Automatic loading method, system, medium and device suitable for dynamic scene

Abstract

The invention provides an automatic loading method, system, medium and device suitable for a dynamic scene. The automatic loading method comprises the steps that loading truck in-place information in a target area is acquired; calculating the coordinate value of a parking space according to a parking auxiliary system, and carrying out the corresponding positioning of the loading and transporting truck and the platform position corresponding to the loading work order; constructing an AGV map based on a navigation technology; the AGV map comprises a target pickup area map and a map in a carriage of a loading and transporting truck; and positioning is carried out based on the loading and transporting truck in-place information and the AGV map, and a loading task is executed through the AGV unmanned automatic forklift, so that the automatic loading process in a dynamic scene is completed. The method can be effectively applied to automatic loading of boxcars, the purpose of auxiliary positioning of automatic equipment carrying equipment is achieved, the flow and efficiency of unmanned automatic loading can be effectively improved, the effect is remarkable, and popularization is convenient.

Description

Technical Field

[0001] The present invention belongs to the technical field of intelligent logistics applications, and relates to an automated loading method, and in particular to an automated loading method, system, medium and device suitable for dynamic scenarios. Background Art

[0002] At present, there are relatively few studies on automatic loading equipment for box-type cargo at home and abroad. Combining the advanced logistics manufacturing industry at home and abroad and the actual use needs on site, we focus on further in-depth research and analysis on the application of its navigation technology.

[0003] In terms of navigation technology, the navigation technologies currently used by AGVs are mostly magnetic nail navigation, laser navigation, QR code + inertial navigation, contour navigation and SLAM natural navigation. Early AGVs mostly used magnetic tape or electromagnetic navigation. These two solutions are simple in principle, mature in technology, and low in cost, but changing or expanding the path and subsequent maintenance are more troublesome, and AGVs can only travel along fixed routes, and cannot achieve intelligent avoidance or real-time task changes. At present, the mainstream navigation method of AGV is QR code + inertial navigation. This method is relatively flexible to use, and it is also easier to lay or change the path, but the path needs regular maintenance.

[0004] With the development of SLAM algorithms, SLAM has become the preferred advanced navigation method for many AGV manufacturers. The SLAM method does not require other positioning facilities, and the form path is flexible and changeable, and can adapt to a variety of on-site environments. I believe that with the maturity of the algorithm and the compression of hardware costs, SLAM will undoubtedly become the mainstream navigation method for AGVs in the future, and it is more suitable for working environments with more complex logistics and warehousing environments. Using SLAM technology, the robot can complete autonomous positioning, effectively track and operate the target, realize autonomous path planning and navigation, and automatically avoid obstacles. It can greatly improve the intelligence and autonomy of the warehousing system and enhance the breadth and depth of the application of mobile handling robots.

[0005] It is worth noting that the sensors of the SLAM system are affected by factors such as their own accuracy, and the information they obtain will have certain errors. Therefore, it is also necessary to effectively observe the environmental landmarks and correct the robot's posture through the acquired environmental landmark information. The project research urgently needs to find a solution that meets the scanning accuracy requirements under the premise of scanning efficiency.

[0006] In terms of positioning technology, the positioning accuracy of the truck in the loading platform is uncontrollable, and there is a problem of poor positioning accuracy, which cannot meet the use requirements of the AGV entering the truck box. In previous studies, we found that the existing truck box positioning devices are mostly peripheral auxiliary devices with external jacking and guiding as the main features. Their working principles are mostly to achieve the displacement of the vehicle box through electrical detection and mechanical action, so that the working environment meets the use requirements of the equipment. Obviously, the above method involves lifting and lowering actions during actual use, which is not suitable for actual application on site. Therefore, achieving accurate positioning of trucks during the research process is also a problem that needs to be solved urgently. Therefore, although automatic loading technology is a booming development direction for AGV cars, there are only a few cases of leading companies in the industry, and it is still a field that urgently needs research and development.

[0007] In summary, in the process of realizing automatic loading technology, the traditional loading mode mostly relies on manual or semi-automatic handling, with a low degree of automation and no functions such as information traceability in the above links.

[0008] Therefore, in the existing automatic loading technology, due to the low degree of automation, the loading efficiency is low, the information feedback is not timely, and there is no function such as information traceability, as well as safety hazards. Summary of the invention

[0009] In view of the shortcomings of the prior art mentioned above, the purpose of the present application is to provide an automated loading method, system, medium and device suitable for dynamic scenarios, which is used to solve the problems of low loading efficiency, untimely information feedback, lack of information traceability and other functions, as well as safety hazards caused by the low degree of automation in the process of realizing automatic loading technology in the prior art.

[0010] To achieve the above-mentioned purpose and other related purposes, in the first aspect, the present application provides an automated loading method suitable for dynamic scenarios, comprising the following steps: obtaining the arrival information of the shipping truck in the target area; calculating the parking space coordinate value according to the parking assistance system, and matching and locating the shipping truck with the platform position corresponding to the loading work order; constructing an AGV map based on navigation technology; the AGV map includes a map of the target pickup area and a map of the interior of the shipping truck; positioning is performed based on the arrival information of the shipping truck and the AGV map, and the loading task is performed by an AGV unmanned automatic forklift to complete the automated loading process in the dynamic scenario.

[0011] In an implementation of the first aspect, obtaining the arrival information of the shipping truck in the target area includes the following steps: arranging the shipping truck to queue at the loading port through a vehicle identification system; determining whether the shipping truck is in place based on a parking assistance system, and obtaining an arrival signal.

[0012] In an implementation of the first aspect, determining whether the shipping truck is in place based on a parking assistance system and obtaining an arrival signal includes the following steps: determining whether the shipping truck is in place based on a detection signal; extending a platform baffle to connect the shipping truck and the platform, and outputting an arrival signal; and the AGV unmanned automatic forklift loads the truck after receiving the arrival signal.

[0013] In an implementation of the first aspect, the parking assistance system includes a first laser radar and a second laser radar; the first laser radar is arranged on a first side of the parking space, and the second laser radar is arranged on a second side of the parking space; the first laser radar and the second laser radar are both set with a 90° sector detection range.

[0014] In an implementation of the first aspect, the parking space coordinate value is calculated according to the parking assistance system, and the platform position corresponding to the loading work order is matched and positioned, including the following steps: when the shipping truck is parked in the parking space, a reference operating route corresponding to the reference parking position of the AGV unmanned automatic forklift and the shipping truck is preset; the lateral offset value of the shipping truck relative to the reference parking position and the offset angle of the shipping truck in the vertical platform direction are detected and obtained by the first laser radar and the second laser radar; the reference operating route is compensated according to the lateral offset value and the offset angle, and the actual operating route corresponding to the actual parking position of the AGV unmanned automatic forklift and the shipping truck is output.

[0015] In an implementation of the first aspect, building an AGV map based on navigation technology includes the following steps: establishing a target pickup area map based on SLAM navigation; establishing different types of shipping truck compartment maps based on SLAM navigation; and splicing the target pickup area map and the shipping truck compartment map through map splicing technology to obtain a complete AGV map.

[0016] In an implementation of the first aspect, a target pickup area map is established based on navigation technology, and establishing different types of shipping truck compartment maps based on navigation technology includes the following steps: initializing the AGV, and obtaining real-time operation data of the AGV unmanned automatic forklift during driving through laser scanning; preprocessing the real-time operation data to obtain processed real-time operation data; constructing a target pickup area map for the processed real-time operation data based on the SLAM algorithm, and locating and storing it; collecting the basic data of the truck compartment in the shipping truck compartment; preprocessing the basic data of the truck compartment to obtain the processed basic data of the truck compartment; constructing a shipping truck compartment map for the processed basic data of the truck compartment based on the SLAM algorithm, and locating and storing it.

[0017] In an implementation of the first aspect, stitching the target pickup area map and the map inside the shipping truck compartment by map stitching technology includes the following steps: acquiring the working environment of the target pickup area by laser scanning to obtain a plurality of scan frames; establishing a sub-map based on the scan frames, and sequentially acquiring a plurality of sub-maps based on all the scan frames; performing pre-processing based on the sub-maps to obtain processed sub-maps; including: performing feature extraction based on the sub-maps, and performing feature matching on features in different sub-maps; converting the geographic coordinates in the sub-maps to a unified coordinate system; optimizing the system accuracy of the converted results to obtain optimized sub-maps; storing the relative postures of the scan frames and using them for closed-loop optimization of the system accuracy; optimizing the relative postures of the scan frames to maximize the probability of the scan points in the sub-maps; stitching the converted and optimized sub-maps to obtain a complete AVG map, and evaluating and correcting the AVG map.

[0018] On the second aspect, the present application provides an automated loading system suitable for dynamic scenarios, including: an acquisition module for acquiring the arrival information of the shipping truck in the target area; a positioning module for calculating the parking space coordinate value according to the parking assistance system, and matching and positioning the shipping truck with the platform position corresponding to the loading work order; a map construction module for constructing an AGV map based on navigation technology; the AGV map includes a target pickup area map and a map inside the shipping truck compartment; a loading execution module for positioning based on the arrival information of the shipping truck and the AGV map, and performing loading tasks through the AGV unmanned automatic forklift to complete the automated loading process in dynamic scenarios.

[0019] In the last aspect, the present application provides an automatic loading device suitable for dynamic scenarios, comprising: a processor and a memory. The memory is used to store a computer program; the processor is connected to the memory and is used to execute the computer program stored in the memory, so that the automatic loading device suitable for dynamic scenarios executes the automatic loading method suitable for dynamic scenarios.

[0020] As described above, the automated loading method, system, medium and device applicable to dynamic scenarios of the present invention have the following beneficial effects:

[0021] This application provides an automated loading method suitable for dynamic scenarios. It replaces the manual loading mode with an unmanned vehicle, filling the gap in the field of automated loading pioneered by the industry; applies the independently developed truck assisted parking system to actual scenarios; completes the concept of splicing maps under SLAM navigation technology, making the SLAM map mode more flexible. At the same time, this application can effectively improve the flow and efficiency of unmanned automated loading, with significant effects and easy to promote. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] Figure 1 It is a schematic flow chart of an automatic loading method applicable to dynamic scenes in one embodiment of the present invention.

[0023] Figure 2 Shown is a schematic diagram of a loading process in an embodiment of an automated loading method applicable to dynamic scenarios of the present invention.

[0024] Figure 3A It is a schematic flow chart of S11 in the automatic loading method applicable to dynamic scenarios of the present invention.

[0025] Figure 3B It is a schematic flow chart of S112 in the automated loading method applicable to dynamic scenarios of the present invention.

[0026] Figure 3C Shown is a schematic diagram of an auxiliary parking device in an embodiment of the automated loading method applicable to dynamic scenarios of the present invention.

[0027] Figure 4A It is a schematic flow chart of S12 in the automatic loading method applicable to dynamic scenarios of the present invention.

[0028] Figure 4B It is a schematic diagram showing route adjustment of an auxiliary device in an embodiment of an automated loading method applicable to dynamic scenarios of the present invention.

[0029] Figure 4C It is a schematic diagram of the auxiliary device route adjustment control flow in an embodiment of the automatic loading method applicable to dynamic scenes of the present invention.

[0030] Figure 4D Shown is a schematic diagram of the plan layout of a finished product cigarette elevated warehouse and a loading platform in an embodiment of the automated loading method suitable for dynamic scenarios of the present invention.

[0031] Figure 5A It is a schematic flow chart of S13 in the automatic loading method applicable to dynamic scenarios of the present invention.

[0032] Figure 5B Shown is a schematic diagram of SLAM navigation modeling in the automated loading method suitable for dynamic scenarios of the present invention.

[0033] Figure 5C Shown is a schematic diagram of the SLAM modeling map inside the compartment of a shipping truck in the automated loading method suitable for dynamic scenarios of the present invention.

[0034] Figure 6Shown is an automatic loading AGV transfer route map in an embodiment of the automatic loading method applicable to dynamic scenarios of the present invention.

[0035] Figure 7 It is a schematic diagram showing the principle structure of an automatic loading system suitable for dynamic scenes in one embodiment of the present invention.

[0036] Figure 8 It is a schematic diagram showing the principle structure of another embodiment of the automatic loading system applicable to dynamic scenes of the present invention.

[0037] Fig. 9 It is a schematic diagram showing the principle structure of an automatic loading device suitable for dynamic scenes in one embodiment of the present invention.

[0038] Component number description

[0039] 71 Get Module

[0040] 72 Positioning module

[0041] 73 Map building blocks

[0042] 74 Loading Execution Module

[0043] 81 Loading platform

[0044] 82 Shipping Truck

[0045] 83 Double Fork Storage AGV

[0046] 84 Finished product smoke high-bay warehouse

[0047] 91 Processor

[0048] 92 Memory

[0049] Steps S11 to S14 DETAILED DESCRIPTION

[0050] The following describes the embodiments of the present invention by specific examples, and those skilled in the art can easily understand other advantages and effects of the present invention from the contents disclosed in this specification. The present invention can also be implemented or applied through other different specific embodiments, and the details in this specification can also be modified or changed in various ways based on different viewpoints and applications without departing from the spirit of the present invention. It should be noted that the following embodiments and features in the embodiments can be combined with each other without conflict.

[0051] It should be noted that the illustrations provided in the following embodiments are only schematic illustrations of the basic concept of the present invention, and thus the drawings only show components related to the present invention rather than being drawn according to the number, shape and size of components in actual implementation. In actual implementation, the type, quantity and proportion of each component may be changed arbitrarily, and the component layout may also be more complicated.

[0052] The following will describe in detail the automated loading method, system, medium and device suitable for dynamic scenarios provided in the embodiments of the present application in conjunction with the drawings in the embodiments of the present application.

[0053] See also Figure 1 and Figure 2 , respectively showing a flow chart of an automatic loading method applicable to a dynamic scene in one embodiment of the present invention and a loading flow chart of an automatic loading method applicable to a dynamic scene in one embodiment of the present invention. Figure 1 and Figure 2 As shown, this embodiment provides an automated loading method suitable for dynamic scenarios.

[0054] The automatic loading method applicable to dynamic scenarios specifically comprises the following steps:

[0055] S11, obtain the arrival information of the shipping truck in the target area. Figure 3A , which is a flow chart of S11 in the automatic loading method applicable to dynamic scenes of the present invention. Figure 3A As shown, the S11 comprises the following steps:

[0056] S111, the shipping trucks are arranged to queue at the loading port through the vehicle identification system.

[0057] In this embodiment, the shipping truck arrives at the factory where the goods are located and enters the target area after license plate recognition.

[0058] S112, judging whether the shipping truck is in place based on the parking assistance system, and obtaining a signal of in place. Figure 3B and Figure 3C , respectively showing a flow chart of S112 in the automatic loading method applicable to dynamic scenes of the present invention and a schematic diagram of an auxiliary parking device in an embodiment of the automatic loading method applicable to dynamic scenes of the present invention.

[0059] like Figure 3B and Figure 3C As shown, the S112 includes the following steps:

[0060] In this embodiment, the system automatically grabs the shipping truck and adds it to the waiting queue. The factory dispatcher arranges the loading work order according to the waiting queue. If there is an unloading task, the vehicle is arranged to enter the loading port to queue up and enter the designated loading port. When the shipping truck has an unloading task, the vehicle is arranged to enter the designated loading port position to queue up and wait for automatic calling. After the shipping truck stops at the platform, the parking assistance system reports the real-time parking status of the vehicle; then, the dispatcher confirms the parking completion through the camera and executes the command to allow docking.

[0061] Specifically, when a loading truck has an unloading task, the vehicle will be arranged to queue up at loading port No. 6; then, after watching the synchronous display and calling of numbers on the square LED screen, the number will be automatically called according to the loading work order platform, sequence, etc.

[0062] S112A, judging whether the shipping truck is in place based on a detection signal.

[0063] In this embodiment, the two sets of radars in the parking assistance system are installed and fixed close to the wall to reduce interference with the truck entering the warehouse, which provides convenience for subsequent data collection, thereby improving the positioning and navigation accuracy of the AGV unmanned automatic forklift and the stability of the system.

[0064] AGV (Automated Guided Vehicle) is equipped with electromagnetic or optical automatic guidance devices, controlled by a computer, characterized by wheeled movement, with its own power or power conversion device, and can automatically travel along a specified guide path. By combining with WMS (Warehouse Management System) and MES (Manufacturing Execution System), AGV realizes automated handling management of warehouses, flexible and dynamic allocation of cargo locations, and changes picking from "people to goods" to "goods to people", improving work efficiency.

[0065] Please continue reading Figure 3C .

[0066] Specifically, the parking assistance system includes: a first laser radar and a second laser radar. The first laser radar is arranged on a first side of the parking space, and the second laser radar is arranged on a second side of the parking space; the first laser radar and the second laser radar are both arranged with a 90° sector detection range.

[0067] The first and second laser radars in the parking assist system measure their relative positions and feed them back to the running AGV unmanned automatic forklift, thereby ensuring the accuracy of each forklift unloading. The two radars are installed and fixed with the center line of the delivery port as the symmetry axis to scan both sides of the truck.

[0068] S112B, extending the platform baffle to connect the shipping truck and the platform, and outputting an arrival signal.

[0069] S112C, the AGV unmanned automatic forklift receives the arrival signal and then loads the vehicle.

[0070] In this embodiment, when the AGV unmanned automatic forklift receives the arrival signal, it loads the vehicle according to the loading task content.

[0071] S12, calculating the parking space coordinates according to the parking assistance system, and aligning and locating the loading truck with the platform position corresponding to the loading work order. Figure 4A , Figure 4B and Figure 4C , respectively showing a flow chart of S12 in the automatic loading method applicable to dynamic scenes of the present invention, a schematic diagram of auxiliary device route adjustment in an embodiment of the automatic loading method applicable to dynamic scenes of the present invention, and a schematic diagram of auxiliary device route adjustment control flow chart of an embodiment of the automatic loading method applicable to dynamic scenes of the present invention. Figure 4A , Figure 4B and Figure 4C As shown, the S12 comprises the following steps:

[0072] S121, when the shipping truck stops at a parking space, a reference running route of the AGV unmanned automatic forklift corresponding to a reference parking position of the shipping truck is preset.

[0073] In this embodiment, a reference running line corresponding to the reference parking position of the automatic handling equipment and the carriage of the shipping truck is preset in the parking area on one side of the platform. The reference running line is set vertically at the platform in the middle of the parking area, and multiple reference delivery points are set at intervals on the reference running line.

[0074] See also Figure 4D , which is a schematic diagram of the plan layout of a finished product cigarette high-bay warehouse and a loading platform in an embodiment of the automated loading method suitable for dynamic scenarios of the present invention.

[0075] Specifically, for example, there are six loading points in the shipping truck on platform D6, namely: E6-1, E6-2, E6-3, E6-4, E6-5, and E6-6.

[0076] S122: Detect and obtain, by means of the first laser radar and the second laser radar, a lateral offset value of the shipping truck relative to a reference parking position and an offset angle of the shipping truck in a direction perpendicular to the platform.

[0077] In this embodiment, the lateral offset value and the offset angle of the actual parking position of the shipping truck compartment relative to the reference parking position are obtained by a first detection module disposed at one side of the parking area and a second detection module disposed at the other side of the parking area.

[0078] Specifically, a first reference point is set on one side of the parking area, and a second reference point is set on the other side of the parking area; a first laser radar is used to detect the distance between the first reference point and the shipping truck compartment along a fixed angle and the distance between the first reference point and the shipping truck compartment along a fixed angle, and a second laser radar is used to detect the distance between the second reference point and the shipping truck compartment along a fixed angle and the distance between the second reference point and the shipping truck compartment along a fixed angle; finally, the lateral offset value is calculated.

[0079] The first reference point and the second reference point are symmetrically arranged on both sides of the reference running line.

[0080] S123, compensating the reference running route according to the lateral offset value and the offset angle, and outputting the actual running route of the AGV unmanned automatic forklift corresponding to the actual parking position of the shipping truck.

[0081] In this embodiment, the reference running line is horizontally rotated around the center point by an offset angle to obtain an intermediate transition running line; the intermediate transition running line is then horizontally shifted to obtain an actual running line, and the vertical distance between the actual running line and the intermediate transition running line is the lateral offset value. All reference delivery points on the reference running line are compensated for the offset angle and lateral offset value in turn to obtain the actual delivery point; all actual delivery points are sequentially connected to finally form the actual running line.

[0082] S13, constructing an AGV map based on navigation technology; the AGV map includes a target pickup area map and a map inside the shipping truck. Figure 5A , Figure 5B and Figure 5C , respectively showing a flow chart of S13 in the automatic loading method applicable to dynamic scenes of the present invention, a SLAM navigation modeling chart in the automatic loading method applicable to dynamic scenes of the present invention, and a SLAM modeling map chart in the compartment of the shipping truck in the automatic loading method applicable to dynamic scenes of the present invention. Figure 5A , Figure 5B and Figure 5C As shown, the S13 comprises the following steps:

[0083] S131, establishing a target pickup area map based on SLAM navigation.

[0084] In this embodiment, the AGV is initialized, and real-time operation data of the AGV unmanned automatic forklift during driving is obtained through laser scanning; the real-time operation data is preprocessed to obtain processed real-time operation data; based on the SLAM algorithm, a target pickup area map is constructed for the processed real-time operation data, and positioning and storage are performed.

[0085] Specifically, first, the AGV is initialized, including: setting the initial position and posture of the AGV and other related data information. The laser radar installed on the AGV unmanned automatic forklift collects the real-time point cloud data generated by the AGV unmanned automatic forklift during driving.

[0086] Then, the collected real-time point cloud data is preprocessed, including: noise removal, filtering, interpolation and other operations, so as to obtain more accurate real-time point cloud data.

[0087] Next, the SLAM algorithm is used to map the processed point cloud data, and then a pickup area map of the environment where the AGV unmanned automatic forklift is located is constructed. The constructed pickup area map is optimized, including: removing redundant information, adding key points, etc., to improve the accuracy and quality of the pickup area map. Then, while constructing the pickup area map, the SLAM algorithm is used to locate the AGV unmanned automatic forklift and determine the exact position of the AGV unmanned automatic forklift in the pickup area map.

[0088] Finally, the constructed pickup area map is stored in the memory of the AGV unmanned automatic forklift, and the pickup area map is continuously updated and stored during the subsequent operation process to ensure the accuracy and real-time performance of the pickup area map. The constructed pickup area map and the positioning information of the AGV unmanned automatic forklift are then used to navigate the AGV unmanned automatic forklift using a path planning algorithm, so that it can automatically and safely complete the specified task.

[0089] For example: Figure 5B From the magnified areas ①②③④ in the figure, it can be seen that the reconstruction precision is very high, and the maximum entity pixel is 2 pixels. For the magnified area ⑤, there is a serious ghosting phenomenon. According to on-site observations, the height of the door opening of the warehouse platform is close to the horizontal plane of the radar, which produces the phenomenon of contour uncertainty. In addition, in the established platform map, platform SLAM positioning is carried out, and the parking repetition accuracy of the vehicle body is within 10mm. The repetition accuracy test is carried out by setting parking marks on the ground. Through scheduling, the AGV reaches the target point for the first time under the laser SLAM navigation.

[0090] S132, establishing interior maps of different types of shipping trucks based on SLAM navigation.

[0091] In this embodiment, basic data of the truck compartment in the shipping truck compartment is collected; the basic data of the truck compartment is preprocessed to obtain processed basic data of the truck; a map of the interior of the shipping truck compartment is constructed based on the processed basic data of the truck based on the SLAM algorithm, and positioning and storage are performed.

[0092] Specifically, first, basic data of the truck compartment in the shipping truck compartment is collected by using a first laser radar and a second laser radar.

[0093] Then, the collected basic data of the truck compartment is preprocessed, including: noise removal, filtering, interpolation and other operations, so as to obtain more accurate basic data of the truck compartment.

[0094] Next, the SLAM algorithm is used to map the processed truck compartment basic data, and then the map of the shipping truck compartment where the AGV unmanned automatic forklift is located is constructed. The constructed map of the shipping truck compartment is optimized, including: removing redundant information, adding key points, etc., to improve the accuracy and quality of the map of the shipping truck compartment. Then, while constructing the map of the shipping truck compartment, the SLAM algorithm is used to locate the AGV unmanned automatic forklift and determine the exact position of the AGV unmanned automatic forklift in the map of the shipping truck compartment.

[0095] Finally, the constructed map inside the shipping truck compartment is stored in the memory of the AGV unmanned automatic forklift, and the map inside the shipping truck compartment is continuously updated and stored during the subsequent operation process to ensure the accuracy and real-time nature of the map inside the shipping truck compartment. Then, the constructed map inside the shipping truck compartment and the positioning information of the AGV unmanned automatic forklift are used to navigate the AGV unmanned automatic forklift using a path planning algorithm, so that it can automatically and safely complete the specified task.

[0096] For example: Figure 5C In the process, a Dongfeng truck is selected to build a map inside the truck compartment. The AGV unmanned automatic forklift is driven into the truck compartment. Due to the serious undulations on the floor of the truck compartment, the parking repetition accuracy of the truck body inside the truck compartment is 10mm higher than that on the platform, reaching 20mm. For double pallets in the truck compartment, there is a minimum spacing of 200mm between the left and right sides and the inner wall of the truck compartment. Therefore, the AGV in the truck compartment has a repetition accuracy of within 20mm and is completely usable.

[0097] S133, splicing the target pickup area map and the inside map of the shipping truck through a map splicing technology to obtain a complete AVG map.

[0098] In this embodiment, the working environment of the target pickup area is acquired through laser scanning to obtain a plurality of scan frames; a sub-graph is established based on the scan frames, and a plurality of sub-graphs are acquired based on all the scan frames in turn; pre-processing is performed based on the sub-graph to obtain a processed sub-graph; including: feature extraction based on the sub-graph, and feature matching of features in different sub-graphs; converting the geographic coordinates in the sub-graphs to a unified coordinate system; optimizing the system accuracy of the converted results to obtain an optimized sub-graph; storing the relative posture of the scan frame, and using it for closed-loop optimization of the system accuracy; optimizing the relative posture of the scan frame to maximize the probability of the scan points in the sub-graph; splicing the converted and optimized sub-graphs to obtain a complete AVG map, and evaluating and correcting the AVG map.

[0099] Specifically, first, the map segmentation method is used to obtain the working environment of the target pickup area through laser scanning, and the map of the target pickup area and the map inside the truck compartment are segmented into several smaller sub-images to obtain several scan frames. The size of the segmented sub-images is approximately between a few hundred pixels and a few thousand pixels. It should be noted that: the size of the segmented sub-images should be moderate to facilitate computer processing; the segmented sub-images should maintain integrity to avoid segmenting the same target pickup area into multiple sub-images; the segmented sub-images should try to maintain their stability to avoid problems in subsequent processing due to image quality issues.

[0100] Then, based on the feature extraction algorithm, the features of the segmented target pickup area sub-image are extracted, such as the edge, corner points, and texture features of the target pickup area sub-image. The features in different sub-images of the target pickup area are then compared to find similar or identical features.

[0101] Next, the geographic coordinates in the sub-maps of different target pickup areas are all converted into a unified coordinate system, generally using affine transformation, polynomial transformation, etc. The geographic coordinates converted into the unified coordinate system are optimized by the nearest point algorithm or radial basis function interpolation method to obtain accurate geographic coordinates.

[0102] Then, the converted and optimized sub-maps are spliced ​​to obtain a complete AVG map.

[0103] For example, the laser observation value in the current posture is defined as a scan frame, and a certain number of scan frames constitute a submap. We can convert the scan frame in the radar coordinate system into a point in the submap coordinate system, and the conversion coefficient used is defined as T ξ p, the formula is as follows:

[0104]

[0105] A series of sub-graphs are established and maintained through a series of scan frames. The sub-graphs are represented in the form of probability grids, which are a series of grid maps. The relative poses of the scan frames are stored in the memory for closed-loop optimization. When there are new scan frames, they will be inserted into the best position in the sub-graph through the scan matching method (Ceres Scan Matching). The scan matching device is responsible for optimizing the pose of the scan frame to maximize the probability of the scan points in the sub-graph. We regard the problem of solving the pose of the scan frame as a nonlinear least squares problem. The formula is as follows:

[0106]

[0107] The scan frame coordinate system is converted to the sub-image coordinate system according to the scan pose, and the probability values ​​in the sub-image are smoothed. The new scan frame is matched only with the current sub-image. However, in this process, since the map is composed of multiple sub-images, as more and more sub-images are created, the cumulative error in the scan matching process will become larger and larger. The pose estimate obtained by scanmatching is reliable in the short term, but there will be cumulative errors in the long term. Therefore, Cartographer applies loop closure detection to optimize the cumulative error.

[0108] Then, the sparse posture adjustment method is adopted to optimize the posture of all scanned frames and sub-graphs. When a sub-graph is constructed, that is, no new scanned frames will be inserted into the sub-graph, the algorithm will add the scanned frames and sub-graphs that are grouped at this time to the optimization. Combined with the loss function to reduce the impact of outliers added to the optimization problem on the system.

[0109] It should be noted that the feature extraction algorithm involved in this embodiment can be implemented by, but is not limited to, LBP local binary algorithm, HOG feature extraction algorithm, SIFT operator and other algorithms.

[0110] S14, based on the arrival information of the shipping truck and the AGV map, positioning is performed, and the AGV unmanned automatic forklift performs the loading task to complete the automated loading process in the dynamic scene. Figure 6 , showing an automatic loading AGV transfer route map in an embodiment of the automatic loading method applicable to dynamic scenarios of the present invention.

[0111] In this embodiment, according to the lateral offset and angular offset provided by the truck positioning system, the truck enters the interior of the truck along the mid-vertical line of the rear of the truck, and puts down the cigarette at the designated position, and repeats this process until the truck is filled with materials and leaves the scene.

[0112] Specifically, after the operator gives the outbound instruction through the WMS, the outbound instruction is transmitted to the double-station AGV unmanned automatic forklift, at which point the AGV unmanned automatic forklift begins to perform the loading task. Next, detect and determine whether it is a full pallet; if it is a full pallet, continue to execute, and the double-station AGV unmanned automatic forklift takes two pallets of cigarettes at the designated position of the finished cigarette high-bay warehouse, and then based on the arrival information of the shipping truck and the AGV map, combined with the calculated lateral offset and angular offset values, calculate the actual running route for delivering the finished cigarettes to the designated platform position, and complete the transportation process. If the detection determines that it is not a full pallet, the double-station AGV unmanned automatic forklift is required to transport the non-full pallet of cigarettes to the system buffer area, and then the AGV unmanned automatic forklift receives the management system instruction and then performs the automatic loading operation. Then, the system determines whether the loading operation is completed and whether the quantity is consistent with the work order quantity. After all are met, the loading operation is completed.

[0113] The automated loading method suitable for dynamic scenarios provided in the present application can be effectively applied to the automated loading of truck compartments to achieve the purpose of auxiliary positioning of automated equipment and handling equipment, and can effectively improve the flow and efficiency of unmanned automated loading.

[0114] The protection scope of the automated loading method suitable for dynamic scenarios described in the embodiment of the present application is not limited to the execution order of the steps listed in the present embodiment. All solutions implemented by adding, reducing or replacing steps in the prior art based on the principles of the present application are included in the protection scope of the present application.

[0115] This embodiment further provides a computer-readable storage medium on which a computer program is stored. When the program is executed by a processor, the following is achieved: Figure 1 The automated loading method is suitable for dynamic scenarios.

[0116] At any possible level of technical detail combination, the present application may be a system, method and / or computer program product. The computer program product may include a computer-readable storage medium carrying computer-readable program instructions for causing a processor to implement various aspects of the present application.

[0117] Computer readable storage medium can be a tangible device that can hold and store instructions used by an instruction execution device. Computer readable storage medium can be, for example, (but not limited to) an electrical storage device, a magnetic storage device, an optical storage device, an electromagnetic storage device, a semiconductor storage device, or any suitable combination thereof. More specific examples (non-exhaustive list) of computer readable storage medium include: a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), a static random access memory (SRAM), a portable compact disk read-only memory (CD-ROM), a digital versatile disk (DVD), a memory stick, a floppy disk, a mechanical encoding device, for example, a punch card or a convex structure in a groove on which instructions are stored, and any suitable combination thereof. The computer readable storage medium used here is not interpreted as a transient signal itself, such as a radio wave or other freely propagating electromagnetic wave, an electromagnetic wave propagated by a waveguide or other transmission medium (for example, a light pulse by an optical fiber cable), or an electrical signal transmitted by a wire.

[0118] The computer-readable program described herein can be downloaded from a computer-readable storage medium to each computing / processing device, or downloaded to an external computer or external storage device through a network, such as the Internet, a local area network, a wide area network, and / or a wireless network. The network can include copper transmission cables, optical fiber transmission, wireless transmission, routers, firewalls, switches, gateway computers, and / or edge servers. The network adapter card or network interface in each computing / processing device receives a computer-readable program instruction from the network, and forwards the computer-readable program instruction for storage in the computer-readable storage medium in each computing / processing device. The computer program instruction for performing the operation of the present application can be an assembly instruction, an instruction set architecture (ISA) instruction, a machine instruction, a machine-related instruction, a microcode, a firmware instruction, a state setting data, an integrated circuit configuration data, or a source code or object code written in any combination of one or more programming languages, wherein the programming language includes an object-oriented programming language, such as Smalltalk, C++, etc., and a procedural programming language, such as "C" language or similar programming language. Computer readable program instructions can be executed completely on a user's computer, partially on a user's computer, as an independent software package, partially on a user's computer, partially on a computer, or completely on a computer or server. In the case of a computer, the computer can be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or can be connected to an external computer (e.g., using an Internet service provider to connect through the Internet). In some embodiments, by using the state information of computer readable program instructions to personalize electronic circuits, such as programmable logic circuits, field programmable gate arrays (FPGAs) or programmable logic arrays (PLAs), the electronic circuits can execute computer readable program instructions, thereby realizing various aspects of the present application.

[0119] An embodiment of the present application also provides an automated loading system suitable for dynamic scenarios, and the automated loading system suitable for dynamic scenarios can implement the automated loading method suitable for dynamic scenarios described in the present application, but the implementation device of the automated loading method suitable for dynamic scenarios described in the present application includes but is not limited to the structure of the automated loading system suitable for dynamic scenarios listed in the present embodiment. All structural deformations and replacements of the prior art made according to the principles of the present application are included in the protection scope of the present application.

[0120] The following will describe in detail the automated loading system applicable to dynamic scenarios provided by this embodiment with reference to the accompanying drawings.

[0121] This embodiment provides an automated loading system suitable for dynamic scenarios, including:

[0122] See also Figure 7 , which is a schematic diagram of the principle structure of an automatic loading system suitable for dynamic scenes in one embodiment of the present invention. Figure 7 As shown, the automated loading system suitable for dynamic scenarios includes: an acquisition module 71 , a positioning module 72 , a map construction module 73 and a loading execution module 74 .

[0123] The acquisition module 71 is used to acquire the arrival information of the shipping trucks in the target area.

[0124] Get the arrival information of the delivery trucks in the target area.

[0125] The shipping truck is arranged to queue at the loading port through the vehicle identification system. In this embodiment, the shipping truck arrives at the factory where the goods are located and enters the target area after the license plate is recognized.

[0126] Based on the parking assistance system, it is determined whether the shipping truck is in place, and an in-place signal is obtained.

[0127] In this embodiment, the system automatically grabs the shipping truck and adds it to the waiting queue. The factory dispatcher arranges the loading work order according to the waiting queue. If there is an unloading task, the vehicle is arranged to enter the loading port to queue up and enter the designated loading port. When the shipping truck has an unloading task, the vehicle is arranged to enter the designated loading port position to queue up and wait for automatic calling. After the shipping truck stops at the platform, the parking assistance system reports the real-time parking status of the vehicle; then, the dispatcher confirms the parking completion through the camera and executes the command to allow docking.

[0128] Specifically, based on a detection signal, it is determined whether the shipping truck is in place. The platform baffle is extended to connect the shipping truck and the platform, and an in-place signal is output. The AGV unmanned automatic forklift executes the loading instruction after receiving the in-place signal.

[0129] The positioning module 72 is connected to the acquisition module 71, and is used to calculate the parking space coordinate value according to the parking assistance system, and to correspond and locate the platform position corresponding to the loading truck and the loading work order.

[0130] In this embodiment, when the shipping truck stops at the parking space, a reference running route corresponding to the reference parking position of the shipping truck is preset for the AGV unmanned automatic forklift. A reference running route corresponding to the reference parking position of the shipping truck compartment is preset in the parking area on one side of the platform. The reference running route is set vertically at the platform in the middle of the parking area, and multiple reference delivery points are set at intervals on the reference running route.

[0131] The first laser radar and the second laser radar are used to detect and obtain a lateral offset value of the shipping truck relative to a reference parking position and an offset angle of the shipping truck in a direction perpendicular to the platform.

[0132] In this embodiment, the lateral offset value and the offset angle of the actual parking position of the shipping truck compartment relative to the reference parking position are obtained by a first detection module disposed at one side of the parking area and a second detection module disposed at the other side of the parking area.

[0133] Specifically, a first reference point is set on one side of the parking area, and a second reference point is set on the other side of the parking area; a first laser radar is used to detect the distance between the first reference point and the shipping truck compartment along a fixed angle and the distance between the first reference point and the shipping truck compartment along a fixed angle, and a second laser radar is used to detect the distance between the second reference point and the shipping truck compartment along a fixed angle and the distance between the second reference point and the shipping truck compartment along a fixed angle; finally, the lateral offset value is calculated.

[0134] The first reference point and the second reference point are symmetrically arranged on both sides of the reference running line.

[0135] Based on the lateral offset value and the offset angle, the reference running route is compensated, and the actual running route corresponding to the actual parking position of the AGV unmanned automatic forklift and the shipping truck is output.

[0136] In this embodiment, the reference running line is horizontally rotated around the center point by an offset angle to obtain an intermediate transition running line; the intermediate transition running line is then horizontally shifted to obtain an actual running line, and the vertical distance between the actual running line and the intermediate transition running line is the lateral offset value. All reference delivery points on the reference running line are compensated for the offset angle and lateral offset value in turn to obtain the actual delivery point; all actual delivery points are sequentially connected to finally form the actual running line.

[0137] The map construction module 73 is used to construct an AGV map based on navigation technology; the AGV map includes a target pickup area map and a map inside the shipping truck compartment.

[0138] Establish a target pickup area map based on SLAM navigation.

[0139] In this embodiment, the AGV is initialized, and real-time operation data of the AGV unmanned automatic forklift during driving is obtained through laser scanning; the real-time operation data is preprocessed to obtain processed real-time operation data; based on the SLAM algorithm, a target pickup area map is constructed for the processed real-time operation data, and positioning and storage are performed.

[0140] Specifically, first, the AGV is initialized, including: setting the initial position and posture of the AGV and other related data information. The laser radar installed on the AGV unmanned automatic forklift collects the real-time point cloud data generated by the AGV unmanned automatic forklift during driving.

[0141] Then, the collected real-time point cloud data is preprocessed, including: noise removal, filtering, interpolation and other operations, so as to obtain more accurate real-time point cloud data.

[0142] Next, the SLAM algorithm is used to map the processed point cloud data, and then a pickup area map of the environment where the AGV unmanned automatic forklift is located is constructed. The constructed pickup area map is optimized, including: removing redundant information, adding key points, etc., to improve the accuracy and quality of the pickup area map. Then, while constructing the pickup area map, the SLAM algorithm is used to locate the AGV unmanned automatic forklift and determine the exact position of the AGV unmanned automatic forklift in the pickup area map.

[0143] Finally, the constructed pickup area map is stored in the memory of the AGV unmanned automatic forklift, and the pickup area map is continuously updated and stored during the subsequent operation process to ensure the accuracy and real-time performance of the pickup area map. The constructed pickup area map and the positioning information of the AGV unmanned automatic forklift are then used to navigate the AGV unmanned automatic forklift using a path planning algorithm, so that it can automatically and safely complete the specified task.

[0144] Establish interior maps of different types of shipping trucks based on SLAM navigation.

[0145] In this embodiment, basic data of the truck compartment in the shipping truck compartment is collected; the basic data of the truck compartment is preprocessed to obtain processed basic data of the truck; a map of the interior of the shipping truck compartment is constructed based on the processed basic data of the truck based on the SLAM algorithm, and positioning and storage are performed.

[0146] Specifically, first, basic data of the truck compartment in the shipping truck compartment is collected by using a first laser radar and a second laser radar.

[0147] Then, the collected basic data of the truck compartment is preprocessed, including: noise removal, filtering, interpolation and other operations, so as to obtain more accurate basic data of the truck compartment.

[0148] Next, the SLAM algorithm is used to map the processed truck compartment basic data, and then the map of the shipping truck compartment where the AGV unmanned automatic forklift is located is constructed. The constructed map of the shipping truck compartment is optimized, including: removing redundant information, adding key points, etc., to improve the accuracy and quality of the map of the shipping truck compartment. Then, while constructing the map of the shipping truck compartment, the SLAM algorithm is used to locate the AGV unmanned automatic forklift and determine the exact position of the AGV unmanned automatic forklift in the map of the shipping truck compartment.

[0149] Finally, the constructed map inside the shipping truck compartment is stored in the memory of the AGV unmanned automatic forklift, and the map inside the shipping truck compartment is continuously updated and stored during the subsequent operation process to ensure the accuracy and real-time nature of the map inside the shipping truck compartment. Then, the constructed map inside the shipping truck compartment and the positioning information of the AGV unmanned automatic forklift are used to navigate the AGV unmanned automatic forklift using a path planning algorithm, so that it can automatically and safely complete the specified task.

[0150] The target pickup area map and the inside map of the shipping truck are spliced ​​together using map splicing technology to obtain a complete AVG map.

[0151] In this embodiment, the working environment of the target pickup area is acquired through laser scanning to obtain a plurality of scan frames; a sub-graph is established based on the scan frames, and a plurality of sub-graphs are acquired based on all the scan frames in turn; pre-processing is performed based on the sub-graph to obtain a processed sub-graph; including: feature extraction based on the sub-graph, and feature matching of features in different sub-graphs; converting the geographic coordinates in the sub-graphs to a unified coordinate system; optimizing the system accuracy of the converted results to obtain an optimized sub-graph; storing the relative posture of the scan frame, and using it for closed-loop optimization of the system accuracy; optimizing the relative posture of the scan frame to maximize the probability of the scan points in the sub-graph; splicing the converted and optimized sub-graphs to obtain a complete AVG map, and evaluating and correcting the AVG map.

[0152] Specifically, first, the map segmentation method is used to obtain the working environment of the target pickup area through laser scanning, and the map of the target pickup area and the map inside the truck compartment are segmented into several smaller sub-images to obtain several scan frames. The size of the segmented sub-images is approximately between a few hundred pixels and a few thousand pixels. It should be noted that: the size of the segmented sub-images should be moderate to facilitate computer processing; the segmented sub-images should maintain integrity to avoid segmenting the same target pickup area into multiple sub-images; the segmented sub-images should try to maintain their stability to avoid problems in subsequent processing due to image quality issues.

[0153] Then, based on the feature extraction algorithm, the features of the segmented target pickup area sub-image are extracted, such as the edge, corner points, and texture features of the target pickup area sub-image. The features in different sub-images of the target pickup area are then compared to find similar or identical features.

[0154] Next, the geographic coordinates in the sub-maps of different target pickup areas are all converted into a unified coordinate system, generally using affine transformation, polynomial transformation, etc. The geographic coordinates converted into the unified coordinate system are optimized by the nearest point algorithm or radial basis function interpolation method to obtain accurate geographic coordinates.

[0155] Then, the converted and optimized sub-maps are spliced ​​to obtain a complete AVG map.

[0156] It should be noted that the feature extraction algorithm involved in this embodiment can be implemented by, but is not limited to, LBP local binary algorithm, HOG feature extraction algorithm, SIFT operator and other algorithms.

[0157] The loading execution module 74 is used to perform positioning based on the arrival information of the shipping truck and the AGV map, and to perform the loading task through the AGV unmanned automatic forklift to complete the automated loading process in a dynamic scenario.

[0158] In this embodiment, according to the lateral offset and angular offset provided by the truck positioning system, the truck enters the interior of the truck along the mid-vertical line of the rear of the truck, and puts down the cigarette at the designated position, and repeats this process until the truck is filled with materials and leaves the scene.

[0159] Specifically, after the operator gives the outbound instruction through the WMS, the outbound instruction is transmitted to the double-station AGV unmanned automatic forklift, at which point the AGV unmanned automatic forklift begins to perform the loading task. Next, detect and determine whether it is a full pallet; if it is a full pallet, continue to execute, and the double-station AGV unmanned automatic forklift takes two pallets of cigarettes at the designated position of the finished cigarette high-bay warehouse, and then based on the arrival information of the shipping truck and the AGV map, combined with the calculated lateral offset and angular offset values, calculate the actual running route for delivering the finished cigarettes to the designated platform position, and complete the transportation process. If the detection determines that it is not a full pallet, the double-station AGV unmanned automatic forklift is required to transport the non-full pallet of cigarettes to the system buffer area, and then the AGV unmanned automatic forklift receives the management system instruction and then performs the automatic loading operation. Then, the system determines whether the loading operation is completed and whether the quantity is consistent with the work order quantity. After all are met, the loading operation is completed.

[0160] This application also provides another automatic loading system suitable for dynamic scenes. Figure 8, which is a schematic diagram of the principle structure of another embodiment of the automatic loading system applicable to dynamic scenes of the present invention. Figure 8 As shown, the system includes: a loading platform 81, a shipping truck 82, a double-fork cargo position AGV 83 and a finished product cigarette high-bay warehouse 84.

[0161] The loading platform 81 is connected to the finished product cigarette high-bay warehouse 84 .

[0162] The shipping truck 82 is arranged at the loading platform and is used to receive the goods from the finished product cigarette high-bay warehouse.

[0163] The double-fork cargo AGV 83 preferably uses 4 sets, and connects the loading platform 81, the shipping truck 82 and the finished cigarette high-bay warehouse 84 in series through AGV technology to transport the finished cigarettes and deliver them to the designated position of the system, so as to achieve the purpose of transporting the goods from the high-bay warehouse to the inside of the truck. The double-fork cargo AGV 83 is implemented by an AGV unmanned automatic forklift.

[0164] Specifically, when the truck starts to dock, the finished cigarette pack delivery port starts to deliver, and the double-pallet AGV goes to the corresponding delivery port to pick up cigarette packs. At this time, the truck has docked, and the truck positioning detection system starts to work, sending the obtained lateral offset and angular offset of the rear of the truck to the double-pallet AGV. After the double-pallet AGV picks up two cigarette packs, it enters the truck compartment along the median vertical line of the rear of the truck according to the lateral offset and angular offset provided by the truck positioning system, and puts down the cigarettes at the designated location, and repeats this process until the truck is full of materials and leaves the site.

[0165] The automated loading model suitable for dynamic scenarios is built. The automated loading system suitable for dynamic scenarios can replace the manual loading mode with an unmanned vehicle, filling the gap in the field of automated loading, which is the first of its kind in the industry. The independently developed truck assisted parking system is applied to actual scenarios.

[0166] It should be noted that it should be understood that the division of the various modules of the above system is only a division of logical functions. In actual implementation, they can be fully or partially integrated into one physical entity, or they can be physically separated. And these modules can all be implemented in the form of software called by processing elements; they can also be all implemented in the form of hardware; some modules can also be implemented in the form of software called by processing elements, and some modules can be implemented in the form of hardware. For example, the x module can be a separately established processing element, or it can be integrated in a certain chip of the above system for implementation. In addition, it can also be stored in the memory of the above system in the form of program code, and called and executed by a certain processing element of the above system. The implementation of other modules is similar. In addition, these modules can be fully or partially integrated together, or they can be implemented independently. The processing element described here can be an integrated circuit with signal processing capabilities. In the implementation process, each step of the above method or each module above can be completed by an integrated logic circuit of hardware in the processor element or instructions in the form of software.

[0167] The above modules may be one or more integrated circuits configured to implement the above methods, such as one or more application specific integrated circuits (ASIC), or one or more digital signal processors (DSP), or one or more field programmable gate arrays (FPGA). For another example, when a module is implemented in the form of a processing element scheduling program code, the processing element may be a general-purpose processor, such as a central processing unit (CPU) or other processor that can call program code. For another example, these modules may be integrated together and implemented in the form of a system-on-a-chip (SOC).

[0168] See also Fig. 9 , which is a schematic diagram of the principle structure of an automatic loading device suitable for dynamic scenes in one embodiment of the present invention. Fig. 9 As shown, this embodiment provides an automated loading device suitable for dynamic scenarios, and the automated loading device suitable for dynamic scenarios includes: a processor 91 and a memory 92; the memory 92 is used to store computer programs; the processor 91 is connected to the memory 92, and is used to execute the computer program stored in the memory 92, so that the automated loading device suitable for dynamic scenarios performs the various steps of the automated loading method suitable for dynamic scenarios as described above.

[0169] Preferably, the memory may include a random access memory (RAM), and may also include a non-volatile memory (non-volatile memory), such as at least one disk memory.

[0170] The above-mentioned processor can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it can also be a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components.

[0171] In summary, the automated loading method, system, medium and device applicable to dynamic scenarios provided by the present application have the following beneficial effects:

[0172] The automated loading method applicable to dynamic scenarios provided by this application fills the gap in the field of automated loading pioneered by the industry by replacing the manual loading mode with an unmanned vehicle; applies the independently developed truck auxiliary parking system to actual scenarios; completes the concept of splicing maps under SLAM navigation technology, making the SLAM map mode more flexible. Therefore, this application can be effectively applied to the automatic loading of truck compartments, achieving the purpose of auxiliary positioning of automated equipment handling equipment, and thus effectively improving the flow and efficiency of unmanned automated loading, with significant results and easy to promote.

[0173] The above embodiments are merely illustrative of the principles and effects of the present invention, and are not intended to limit the present invention. Anyone familiar with the art may modify or alter the above embodiments without departing from the spirit and scope of the present invention. Therefore, all equivalent modifications or alterations made by a person of ordinary skill in the art without departing from the spirit and technical concept disclosed by the present invention shall still be covered by the claims of the present invention.

Claims

1. An automated loading method suitable for dynamic scenarios, characterized in that: The following steps are involved: Obtaining information on the arrival of shipping trucks in the target area; Calculate the parking space coordinates according to the parking assistance system, and correspond and locate the loading truck to the platform position corresponding to the loading work order; Build AGV maps based on navigation technology; The AGV map includes a target pickup area map and a shipping truck compartment map; Based on the arrival information of the shipping truck and the AGV map, positioning is performed and the loading task is performed by the AGV unmanned automatic forklift to complete the automated loading process in a dynamic scenario.

2. The automatic loading method applicable to dynamic scenes according to claim 1, characterized in that: Obtaining the arrival information of the shipping truck in the target area includes the following steps: Arrange the shipping trucks to queue at the loading port through the vehicle identification system; Based on the parking assistance system, it is determined whether the shipping truck is in place, and an in-place signal is obtained.

3. The automatic loading method applicable to dynamic scenes according to claim 2, characterized in that: Determining whether the shipping truck is in place based on the parking assistance system and obtaining an in-place signal includes the following steps: Determining whether a shipping truck is in place based on a detection signal; Extending the platform baffle to connect the shipping truck and the platform, and outputting an arrival signal; The AGV unmanned automatic forklift loads the vehicle after receiving the arrival signal.

4. The automatic loading method applicable to dynamic scenes according to claim 2, characterized in that: The parking assistance system includes a first laser radar and a second laser radar; A first laser radar is arranged on a first side of the parking space, and a second laser radar is arranged on a second side of the parking space; The first laser radar and the second laser radar are both set with a 90° sector detection range.

5. The automatic loading method applicable to dynamic scenes according to claim 1 or 4, characterized in that: Calculating the parking space coordinates according to the parking assistance system and aligning and locating the loading truck with the platform position corresponding to the loading work order includes the following steps: When the shipping truck stops at the parking space, a reference running route of the AGV unmanned automatic forklift corresponding to the reference parking position of the shipping truck is preset; Detecting and acquiring, by means of the first laser radar and the second laser radar, a lateral offset value of the shipping truck relative to a reference parking position and an offset angle of the shipping truck in a direction perpendicular to the platform; The reference running route is compensated according to the lateral offset value and the offset angle, and an actual running route corresponding to the actual parking position of the AGV unmanned automatic forklift and the shipping truck is output.

6. The automatic loading method applicable to dynamic scenes according to claim 1, characterized in that: Building an AGV map based on navigation technology includes the following steps: Establish a target pickup area map based on SLAM navigation; Building interior maps of different types of shipping trucks based on SLAM navigation; The target pickup area map and the inside map of the shipping truck are spliced ​​together using map splicing technology to obtain a complete AVG map.

7. The automatic loading method applicable to dynamic scenes according to claim 6, characterized in that: Establishing a target pickup area map based on navigation technology, and establishing different types of truck compartment maps based on navigation technology include the following steps: Initialize the AGV and obtain real-time operation data of the AGV during driving through laser scanning; Preprocessing the real-time operation data to obtain processed real-time operation data; Based on the SLAM algorithm, a map of the target pickup area is constructed for the processed real-time operation data, and positioning and storage are performed; Collecting basic data of the truck compartment in the shipping truck compartment; Preprocessing the basic data of the truck compartment to obtain processed basic data of the truck compartment; Based on the SLAM algorithm, a map inside the shipping truck compartment is constructed for the processed truck compartment basic data, and positioning and storage are performed.

8. The automatic loading method applicable to dynamic scenes according to claim 6, characterized in that: The process of splicing the target pickup area map and the inside map of the shipping truck by using a map splicing technology comprises the following steps: Acquire the working environment of the target pickup area through laser scanning to obtain a plurality of scan frames; Establish a sub-image based on the scanned frame, and sequentially acquire a plurality of sub-images based on all the scanned frames; Preprocessing is performed based on the sub-graph to obtain a processed sub-graph; including: extracting features based on the sub-graph and matching features in different sub-graphs; converting the geographic coordinates in the sub-graph to a unified coordinate system; optimizing the system accuracy of the converted results to obtain an optimized sub-graph; storing the relative posture of the scan frame and using it to optimize the system accuracy in a closed loop; optimizing the relative posture of the scan frame to maximize the probability of the scan point in the sub-graph; The converted and optimized sub-maps are spliced ​​to obtain a complete AVG map, and the AVG map is evaluated and corrected.

9. An automated loading system suitable for dynamic scenarios, characterized in that: include: An acquisition module is used to obtain the arrival information of the shipping trucks in the target area; A positioning module, used to calculate the parking space coordinate value according to the parking assistance system, and correspond and locate the loading truck to the platform position corresponding to the loading work order; Map construction module, used to build AGV maps based on navigation technology; The AGV map includes a target pickup area map and a shipping truck compartment map; The loading execution module is used to perform positioning based on the arrival information of the shipping truck and the AGV map, and to perform the loading task through the AGV unmanned automatic forklift to complete the automated loading process in a dynamic scenario.

10. An automatic loading device suitable for dynamic scenes, characterized in that: include: Processor and memory; The memory is used to store computer programs; The processor is connected to the memory and is used to execute the computer program stored in the memory so that the automatic loading device suitable for dynamic scenarios executes the automatic loading method suitable for dynamic scenarios as described in any one of claims 1 to 8.

Images