An AGV system based on fixed surveillance camera collision avoidance

Abstract

The present invention relates to the field of drill bit detection technology, and specifically to an AGV system based on fixed surveillance camera collision avoidance, the system comprising: a number of AGV trolleys for transporting specific goods; a plurality of camera devices, which are respectively installed in specific areas in the warehouse and used to obtain images of the AGV trolleys to set the pixel coordinates of the AGV trolleys in the camera devices; and a processing module, which is used to assign transportation routes to the AGV trolleys and set collision thresholds according to the parameters of adjacent AGV trolleys. The purpose of the present invention is to provide an AGV system based on fixed surveillance camera collision avoidance, which solves the problems of high cost and multiple limitations of AGV trolley self-positioning through low-cost, high-precision fixed camera devices.

Description

Technical Field

[0001] The present invention relates to the technical field of warehouse management, and in particular to an AGV system based on fixed monitoring camera collision avoidance. Background Art

[0002] Warehousing is an important part of modern logistics and plays a vital role in the logistics system. Inventory is an important task in warehousing logistics. For a long time, manual inventory has been used to count goods. This traditional inventory method has the disadvantages of low efficiency, poor timeliness and high safety risks. With the rapid development of automation, in order to improve the efficiency of warehouse operations, an intelligent positioning and navigation device is needed to replace manual inventory. At present, in the field of positioning and navigation, the traditional positioning method based on inertial sensors and global positioning system (GPS) has been difficult to meet actual needs, because GPS has low positioning accuracy under weak indoor signal conditions, and inertial sensors have cumulative errors, and the positioning accuracy will decrease after working for a long time.

[0003] At present, the positioning and navigation of logistics warehousing are mainly based on magnetic stripe navigation technology, QR code navigation technology, pure visual navigation and pure laser navigation. In magnetic stripe navigation, the magnetic stripe is easy to break and needs regular maintenance. The magnetic stripe needs to be re-laid when the path changes. The automated guided vehicle (AGV) can only move along the magnetic stripe and cannot achieve intelligent avoidance or real-time task changes through the control system; in QR code navigation, the path needs regular maintenance. If the site is complex, the QR code needs to be replaced frequently. Strict requirements are placed on the accuracy and service life of the gyroscope. There are also certain requirements for the flatness of the site, and the price is relatively high; in visual navigation, the visual sensor cannot directly measure distance information. Even if binoculars are used, there is still a problem of low depth estimation accuracy, and it is difficult to model complex environments; in laser navigation, it is easily limited by the radar detection range, the installation structure requirements are high, and the production cost and price are relatively high.

[0004] Therefore, how to achieve accurate positioning of intelligent positioning and navigation equipment in complex environments is a technical problem that needs to be solved urgently. Summary of the invention

[0005] In order to overcome the shortcomings and deficiencies in the prior art, the purpose of the present invention is to provide an AGV system based on fixed surveillance camera collision avoidance, which solves the problems of high cost and multiple limitations of AGV vehicle's own positioning through a low-cost, high-precision fixed camera device.

[0006] The present invention is achieved through the following technical solutions:

[0007] In a first aspect, the present invention provides an AGV system based on fixed surveillance camera collision avoidance, comprising:

[0008] Several AGVs are used to transport specific goods;

[0009] A plurality of camera devices are installed in specific areas of the warehouse and are used to obtain images of the AGV to set the pixel coordinates of the AGV in the camera device;

[0010] and a processing module for allocating transport routes to AGVs and setting collision thresholds based on parameters of adjacent AGVs;

[0011] In a second aspect, the method for using the AGV system comprises the following steps:

[0012] S100 sets the camera layout function according to the size of the warehouse, calculates the position, quantity and placement angle of the camera;

[0013] S200. According to the camera device to obtain the current image of each AGV car in the warehouse, set the pixel coordinates of the AGV car in the camera device, and number each AGV car in the order of entry;

[0014] S300. The processing module calculates the actual coordinates of each AGV car in the warehouse, and cooperates with the camera device to update the actual coordinates of each AGV car in the warehouse according to a certain time period;

[0015] S400 sets the collision threshold of each AGV car. When the processing module determines that an adjacent AGV car is less than the collision threshold, the moving path of the AGV car is replanned;

[0016] Step S500: The processing module performs secondary numbering according to the power level of the AGV, sorts the charging order of the AGV according to the size of the secondary number, and divides them into two charging sets and a set to be charged according to the numbering order; at the same time, the processing module makes a judgment based on the distance between each AGV and the charging station. If the distance between the AGV and the nearest charging station in a unit time is greater than the threshold set by the processing module and is in the set to be charged, the secondary number of the AGV is swapped with the secondary number of the AGV with the smallest number in the charging set.

[0017] In combination with the second aspect, further, in step S100, the layout function of the camera device is expressed as:

[0018]

[0019]

[0020]

[0021] in, is the number of camera devices that should be arranged, are the length, width and height of the warehouse respectively. is the viewing angle of the camera device, is the number of cameras arranged along the length of the warehouse, is the average number of shelves in the length direction of the warehouse, is the number of cameras arranged along the length of the warehouse, It is the average number of shelves in the length direction of the warehouse.

[0022] In combination with the second aspect, further, in step S200, the processing module performs denoising on the AGV, and the denoising steps are as follows:

[0023] S201 collects the pixel coordinate position data of the AGV car within a certain period of time to form a data set;

[0024] S202. Select the pixel coordinates of the AGV car that are greater than a specific threshold within the time period;

[0025] S203. Smoothing the position data using a moving average method and performing a median filter on the position data;

[0026] S204. Combine the results of smoothing and median filtering.

[0027] In combination with the second aspect, further, in step S203, the mathematical formula for smoothing is expressed as:

[0028]

[0029]

[0030]

[0031]

[0032] in, , is the position data within time t, To smooth the result, is the window size of the moving average, is the window size of the median filter;

[0033] In step S204, the combined calculation formula is expressed as:

[0034] , .

[0035] In combination with the second aspect, further, in step S300, the pixel coordinates of the AGV are set to , then the actual coordinates of the AGV car The calculation method is:

[0036]

[0037] in, is the vertical distance to the ground, and is the focal length parameter of the camera device.

[0038] In combination with the second aspect, further, in step S400, the collision threshold of the AGV is set to:

[0039]

[0040] in, is the collision threshold of the AGV, is the minimum distance between the two devices. is the relative speed of the two AGVs, , are the accelerations of the two AGVs, It is the communication time between adjacent AGVs and processing modules.

[0041] The value of the charging number set is less than or equal to the value of the waiting-to-charge number set.

[0042] In a third aspect, the present invention provides a computer device, including a processor and a storage medium;

[0043] The storage medium is used to store instructions;

[0044] The processor is used to operate according to the instructions to execute the steps of any one of the above methods.

[0045] Beneficial effects of the present invention:

[0046] The AGV system based on fixed surveillance camera collision avoidance of the present invention is based on multiple camera devices fixed in the warehouse, uses visual technology to achieve real-time positioning of the AGV car, and delivers relevant commands to the car according to the position of the car. It can reduce costs and facilitate maintenance, effectively improve the efficiency of the system, and solve the problems of high cost and multiple limitations of the AGV car's own positioning. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] The present invention is further described using the accompanying drawings, but the embodiments in the accompanying drawings do not constitute any limitation to the present invention. A person skilled in the art can obtain other drawings based on the following drawings without creative work.

[0048] Figure 1 The flowchart of the selection method of the present invention is shown in FIG. DETAILED DESCRIPTION

[0049] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the specific embodiments of the present invention are described in detail below in conjunction with the accompanying drawings. In the following description, many specific details are set forth to facilitate a full understanding of the present invention. However, the present invention can be implemented in many other ways different from those described herein, and those skilled in the art can make similar improvements without violating the connotation of the present invention, so the present invention is not limited by the specific embodiments disclosed below.

[0050] At present, the positioning and navigation of logistics warehousing are mainly based on magnetic stripe navigation technology, QR code navigation technology, pure visual navigation and pure laser navigation. In magnetic stripe navigation, the magnetic stripe is easy to break and needs regular maintenance. The magnetic stripe needs to be re-laid when the path changes. The automated guided vehicle (AGV) can only move along the magnetic stripe and cannot achieve intelligent avoidance or real-time task changes through the control system; in QR code navigation, the path needs regular maintenance. If the site is complex, the QR code needs to be replaced frequently. Strict requirements are placed on the accuracy and service life of the gyroscope. There are also certain requirements for the flatness of the site, and the price is relatively high; in visual navigation, the visual sensor cannot directly measure distance information. Even if binoculars are used, there is still a problem of low depth estimation accuracy, and it is difficult to model complex environments; in laser navigation, it is easily limited by the radar detection range, the installation structure requirements are high, and the production cost and price are relatively high.

[0051] Therefore, how to achieve accurate positioning of intelligent positioning and navigation equipment in complex environments is a technical problem that needs to be solved urgently.

[0052] Example 1

[0053] In order to solve the above problems, this embodiment provides an AGV system based on fixed surveillance camera collision avoidance, which includes:

[0054] Several AGVs are used to transport specific goods;

[0055] A plurality of camera devices are installed in specific areas of the warehouse and are used to obtain images of the AGV to set the pixel coordinates of the AGV in the camera device;

[0056] and a processing module for allocating transport routes to AGVs and setting collision thresholds according to parameters of adjacent AGVs.

[0057] It should be noted that, in this embodiment, the camera device is preferably a high-definition camera, and the processing module is preferably a computer.

[0058] In addition, this embodiment also provides a collision avoidance method based on a fixed surveillance camera, which includes the following steps:

[0059] S100 sets the camera layout function according to the size of the warehouse, calculates the position, quantity and placement angle of the camera;

[0060] S200. According to the camera device to obtain the current image of each AGV car in the warehouse, set the pixel coordinates of the AGV car in the camera device, and number each AGV car in the order of entry;

[0061] S300. The processing module calculates the actual coordinates of each AGV car in the warehouse, and cooperates with the camera device to update the actual coordinates of each AGV car in the warehouse according to a certain time period;

[0062] S400. Set a collision threshold for each AGV. When the processing module determines that an adjacent AGV is smaller than the collision threshold, re-plan the moving path of the AGV.

[0063] Step S500: The processing module performs secondary numbering according to the power level of the AGV, sorts the charging order of the AGV according to the size of the secondary number, and divides them into two charging sets and a set to be charged according to the numbering order; at the same time, the processing module makes a judgment based on the distance between each AGV and the charging station. If the distance between the AGV and the nearest charging station in a unit time is greater than the threshold set by the processing module and is in the set to be charged, the secondary number of the AGV is swapped with the secondary number of the AGV with the smallest number in the charging set.

[0064] In this embodiment, the charging number set and the to-be-charged number set are both positive integer sets, and the value of the charging number set is less than or equal to the value of the to-be-charged number set to ensure that the number of vehicles in operation is not too low. After the processing module sends the command to the AGV vehicle in the charging number set, it will re-execute step S500 to ensure the smooth operation of the system.

[0065] In order to more clearly illustrate the method for selecting samples for random inspection of the present invention, the following is combined with Figure 1 Each step in the embodiment of the present invention is described in detail.

[0066] Furthermore, in step S100, the layout function of the camera device is expressed as:

[0067]

[0068]

[0069]

[0070] in, is the number of camera devices that should be arranged, are the length, width and height of the warehouse respectively. is the viewing angle of the camera device, is the number of cameras arranged along the length of the warehouse, is the average number of shelves in the length direction of the warehouse, is the number of cameras arranged along the length of the warehouse, It is the average number of shelves in the length direction of the warehouse.

[0071] This arrangement of camera devices ensures that every area in the warehouse can be covered by at least one camera, thereby achieving all-round monitoring of the AGV.

[0072] Furthermore, in step S200, the processing module performs denoising on the AGV, and the denoising steps are as follows:

[0073] S201 collects the pixel coordinate position data of the AGV car within a certain period of time to form a data set;

[0074] S202. Select the pixel coordinates of the AGV car that are greater than a specific threshold within the time period;

[0075] S203. Smoothing the position data using a moving average method and performing a median filter on the position data;

[0076] S204. Combine the results of smoothing and median filtering.

[0077] Furthermore, in step S203, the mathematical formula for smoothing is expressed as:

[0078]

[0079]

[0080]

[0081]

[0082] in, , is the position data within time t, To smooth the result, is the window size of the moving average, is the window size of the median filter;

[0083] In step S204, the combined calculation formula is expressed as:

[0084] , .

[0085] Further, in step S300, the pixel coordinates of the AGV are set to , then the actual coordinates of the AGV car The calculation method is:

[0086]

[0087] in, is the vertical distance to the ground, and is the focal length parameter of the camera device.

[0088] Furthermore, in step S400, the collision threshold of the AGV is set to:

[0089]

[0090] in, is the collision threshold of the AGV, is the minimum distance between the two devices. is the relative speed of the two AGVs, , are the accelerations of the two AGVs, It is the communication time between adjacent AGVs and processing modules.

[0091] In this embodiment, It is set according to the volume of the AGV, generally between 0.5 and 1 meter. The calculation method ensures that the collision threshold increases with the increase of acceleration. In this way, even when the AGV accelerates rapidly, there is enough time and space to avoid collision.

[0092] Example 2

[0093] This embodiment provides a computer device, including a processor and a storage medium;

[0094] The storage medium is used to store instructions;

[0095] The processor is used to operate according to the instructions to execute the steps of any method described in Example 1.

[0096] Example 3

[0097] An embodiment of the present invention further provides a computer-readable storage medium on which a computer program is stored. When the program is executed by a processor, the steps of the method described in Embodiment 1 are implemented.

[0098] In summary, the AGV system based on fixed surveillance camera collision avoidance in this embodiment is based on multiple camera devices fixed in the warehouse, uses visual technology to achieve real-time positioning of the AGV car, and delivers relevant commands to the car according to the position of the car. It can reduce costs and facilitate maintenance, effectively improve the efficiency of the system, and solve the problems of high cost and multiple limitations of the AGV car's own positioning.

[0099] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present application may adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program codes.

[0100] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0101] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0102] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0103] Finally, it should be noted that the above embodiments are only used to illustrate the technical solution of the present invention, rather than to limit the scope of protection of the present invention. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solution of the present invention can be modified or replaced by equivalents without departing from the essence and scope of the technical solution of the present invention.

Claims

1. An AGV system based on fixed surveillance camera collision avoidance, characterized in that: include: Several AGV carts for transporting goods; A plurality of camera devices are installed in areas within the warehouse and are used to obtain images of the AGV to set the pixel coordinates of the AGV in the camera devices; and a processing module for allocating transport routes to AGVs and setting collision thresholds based on parameters of adjacent AGVs; The method for using the AGV system comprises the following steps: S100. Set the camera layout function according to the size of the warehouse, and calculate the position, quantity and placement angle of the camera; S200. Obtain the image of each AGV car in the warehouse according to the camera device, set the pixel coordinates of the AGV car in the camera device, and number each AGV car according to the order of entry; S300. The processing module calculates the actual coordinates of each AGV in the warehouse, and cooperates with the camera device to update the actual coordinates of each AGV in the warehouse according to a certain time period; S400. Set the collision threshold of each AGV. When the processing module determines that an adjacent AGV is smaller than the collision threshold, re-plan the moving path of the AGV; In step S100, the layout function of the camera device is expressed as: Where f(L, W, H, θ) is the number of cameras that should be deployed, L, W, H are the length, width and height of the warehouse respectively, θ is the viewing angle of the camera, f(L) is the number of cameras deployed along the length of the warehouse, and h L is the average number of shelves in the length direction of the warehouse, f(W) is the number of cameras arranged along the width of the warehouse, and h w It is the average number of shelves in the width direction of the warehouse.

2. The AGV system based on fixed surveillance camera collision avoidance according to claim 1, characterized in that: In step S200, the processing module performs denoising on the AGV, and the denoising steps are as follows: S201. Collect the pixel coordinate position data of the AGV car within a certain period of time to form a data set; S202. Select the pixel coordinates of the AGV car that are greater than the threshold value within the time period; S203. Smoothing the position data using a moving average method and performing a median filter on the position data; S204. Combine the results of smoothing and median filtering.

3. The AGV system based on fixed surveillance camera collision avoidance according to claim 1, characterized in that: In step S300, the pixel coordinates of the AGV are set to (x p ,y p ), then the actual coordinates (x, y) of the AGV are calculated as follows: Where D is the vertical distance to the ground, f x and f y is the focal length parameter of the camera device.

4. The AGV system based on fixed surveillance camera collision avoidance according to claim 1, characterized in that: In step S400, the collision threshold of the AGV is set to: Among them, V is the collision threshold of the AGV, d0 is the set minimum separation distance, v1-v2 is the relative speed of the two AGVs, a1 and a2 are the accelerations of the two AGVs respectively, and t is the communication time between adjacent AGVs and the processing module.

5. The AGV system based on fixed surveillance camera collision avoidance according to claim 1, characterized in that: It also includes step S500: the processing module performs secondary numbering according to the power level of the AGV, sorts the charging order of the AGV according to the size of the secondary number, and divides them into two charging sets and a set to be charged according to the numbering order. At the same time, the processing module makes a judgment based on the distance between each AGV and the charging station. If the distance between the AGV and the nearest charging station in unit time is greater than the threshold set by the processing module and is in the set to be charged, the secondary number of the AGV is swapped with the secondary number of the smallest AGV in the charging set.

6. The AGV system based on fixed surveillance camera collision avoidance according to claim 5, characterized in that: The value of the charging number set is less than or equal to the value of the waiting-to-charge number set.

Images