A navigation server, AGV, navigation system and method
Through the navigation method combining AGV's own visual encoding identification and factory obstacle status information, navigation parameters are planned in real time, which solves the problem of obstacle collision in AGV navigation, improves navigation safety and reliability, and reduces hardware costs.
Patent Information
- Application Number
- CN201911218893.6
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2019-11-29
- Publication Date
- 2024-11-15
- Estimated Expiration
- 2039-11-29
AI Technical Summary
Existing AGV navigation technology is difficult to achieve safe and reliable navigation, especially in complex factory environments to avoid obstacle collisions.
Real-time location is determined through visual encoding recognition carried by the AGV itself, and navigation parameters are planned in real time in combination with obstacle status information in the factory area, and AGV walks to avoid obstacle collisions.
It improves the security and reliability during AGV navigation, reduces hardware costs, and enhances the real-time and accuracy of the navigation system.
Smart Images

Figure CN112987710B_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of AGV navigation technology, and in particular to a navigation server, AGV, navigation system and method. Background Art
[0002] AGV (Automated Guided Vehicle) is an automatic guided device that can travel along a specified guide path and has safety protection and various transfer functions.
[0003] At present, many companies are developing various AGVs for different fields. In this process, how to achieve safe and reliable navigation of AGV is a key technology that people generally pay attention to, and it is also a technical problem that people urgently need to overcome. Summary of the invention
[0004] In view of this, the purpose of the present invention is to provide a navigation server, AGV, navigation system and method, which can safely and reliably navigate the AGV. The specific scheme is as follows:
[0005] In a first aspect, the present invention discloses an AGV navigation method, which is applied to a navigation server and includes:
[0006] When a new task is obtained, a target AGV for executing the new task is determined;
[0007] Obtaining the current real-time position of the target AGV determined by identifying the visual code carried by the target AGV itself;
[0008] Get the status information of obstacles in the current factory area;
[0009] According to the current real-time position of the target AGV, the status information of obstacles in the current factory area, and the start and end positions corresponding to the new task, the navigation parameters are planned for the target AGV in real time;
[0010] The target AGV is controlled to move according to the real-time planned navigation parameters.
[0011] It can be seen that this solution determines the current real-time position of the AGV by identifying the visual code carried by the AGV itself; in addition, before planning the navigation parameters for the AGV, it is also necessary to obtain the status information of the obstacles in the current factory area; then, combined with the current real-time position of the AGV, the status information of the obstacles in the current factory area, and the start and end positions corresponding to the new task assigned to the AGV, the corresponding navigation parameters are planned in real time, and then the AGV is controlled according to the real-time planned navigation parameters, thereby realizing the navigation of the AGV, and effectively avoiding collisions with obstacles during the navigation process, thereby improving the safety and reliability of the navigation process.
[0012] Optionally, the visual code includes a one-dimensional barcode or a two-dimensional barcode.
[0013] In this solution, the visual code carried by the AGV itself can be a one-dimensional barcode or a two-dimensional barcode. By identifying the one-dimensional barcode or the two-dimensional barcode carried by the AGV itself, the current real-time position of the AGV can be determined.
[0014] Optionally, determining a target AGV for executing the new task includes:
[0015] According to the current real-time position of each AGV, the task load of each AGV to be executed and the starting position of the new task, a target AGV for executing the new task is determined from all AGVs.
[0016] In this solution, the AGV used to execute the new task is determined based on the current real-time position of each AGV, the task load of the task to be executed by each AGV, and the starting position of the new task, thereby avoiding the AGV that is too heavy in the current task or is far away from the starting position of the new task from executing the new task.
[0017] Optionally, the obtaining of the current real-time position of the target AGV determined by identifying a visual code carried by the current target AGV itself includes:
[0018] Obtaining a coded image obtained by capturing the visual code carried by the current target AGV by a camera;
[0019] Performing information recognition processing on the coded image to obtain specific coded content, coded shape and size, and position of the visual code in the coded image;
[0020] According to the specific coding content, coding shape and size of the visual coding and the position in the coding image, the position of the visual coding carried by the current target AGV itself in the factory is determined to obtain the current real-time position of the target AGV.
[0021] In this scheme, when identifying the visual code carried by the target AGV itself, not only the specific coding content of the visual code is identified, but also the coding shape and size of the visual code and the position of the visual code in the coding image are identified. Then, based on the above-mentioned three types of information identified, the current real-time position of the target AGV can be determined.
[0022] Optionally, the process of controlling the target AGV to walk according to the real-time planned navigation parameters further includes:
[0023] The speed information of the target AGV is determined by using the multiple frames of the coded images of the visual code collected by the camera at different times.
[0024] In this solution, the speed information of the AGV can be determined by using multiple frames of coded images collected at different times, without having to install a speed sensor on each AGV, thereby saving a lot of hardware costs.
[0025] Optionally, the obtaining of status information of obstacles in the current factory area includes:
[0026] Obtain the factory area image obtained after the camera collects images of the current factory area;
[0027] Using the factory area image, identifying the current real-time position and speed information of obstacles in the current factory area;
[0028] The obstacles include other AGVs, human bodies, and other types of obstacles.
[0029] In this solution, by using the factory images captured by the camera, the current real-time position and speed information of other AGVs, human bodies or other types of obstacles in the current factory area can be identified. By taking into account the various status information of the above obstacles in the subsequent navigation parameter planning process, the target AGV can effectively avoid encountering obstacles during its movement.
[0030] Optionally, the real-time planning of navigation parameters for the target AGV according to the current real-time position of the target AGV, the state information of obstacles in the current factory area, and the start and end positions corresponding to the new task includes:
[0031] According to the status information of the obstacles in the current factory area, predict the movement trend of the obstacles;
[0032] According to the current real-time position of the target AGV, the start and end positions corresponding to the new task, and the movement trend of the obstacle, and based on the parameter planning principle of avoiding collision, the navigation parameters are planned in real time for the target AGV;
[0033] The navigation parameters include navigation speed and / or navigation path.
[0034] In this solution, the movement trend of obstacles is predicted by using the status information of obstacles in the current factory area, and then the navigation parameters are planned according to the movement trend of the obstacles, the current real-time position of the target AGV and the start and end positions corresponding to the new task.
[0035] In a second aspect, the present invention discloses a navigation server, comprising a processor and a memory; wherein the processor implements the following steps when executing a computer program stored in the memory:
[0036] When a new task is obtained, a target AGV for executing the new task is determined;
[0037] Obtaining the current real-time position of the target AGV determined by identifying the visual code carried by the target AGV itself;
[0038] Get the status information of obstacles in the current factory area;
[0039] According to the current real-time position of the target AGV, the status information of obstacles in the current factory area, and the start and end positions corresponding to the new task, the navigation parameters are planned for the target AGV in real time;
[0040] The target AGV is controlled to move according to the real-time planned navigation parameters.
[0041] This solution discloses a navigation server, which has the same technical effect as the aforementioned disclosed AGV navigation method.
[0042] In a third aspect, the present invention discloses an AGV, wherein the AGV is provided with a visual code, and further comprises:
[0043] A command receiving device for acquiring a walking control command sent by the aforementioned navigation server;
[0044] A walking component is used to respond to the walking control command.
[0045] This solution discloses an AGV that can obtain and execute the walking control command sent by the aforementioned navigation server, and has the same technical effect as the aforementioned AGV navigation method.
[0046] In a fourth aspect, the present invention discloses an AGV navigation system, comprising:
[0047] The aforementioned navigation server disclosed;
[0048] The aforementioned disclosed AGV;
[0049] A camera connected to the navigation server.
[0050] This solution discloses an AGV navigation system, which has the same technical effect as the aforementioned disclosed AGV navigation method.
[0051] Optionally, the AGV navigation system includes a plurality of cameras located at different locations in the factory.
[0052] In this solution, multiple cameras are installed at different locations in the factory, which can effectively reduce the probability of failing to capture images and identify information for the visual codes on the AGV, and improve the reliability of the entire system. BRIEF DESCRIPTION OF THE DRAWINGS
[0053] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying creative work.
[0054] Figure 1 A flow chart of an AGV navigation method disclosed in an embodiment of the present invention;
[0055] Figure 2 This is a schematic diagram of the interior of an AGV plant area disclosed in an embodiment of the present invention;
[0056] Figure 3 A specific AGV navigation method flow chart disclosed in an embodiment of the present invention;
[0057] Figure 4 A schematic diagram of the structure of a navigation server disclosed in an embodiment of the present invention;
[0058] Figure 5 A schematic diagram of an AGV structure disclosed in an embodiment of the present invention;
[0059] Figure 6 The present invention discloses an AGV navigation system structure diagram. DETAILED DESCRIPTION
[0060] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.
[0061] The embodiment of the present invention discloses an AGV navigation method, which is applied to a navigation server, see Figure 1 As shown, the method includes:
[0062] Step S11: When a new task is acquired, a target AGV for executing the new task is determined.
[0063] In this embodiment, the target AGV for executing the above-mentioned new task can be determined by manual confirmation, that is, this embodiment can provide the user with an AGV selection interface in advance, through which the information of the AGV selected by the user for executing the new task can be obtained. Considering that the manual determination method is inefficient and difficult to adapt to occasions where a large number of AGVs are used, this embodiment can also allow the background system to automatically assign the corresponding AGV to the new task according to the specifics of the new task and the current status of each AGV itself.
[0064] It should be noted that the navigation server in this embodiment can be an ordinary physical server or a cloud server. In addition, when the navigation server obtains multiple different new tasks, it can first assign different priorities to the above multiple different new tasks according to the urgency of the tasks, and then assign corresponding AGVs to different new tasks in order of priority. In addition, the number of new tasks assigned to each AGV can be one or more, which is not specifically limited here.
[0065] Step S12: obtaining the current real-time position of the target AGV determined by identifying the visual code carried by the target AGV itself.
[0066] In this embodiment, each AGV is provided with a visual code corresponding to itself, that is, different AGVs correspond to different visual codes, wherein the visual code here refers to the code obtained by encoding information using visual elements that can be detected by image sensors such as cameras, and the above visual elements may include but are not limited to color, text, brightness, and lines. Specifically, the visual code in this embodiment can be a one-dimensional barcode, or a two-dimensional barcode, or of course, a color block of various shapes. For example, in Figure 2In the embodiment, the visual code carried by the AGV is a one-dimensional barcode. In addition to the AGV, there may be people or other types of obstacles in the factory area. In addition, in order to improve the recognition success rate and accuracy of the visual code and avoid the situation where the recognition cannot be made due to the possible blind spot when only one camera is set, multiple cameras can be set at different locations in the factory area. Each camera can simultaneously recognize the visual codes on multiple AGVs moving in the factory area, thereby improving the recognition success rate of the visual code on the AGV. In addition, the specific code content carried by the visual code of any AGV in this embodiment can be the identity feature information of the AGV, such as the equipment identification number of the AGV.
[0067] In the above step S12, the specific process can be: determine the current position of the target AGV, obtain corresponding position information, and identify the visual code on the target AGV to determine the identity feature information of the target AGV, thereby determining that the above-mentioned position information belongs to the position information of the target AGV, that is, obtaining the current real-time position of the target AGV.
[0068] It should be noted that any AGV in this embodiment may have only one visual code, and in order to improve the recognition success rate of the visual code on the AGV, this embodiment may also have multiple visual codes on one AGV, and each of the multiple visual codes is located on a different side of the AGV. It is understandable that when multiple visual codes are provided on an AGV, each of the multiple visual codes uniquely corresponds to the AGV.
[0069] Step S13: Obtain status information of obstacles in the current factory area.
[0070] In this embodiment, the state information of obstacles in the current AGV factory area can be obtained by manual input, that is, this embodiment can provide the user with a state information input interface in advance, through which the obstacle position marked by the user on the factory electronic map and the input related information such as obstacle moving direction, moving speed, etc. can be obtained. Of course, in order to improve the efficiency of information acquisition and the accuracy of information, this embodiment can also use machine vision technology to identify objects in the current factory area that are relative to the target AGV and hinder the progress of the target AGV, so as to determine the real-time position, speed, moving direction and other state information of these obstacles.
[0071] It is understandable that in this embodiment, steps S12 and S13 have no clear sequence in actual execution.
[0072] Step S14: planning navigation parameters for the target AGV in real time according to the current real-time position of the target AGV, the status information of obstacles in the current factory area, and the start and end positions corresponding to the new task.
[0073] In this embodiment, navigation parameters are planned for the target AGV based on the current real-time position of the target AGV and the starting and ending positions of the new task, combined with the status information of obstacles in the current factory area. This not only allows the target AGV to move from the current real-time position to the starting position corresponding to the new task, and then move from the starting position corresponding to the new task to the end position corresponding to the new task, but also ensures that the target AGV will not collide with other AGVs, human bodies and other obstacles during the entire process of executing the new task, thereby ensuring the safety of travel.
[0074] Step S15: Control the target AGV to move according to the real-time planned navigation parameters.
[0075] In this embodiment, a corresponding travel control instruction can be generated according to the real-time planned navigation parameters, and the travel control instruction can be sent to the target AGV to control the movement of the target AGV using the instruction, thereby achieving safe navigation of the target AGV.
[0076] It can be seen that the embodiment of the present invention determines the current real-time position of the AGV by identifying the visual code carried by the AGV itself; in addition, before planning the navigation parameters for the AGV, it is also necessary to obtain the status information of the obstacles in the current factory area; then, in combination with the current real-time position of the AGV, the status information of the obstacles in the current factory area, and the start and end positions corresponding to the new task assigned to the AGV, the corresponding navigation parameters are planned in real time, and then the AGV is controlled according to the above navigation parameters, thereby realizing the navigation of the AGV, and effectively avoiding collision with obstacles during the navigation process, thereby improving the safety and reliability of the navigation process.
[0077] Based on the above embodiments, the present invention discloses a specific AGV navigation method, which is applied to a navigation server. Figure 3 As shown, the method includes:
[0078] Step S21: When a new task is acquired, a target AGV for executing the new task is determined from all AGVs according to the current real-time position of each AGV, the task load of each AGV to execute the task, and the starting position of the new task.
[0079] Specifically, after acquiring a new task, this embodiment can determine the target AGV for executing the new task from all AGVs based on the distance between each AGV and the starting position of the new task and the task load of each AGV's current task to be executed. It can be understood that if the distance between an AGV and the starting position of the new task is smaller, it is more likely to be selected as the target AGV, and if the task load of an AGV's current task to be executed is smaller, it is more likely to be selected as the target AGV.
[0080] In a specific implementation, the distance between each current AGV and the starting position of the new task can be set as the main factor for determining the target AGV, and the task load of the task to be performed by each current AGV can be set as the secondary factor for determining the target AGV, that is, the weight of the influence of the distance on the determination result of the target AGV is set to a larger value, and the weight of the influence of the task load of the task to be performed on the determination result of the target AGV is set to a smaller value. For example, the AGV with the smallest task load of the task to be performed can be selected from multiple AGVs that are currently close to the starting position of the new task as the target AGV.
[0081] In another specific implementation, the task load of the task to be performed by each AGV can be set as the main factor for determining the target AGV, and the distance between each AGV and the starting position of the new task can be set as the secondary factor for determining the target AGV, that is, the weight of the impact of the task load of the task to be performed on the determination result of the target AGV is set to a larger value, and the weight of the impact of the distance size on the determination result of the target AGV is set to a smaller value. For example, the AGV that is currently closest to the starting position of the new task can be selected from multiple AGVs with relatively small task loads to be performed as the target AGV.
[0082] Step S22: obtaining a coded image obtained by capturing the visual code carried by the current target AGV through a camera.
[0083] In this embodiment, in order to improve the recognition success rate and recognition accuracy of the visual code and avoid the situation where no recognition can be made due to possible blind spots in the field of vision when only one camera is installed, multiple cameras can be preferably installed at different locations in the factory. Each camera can simultaneously identify the visual codes on multiple AGVs moving in the factory to determine the identity information of each AGV.
[0084] Step S23: performing information recognition processing on the coded image to obtain the specific coding content, coding shape and size of the visual code and the position in the coded image.
[0085] Step S24: According to the specific coding content, coding shape and size of the visual coding and the position in the coding image, the position of the visual coding carried by the current target AGV itself in the factory is determined to obtain the current real-time position of the target AGV.
[0086] In this embodiment, the specific coding content of the above-identified visual coding reflects the identity information of the target AGV, the shape and size of the coding can reflect the posture information of the target AGV and the distance information of the target AGV from the camera, and the position of the visual coding in the coded image can reflect the direction information of the target AGV relative to the camera. Based on the identity information, posture information, distance information from the camera, and direction information relative to the camera of the above-mentioned target AGV, this embodiment can determine the real-time location information of the target AGV in the factory area, with high positioning accuracy.
[0087] It is understandable that the information obtained after information recognition processing of the coded image collected by any camera can determine the position of the visual code carried by the current target AGV itself in the factory area. In order to further improve the positioning accuracy, this embodiment can also obtain multiple sets of current real-time positions of the target AGV based on multiple coded images corresponding to the target AGV collected by multiple cameras, and then fuse the above multiple sets of current real-time positions to eliminate possible errors, so as to finally determine a real-time position information with higher accuracy.
[0088] Furthermore, in the subsequent process of the controlled movement of the target AGV, in order to determine the speed information of the target AGV at a low cost, the present embodiment can use the camera to collect multiple frames of coded images of the visual code on the target AGV at different times, and then determine the speed information such as the speed size and direction of the target AGV according to the position information of the target AGV corresponding to each of the above-mentioned multiple frames of coded images and the corresponding time interval. Of course, without considering the hardware cost, the present embodiment can also pre-install a speed sensor on the target AGV, and then directly obtain the speed information sent by the target AGV and collected by the speed sensor, so as to achieve the purpose of determining the speed information of the target AGV.
[0089] Step S25: obtaining a factory area image obtained by a camera after collecting images of the current factory area; using the factory area image, identifying the current real-time position and speed information of obstacles in the current factory area;
[0090] The obstacles include other AGVs, human bodies, and other types of obstacles.
[0091] In a specific implementation, after acquiring the factory image captured by the camera, the present embodiment can first identify the current real-time position and speed information of all objects in the factory image, and then remove the state information corresponding to the current real-time position of the target AGV from the state information of all objects identified, thereby obtaining the state information of all obstacles in the current factory that hinder the forward direction of the target AGV, such as other AGVs, human bodies or other types of obstacles. Among them, the process of identifying the state information of all objects in the factory can specifically include: comparing the real-time acquired factory image with the pre-collected factory background image to obtain a corresponding comparison result, and then determining the current real-time position of all objects in the factory based on the above comparison result, and then using the object position information and corresponding time intervals corresponding to each of the multiple frames of factory images collected at different times to determine the speed information of all objects in the factory, thereby obtaining the state information of all objects in the factory. It can be understood that the above factory background image refers to the background image obtained after the camera is used to collect images of the factory when there is no AGV placed in the AGV factory.
[0092] In another specific implementation, after acquiring the factory image captured by the camera, the image area corresponding to the target AGV in the factory image is first identified, and then the status information of objects in the remaining areas of the factory image except the above-mentioned image area is identified, thereby obtaining the status information of all obstacles in the current factory that hinder the forward direction of the target AGV.
[0093] Step S26: predicting the movement trend of the obstacle according to the status information of the obstacle in the current factory area.
[0094] That is, this embodiment can also predict the movement trend of the obstacle by using the current real-time position and speed information of the obstacle obtained in step S25, thereby obtaining the corresponding obstacle movement trend prediction result. Specifically, this embodiment can infer the current acceleration of the obstacle based on the current movement speed and movement direction of the obstacle, and then infer the movement trend of the obstacle by combining the current real-time position, movement speed, movement direction and acceleration of the obstacle, including but not limited to the position, movement direction and movement trajectory reached by the obstacle at the next moment.
[0095] Step S27: According to the current real-time position of the target AGV, the start and end positions corresponding to the new task, and the movement trend of the obstacle, and based on the parameter planning principle of avoiding collision, the navigation parameters are planned in real time for the target AGV.
[0096] In this embodiment, the navigation parameters planned in real time for the target AGV may specifically include a navigation speed and / or a navigation path.
[0097] In a specific implementation, based on the navigation path planning principle of avoiding collision, a navigation path that will not intersect with the movement trajectory of obstacles in the current factory environment can be planned in real time for the target AGV.
[0098] In another specific implementation, based on the navigation speed planning principle of avoiding collisions, real-time planning can be performed on a navigation speed that will enable the target AGV to not collide with other obstacles in the next time period. After multiple navigation speed plannings, multiple sets of navigation speeds in multiple time periods can be obtained. According to the above multiple sets of navigation speeds, the target AGV can be controlled to first move to the starting position of the new task, and then move from the starting position of the new task to the end position of the new task, thereby successfully and safely completing the new task.
[0099] In another specific implementation, based on the planning principle of navigation speed and navigation path to avoid collision, a navigation path with a shorter path distance can be planned for the target AGV. Considering that this navigation path may intersect or overlap with the travel trajectories of other obstacles, this embodiment, on the basis of planning the above navigation path, further plans the navigation speed for the target AGV when traveling along the above navigation path. By adjusting the real-time navigation speed of the target AGV, the target AGV and the obstacle will not pass through the above-mentioned intersection or overlap location area at the same time, thereby avoiding collision between the target AGV and the obstacle and successfully completing the above-mentioned new task.
[0100] Step S28: Controlling the target AGV to move according to the real-time planned navigation parameters.
[0101] In addition, according to the aforementioned disclosed content, in the process of controlling the walking of the target AGV according to the navigation parameters planned in real time, it can further include: using the multiple frames of the coded images of the visual code collected by the camera at different times to determine the speed information of the target AGV. By acquiring the speed information of the current target AGV in real time, the background system can know whether the speed information of the current target AGV is consistent with the pre-planned navigation speed. It is understandable that if the speed information of the target AGV acquired in real time is inconsistent with the pre-planned navigation speed, the navigation speed at the next moment can be adjusted accordingly based on the difference between the two.
[0102] Correspondingly, the embodiment of the present invention also discloses a navigation server, see Figure 4 As shown, the navigation server includes a processor 11 and a memory 12; wherein the processor 11 implements the following steps when executing the computer program stored in the memory 12:
[0103] When a new task is acquired, a target AGV for executing the new task is determined; the current real-time position of the target AGV is determined by identifying the visual code carried by the target AGV itself; the status information of obstacles in the current factory area is acquired; according to the current real-time position of the target AGV, the status information of obstacles in the current factory area and the start and end positions corresponding to the new task, navigation parameters are planned for the target AGV in real time; and the target AGV is controlled to move according to the real-time planned navigation parameters.
[0104] For more specific execution processes of the above steps, please refer to the corresponding contents disclosed in the aforementioned embodiments, which will not be repeated here.
[0105] Furthermore, the present invention also discloses an AGV, see Figure 5 As shown, the AGV is provided with a visual code 21, and further includes:
[0106] A command receiving device 22 for acquiring the walking control command sent by the navigation server disclosed in the above embodiment;
[0107] A walking component 23 is used to respond to the walking control command.
[0108] It can be understood that, in this embodiment, the walking control command sent by the navigation server is a corresponding control command generated according to the navigation parameters of real-time planning. The navigation server sends the walking control command generated according to the navigation parameters to the command receiving device on the AGV, and the walking components on the AGV drive the AGV to walk under the control of the above-mentioned walking control command. In addition, the transmission of walking control commands between the navigation server and the command receiving device of the AGV can be based on various existing or future communication protocols, and the above-mentioned communication protocols are not specifically limited here. Secondly, the specific structure and working principle of the above-mentioned walking components can refer to the corresponding technical solutions disclosed in the prior art, which will not be repeated here.
[0109] Furthermore, the present invention also discloses an AGV navigation system. Figure 6 As shown, the system includes:
[0110] The navigation server 31 disclosed in the above embodiment;
[0111] The AGV32 disclosed in the aforementioned embodiment;
[0112] A camera 33 connected to the navigation server 31 .
[0113] In order to improve the recognition success rate and accuracy of visual coding and avoid the situation where recognition cannot be achieved due to possible blind spots in the field of vision when only one camera is provided, the AGV navigation system in this embodiment may include a plurality of cameras located at different locations in the factory.
[0114] Regarding the respective working processes of the above-mentioned navigation server, AGV and camera, reference may be made to the corresponding contents disclosed in the aforementioned embodiments, which will not be elaborated here.
[0115] In this specification, each embodiment is described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the embodiments can be referred to each other. For the device disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant parts can be referred to the method part.
[0116] Professionals may further appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the composition and steps of each example have been generally described in the above description according to function. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professionals and technicians may use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.
[0117] The steps of the method or algorithm described in conjunction with the embodiments disclosed herein may be implemented directly using hardware, a software module executed by a processor, or a combination of the two. The software module may be placed in a random access memory (RAM), a memory, a read-only memory (ROM), an electrically programmable ROM, an electrically erasable programmable ROM, a register, a hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the art.
[0118] Finally, it should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the presence of other identical elements in the process, method, article or device including the elements.
[0119] The above is a detailed introduction to a navigation server, AGV, navigation system and method provided by the present invention. Specific examples are used in this article to illustrate the principles and implementation methods of the present invention. The description of the above embodiments is only used to help understand the method of the present invention and its core idea; at the same time, for general technical personnel in this field, according to the idea of the present invention, there will be changes in the specific implementation method and application scope. In summary, the content of this specification should not be understood as a limitation on the present invention.
Claims
1. An AGV navigation method, It is characterized in that Applicable to navigation servers, including: When a new task is obtained, the target AGV for executing the new task is determined from all AGVs according to the current real-time position of each AGV, the task load of each AGV to be executed, and the starting position of the new task; Obtain a coded image obtained by a camera capturing an image of a visual code carried by the current target AGV; the target AGV is provided with a plurality of visual codes, the plurality of visual codes are respectively located on different sides of the target AGV, and each of the plurality of visual codes uniquely corresponds to the target AGV; the visual code includes a one-dimensional barcode or a two-dimensional barcode; Performing information recognition processing on the coded image to obtain specific coded content, coded shape and size, and position of the visual code in the coded image; Determine the location of the visual code carried by the target AGV itself within the factory area according to the specific coding content, coding shape and size, and the location in the coding image of the visual code; Based on multiple coded images corresponding to the target AGV acquired by multiple cameras, multiple sets of real-time positions of the target AGV are obtained respectively, and the multiple sets of real-time positions of the target AGV are fused to obtain the current real-time position of the target AGV; multiple cameras are arranged at different positions of the factory area, and each camera can simultaneously identify the visual codes on multiple AGVs moving in the factory area respectively; the factory area image obtained after the camera acquires the image of the current factory area; Using the factory area image, identifying the current real-time position and speed information of obstacles in the current factory area; Wherein, the obstacles include other AGVs, human bodies, and other types of obstacles; According to the status information of the obstacles in the current factory area, predict the movement trend of the obstacles; According to the current real-time position of the target AGV, the start and end positions corresponding to the new task, and the movement trend of the obstacle, and based on the parameter planning principle of avoiding collision, the navigation parameters are planned for the target AGV in real time; wherein the navigation parameters include navigation speed and / or navigation path; Controlling the target AGV to walk according to the real-time planned navigation parameters; The process of controlling the target AGV to walk also includes: Determine the speed information of the target AGV by using the multiple frames of the coded images of the visual code collected by the camera at different times; When the background system determines that the speed information of the target AGV is inconsistent with the navigation speed planned in advance by the target AGV, the navigation speed of the target AGV at the next moment is adjusted according to the difference between the speed information of the target AGV and the navigation speed planned in advance by the target AGV.
2. A navigation server, It is characterized in that The invention comprises a processor and a memory; wherein the processor implements the following steps when executing a computer program stored in the memory: When a new task is obtained, the target AGV for executing the new task is determined from all AGVs according to the current real-time position of each AGV, the task load of each AGV to be executed, and the starting position of the new task; Obtain a coded image obtained by a camera capturing an image of a visual code carried by the current target AGV; the target AGV is provided with a plurality of visual codes, the plurality of visual codes are respectively located on different sides of the target AGV, and each of the plurality of visual codes uniquely corresponds to the target AGV; the visual code includes a one-dimensional barcode or a two-dimensional barcode; Performing information recognition processing on the coded image to obtain specific coded content, coded shape and size, and position of the visual code in the coded image; Determine the location of the visual code carried by the target AGV itself within the factory area according to the specific coding content, coding shape and size, and the location in the coding image of the visual code; Based on multiple coded images corresponding to the target AGV acquired by multiple cameras, multiple sets of real-time positions of the target AGV are obtained respectively, and the multiple sets of real-time positions of the target AGV are fused to obtain the current real-time position of the target AGV; multiple cameras are arranged at different positions of the factory area, and each camera can simultaneously identify the visual codes on multiple AGVs moving in the factory area respectively; the factory area image obtained after the camera acquires the image of the current factory area; Using the factory area image, identifying the current real-time position and speed information of obstacles in the current factory area; Wherein, the obstacles include other AGVs, human bodies, and other types of obstacles; According to the status information of the obstacles in the current factory area, predict the movement trend of the obstacles; According to the current real-time position of the target AGV, the start and end positions corresponding to the new task, and the movement trend of the obstacle, and based on the parameter planning principle of avoiding collision, the navigation parameters are planned for the target AGV in real time; wherein the navigation parameters include navigation speed and / or navigation path; Controlling the target AGV to walk according to the real-time planned navigation parameters; The process of controlling the target AGV to walk also includes: Determine the speed information of the target AGV by using the multiple frames of the coded images of the visual code collected by the camera at different times; When the background system determines that the speed information of the target AGV is inconsistent with the navigation speed planned in advance by the target AGV, the navigation speed of the target AGV at the next moment is adjusted according to the difference between the speed information of the target AGV and the navigation speed planned in advance by the target AGV.
3. An AGV, It is characterized in that The AGV is provided with a visual code and further comprises: A command receiving device for acquiring the walking control command sent by the navigation server as claimed in claim 2; A walking component is used to respond to the walking control command.
4. An AGV navigation system, It is characterized in that include: The navigation server as claimed in claim 2; The AGV as claimed in claim 3; A camera connected to the navigation server.
