AGV vehicle obstacle avoidance methods, devices, equipment and storage media

Abstract

This application discloses a method, apparatus, device, and storage medium for obstacle avoidance in AGV (Automated Guided Vehicle) transportation, belonging to the field of AGVs. The method includes: acquiring point cloud coordinates, wherein the point cloud coordinates are obtained by scanning the pallet legs with a LiDAR scanner, and the point cloud coordinates are in a coordinate system with the center of the AGV vehicle as the origin; obtaining an estimated pose by matching the pallet pose set based on the point cloud coordinates; and determining the target point cloud coordinates from the point cloud coordinates based on the estimated pose. In this application, after scanning to obtain the point cloud coordinates of the pallet legs, the current pose of the pallet on the AGV vehicle is obtained by matching the point cloud coordinates, and the point cloud coordinates of the pallet legs are determined based on the current pose. The current pose can be quickly obtained from the scanned point cloud coordinates, enhancing real-time performance and avoiding the latency problem that occurs when the point cloud coordinates of the legs need to be distinguished only after training the model. That is, it improves the obstacle avoidance accuracy of the AGV vehicle during transportation.

Description

Technical Field

[0001] This application relates to the field of AGVs, and more particularly to a method, apparatus, equipment, and storage medium for obstacle avoidance in AGV transportation. Background Technology

[0002] Currently, AMR vehicles, as a type of AGV vehicle, play a significant role in industrial production. When transporting goods, AMR vehicles avoid obstacles in the surrounding environment. The pallet on the AMR vehicle is used to load goods, and the AMR vehicle needs to distinguish between the pallet legs and obstacles.

[0003] In existing technologies, when AMR vehicles distinguish between pallet legs and obstacles, they cluster the scanned point clouds and then train a model to differentiate between the pallet leg point clouds and obstacle point clouds. However, the training model is based on the point clouds from previous scans, which introduces a time delay and prevents real-time differentiation. Consequently, obstacle avoidance based on the pallet leg point clouds is not very accurate. In other words, existing technologies suffer from low obstacle avoidance accuracy when AGV vehicles are transporting goods.

[0004] The above content is only used to help understand the technical solution of this application and does not represent an admission that the above content is prior art. Summary of the Invention

[0005] The main objective of this invention is to provide an obstacle avoidance method for AGV vehicles during transportation, aiming to solve the problem of low obstacle avoidance accuracy in the prior art when AGV vehicles are transporting vehicles.

[0006] To achieve the above objectives, this application provides a method for obstacle avoidance in the transportation of AGV vehicles, and an AGV vehicle obstacle avoidance device applied to an AGV vehicle obstacle avoidance system. The AGV vehicle obstacle avoidance system further includes an AGV vehicle, a lifting mechanism, a pallet, and obstacles. The AGV vehicle obstacle avoidance device is equipped with a lidar sensor. The AGV vehicle is used to transport goods. The pallet includes pallet legs, and the pallet is lifted by the lifting mechanism. The AGV vehicle obstacle avoidance method includes:

[0007] When transporting goods based on a preset path, point cloud coordinates are obtained, wherein the point cloud coordinates are obtained by the LiDAR scanning the pallet legs, and the point cloud coordinates are in a coordinate system with the center of the AGV vehicle as the origin.

[0008] Based on the point cloud coordinates, the estimated pose is obtained by matching from a preset tray pose set;

[0009] Based on the estimated pose, the target point cloud coordinates are determined from the point cloud coordinates;

[0010] Obstacle avoidance is performed based on the target point cloud coordinates.

[0011] In one possible implementation of this application, the step of obtaining the estimated pose by matching from a preset tray pose set based on the point cloud coordinates includes:

[0012] A preset error range is determined, wherein the error range is the range of the distance from the center of the AGV vehicle to a preset error radius, the error range includes a first number of candidate pallet centers, each candidate pallet center corresponds to a pallet pose, and the multiple pallet poses corresponding to all candidate pallet centers constitute the pallet pose set.

[0013] The point cloud coordinates are filtered to obtain a first point cloud with the number of the first quantity, wherein the point cloud coordinates within the range of the center of the pallet leg corresponding to the center of each candidate pallet center are retained;

[0014] Based on the number of point cloud coordinates carried in the first point cloud, the estimated pose is obtained by matching from the tray pose set within the error range.

[0015] In one possible implementation of this application, after the step of determining the target point cloud coordinates from the point cloud coordinates based on the estimated pose, the method includes:

[0016] Obtain the geometric dimensions of the pallet;

[0017] Based on the target point cloud coordinates, determine the estimated size of the pallet;

[0018] If it is determined that the estimated size of the pallet is not equal to the geometric size of the pallet, the target point cloud coordinates are updated to obtain the updated target point cloud coordinates.

[0019] In one possible implementation of this application, the step of matching the estimated pose from the tray pose set within the error range based on the number of point cloud coordinates carried in the first point cloud includes:

[0020] Based on the number of point cloud coordinates carried in the first point cloud, the first point clouds of the first quantity are sorted in descending order of the number of point cloud coordinates carried to obtain the arrangement order of the first point clouds.

[0021] Based on the arrangement order, the estimated pose is obtained by matching the tray pose set within the error range, wherein the pose corresponding to the first point cloud located in the first position in the arrangement order is determined as the estimated pose.

[0022] In one possible implementation of this application, the step of updating the target point cloud coordinates to obtain updated target point cloud coordinates if it is determined that the estimated size of the pallet is not equal to the geometric size of the pallet includes:

[0023] If it is determined that the estimated size of the pallet is not equal to the geometric size of the pallet, then calculate the sum of the residuals between the point cloud coordinates and the target point cloud;

[0024] Determine the minimum residual and the corresponding target point cloud coordinates as the new target point cloud coordinates;

[0025] Based on the new target point cloud coordinates, the target point cloud coordinates are updated to obtain the updated target point cloud coordinates.

[0026] In one possible embodiment of this application, the tray is a rectangular tray, and the tray's geometric dimensions include the length and width of the tray. The step of determining the estimated size of the tray based on the target point cloud coordinates includes:

[0027] Based on the target point cloud coordinates, the estimated size of the pallet is determined, which includes the estimated length and the estimated width of the pallet.

[0028] In one possible implementation of this application, the AGV vehicle is an AMR vehicle.

[0029] Furthermore, to achieve the above objectives, this application also provides a transport obstacle avoidance device for AGV vehicles, the device comprising:

[0030] The acquisition module is used to acquire point cloud coordinates when transporting based on a preset path. The point cloud coordinates are obtained by the lidar scanning the pallet legs and are in a coordinate system with the center of the AGV vehicle as the origin.

[0031] The matching module is used to match the point cloud coordinates from a preset tray pose set to obtain the estimated pose.

[0032] The determination module is used to determine the target point cloud coordinates from the point cloud coordinates based on the estimated pose;

[0033] The obstacle avoidance module is used to perform obstacle avoidance based on the target point cloud coordinates.

[0034] In addition, to achieve the above objectives, this application also provides a transportation obstacle avoidance device for AGV vehicles. The transportation obstacle avoidance device for AGV vehicles is a physical node device. The transportation obstacle avoidance device for AGV vehicles includes: a memory, a processor, and an AGV vehicle transportation obstacle avoidance program stored in the memory and executable on the processor. The processor executes the AGV vehicle transportation obstacle avoidance program to implement the steps of the AGV vehicle transportation obstacle avoidance method.

[0035] In addition, to achieve the above objectives, this application also provides a storage medium storing a program for implementing a method for obstacle avoidance in the transportation of AGV vehicles. When the AGV vehicle obstacle avoidance program is executed by a processor, it implements the steps of the AGV vehicle obstacle avoidance method described above.

[0036] This application provides a method, apparatus, device, and storage medium for obstacle avoidance in AGV (Automated Guided Vehicle) transportation. Compared with the prior art, where AGVs have low obstacle avoidance accuracy in their surrounding environment during transportation, this application acquires point cloud coordinates during transportation based on a preset path. These point cloud coordinates are obtained by scanning the pallet legs with a lidar, and are in a coordinate system with the AGV center as the origin. Based on these point cloud coordinates, an estimated pose is obtained by matching from a preset pallet pose set. Based on the estimated pose, the target point cloud coordinates are determined from the point cloud coordinates. In this application, after scanning the point cloud coordinates of the pallet legs, the current pose of the pallet on the AGV is obtained by matching these coordinates, and the point cloud coordinates of the pallet legs are determined based on the current pose. The current pose can be quickly derived from the scanned point cloud coordinates, enhancing real-time performance and avoiding the latency problem of distinguishing leg point clouds only after training a model. Therefore, this improves the obstacle avoidance accuracy of AGVs during transportation. Attached Figure Description

[0037] Figure 1 This is a flowchart illustrating the first embodiment of the obstacle avoidance method for AGV vehicles in this application.

[0038] Figure 2 This is a schematic diagram of the AGV vehicle lifting pallet in the first embodiment of the AGV vehicle transportation obstacle avoidance method of this application;

[0039] Figure 3 This is a top view of the AGV vehicle in the first embodiment of the obstacle avoidance method for transporting AGV vehicles according to this application;

[0040] Figure 4 This is a schematic diagram of the obstacle avoidance device for AGV vehicles in the third embodiment of the obstacle avoidance method for AGV vehicles in this application.

[0041] Figure 5 This is a schematic diagram of the equipment structure of the hardware operating environment involved in the fourth embodiment of the obstacle avoidance method for AGV vehicles in this application. Detailed Implementation

[0042] Exemplary embodiments will now be described in detail, examples of which are illustrated in the accompanying drawings. When the following description relates to the drawings, unless otherwise indicated, the same numbers in different drawings denote the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this application. Rather, they are merely examples of apparatuses and methods consistent with some aspects of this application as detailed in the appended claims.

[0043] It should be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element. Furthermore, components, features, and elements with the same names in different embodiments of this application may have the same meaning or different meanings, the specific meaning of which must be determined by its interpretation in that specific embodiment or further in conjunction with the context of that specific embodiment.

[0044] It should be understood that although the terms first, second, third, etc., may be used herein to describe various information, such information should not be limited to these terms. These terms are used only to distinguish information of the same type from one another. For example, without departing from the scope of this document, first information may also be referred to as second information, and similarly, second information may also be referred to as first information. Depending on the context, the word "if," as used herein, may be interpreted as "when," "when," or "in response to determination." Furthermore, as used herein, the singular forms "a," "an," and "the" are intended to also include the plural forms unless the context indicates otherwise. It should be further understood that the terms "comprising," "including," indicate the presence of the stated feature, step, operation, element, component, item, kind, and / or group, but do not exclude the presence, occurrence, or addition of one or more other features, steps, operations, elements, components, items, kinds, and / or groups. The terms "or," "and / or," "including at least one of the following," etc., as used in this application, may be interpreted as inclusive, or mean any one or any combination thereof. For example, "including at least one of the following: A, B, C" means "any one of the following: A; B; C; A and B; A and C; B and C; A and B and C." Similarly, "A, B, or C" or "A, B, and / or C" means "any one of the following: A; B; C; A and B; A and C; B and C; A and B and C." Exceptions to this definition only occur when the combination of elements, functions, steps, or operations is inherently mutually exclusive in some way.

[0045] It should be understood that although the steps in the flowcharts of this application's embodiments are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some of the steps in the figures may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily completed at the same time, but can be executed at different times, and their execution order is not necessarily sequential, but can be performed alternately or in turn with other steps or at least a portion of the sub-steps or stages of other steps.

[0046] Depending on the context, the words “if” or “suppose” as used here can be interpreted as “when” or “in response to determination” or “in response to detection.” Similarly, depending on the context, the phrases “if determination” or “if detection (of the stated condition or event)” can be interpreted as “when determination” or “in response to determination” or “when detection (of the stated condition or event)” or “in response to detection (of the stated condition or event).”

[0047] It should be noted that step designations such as S10 and S20 are used in this document for the purpose of more clearly and concisely describing the corresponding content, and do not constitute a substantial limitation on the order. In specific implementation, those skilled in the art may execute S20 first and then S10, etc., but these should all be within the protection scope of this application.

[0048] It should be understood that the specific embodiments described herein are merely illustrative of this application and are not intended to limit this application.

[0049] In the following description, the use of suffixes such as "module," "part," or "unit" to denote elements is solely for the purpose of illustration and has no specific meaning in itself. Therefore, "module," "part," or "unit" may be used interchangeably.

[0050] To make the above-mentioned objects, features, and advantages of the present invention more apparent and understandable, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0051] Example 1

[0052] This application provides a method for obstacle avoidance in the transportation of AGV vehicles. In the first embodiment of this method, referring to... Figure 1 An AGV (Automated Guided Vehicle) obstacle avoidance device is used in an AGV transportation obstacle avoidance system. The AGV transportation obstacle avoidance system also includes an AGV, a lifting mechanism, a pallet, and obstacles. The AGV transportation obstacle avoidance device is equipped with a lidar sensor. The AGV is used to transport goods. The pallet includes pallet legs and is lifted by the lifting mechanism. The AGV transportation obstacle avoidance method includes:

[0053] Step S10: When transporting based on a preset path, obtain point cloud coordinates, wherein the point cloud coordinates are obtained by the laser radar scanning the pallet legs, and the point cloud coordinates are in a coordinate system with the center of the AGV vehicle as the origin.

[0054] Step S20: Based on the point cloud coordinates, match from a preset tray pose set to obtain the estimated pose;

[0055] Step S30: Based on the estimated pose, determine the target point cloud coordinates from the point cloud coordinates;

[0056] Step S40: Obstacle avoidance is performed based on the target point cloud coordinates.

[0057] In this embodiment, the application scenario is:

[0058] AGV vehicles need to distinguish between pallet legs and obstacles. When distinguishing between pallet legs and obstacles, the AGV trains a model by clustering the scanned point clouds to differentiate between the pallet leg point clouds and obstacle point clouds. However, since the model is trained based on previously scanned point clouds to differentiate between subsequently scanned point clouds, there is a time delay, making real-time differentiation impossible. Therefore, obstacle avoidance based on the pallet leg point clouds results in low accuracy. In other words, existing technologies suffer from low obstacle avoidance accuracy when AGV vehicles are transporting goods.

[0059] This embodiment aims to improve the obstacle avoidance accuracy of AGV vehicles during transportation, enabling them to avoid obstacles in their surrounding environment.

[0060] In this embodiment, the obstacle avoidance method for AGV vehicles is applied to the obstacle avoidance device of the AGV vehicle in the obstacle avoidance system of the AGV vehicle. The obstacle avoidance system of the AGV vehicle also includes the AGV vehicle, the lifting mechanism, the pallet, and the obstacle. The obstacle avoidance device of the AGV vehicle is equipped with a lidar. The AGV vehicle is used to transport goods. The pallet includes pallet legs. The pallet is lifted by the lifting mechanism to achieve unloading.

[0061] As an example, such as Figure 2 This is a schematic diagram of an AGV vehicle lifting a pallet, including the AGV vehicle, the lifting mechanism, and the pallet.

[0062] The specific steps are as follows:

[0063] Step S10: When transporting based on a preset path, obtain point cloud coordinates, wherein the point cloud coordinates are obtained by the laser radar scanning the pallet legs, and the point cloud coordinates are in a coordinate system with the center of the AGV vehicle as the origin.

[0064] In this embodiment, the preset path is the path that the AGV vehicle needs to take when transporting goods. It can be a fixed path or a non-fixed path. As an example, the preset path is a fixed path.

[0065] As an example, AGV vehicles are AMR vehicles.

[0066] In this embodiment, the lidar scans the pallet legs to obtain a series of point cloud coordinates. Among these point cloud coordinates, some are the actual point clouds of the pallet legs, and some are the point clouds of obstacles outside the pallet legs. Therefore, it is necessary to distinguish between these two parts of the point cloud, that is, to determine the target point cloud coordinates (the point cloud coordinates of the pallet legs) from the point cloud coordinates.

[0067] In this embodiment, when transporting based on a preset path, point cloud coordinates are obtained. The point cloud coordinates are obtained by scanning the pallet legs with the lidar, and the point cloud coordinates are in a coordinate system with the center of the AGV vehicle as the origin.

[0068] Step S20: Based on the point cloud coordinates, match from a preset tray pose set to obtain the estimated pose;

[0069] As an example, such as Figure 3 This is a top-down view of the AGV vehicle, including the AGV vehicle, the pallet, the AGV center, and the pallet center. At the start of transport, the AGV vehicle's center coincides with the pallet center, but due to shaking or other reasons during actual transport, the two centers shift. Figure 3 If the center of the vehicle body and the center of the tray do not coincide, the coordinates of the point cloud obtained by scanning will be inaccurate, the obtained target point cloud will be too far from the real point cloud, and the obstacle avoidance accuracy will be low.

[0070] Therefore, a preset error range is determined near the center of the vehicle body. In this embodiment, the error range is the range within a preset error radius from the center of the AGV vehicle. The error range is the area where the pallet center may deviate. The error range includes a first number of candidate pallet centers. As an example, the first number is 100. Thus, 100 possible offset positions of the pallet center are set for the center of the vehicle body. These 100 offset pallet centers are the 100 candidate pallet centers. Each of the 100 candidate pallet centers corresponds to a pallet pose. The multiple pallet poses corresponding to all the candidate pallet centers constitute the pallet pose set. The 100 pallet centers are numbered from 1 to 100, thus obtaining poses 1 to 100.

[0071] Step S20, which involves matching the estimated pose from a preset tray pose set based on the point cloud coordinates, includes:

[0072] Step S21: Determine a preset error range, wherein the error range is the range of the distance from the center of the AGV vehicle to a preset error radius, the error range includes a first number of candidate pallet centers, each candidate pallet center corresponds to a pallet pose, and the multiple pallet poses corresponding to all candidate pallet centers constitute the pallet pose set.

[0073] Step S22: Filter the point cloud coordinates to obtain a first point cloud with the number of points equal to the first quantity, wherein the point cloud coordinates corresponding to the center of each candidate pallet center are retained within the range of the center of the pallet leg that is a preset pallet leg radius.

[0074] As an example, a preset error range is determined near the center of the vehicle body, and the error range contains 100 candidate pallet centers, corresponding to 100 possible positions of the pallet on the AGV vehicle.

[0075] As an example, the point cloud coordinates obtained from the scan are filtered to obtain 100 first point clouds.

[0076] As an example, with the radius of the pallet legs being x, taking pose number 1 as an example, in pose 1, multiple pallet legs correspond to pallet leg centers. Based on the pallet's geometry, the point cloud coordinates within the vicinity of the pallet leg center are retained, while those outside this vicinity are deleted. The vicinity is a circular area with a radius equal to the pallet leg radius. Based on this, the point cloud coordinates of all legs in pose 1 can be obtained, i.e., the first point cloud, which contains the first number of point cloud coordinates. The point cloud selection method for poses 2 through 100 is the same as that for pose 1.

[0077] As an example, in pose 1, the first number of point cloud coordinates is 100, and in pose 2, the first number of point cloud coordinates is 150.

[0078] Step S23: Based on the number of point cloud coordinates carried in the first point cloud, the estimated pose is obtained by matching from the tray pose set within the error range.

[0079] In this embodiment, the number of point cloud coordinates carried in the first point cloud is the first quantity. If 150 point cloud coordinates are obtained under pose 2, then the first quantity of pose 2 is 150.

[0080] In this embodiment, the estimated pose is obtained by matching the tray pose set within the error range based on the number of point cloud coordinates carried in the first point cloud, i.e., the first number.

[0081] Step S23, which involves matching the estimated pose from the tray pose set within the error range based on the number of point cloud coordinates carried in the first point cloud, includes:

[0082] Step A1: Based on the number of point cloud coordinates carried in the first point cloud, sort the first point clouds of the first quantity in descending order of the number of point cloud coordinates carried to obtain the arrangement order of the first point clouds.

[0083] Step A2: Based on the arrangement order, match the tray pose set within the error range to obtain the estimated pose, wherein the pose corresponding to the first point cloud located in the first position in the arrangement order is determined as the estimated pose.

[0084] As an example, point cloud coordinates with a first quantity of 100 are obtained from pose 1, point cloud coordinates with a first quantity of 150 are obtained from pose 2, and point cloud coordinates with a first quantity of 100 are obtained from poses 3 to 100. The first point clouds from these 100 poses are then sorted according to their first quantity, in descending order of the first quantity (from most to least number of point cloud coordinates). The resulting order of the first point clouds is as follows: pose 2 has a first quantity of 150, while the other poses have a first quantity of 100. Therefore, pose 2 has the most point cloud coordinates, and its order is first. Matching pose 2 among the 100 poses yields the estimated pose.

[0085] Step S30: Based on the estimated pose, determine the target point cloud coordinates from the point cloud coordinates;

[0086] In this embodiment, the target point cloud coordinates are determined from the point cloud coordinates of the estimated pose 2.

[0087] Step S40: Obstacle avoidance is performed based on the target point cloud coordinates.

[0088] In this embodiment, obstacle avoidance is performed based on the target point cloud coordinates.

[0089] This application provides a method, apparatus, device, and storage medium for obstacle avoidance in AGV (Automated Guided Vehicle) transportation. Compared with the prior art, where AGVs have low obstacle avoidance accuracy in their surrounding environment during transportation, this application acquires point cloud coordinates during transportation based on a preset path. These point cloud coordinates are obtained by scanning the pallet legs with a lidar, and are in a coordinate system with the AGV center as the origin. Based on these point cloud coordinates, an estimated pose is obtained by matching from a preset pallet pose set. Based on the estimated pose, the target point cloud coordinates are determined from the point cloud coordinates. In this application, after scanning the point cloud coordinates of the pallet legs, the current pose of the pallet on the AGV is obtained by matching these coordinates, and the point cloud coordinates of the pallet legs are determined based on the current pose. The current pose can be quickly derived from the scanned point cloud coordinates, enhancing real-time performance and avoiding the latency problem of distinguishing leg point clouds only after training a model. Therefore, this improves the obstacle avoidance accuracy of AGVs during transportation.

[0090] Example 2

[0091] Furthermore, based on Embodiment 1 of this application, another embodiment of this application is provided. In this embodiment, the first VR device is further configured with a third monitoring element. After step S30, which determines the target point cloud coordinates from the point cloud coordinates based on the estimated pose, the following steps S31-S32 are included:

[0092] Step S31: Obtain the geometric dimensions of the pallet;

[0093] In this embodiment, the geometric dimensions of the pallet are related to the shape of the pallet. As an example, if the pallet is a circular pallet, then the geometric dimension of the pallet is the radius of the circular pallet. As an example, if the pallet is a square pallet, then the geometric dimension of the pallet is the side length of the square pallet.

[0094] Step S32: Determine the estimated size of the pallet based on the target point cloud coordinates;

[0095] In this embodiment, the estimated size of the pallet can be calculated based on the target point cloud coordinates.

[0096] Wherein, the tray is a rectangular tray, and the tray's geometric dimensions include the tray's length and width. Step S32, the step of determining the estimated size of the tray based on the target point cloud coordinates, includes:

[0097] Based on the target point cloud coordinates, the estimated size of the pallet is determined, which includes the estimated length and the estimated width of the pallet.

[0098] As an example, if the pallet is a rectangular pallet, the dimensions of the rectangular pallet include the length and the width of the pallet. Correspondingly, when estimating the estimated dimensions of the pallet based on the target point cloud coordinates, the estimated length and the estimated width of the pallet are also obtained.

[0099] In this embodiment, the center coordinates of the pallet legs can be determined based on the target point cloud coordinates. As an example, a rectangular pallet has four pallet legs. The distance between the two center coordinates is calculated based on the center coordinates of the two legs in the width direction of the pallet. The distance is the estimated width of the pallet. Similarly, the estimated length of the pallet can be obtained.

[0100] Step S33: If it is determined that the estimated size of the pallet is not equal to the geometric size of the pallet, then the target point cloud coordinates are updated to obtain the updated target point cloud coordinates.

[0101] As an example, if the estimated width of the pallet is not equal to the estimated width of the pallet, or the estimated length of the pallet is not equal to the estimated length of the pallet, the target point cloud coordinates are updated to obtain the updated target point cloud coordinates.

[0102] In this embodiment, the estimated pallet size is compared with the actual geometric size. Based on the comparison result, it is determined whether to update the target point cloud coordinates. If the two are not equal, an update is performed to avoid the obtained target point cloud coordinates deviating from the actual target point cloud coordinates. The updated target point cloud coordinates improve the accuracy of obstacle recognition, that is, improve the obstacle avoidance accuracy of AGV vehicles when avoiding obstacles in the surrounding environment.

[0103] Example 3

[0104] Furthermore, based on all the above embodiments, another embodiment of this application is provided, in which, as... Figure 4 A transportation obstacle avoidance device for AGV vehicles is provided, the device comprising:

[0105] The acquisition module is used to acquire point cloud coordinates when transporting based on a preset path. The point cloud coordinates are obtained by the lidar scanning the pallet legs and are in a coordinate system with the center of the AGV vehicle as the origin.

[0106] The matching module is used to match the point cloud coordinates from a preset tray pose set to obtain the estimated pose.

[0107] The determination module is used to determine the target point cloud coordinates from the point cloud coordinates based on the estimated pose;

[0108] The obstacle avoidance module is used to perform obstacle avoidance based on the target point cloud coordinates.

[0109] In one possible implementation of this application, the device for the step of obtaining the estimated pose by matching from a preset tray pose set based on the point cloud coordinates includes:

[0110] The first determining module is used to determine a preset error range, wherein the error range is the range of the distance from the center of the AGV vehicle to a preset error radius, the error range includes a first number of candidate pallet centers, each candidate pallet center corresponds to a pallet pose, and the multiple pallet poses corresponding to all candidate pallet centers constitute the pallet pose set.

[0111] The filtering module is used to filter the point cloud coordinates to obtain a first point cloud with the number of points equal to the first quantity, wherein the point cloud coordinates corresponding to the center of the pallet leg of each candidate pallet are retained within a preset pallet leg radius.

[0112] The first matching module is used to match the estimated pose from the tray pose set within the error range based on the number of point cloud coordinates carried in the first point cloud.

[0113] In one possible implementation of this application, the apparatus for obtaining the estimated pose by matching from the tray pose set within the error range based on the number of point cloud coordinates carried in the first point cloud includes:

[0114] The sorting module is used to sort the first number of first point clouds according to the number of point cloud coordinates carried in the first point cloud in descending order, so as to obtain the arrangement order of the first point clouds.

[0115] The second matching module is used to match the tray pose set within the error range based on the arrangement order to obtain an estimated pose, wherein the pose corresponding to the first point cloud located in the first position of the arrangement order is determined as the estimated pose.

[0116] In one possible implementation of this application, after the step of determining the target point cloud coordinates from the point cloud coordinates based on the estimated pose, the apparatus includes:

[0117] The first acquisition module is used to acquire the geometric dimensions of the pallet;

[0118] The second determining module is used to determine the estimated size of the pallet based on the target point cloud coordinates;

[0119] The first update module is used to update the target point cloud coordinates if it is determined that the estimated size of the pallet is not equal to the geometric size of the pallet, so as to obtain the updated target point cloud coordinates.

[0120] In one possible implementation of this application, the device for updating the target point cloud coordinates to obtain updated target point cloud coordinates if it is determined that the estimated size of the pallet is not equal to the geometric size of the pallet includes:

[0121] The calculation module is used to calculate the sum of the residuals between the point cloud coordinates and the target point cloud if it is determined that the estimated size of the pallet is not equal to the geometric size of the pallet;

[0122] The third determination module is used to determine the minimum residual and the corresponding target point cloud coordinates, which are then used to determine the new target point cloud coordinates.

[0123] The second update module is used to update the target point cloud coordinates based on the new target point cloud coordinates to obtain the updated target point cloud coordinates.

[0124] In one possible embodiment of this application, the tray is a rectangular tray, and the tray's geometric dimensions include the tray's length and width. The device for determining the estimated tray size based on the target point cloud coordinates includes:

[0125] The fourth determining module is used to determine the estimated size of the pallet based on the target point cloud coordinates. The estimated size of the pallet includes the estimated length and the estimated width of the pallet.

[0126] In one possible implementation of this application, the AGV vehicle is an AMR vehicle.

[0127] The specific implementation method of the obstacle avoidance device for AGV vehicles in this application is basically the same as the various embodiments of the obstacle avoidance method for AGV vehicles described above, and will not be repeated here.

[0128] Example 4

[0129] Furthermore, based on all the above embodiments, another embodiment of this application is provided. In this embodiment, a transportation obstacle avoidance device for AGV vehicles is provided. The transportation obstacle avoidance device for AGV vehicles is a physical node device. The transportation obstacle avoidance device for AGV vehicles includes: a memory, a processor, and a program stored in the memory for implementing the transportation obstacle avoidance method for AGV vehicles. The memory is used to store the program for implementing the transportation obstacle avoidance method for AGV vehicles; the processor is used to execute the program for implementing the transportation obstacle avoidance method for AGV vehicles to implement the steps of the transportation obstacle avoidance method for AGV vehicles in the above embodiments.

[0130] Reference Figure 5 , Figure 5 This is a schematic diagram of the device structure of the hardware operating environment involved in the embodiments of this application.

[0131] like Figure 5 As shown, the obstacle avoidance device for the AGV vehicle may include: a processor 1001, such as a CPU, a memory 1005, and a communication bus 1002. The communication bus 1002 is used to establish communication between the processor 1001 and the memory 1005. The memory 1005 may be a high-speed RAM or a stable, non-volatile memory, such as a disk drive. Optionally, the memory 1005 may also be a storage device independent of the aforementioned processor 1001.

[0132] In one possible embodiment of this application, the obstacle avoidance device of the AGV vehicle may further include a network interface, audio circuit, display, connecting cable, sensor, input module, etc. The network interface may optionally include a standard wired interface or a wireless interface (such as a WI-FI interface or a Bluetooth interface), and the input module may optionally include a keyboard, a system soft keyboard, voice input, wireless receiver input, etc.

[0133] Those skilled in the art will understand that the structure of the obstacle avoidance device for AGV vehicles does not constitute a limitation on the obstacle avoidance device for AGV vehicles, and may include more or fewer components than shown in the figure, or combine certain components, or have different component arrangements.

[0134] A memory, as a computer storage medium, may include an operating system, an information exchange module, and the obstacle avoidance program for the AGV vehicle. The operating system is a program that manages and controls the hardware and software resources of the AGV vehicle's obstacle avoidance equipment, supporting the operation of the AGV vehicle's obstacle avoidance program and other software and / or programs. The information exchange module is used to enable communication between the various components within the memory, as well as communication with other hardware and software in the management system.

[0135] In the obstacle avoidance device for AGV vehicles, the processor is used to execute the obstacle avoidance program for AGV vehicles stored in the memory, and to implement the above-mentioned obstacle avoidance steps for AGV vehicles.

[0136] The specific implementation method of the obstacle avoidance device for AGV vehicles in this application is basically the same as the various embodiments of the obstacle avoidance method for AGV vehicles described above, and will not be repeated here.

[0137] Example 5

[0138] This application provides a storage medium that stores one or more programs, which can be executed by one or more processors to implement the steps of the AGV vehicle obstacle avoidance method described in the above embodiments.

[0139] The specific implementation of the storage medium in this application is basically the same as the various embodiments of the AGV vehicle transportation obstacle avoidance method described above, and will not be repeated here.

[0140] It should be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or system that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or system. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or system that includes that element.

[0141] The sequence numbers of the embodiments in this application are for descriptive purposes only and do not represent the superiority or inferiority of the embodiments.

[0142] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods of the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as ROM or RAM, magnetic disk, optical disk) as described above, and includes several instructions to cause a terminal device (which may be a mobile phone, computer, server, air conditioner, or network device, etc.) to execute the methods described in the various embodiments of this application.

[0143] The above are merely preferred embodiments of this application and do not limit the patent scope of this application. Any equivalent structural or procedural transformations made using the content of this application's specification and drawings, or direct or indirect applications in other related technical fields, are similarly included within the patent protection scope of this application.

Claims

1. A method for obstacle avoidance during transport by an AGV vehicle, characterized in that, An AGV (Automated Guided Vehicle) obstacle avoidance system is provided, comprising an AGV vehicle, a lifting mechanism, a pallet, and obstacles. The obstacle avoidance device is equipped with a lidar sensor. The AGV is used to transport goods. The pallet includes pallet legs and is lifted by the lifting mechanism. The obstacle avoidance method for the AGV includes: When transporting goods based on a preset path, point cloud coordinates are obtained, wherein the point cloud coordinates are obtained by the LiDAR scanning the pallet legs, and the point cloud coordinates are in a coordinate system with the center of the AGV vehicle as the origin. Based on the point cloud coordinates, the estimated pose is obtained by matching from a preset tray pose set; Based on the estimated pose, the target point cloud coordinates are determined from the point cloud coordinates; Obstacle avoidance is performed based on the target point cloud coordinates; The step of obtaining the estimated pose by matching from a preset tray pose set based on the point cloud coordinates includes: A preset error range is determined, wherein the error range is the range of the distance from the center of the AGV vehicle to a preset error radius, the error range includes a first number of candidate pallet centers, each candidate pallet center corresponds to a pallet pose, and the multiple pallet poses corresponding to all candidate pallet centers constitute the pallet pose set. The point cloud coordinates are filtered to obtain a first point cloud with the number of the first quantity, wherein the point cloud coordinates within the range of the center of the pallet leg corresponding to the center of each candidate pallet center are retained; Based on the number of point cloud coordinates carried in the first point cloud, the estimated pose is obtained by matching from the tray pose set within the error range.

2. The obstacle avoidance method for AGV vehicles according to claim 1, characterized in that, The step of obtaining an estimated pose by matching the tray pose set within the error range based on the number of point cloud coordinates carried in the first point cloud includes: Based on the number of point cloud coordinates carried in the first point cloud, the first point clouds of the first quantity are sorted in descending order of the number of point cloud coordinates carried to obtain the arrangement order of the first point clouds. Based on the arrangement order, the estimated pose is obtained by matching the tray pose set within the error range, wherein the pose corresponding to the first point cloud located in the first position in the arrangement order is determined as the estimated pose.

3. The obstacle avoidance method for AGV vehicles according to claim 1, characterized in that, After the step of determining the target point cloud coordinates from the point cloud coordinates based on the estimated pose, the following steps are included: Obtain the geometric dimensions of the pallet; Based on the target point cloud coordinates, determine the estimated size of the pallet; If it is determined that the estimated size of the pallet is not equal to the geometric size of the pallet, the target point cloud coordinates are updated to obtain the updated target point cloud coordinates.

4. The obstacle avoidance method for AGV vehicles according to claim 3, characterized in that, The step of updating the target point cloud coordinates to obtain the updated target point cloud coordinates if it is determined that the estimated size of the pallet is not equal to the geometric size of the pallet includes: If it is determined that the estimated size of the pallet is not equal to the geometric size of the pallet, then calculate the sum of the residuals between the point cloud coordinates and the target point cloud; Determine the minimum residual and the corresponding target point cloud coordinates as the new target point cloud coordinates; Based on the new target point cloud coordinates, the target point cloud coordinates are updated to obtain the updated target point cloud coordinates.

5. The obstacle avoidance method for AGV vehicles according to claim 3, characterized in that, The tray is a rectangular tray, and the tray's geometric dimensions include its length and width. The step of determining the estimated size of the tray based on the target point cloud coordinates includes: Based on the target point cloud coordinates, the estimated size of the pallet is determined, which includes the estimated length and the estimated width of the pallet.

6. The obstacle avoidance method for AGV vehicles according to claim 1, characterized in that, The AGV vehicle is an AMR vehicle.

7. A transport obstacle avoidance device for AGV vehicles, characterized in that, The obstacle avoidance device for AGV vehicles includes: The acquisition module is used to acquire point cloud coordinates when transporting based on a preset path. The point cloud coordinates are obtained by scanning the pallet legs with a lidar and are in a coordinate system with the center of the AGV vehicle as the origin. The matching module is used to match the point cloud coordinates from a preset tray pose set to obtain the estimated pose. The determination module is used to determine the target point cloud coordinates from the point cloud coordinates based on the estimated pose; An obstacle avoidance module is used to avoid obstacles based on the target point cloud coordinates; The matching module is used to achieve: A preset error range is determined, wherein the error range is the range of the distance from the center of the AGV vehicle to a preset error radius, the error range includes a first number of candidate pallet centers, each candidate pallet center corresponds to a pallet pose, and the multiple pallet poses corresponding to all candidate pallet centers constitute the pallet pose set. The point cloud coordinates are filtered to obtain a first point cloud with the number of the first quantity, wherein the point cloud coordinates within the range of the center of the pallet leg corresponding to the center of each candidate pallet center are retained; Based on the number of point cloud coordinates carried in the first point cloud, the estimated pose is obtained by matching from the tray pose set within the error range.

8. A transport obstacle avoidance device for AGV vehicles, characterized in that, The method includes a memory, a processor, and an AGV vehicle transport obstacle avoidance program stored in the memory and executable on the processor. The processor executes the AGV vehicle transport obstacle avoidance program to implement the steps of the AGV vehicle transport obstacle avoidance method according to any one of claims 1 to 6.

9. A storage medium, characterized in that, The storage medium stores a program for implementing a method for obstacle avoidance in the transportation of AGV vehicles. The program for implementing the method for obstacle avoidance in the transportation of AGV vehicles is executed by a processor to implement the steps of the method for obstacle avoidance in the transportation of AGV vehicles as described in any one of claims 1 to 6.

Images