, the robotic arm 20 includes a robotic arm body 21 and an electric suction cup 22. An electric suction cup 22 is provided at one end of the robotic arm body 21. Figure 8 , Figure 9 and Figure 10 As shown, in this embodiment, when the AGV of the collaborative robot identifies that the obstacle on the preset route is solid, it sends a first control command to the robotic arm 20. After receiving the first control command, the robotic arm 20 moves the obstacle out of the preset route.

[0088] Furthermore, the specific methods by which the robotic arm 20 removes the obstacle include:

[0089] The obstacle image acquired by the camera module 11 is mapped onto a pre-constructed three-dimensional coordinate system; in order to facilitate the acquisition of the adsorption coordinates in the following text, the three-dimensional coordinate system is constructed with the camera module 11 as the origin;

[0090] The obstacle image acquired by the camera module 11 is processed in grayscale to obtain the grayscale value of each pixel in the obstacle image;

[0091] The difference between the gray value of each pixel and the gray value of its neighboring pixels is obtained sequentially. The edge pixels of the region with a difference less than the preset difference threshold are connected to obtain y regions to be adsorbed. The smaller the difference in gray value between adjacent pixels, the closer the adjacent pixels are to a plane, which makes it easier for the electric suction cup 22 to adsorb the plane later. The difference threshold is set according to the suction power of the electric suction cup 22. The greater the suction power, the larger the difference threshold can be set, and vice versa. The difference threshold should be set to ensure that the electric suction cup 22 can adsorb the region to be adsorbed.

[0092] Traverse the pixels of the area to be adsorbed, and draw a circle with the smallest adsorption radius of the electric suction cup 22 as the center of the traversed pixels. The minimum adsorption area is obtained. The minimum adsorption radius is the radius of the obstacle that the electric suction cup 22 can adsorb.

[0093] The region whose edge line of the minimum adsorption region lies within the region to be adsorbed is marked as the adsorption region;

[0094] The pixel corresponding to the smallest adsorption area within the adsorption area is taken as the center, and the pixel coordinates corresponding to the center are taken as adsorption coordinates. The robotic arm 20 aligns the center of the electric suction cup 22 with the adsorption coordinates, adsorbs the obstacle, and then moves it out of the preset route.

[0095] It should be noted that the robotic arm 20 is moved to the coordinate position according to the coordinate control, which is existing technology and will not be described in detail here;

[0096] If the edge of the smallest adsorption area is outside the area to be adsorbed, it means that no area can be found on the obstacle for the electric suction cup 22 to adsorb, and the adsorption action cannot be completed. In this case, the coordinates of any pixel on the obstacle are used as the pushing coordinates. Similarly, the robotic arm 20 pushes the electric suction cup 22 against the obstacle according to the pushing coordinates, pushing the obstacle out of the preset route so that the obstacle is no longer covered on the preset route, ensuring that the AGV of the collaborative robot can continue to move according to the preset route.

[0097] S60: The second control module 15 generates an obstacle state coefficient based on the obstacle surface information, compares the obstacle state coefficient with the state coefficient threshold, and determines whether to generate a second control command or a third control command.

[0098] It should be noted that, as Figure 3 As shown, the robotic arm 20 also includes an ultrasonic detector 23, which is also located at one end of the robotic arm 20. The obstacle surface information includes obstacle surface density, obstacle surface viscosity, and echo amplitude. Echo amplitude refers to the amplitude or vibration measured from the reflected sound wave when detecting the obstacle surface. The robotic arm 20 moves to the area where the obstacle is located according to the detection command and detects the surface of the obstacle through the ultrasonic detector 23 to obtain the obstacle surface density, obstacle surface viscosity, and echo amplitude. The specific formula for generating the obstacle state coefficient is as follows:

[0099] ;

[0100] in, For obstacle state coefficients, The surface density of the obstacle, The viscosity of the obstacle surface. Echo amplitude, This represents the number of ultrasonic tests performed. All are weighting coefficients, and All are greater than 0.

[0101] The specific logic for determining whether to generate a second or third control command is as follows:

[0102] If the obstacle state coefficient is less than the state coefficient threshold, a second control command is generated;

[0103] If the obstacle state coefficient is greater than or equal to the state coefficient threshold, a third control command is generated.

[0104] S70: Obstacle removal unit 30 removes obstacles on a preset route according to a second control command or a third control command;

[0105] Specifically, such as Figure 4 and Figure 5 As shown, the obstacle removal unit 30 includes a main housing 31, a drive motor 32, a receiving housing 33, an electric slide rail 34, a support member 35, and an adsorption member 36. The main housing 31 is fixedly connected to the bottom end of the trolley body 10. The drive motor 32 is fixedly installed inside the main housing 31. The output end of the drive motor 32 is fixedly connected to the receiving housing 33. The inner wall of the receiving housing 33 is provided with an electric slide rail 34. A support member 35 is provided on one side of the electric slide rail 34. The electric slide rail 34 drives the support member 35 to move up and down. Multiple adsorption members 36 are provided at the bottom end of the support member 35.

[0106] The second control command includes the extension command and the descent command;

[0107] The drive motor 32 moves the receiving box 33 according to the extension command until the receiving box 33 is completely moved out of the main box 31.

[0108] The electric slide rail 34 drives the support 35 to move downwards according to the descent command until the bottom end of the suction member 36 contacts the ground.

[0109] It is understandable that, such as Figure 11 , Figure 12 and Figure 13 As shown, in this embodiment, when the AGV of the collaborative robot identifies an obstacle on the preset route as a liquid and the liquid surface is not solidified, it sends a second control command to the obstacle removal unit 30. The drive motor 32 pushes the receiving box 33 to move through the output end until the receiving box 33 is completely moved out of the main box 31. Then the drive motor 32 stops working, the electric slide rail 34 drives the support member 35 to move downward, and the adsorption member 36 also moves downward with the support member 35 until the bottom end of the adsorption member 36 contacts the ground. Then the electric slide rail 34 stops working. When the AGV of the collaborative robot continues to walk and enters the area covered by the obstacle, the adsorption member 36 can remove the obstacle covering the preset route in advance, so that the AGV of the collaborative robot can continue to walk according to the preset route without being affected by the obstacle, and ensure that the AGV of the collaborative robot can carry out transportation work normally.

[0110] like Figure 5 , Figure 6 and Figure 7 As shown, the bottom end of the support member 35 is also provided with a plurality of liquid storage boxes 37, the liquid storage boxes 37 and the adsorption member 36 are spaced apart at the bottom end of the support member 35, and the bottom end of the liquid storage box 37 is provided with a plurality of heating nozzles 38.

[0111] The third control command includes the extension command, the descent command, and the heating command;

[0112] The drive motor 32 moves the receiving box 33 according to the extension command until the receiving box 33 is completely moved out of the main box 31.

[0113] The electric slide rail 34 drives the support 35 to move downwards according to the descent command until the bottom end of the suction member 36 contacts the ground.

[0114] Heated nozzle 38 sprays heated mist onto the surface of the obstacle according to the heating command.

[0115] Understandably, in this embodiment, when the AGV of the collaborative robot identifies an obstacle on the preset route as a liquid and the liquid surface is solidified, it sends a third control command to the obstacle removal unit 30. The drive motor 32 pushes the receiving box 33 to move through its output end until the receiving box 33 is completely moved out of the main box 31. Then, the drive motor 32 stops working, the electric slide rail 34 drives the support member 35 to move downward, and the suction member 36 also moves downward with the support member 35 until the bottom end of the suction member 36 contacts the ground. Then, the electric slide rail 34 stops working, and the heating nozzle 38 introduces the liquid inside the liquid storage box 37 into the interior, and... The body is heated, and then the heated liquid is sprayed onto the surface of the liquid. Since the sprayed liquid is a mist, it will release heat instantly when it reaches the solidified surface of the liquid. The surface of the liquid changes from a solidified state to a liquid state after being heated. When the collaborative robot's AGV continues to move and enters the area covered by obstacles, the heating nozzle 38 first changes the surface of the obstacle from a solidified state to a liquid state. In this way, the adsorption component 36 can more easily remove the obstacles covering the preset route, so that the collaborative robot's AGV can continue to move according to the preset route without being affected by obstacles, ensuring that the collaborative robot's AGV can carry out transportation work normally.

[0116] Example 2

[0117] This embodiment discloses a control method for an AGV (Automated Guided Vehicle) based on Embodiment 1, such as... Figure 14 As shown, the specific methods include:

[0118] Used to acquire images of obstacles along a preset route;

[0119] Preprocess the obstacle images;

[0120] The obstacle image is input into the matter state discrimination model, and the matter state category is output.

[0121] Based on the material state category, determine whether to generate the first control command or detection command;

[0122] According to the first control command, the obstacle on the preset route is moved out, or according to the detection command, the surface of the obstacle is ultrasonically detected to obtain the surface information of the obstacle;

[0123] Based on the obstacle surface information, an obstacle state coefficient is generated. The obstacle state coefficient is compared with the state coefficient threshold to determine whether to generate a second or third control command.

[0124] Remove obstacles on the preset route according to the second or third control command.

[0125] The above formulas are all dimensionless calculations. The formulas are derived from software simulations based on a large amount of collected data to obtain the most recent real-world results. The preset parameters, weights, and thresholds in the formulas are set by those skilled in the art according to the actual situation.

[0126] The above embodiments can be implemented, in whole or in part, by software, hardware, firmware, or any other combination thereof. When implemented using software, the above embodiments can be implemented, in whole or in part, as a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, all or part of the processes or functions described in the embodiments of the present invention are generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via a wired or wireless network. The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that includes one or more sets of available media. The available medium can be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium. A semiconductor medium can be a solid-state drive.

[0127] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed in this invention can be implemented in electronic hardware or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementations should not be considered beyond the scope of this invention.

[0128] Those skilled in the art will understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0129] In the several embodiments provided by this invention, it should be understood that the disclosed systems, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only one method, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between apparatuses or units may be electrical, mechanical, or other forms.

[0130] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment, depending on actual needs.

[0131] In addition, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0132] The above description is merely a specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the technical scope disclosed in the present invention should be included within the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be determined by the scope of the claims.

[0133] In conclusion, the above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

Claims

1. An AGV (Automated Guided Vehicle) for collaborative robots, characterized in that, The system includes a car body (10), a robotic arm (20) is provided on one side of the car body (10), an obstacle removal part (30) is provided at the bottom of the car body (10), and the car body (10) includes a camera module (11), an image processing module (12), a material state discrimination module (13), a first control module (14), and a second control module (15). The camera module (11) is used to acquire images of obstacles on a preset route; The image processing module (12) preprocesses the obstacle image; The material state discrimination module (13) inputs the obstacle image into the material state discrimination model and outputs the material state category; The first control module (14) determines and generates a first control command or a detection command based on the material state category; The robotic arm (20) removes obstacles on the preset route according to the first control command or performs ultrasonic detection on the surface of the obstacle according to the detection command to obtain the surface information of the obstacle; The second control module (15) generates obstacle state coefficients based on obstacle surface information, compares the obstacle state coefficients with the state coefficient threshold, and determines whether to generate a second control command or a third control command. The obstacle removal unit (30) removes obstacles on the preset route according to the second control command or the third control command.

2. The AGV (Automated Guided Vehicle) for collaborative robots according to claim 1, characterized in that, Preprocessing includes noise reduction, contrast enhancement, and image segmentation; the material state categories include solid and liquid states.

3. The AGV (Automated Guided Vehicle) for collaborative robots according to claim 2, characterized in that, The training process of the matter state discrimination model is as follows: acquire i sets of data, where i is a positive integer greater than 1. The data includes obstacle images and matter state categories. Use the obstacle images and matter state categories as sample sets. Divide the sample sets into training sets and test sets. Construct a classifier. Use the obstacle images in the training set as input data and the matter state categories in the training set as output data. Train the classifier to obtain an initial classifier. Test the initial classifier using the test set. Output a classifier that meets the preset accuracy as the matter state discrimination model.

4. The AGV (Automated Guided Vehicle) for collaborative robots according to claim 2, characterized in that, The logic for generating the first control command and detection command is as follows: If the state of matter is solid, then the first control command is generated; If the state of matter is liquid, a detection command is generated.

5. The AGV (Automated Guided Vehicle) for collaborative robots according to claim 1, characterized in that, The robotic arm (20) includes a robotic arm body (21), an electric suction cup (22) and an ultrasonic detector (23). One end of the robotic arm body (21) is equipped with an electric suction cup (22) and an ultrasonic detector (23). The robotic arm (20) moves to the area where the obstacle is located according to the detection command and obtains the surface information of the obstacle.

6. The AGV (Automated Guided Vehicle) for collaborative robots according to claim 5, characterized in that, Obstacle surface information includes obstacle surface density, obstacle surface viscosity, and echo amplitude. The obstacle state coefficient generation formula is: ； in, The obstacle state coefficient, The surface density of the obstacle, The viscosity of the obstacle surface. Echo amplitude, This represents the number of ultrasonic tests performed. All are weighting coefficients, and All are greater than 0.

7. The AGV (Automated Guided Vehicle) for collaborative robots according to claim 6, characterized in that, The logic for determining whether to generate a second or third control command is as follows: If the obstacle state coefficient is less than the state coefficient threshold, a second control command is generated; If the obstacle state coefficient is greater than or equal to the state coefficient threshold, a third control command is generated.

8. The AGV (Automated Guided Vehicle) for collaborative robots according to claim 1, characterized in that, The obstacle removal unit (30) includes a main box (31), a drive motor (32), a receiving box (33), an electric slide rail (34), a support member (35), and an adsorption member (36). The main box (31) is fixedly connected to the bottom end of the trolley body (10). The drive motor (32) is fixedly installed inside the main box (31). The output end of the drive motor (32) is fixedly connected to the receiving box (33). The inner wall of the receiving box (33) is provided with an electric slide rail (34). A support member (35) is provided on one side of the electric slide rail (34). The electric slide rail (34) drives the support member (35) to move up and down. Multiple adsorption members (36) are provided at the bottom end of the support member (35).

9. The AGV (Automated Guided Vehicle) for a collaborative robot according to claim 8, characterized in that, The second control command includes the extension command and the descent command; The drive motor (32) moves the receiving box (33) according to the extension command until the receiving box (33) is completely moved out of the main box (31); The electric slide rail (34) moves the support (35) downward according to the descent command until the bottom of the suction component (36) contacts the ground.

10. The AGV (Automated Guided Vehicle) for a collaborative robot according to claim 8, characterized in that, The bottom end of the support (35) is also provided with multiple liquid storage boxes (37), and the liquid storage boxes (37) and the adsorption components (36) are spaced apart at the bottom end of the support (35). The bottom end of the liquid storage boxes (37) is provided with multiple heating nozzles (38).

11. The AGV (Automated Guided Vehicle) for a collaborative robot according to claim 9, characterized in that, The third control command includes the extension command, the descent command, and the heating command; The drive motor (32) moves the receiving box (33) according to the extension command until the receiving box (33) is completely moved out of the main box (31); The electric slide rail (34) moves the support (35) downward according to the descent command until the bottom of the suction component (36) contacts the ground; Heating nozzle (38) sprays heated mist onto the surface of the obstacle according to the heating command.

12. The AGV (Automated Guided Vehicle) for collaborative robots according to claim 5, characterized in that, The robotic arm (20) removes obstacles using the following methods: The obstacle image acquired by the camera module (11) is mapped onto a pre-constructed three-dimensional coordinate system; The obstacle image acquired by the camera module (11) is processed in grayscale to obtain the grayscale value of each pixel in the obstacle image; The difference between the gray value of each pixel and the gray value of its neighboring pixels is obtained sequentially. The edge pixels of the regions with a difference less than a preset difference threshold are connected to obtain y regions to be snapped, where y is a positive integer greater than or equal to 1. Traverse the pixels in the area to be adsorbed, and draw a circle with the smallest adsorption radius of the electric suction cup (22) as the center of the traversed pixels. The smallest adsorption area is obtained. The smallest adsorption radius is the radius of the obstacle that the electric suction cup (22) can adsorb. The region whose edge line of the minimum adsorption region lies within the region to be adsorbed is marked as the adsorption region; The pixel corresponding to the smallest adsorption area within the adsorption area is taken as the center, and the pixel coordinates corresponding to the center are taken as adsorption coordinates. The robotic arm (20) aligns the center of the electric suction cup (22) with the adsorption coordinates, adsorbs the obstacle, and then moves it out of the preset route.

13. A control method for an AGV (Automated Guided Vehicle), implemented based on the AGV of a collaborative robot according to any one of claims 1-9, characterized in that: The method includes: Acquire images of obstacles along the preset route; Preprocess the obstacle images; The obstacle image is input into the matter state discrimination model, and the matter state category is output. Based on the material state category, determine whether to generate the first control command or detection command; According to the first control command, the obstacle on the preset route is moved out, or according to the detection command, the surface of the obstacle is ultrasonically detected to obtain the surface information of the obstacle; Based on the obstacle surface information, an obstacle state coefficient is generated. The obstacle state coefficient is compared with the state coefficient threshold to determine whether to generate a second or third control command. Remove obstacles on the preset route according to the second or third control command.

Images