AGV Navigation Method, Device, Equipment, Medium and Program Product

Abstract

The present application provides an AGV navigation method, device, equipment, medium and program product. The method includes: obtaining real-time visual data and target position data, where the real-time visual data represents the real-time environment where the AGV is located, and the target position data represents the destination position of the AGV; positioning the AGV according to the real-time visual data and a preset positioning algorithm to obtain the first real-time position information of the AGV; evaluating the performance of the preset positioning algorithm according to the first real-time position information to obtain a position evaluation result, where the position evaluation result represents the closed-loop detection ability of the preset positioning algorithm; correcting the first real-time position information according to the position evaluation result to obtain second real-time position data, where the second real-time position data represents the real-time position of the AGV; generating real-time navigation information according to the target position data and the second real-time position data, and the real-time navigation information is used to control the AGV to travel from the second real-time position to the destination position.

Description

Technical Field

[0001] The present application relates to the technical field of indoor navigation, and in particular, to an AGV navigation method, device, equipment, medium, and program product. Background Art

[0002] In the process of navigation and positioning of an Automated Guided Vehicle (AGV), the Simultaneous Localization and Mapping (SLAM) algorithm is widely used to determine the real-time position of the vehicle. This algorithm collects environmental information through sensors and combines the existing map data to estimate the position and attitude of the AGV, thereby achieving autonomous navigation.

[0003] However, in environments with highly consistent structures such as warehouses and production workshops, due to the lack of significant features in the surrounding environment, it is difficult for the SLAM algorithm based on visual or other sensor inputs to provide accurate position information, and it may even generate multiple seemingly reasonable but actually incorrect position solutions. The position coordinates output by the SLAM algorithm may have a large error, affecting the path planning and navigation accuracy of the AGV, and further increasing the risk of reduced operation efficiency or task failure.

[0004] Therefore, how to perform more accurate path planning for the Automated Guided Vehicle is a technical problem that needs to be solved urgently by those skilled in the art. Summary of the Invention

[0005] The present application provides an AGV navigation method, device, equipment, medium, and program product to solve the technical problem of inaccurate path planning.

[0006] In a first aspect, the present application provides an AGV navigation method, including:

[0007] Obtain real-time visual data and target position data, where the real-time visual data represents the real-time environment where the AGV is located, and the target position data represents the destination position of the AGV;

[0008] Locate the AGV according to the real-time visual data and a preset positioning algorithm to obtain the first real-time position information of the AGV;

[0009] Evaluate the performance of the preset positioning algorithm according to the first real-time position information to obtain a position evaluation result, where the position evaluation result represents the closed-loop detection ability of the preset positioning algorithm;

[0010] Correct the first real-time position information according to the position evaluation result to obtain second real-time position data, where the second real-time position data represents the real-time position of the AGV;

[0011] Generate real-time navigation information based on the target position data and the second real-time position data, where the real-time navigation information is used to control the AGV to travel from the second real-time position to the destination position.

[0012] Optionally, the correcting the first real-time position information according to the position evaluation result to obtain second real-time position data includes:

[0013] When the position evaluation result is unqualified, determine the target visual feature corresponding to the first real-time position information from the pre-stored visual features, where the pre-stored visual features can be obtained based on map data;

[0014] For each of the first real-time position information, perform feature comparison based on the target visual feature corresponding to the first real-time position information and the real-time visual data to obtain a feature comparison result corresponding to the first real-time position information, where the feature comparison result indicates whether the real-time visual data contains the target visual feature;

[0015] Screen the first real-time position information according to multiple feature comparison results to obtain second real-time position data.

[0016] Optionally, the real-time visual data includes multiple key frames updated in real time;

[0017] The performing feature comparison based on the target visual feature corresponding to the first real-time position information and the real-time visual data to obtain a feature comparison result corresponding to the first real-time position information includes:

[0018] When a new key frame is detected in the real-time visual data, determine the neighbor key frames corresponding to the new key frame according to the pre-stored visual features and map data, where the neighbor key frames are the key frames directly connected to the new key frame among the multiple key frames;

[0019] Obtain two target key frames based on the new key frame and multiple neighbor key frames, where the target key frames are the two neighbor key frames most similar to the new key frame;

[0020] Obtain a feature comparison result based on the target visual feature corresponding to the first real-time position information and the new key frame and its corresponding two target key frames.

[0021] Optionally, after determining the neighbor key frames corresponding to the new key frame according to the pre-stored visual features and map data, the method further includes:

[0022] Judge whether the neighbor key frames meet the key frame quantity threshold;

[0023] Otherwise, obtain the previous key frame corresponding to the new key frame, and query the second position data corresponding to the previous key frame, where the second position data is the second real-time position data corresponding to the previous key frame;

[0024] Obtain the steering angle corresponding to the new key frame, and determine a substitute key frame in the map data according to the second position data and the steering angle, where the substitute key frame represents the missing visual data between the previous key frame and the new key frame;

[0025] Update the neighbor key frame based on the substitute key frame to obtain a new neighbor key frame.

[0026] Optionally, the generating real-time navigation information according to the target position data and the second real-time position data includes:

[0027] Obtain the environmental type where the AGV is located;

[0028] Determine a target planning algorithm in the path planning algorithm according to the environmental type;

[0029] Input the target position data and the second real-time position data into the target planning algorithm to obtain real-time navigation information.

[0030] Optionally, after the generating real-time navigation information according to the target position data and the second real-time position data, the method further includes:

[0031] Obtain real-time road condition features according to the real-time visual data;

[0032] Perform speed planning on the real-time navigation information according to the real-time road condition features to obtain real-time navigation information including speed setting.

[0033] In a second aspect, the present application provides an AGV navigation device, including:

[0034] An acquisition module, configured to acquire real-time visual data and target position data, where the real-time visual data represents the real-time environment where the AGV is located, and the target position data represents the destination position of the AGV;

[0035] A positioning module, configured to position the AGV according to the real-time visual data and a preset positioning algorithm to obtain the first real-time position information of the AGV;

[0036] An evaluation module, configured to evaluate the performance of the preset positioning algorithm according to the first real-time position information to obtain a position evaluation result, where the position evaluation result represents the closed-loop detection ability of the preset positioning algorithm;

[0037] A correction module, configured to correct the first real-time position information according to the position evaluation result to obtain second real-time position data, where the second real-time position data represents the real-time position of the AGV;

[0038] A generation module, configured to generate real-time navigation information according to the target position data and the second real-time position data, where the real-time navigation information is used to control the AGV to travel from the second real-time position to the destination position.

[0039] Optionally, when the correction module executes the correction of the first real-time position information according to the position evaluation result to obtain second real-time position data, it is configured to:

[0040] When the position evaluation result is unqualified, in the pre-stored visual features, determine the target visual feature corresponding to the first real-time position information, where the pre-stored visual features can be obtained based on map data;

[0041] For each first real-time position information, perform feature comparison according to the target visual feature corresponding to the first real-time position information and the real-time visual data to obtain a feature comparison result corresponding to the first real-time position information, where the feature comparison result represents whether the real-time visual data contains the target visual feature;

[0042] Filter the first real-time position information according to multiple feature comparison results to obtain second real-time position data.

[0043] For the correction module, the real-time visual data includes multiple key frames updated in real time. When performing the feature comparison according to the target visual feature corresponding to the first real-time position information and the real-time visual data to obtain a feature comparison result corresponding to the first real-time position information, it is configured to:

[0044] When a new key frame is detected in the real-time visual data, determine the neighbor key frames corresponding to the new key frame according to the pre-stored visual features and map data, where the neighbor key frames are the key frames directly connected to the new key frame among the multiple key frames;

[0045] Obtain two target key frames according to the new key frame and multiple neighbor key frames, where the target key frames are the two neighbor key frames most similar to the new key frame;

[0046] Obtain a feature comparison result according to the target visual feature corresponding to the first real-time position information and the new key frame and its corresponding two target key frames.

[0047] Optionally, the above device further includes a replacement module;

[0048] The backup module is used for:

[0049] Determine whether the neighbor key frame meets the key frame quantity threshold;

[0050] If not, obtain the previous key frame corresponding to the new key frame, and query the second position data corresponding to the previous key frame, where the second position data is the second real-time position data corresponding to the previous key frame;

[0051] Obtain the steering angle corresponding to the new key frame, and determine a backup key frame in the map data according to the second position data and the steering angle, where the backup key frame represents the missing visual data between the previous key frame and the new key frame;

[0052] Update the neighbor key frame based on the backup key frame to obtain a new neighbor key frame.

[0053] Optionally, when the above generation module executes the generation of the real-time navigation information according to the target position data and the second real-time position data, it is used for:

[0054] Obtain the environmental type where the AGV is located;

[0055] Determine a target path planning algorithm according to the environmental type in the path planning algorithm;

[0056] Input the target position data and the second real-time position data into the target path planning algorithm to obtain real-time navigation information.

[0057] Optionally, the above device further includes a constant speed module;

[0058] The constant speed module is used for:

[0059] Obtain real-time road condition features according to the real-time visual data;

[0060] Perform speed planning on the real-time navigation information according to the real-time road condition features to obtain real-time navigation information including speed setting.

[0061] In a third aspect, the present application provides an AGV device, including: a processor, and a memory communicatively connected to the processor;

[0062] The memory stores computer execution instructions;

[0063] The processor executes the computer execution instructions stored in the memory to implement the AGV navigation method according to any one of the first aspect.

[0064] Fourthly, the present application provides a computer-readable storage medium storing computer-executable instructions, which are used to implement the AGV navigation method according to any one of the first aspect when executed by a processor.

[0065] Fifthly, the present application provides a computer program product including a computer program, which implements the AGV navigation method according to any one of the first aspect when executed by a processor.

[0066] The AGV navigation method provided by the present application determines the location and destination of the AGV by acquiring real-time visual data and target location data; locates the AGV according to the real-time visual data and a preset positioning algorithm to obtain the first real-time position information of the AGV; evaluates the performance of the preset positioning algorithm according to the first real-time position information to obtain a position evaluation result, where the position evaluation result characterizes the closed-loop detection ability of the preset positioning algorithm; when the first real-time position information is not unique, it proves that there is an error. At this time, the wrong position is screened by comparing with an existing map to ensure the positioning accuracy, thereby improving the navigation accuracy. BRIEF DESCRIPTION OF THE DRAWINGS

[0067] The accompanying drawings herein are incorporated into and constitute a part of this specification, showing embodiments consistent with the present application, and are used together with the specification to explain the principles of the present application.

[0068] Figure 1 It is a schematic flowchart of an AGV navigation method provided by an embodiment of the present application;

[0069] Figure 2 It is a schematic structural diagram of an AGV navigation device provided by an embodiment of the present application;

[0070] Figure 3 It is a schematic structural diagram of an AGV device provided by the present application.

[0071] Through the above accompanying drawings, specific embodiments of the present application have been shown, and there will be more detailed descriptions hereinafter. These drawings and the written description are not intended to limit the scope of the concept of the present application in any way, but to illustrate the concept of the present application to those skilled in the art by referring to specific embodiments. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0072] Here, the exemplary embodiments will be described in detail, and the examples are shown in the accompanying drawings. When the following description refers to the accompanying drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present application. On the contrary, they are merely examples of devices and methods consistent with some aspects of the present application as detailed in the appended claims.

[0073] During the navigation and positioning process of an Automated Guided Vehicle (AGV), the Simultaneous Localization and Mapping (SLAM) algorithm is widely used to determine the vehicle's real-time position. This algorithm collects environmental information through sensors and combines it with existing map data to estimate the position and orientation of the AGV, thereby achieving autonomous navigation.

[0074] However, in some special application scenarios, such as environments with highly consistent structures like warehouses and production workshops, the SLAM algorithm faces challenges in identifying the specific position of the AGV. Due to the lack of significant features in the surrounding environment, the SLAM algorithm based on visual or other sensor inputs is difficult to provide accurate position information and may even generate multiple seemingly reasonable but actually incorrect position solutions.

[0075] In the prior art, although the SLAM algorithm itself is quite mature, the problem of its limited performance under the above specific conditions has not been completely solved. When encountering extremely similar environments, the position coordinates output by the SLAM algorithm may have large errors, affecting the path planning and navigation accuracy of the AGV, and further increasing the risk of reduced operation efficiency or task failure.

[0076] Therefore, an improved method is needed to overcome this limitation and ensure high-precision positioning and navigation capabilities even in environments with unclear features. By introducing an additional map verification step, incorrect position solutions can be effectively filtered out when position uncertainty is detected, improving the overall system reliability and navigation accuracy. This method not only enhances the adaptability and flexibility of the AGV in complex environments but also provides technical support for a wider range of application scenarios.

[0077] An AGV navigation method provided by an embodiment of this application aims to solve the above technical problems in the prior art and is executed by a control component in the above AGV. Hereinafter, the AGV is simply referred to as the execution subject.

[0078] The following uses specific embodiments to elaborate in detail on the technical solutions of this application and how the technical solutions of this application solve the above technical problems. These several specific embodiments can be combined with each other, and the same or similar concepts or processes may not be repeated in some embodiments. The following will describe the embodiments of this application with reference to the accompanying drawings.

[0079] As Figure 1 shown, Figure 1 is a flowchart of an AGV navigation method provided by an embodiment of this application. As Figure 1As shown in the figure, an AGV navigation method may specifically include steps S201 to S204, where:

[0080] S201. Obtain real-time visual data and target position data.

[0081] The real-time visual data represents the real-time environment where the AGV is located, and the target position data represents the destination position of the AGV.

[0082] In the method of obtaining real-time visual data and target position data, first, at least one image acquisition device is configured on the automated guided vehicle (AGV). This device is used to continuously capture the visual information of the environment around the AGV, and the visual information accurately represents the actual situation of the environment where the AGV is located. Then, through a positioning system (such as GPS, indoor positioning system, etc.) or preset target coordinates, the destination position data of the AGV is determined and obtained. This position data accurately describes the target location that the AGV needs to reach. Then, the obtained real-time visual data and target position data are transmitted to the central processing unit of the AGV. Among them, the central processing unit processes and analyzes the received data for subsequent navigation decision-making.

[0083] S202. Locate the AGV according to the real-time visual data and a preset positioning algorithm to obtain the first real-time position information of the AGV.

[0084] In the process of determining the first real-time position information of the automated guided vehicle (AGV), first, the previously obtained real-time visual data is used to identify and extract the information of feature points or landmarks in the environment through image processing technology. Then, the information of these feature points or landmarks is compared and matched with the environmental map data pre-stored in the database to achieve preliminary positioning. Then, a preset positioning algorithm is applied, such as an algorithm based on the extended Kalman filter (EKF), particle filter, or other advanced SLAM (Simultaneous Localization and Mapping) technologies, to integrate the real-time data stream from the AGV sensors, including but not limited to the data from laser rangefinders and inertial measurement units (IMUs), to accurately calculate the exact position of the AGV in the current environment. Finally, this process outputs the first real-time position information of the AGV, providing an accurate basis for subsequent path planning and navigation decision-making.

[0085] S203. Evaluate the performance of the preset positioning algorithm according to the first real-time position information to obtain a position evaluation result.

[0086] The position evaluation result represents the closed-loop detection ability of the preset positioning algorithm.

[0087] In the process of evaluating the performance of the preset positioning algorithm, first, the first real-time position information of the AGV obtained previously is used as a reference. Then, the reference position is compared and analyzed with the AGV position information calculated by the positioning algorithm at the same time point, and the deviation degree between the two is calculated, including but not limited to statistical indicators such as average error, maximum error, and standard deviation of the error. Then, based on these quantitative analysis results of the standard deviation, combined with the requirements for positioning accuracy, stability, and response speed in the actual application scenario, the performance of the positioning algorithm is comprehensively evaluated. Finally, based on the above analysis and evaluation process, a detailed position evaluation result is formed.

[0088] S204. Correct the first real-time position information according to the position evaluation result to obtain the second real-time position data.

[0089] The second real-time position data represents the real-time position of the AGV.

[0090] After obtaining the position evaluation result, first analyze the first real-time position information to identify the deviation and error patterns therein. Based on this analysis, apply the corresponding correction algorithm or model to adjust the first real-time position information. This correction process may involve but is not limited to technical means such as coordinate transformation and error compensation to reduce the error generated by the previous positioning algorithm. Then, verify the matching degree between the corrected data and the actual position to ensure the effectiveness and accuracy of the correction. Finally, generate the second real-time position data, which more accurately reflects the actual position state of the AGV.

[0091] S205. Generate real-time navigation information according to the target position data and the second real-time position data.

[0092] The real-time navigation information is used to control the AGV to travel from the second real-time position to the destination position.

[0093] The AGV device first obtains the target position data and its own second real-time position data, and calculates the relative position and direction difference between the two through the built-in algorithm. Based on this information, the AGV performs path planning to determine an optimal travel route from the current real-time position to the target position, considering factors including but not limited to the shortest distance, obstacle avoidance, and compliance with traffic rules. Subsequently, according to the selected path, the AGV generates a series of control instructions, which precisely guide its speed adjustment, steering operation, and other necessary actions to ensure accurate progress along the predetermined trajectory. During the travel process, the AGV continuously updates its position information using sensors and adjusts the navigation instructions in real time to ensure efficient and safe arrival at the destination even in the face of dynamic environmental changes.

[0094] The AGV navigation method provided by the embodiment of this application determines the location and destination of the AGV by obtaining real-time visual data and target location data; locates the AGV according to the real-time visual data and a preset positioning algorithm to obtain the first real-time position information of the AGV; evaluates the performance of the preset positioning algorithm according to the first real-time position information to obtain a position evaluation result, and the position evaluation result characterizes the closed-loop detection ability of the preset positioning algorithm; when the first real-time position information is not unique, it proves that there is an error. At this time, the wrong position is screened by comparing with the existing map to ensure the positioning accuracy, thereby improving the navigation accuracy.

[0095] In an implementable manner, correcting the first real-time position information according to the position evaluation result to obtain second real-time position data includes:

[0096] When the position evaluation result is unqualified, in the pre-stored visual features, determine the target visual feature corresponding to the first real-time position information, and the pre-stored visual features can be obtained based on the map data.

[0097] Specifically, when the AGV device (i.e., AGV) evaluates that the accuracy of the current position does not reach the preset standard (there are multiple pieces of first real-time position information), the system will automatically identify that the position evaluation is unqualified. At this time, the AGV searches for the target visual feature matching the first real-time position information in the pre-stored visual feature library (i.e., pre-stored visual features) according to the built-in map data. This process involves comparing the currently captured visual information with the feature descriptions in the pre-stored data to find the closest corresponding item. These pre-stored visual features are pre-established based on the map data and contain detailed visual identifications of multiple possible position points, and the map data is a real-time map. Through this matching method, the AGV can accurately determine its relative position in the environment and use this information for necessary correction to restore to the expected navigation accuracy.

[0098] For each piece of first real-time position information, perform feature comparison according to the target visual feature corresponding to the first real-time position information and the real-time visual data to obtain a feature comparison result corresponding to the first real-time position information, where the feature comparison result characterizes whether the real-time visual data contains the target visual feature.

[0099] First, identify the corresponding target visual feature according to the first real-time position information. Then, use the currently obtained real-time visual data to make a detailed comparison with the previously determined target visual feature. This process involves analyzing and matching the elements in the real-time visual data with the pre-stored target visual feature to evaluate the consistency or similarity between the two. The finally obtained feature comparison result clearly indicates whether the real-time visual data contains the expected target visual feature, thereby verifying the positioning accuracy of the AGV device at a specific position.

[0100] Filter the first real-time position information based on multiple feature comparison results to obtain the second real-time position data.

[0101] Use the first real-time position information containing the target visual feature as the second real-time position data.

[0102] The AGV navigation method provided by the embodiments of this application determines the target visual feature corresponding to the first real-time position information among the pre-stored visual features when the position evaluation result is unqualified, so as to determine the pre-stored visual feature at the first real-time position in the map data; for each piece of the first real-time position information, determine whether the real-time visual data contains the target visual feature by comparing the target visual feature corresponding to the first real-time position information with the real-time visual data; filter the first real-time position information according to multiple feature comparison results to obtain the second real-time position data, thereby screening out the inconsistent first real-time position data by determining whether the real-time visual data matches the pre-stored visual feature, and obtaining the second real-time position data.

[0103] In one implementable manner, the real-time visual data includes multiple key frames updated in real time. Comparing the target visual feature corresponding to the first real-time position information with the real-time visual data to obtain the feature comparison result corresponding to the first real-time position information includes:

[0104] When a new key frame is detected in the real-time visual data, determine the neighbor key frame corresponding to the new key frame according to the pre-stored visual feature and the map data. The neighbor key frame is a key frame directly connected to the new key frame among multiple key frames.

[0105] Among them, key frames (Keyframe) are of great significance in animation production, video editing, and computer graphics. It refers to a specific frame used to define significant changes in the attributes of an object or scene on a sequence or timeline. The key frame technology allows creators to specify the start and end states, as well as any important state change points in between, and the software automatically calculates the transitions between these key frames (this process is usually called interpolation) to generate a smooth animation effect.

[0106] It can be understood that in the related technology, the neighbor key frames are directly connected. Among them, the direct connection in the related technology means that there is an overlapping point (the same reference object) between the two. However, when the AGV turns, if the camera is disconnected and returns to normal after the turn, and the field of view before and after the turn is a dead angle to each other, a key frame loss situation will occur at this time, and the neighbor key frame cannot be found in the real-time visual data.

[0107] Two target key frames are obtained according to the new key frame and multiple neighboring key frames, where the target key frames are the two neighboring key frames that are most similar to the new key frame.

[0108] Among them, there is a chronological relationship between the new key frame and the two target key frames, and the moment corresponding to the new key frame is located between the moments corresponding to the two target key frames respectively.

[0109] A feature comparison result is obtained according to the target visual feature corresponding to the first real-time position information, the new key frame and the two target key frames corresponding thereto.

[0110] Specifically, calculate the similarity scores of the target visual feature corresponding to the first real-time position information, the new key frame and the two target key frames corresponding thereto respectively, and then take the average value of these three similarity scores. If the above average value is greater than the preset average value, it indicates that the feature comparison result is qualified, otherwise it is unqualified.

[0111] In one implementable manner, after determining the neighboring key frames corresponding to the new key frame according to the pre-stored visual features and map data, the method further includes:

[0112] Determine whether the neighboring key frames meet the key frame quantity threshold.

[0113] If not, obtain the previous key frame corresponding to the new key frame, and query the second position data corresponding to the previous key frame, where the second position data is the second real-time position data corresponding to the previous key frame.

[0114] The acquisition moment of the previous key frame is adjacent to that of the new key frame.

[0115] Obtain the steering angle corresponding to the new key frame, and determine a substitute key frame in the map data according to the second position data and the steering angle, where the substitute key frame represents the missing visual data between the previous key frame and the new key frame.

[0116] The steering angle can be obtained based on the IMU module.

[0117] Specifically, among the preset visual features of the map data, determine the multiple preset visual features included in the position corresponding to the second position data, and the above multiple preset visual features correspond to different acquisition angles. Among them, in the preset visual feature preparation stage, the AGV uses a camera device and an IMU module to collect visual data including historical key frames. It should be noted that the historical key frames carry three tags: steering angle, position data, and visual features; in the historical key frames, determine the substitute key frame corresponding to the steering angle of the new key frame.

[0118] Update the neighboring key frames based on the substitute key frame to obtain new neighboring key frames.

[0119] Specifically, between the acquisition moments corresponding to the previous key frame and the new key frame respectively, determine the insertion moment for the substitute key frame; enter the insertion moment as a time tag into the substitute key frame; based on the insertion moment, add the substitute key frame as a new neighbor key frame to the original neighbor key frames to complete the update of the neighbor key frames.

[0120] The AGV navigation method provided by the embodiments of the present application maintains the stability of the indoor positioning process by supplementing the missing visual data between the previous key frame and the new key frame.

[0121] In an implementable manner, the above S205 generates real-time navigation information according to the target position data and the second real-time position data, which may specifically include:

[0122] Obtain the environmental type where the AGV is located. The environmental type is an indoor environment or an outdoor environment, which represents the static environment where the AGV device is located.

[0123] According to the environmental type, determine the target planning algorithm in the path planning algorithm, where the path planning algorithm includes the A* algorithm, Dijkstra, and RRT.

[0124] Input the target position data and the second real-time position data into the target planning algorithm to obtain real-time navigation information.

[0125] In an implementable manner, after the above S205 generates real-time navigation information according to the target position data and the second real-time position data, the method further includes:

[0126] Obtain real-time road condition features according to the real-time visual data, where the real-time road condition features represent the dynamic environment where the AGV device is located, such as moving objects such as pedestrians and vehicles.

[0127] Perform speed planning on the real-time navigation information according to the real-time road condition features to obtain real-time navigation information including speed settings.

[0128] It should be noted that for the foregoing method embodiments, for the sake of simple description, they are all expressed as a series of action combinations. However, those skilled in the art should know that the present application is not limited by the described action sequence, because according to the present application, certain steps can be performed in other sequences or simultaneously. Secondly, those skilled in the art should also know that the embodiments described in the specification are all optional embodiments, and the actions and modules involved are not necessarily essential to the present application.

[0129] It should be further noted that although the steps in the flowchart are sequentially displayed according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless otherwise clearly stated in this document, the execution of these steps has no strict order limit, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowchart may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily executed at the same time, but can be executed at different times. The execution order of these sub-steps or stages is not necessarily sequential, but can be executed alternately or in turn with at least a part of other steps or sub-steps or stages of other steps.

[0130] Figure 2 The following is a schematic structural diagram of an AGV navigation device provided by an embodiment of the present application, as Figure 2 shown, the AGV navigation device 40 provided by the embodiment of the present application includes:

[0131] An acquisition module 401, configured to acquire real-time visual data and target position data, where the real-time visual data represents the real-time environment where the AGV is located, and the target position data represents the destination position of the AGV;

[0132] A positioning module 402, configured to position the AGV according to the real-time visual data and a preset positioning algorithm to obtain the first real-time position information of the AGV;

[0133] An evaluation module 403, configured to evaluate the performance of the preset positioning algorithm according to the first real-time position information to obtain a position evaluation result, where the position evaluation result represents the closed-loop detection ability of the preset positioning algorithm;

[0134] A correction module 404, configured to correct the first real-time position information according to the position evaluation result to obtain second real-time position data, where the second real-time position data represents the real-time position of the AGV;

[0135] A generation module 405, configured to generate real-time navigation information according to the target position data and the second real-time position data, where the real-time navigation information is used to control the AGV to travel from the second real-time position to the destination position.

[0136] Optionally, when the correction module 404 executes the correction of the first real-time position information according to the position evaluation result to obtain the second real-time position data, it is configured to:

[0137] When the position evaluation result is unqualified, determine the target visual feature corresponding to the first real-time position information among the pre-stored visual features, and the pre-stored visual features can be obtained based on the map data;

[0138] For each piece of first real-time position information, perform feature comparison based on the target visual feature corresponding to the first real-time position information and the real-time visual data to obtain a feature comparison result corresponding to the first real-time position information, where the feature comparison result indicates whether the real-time visual data contains the target visual feature;

[0139] Screen the first real-time position information according to multiple feature comparison results to obtain second real-time position data.

[0140] For the above correction module 404, the real-time visual data includes multiple key frames that are updated in real time. When performing feature comparison based on the target visual feature corresponding to the first real-time position information and the real-time visual data to obtain a feature comparison result corresponding to the first real-time position information, it is used for:

[0141] When a new key frame is detected in the real-time visual data, determine the neighbor key frames corresponding to the new key frame according to the pre-stored visual features and map data, where the neighbor key frames are the key frames that have a direct connection with the new key frame among the multiple key frames;

[0142] Obtain two target key frames based on the new key frame and multiple neighbor key frames, where the target key frames are the two neighbor key frames that are most similar to the new key frame;

[0143] Obtain a feature comparison result according to the target visual feature corresponding to the first real-time position information and the new key frame and its corresponding two target key frames.

[0144] Optionally, the above AGV navigation device 40 further includes a substitute module;

[0145] The substitute module is used for:

[0146] Judge whether the neighbor key frames meet the key frame quantity threshold;

[0147] If not, obtain the previous key frame corresponding to the new key frame, and query the second position data corresponding to the previous key frame, where the second position data is the second real-time position data corresponding to the previous key frame;

[0148] Obtain the steering angle corresponding to the new key frame, and determine a substitute key frame in the map data according to the second position data and the steering angle, where the substitute key frame represents the lost visual data between the previous key frame and the new key frame;

[0149] Update the neighbor key frames based on the substitute key frame to obtain new neighbor key frames.

[0150] Optionally, when the above generation module 405 executes to generate real-time navigation information according to the target position data and the second real-time position data, it is used for:

[0151] Get the type of environment the AGV is in;

[0152] According to the type of environment, in the path planning algorithm, determine the target planning algorithm;

[0153] The target position data and the second real-time position data are input into the target planning algorithm to obtain real-time navigation information.

[0154] Optionally, the AGV navigation device 40 further includes a speed control module;

[0155] Fixed speed module for:

[0156] According to the real-time visual data, the real-time road condition characteristics are obtained;

[0157] Speed ​​planning is performed on the real-time navigation information according to the real-time road condition characteristics to obtain real-time navigation information including speed setting.

[0158] The AGV navigation device provided in this embodiment can execute the method provided in the above method embodiment, and its implementation principle and technical effect are similar, so this embodiment will not be described in detail here.

[0159] It should be understood that the above-mentioned device embodiments are only illustrative, and the device of the present application can also be implemented in other ways. For example, the division of units / modules in the above-mentioned embodiments is only a logical function division, and there may be other division methods in actual implementation. For example, multiple units, modules or components can be combined, or can be integrated into another system, or some features can be ignored or not executed.

[0160] In addition, unless otherwise specified, each functional unit / module in each embodiment of the present application may be integrated into one unit / module, each unit / module may exist physically separately, or two or more units / modules may be integrated together. The above-mentioned integrated unit / module may be implemented in the form of hardware or in the form of a software program module.

[0161] If the integrated unit / module is implemented in the form of hardware, the hardware may be a digital circuit, an analog circuit, etc. The physical implementation of the hardware structure includes but is not limited to a transistor, a memristor, etc.

[0162] Figure 3 This is a schematic diagram of the structure of the AGV equipment provided in this application. Figure 3 As shown, the AGV device 50 provided in this embodiment includes: at least one processor 501 and a memory 502. Optionally, the AGV device 50 also includes a communication component 503. The processor 501, the memory 502 and the communication component 503 are connected via a bus 504.

[0163] In the specific implementation process, at least one processor 501 executes the computer-executable instructions stored in the memory 502, so that at least one processor 501 executes the above-mentioned method.

[0164] For the specific implementation process of the processor 501, reference can be made to the above method embodiment. The implementation principle and technical effects are similar, and will not be elaborated here in this embodiment.

[0165] Unless otherwise specified, the processor 501 can be any suitable hardware processor, such as CPU, GPU, FPGA, DSP, and ASIC, etc. Unless otherwise specified, the memory 502 can be any suitable magnetic storage medium or magneto-optical storage medium, such as resistive random access memory (RRAM), dynamic random access memory (DRAM), static random access memory (SRAM), enhanced dynamic random access memory (EDRAM), high-bandwidth memory (HBM), hybrid memory cube (HMC), etc.

[0166] If the integrated unit / module is implemented in the form of a software program module and sold or used as an independent product, it can be stored in a computer-readable memory. Based on such an understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of this technical solution, can be embodied in the form of a software product. This computer software product is stored in a memory and includes several instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods of the various embodiments of this application. And the aforementioned memory includes: USB flash drive, read-only memory (ROM), random access memory (RAM), mobile hard disk, magnetic disk, or optical disc and other various media that can store program codes.

[0167] This application embodiment also provides a computer-readable storage medium. Computer-executable instructions are stored in the computer-readable storage medium. When the processor executes the computer-executable instructions, the redundant field update method for a distributed system as described above is implemented.

[0168] An embodiment of the present application also provides a computer program product, including a computer program, which, when executed by a processor, implements the above-mentioned redundant field update method for a distributed system.

[0169] In the above embodiments, the descriptions of the respective embodiments have their own focuses. For parts not detailed in a certain embodiment, reference may be made to the relevant descriptions of other embodiments. The technical features of the above embodiments can be combined arbitrarily. For the sake of brevity of description, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, it should be considered as the scope described in this specification.

[0170] Those skilled in the art will readily conceive of other implementations of the present application after considering the specification and practicing the invention disclosed herein. The present application is intended to cover any variations, uses, or adaptations of the present application, which follow the general principles of the present application and include known common general knowledge or conventional technical means in the technical field not disclosed in the present application. The specification and embodiments are only regarded as exemplary, and the true scope and spirit of the present application are pointed out by the following claims.

[0171] It should be understood that the present application is not limited to the exact structures described above and shown in the drawings, and various modifications and changes can be made without departing from its scope. The scope of the present application is only limited by the appended claims.

Claims

1. An AGV navigation method, characterized in that: Applied to AGV, the method comprises: Acquire real-time visual data and target position data, wherein the real-time visual data represents the real-time environment where the AGV is located, and the target position data represents the destination position of the AGV, and the real-time visual data includes a plurality of key frames updated in real time; Positioning the AGV according to the real-time visual data and a preset positioning algorithm to obtain first real-time position information of the AGV; Performing a performance evaluation on the preset positioning algorithm according to the first real-time position information to obtain a position evaluation result, wherein the position evaluation result represents a closed-loop detection capability of the preset positioning algorithm; Correcting the first real-time position information according to the position assessment result to obtain second real-time position data, wherein the second real-time position data represents the real-time position of the AGV, and the correction process can be performed based on the visual features included in the first real-time position information, the received new key frame, and the neighbor key frame corresponding to the new key frame; generating real-time navigation information according to the target position data and the second real-time position data, wherein the real-time navigation information is used to control the AGV to travel from the second real-time position to the destination position; The method further includes an updating process of the neighbor key frame; the updating process includes: When the position assessment result is unqualified, detecting whether there is a new key frame in the real-time visual data; if so, determining a neighbor key frame corresponding to the new key frame according to pre-stored visual features and map data; Determine whether the neighbor key frame meets the key frame quantity threshold; if not, obtain the second real-time position data of the previous key frame corresponding to the new key frame, the second real-time position data being the second real-time position data corresponding to the previous key frame; and in combination with the turning angle of the new key frame, generate a substitute key frame from the map data to supplement the lost visual data, and update the neighbor key frame based on the substitute key frame.

2. The AGV navigation method according to claim 1, characterized in that: The step of correcting the first real-time location information according to the location assessment result to obtain second real-time location data includes: When the position evaluation result is unqualified, determining a target visual feature corresponding to the first real-time position information from pre-stored visual features, wherein the pre-stored visual features can be obtained based on map data; For each of the first real-time position information, a feature comparison is performed according to the target visual feature corresponding to the first real-time position information and the real-time visual data to obtain a feature comparison result corresponding to the first real-time position information, wherein the feature comparison result indicates whether the real-time visual data contains the target visual feature; The first real-time location information is screened according to the plurality of feature comparison results to obtain second real-time location data.

3. The AGV navigation method according to claim 2, characterized in that: The performing feature comparison according to the target visual feature corresponding to the first real-time position information and the real-time visual data to obtain the feature comparison result corresponding to the first real-time position information includes: When a new key frame is detected in the real-time visual data, a neighbor key frame corresponding to the new key frame is determined according to pre-stored visual features and map data, wherein the neighbor key frame is a key frame directly connected to the new key frame among the multiple key frames; According to the new key frame and the plurality of neighbor key frames, two target key frames are obtained, wherein the target key frames are two neighbor key frames that are most similar to the new key frame; A feature comparison result is obtained according to the target visual feature corresponding to the first real-time position information and the new key frame and its corresponding two target key frames.

4. The AGV navigation method according to claim 1, characterized in that: Before generating a substitute key frame from the map data in combination with the steering angle of the new key frame to supplement the lost visual data, the method further includes: Get the steering angle corresponding to the new key frame.

5. The AGV navigation method according to claim 1, characterized in that: The generating real-time navigation information according to the target position data and the second real-time position data comprises: Obtain the type of environment in which the AGV is located; According to the environment type, in the path planning algorithm, determining a target planning algorithm; The target position data and the second real-time position data are input into the target planning algorithm to obtain real-time navigation information.

6. The AGV navigation method according to any one of claims 1 to 5, characterized in that: After generating the real-time navigation information according to the target position data and the second real-time position data, the method further includes: Obtaining real-time road condition features according to the real-time visual data; Speed ​​planning is performed on the real-time navigation information according to the real-time traffic characteristics to obtain real-time navigation information including speed setting.

7. An AGV navigation device, characterized in that: include: An acquisition module, used to acquire real-time visual data and target position data, wherein the real-time visual data represents the real-time environment where the AGV is located, and the target position data represents the destination position of the AGV, and the real-time visual data includes a plurality of key frames updated in real time; A positioning module, used to locate the AGV according to the real-time visual data and a preset positioning algorithm to obtain first real-time position information of the AGV; An evaluation module, configured to evaluate the performance of the preset positioning algorithm according to the first real-time position information to obtain a position evaluation result, wherein the position evaluation result represents the closed-loop detection capability of the preset positioning algorithm; A correction module, used for correcting the first real-time position information according to the position assessment result to obtain second real-time position data, wherein the second real-time position data represents the real-time position of the AGV, and the correction process can be performed based on the received new key frame and the neighbor key frame corresponding to the new key frame; A generating module, configured to generate real-time navigation information according to the target position data and the second real-time position data, wherein the real-time navigation information is used to control the AGV to travel from the second real-time position to the destination position; The correction module is also used to update the neighbor key frame: When the position assessment result is unqualified, detecting whether there is a new key frame in the real-time visual data; if so, determining the neighbor key frame corresponding to the new key frame according to the pre-stored visual features and map data; and judging whether the neighbor key frame meets the key frame quantity threshold; If not, obtaining the second real-time position data of the previous key frame corresponding to the new key frame, wherein the second real-time position data is the second real-time position data corresponding to the previous key frame; In combination with the steering angle of the new key frame, a substitute key frame is generated from the map data to supplement the lost visual data, and the neighbor key frame is updated based on the substitute key frame.

8. An AGV device, characterized in that: include: A processor, and a memory communicatively connected to the processor; The memory stores computer-executable instructions; The processor executes the computer-executable instructions stored in the memory to implement the method according to any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer-executable instructions, which are used to implement the method according to any one of claims 1 to 6 when executed by a processor.

10. A computer program product, comprising a computer program, wherein when the computer program is executed by a processor, the method according to any one of claims 1 to 6 is implemented.

Images