IGV navigation warning method, system, terminal and storage medium

Abstract

The present invention relates to the technical field of automatic guided vehicles, and specifically provides an IGV navigation warning method, system, terminal and storage medium, including: receiving a handling task, extracting a planned path generated based on a satellite map from the handling task, the planned path including a coordinate sequence to reach the location of the target object; obtaining its own positioning coordinates and posture data through a pre-deployed sensor combination; obtaining 360° laser point cloud data, and using a map construction algorithm to build a grid map based on the laser point cloud data; overlaying the planned path to the grid map, generating an avoidance route for the obstacle area on the planned path, and updating the planned path based on the avoidance route to obtain an execution path; calculating the similarity between the execution path and the planned path, and if the similarity does not reach a preset threshold, generating a warning prompt message of the path change. The present invention improves the navigation accuracy and efficiency of IGVs.

Description

Technical Field

[0001] The present invention belongs to the technical field of automatic guided vehicles, and in particular relates to an IGV navigation warning method, system, terminal and storage medium. Background Art

[0002] Automated Guided Vehicle (IGV), as an important part of modern industrial automation, is also called automatic guided vehicle or automatic guided vehicle. This type of vehicle can flexibly load goods automatically or manually, then automatically drive along a preset precise route, or tow a cargo trolley directly to a designated location, and complete the loading and unloading of goods again automatically or manually at the destination.

[0003] Currently, automated guided vehicles generally rely on advanced LiDAR technology to achieve automatic navigation and obstacle avoidance by collecting three-dimensional point cloud data of the surrounding environment. However, although this method is efficient, it is accompanied by huge computing requirements, which poses a challenge to the IGV system with relatively limited computing power. In order to ensure the real-time navigation, the system often needs to make a trade-off between computing accuracy and response speed, and sometimes has to sacrifice some obstacle avoidance accuracy to meet the needs of real-time processing. Therefore, the future development of IGV technology will focus on optimizing algorithm design, improving computing efficiency, and exploring more efficient and accurate navigation and obstacle avoidance strategies to better adapt to complex and changing industrial environments. Summary of the invention

[0004] In view of the above-mentioned deficiencies in the prior art, the present invention provides an IGV navigation warning method, system, terminal and storage medium to solve the above-mentioned technical problems.

[0005] In a first aspect, the present invention provides an IGV navigation warning method, comprising:

[0006] receiving a transport task, and extracting a planned path generated based on a satellite map from the transport task, wherein the planned path includes a coordinate sequence to reach a location of a target object;

[0007] Obtain its own positioning coordinates and posture data through a combination of pre-deployed sensors;

[0008] Acquire 360° laser point cloud data, and construct a raster map based on the laser point cloud data using a map construction algorithm;

[0009] Overlaying the planned path onto the grid map, generating an avoidance route for an obstacle area on the planned path, and updating the planned path based on the avoidance route to obtain an execution path;

[0010] The similarity between the execution path and the planned path is calculated, and if the similarity does not reach a preset threshold, an early warning prompt message of the path change is generated.

[0011] In an optional embodiment, obtaining the positioning coordinates and posture data of the vehicle through a combination of pre-deployed sensors includes:

[0012] The speed, acceleration and rotation angle are collected through the speed sensor, acceleration sensor and gyroscope;

[0013] Use the positioning chip to obtain the positioning coordinates.

[0014] In an optional embodiment, obtaining 360° laser point cloud data and constructing a grid map based on the laser point cloud data using a map construction algorithm includes:

[0015] Monitor the quality of communication with the cloud computing platform;

[0016] If the communication quality reaches a preset quality level, the laser point cloud data is sent to the cloud computing platform to obtain the raster map and walking posture data returned by the cloud computing platform;

[0017] If the communication quality does not reach the quality level, the laser point cloud data is deleted, and the grid map and walking posture data are updated based on the deleted laser point cloud data.

[0018] In an optional embodiment, the method further comprises:

[0019] Arrange the posture data in order of collection time into a first posture sequence;

[0020] Arranging the walking posture data into a second posture sequence according to the generation time;

[0021] Aligning the second pose sequence with the first pose sequence;

[0022] Obtain the number of new pose data that is greater than the number of new pose data in the first pose sequence than in the second pose sequence, and calculate the delay time of laser point cloud data processing based on the number of new pose data and the interval value of adjacent pose data;

[0023] The delay time is compared with a preset time threshold. If the delay time reaches the time threshold, the walking mechanism is controlled to pause until the pause time reaches a preset time limit.

[0024] In a second aspect, the present invention provides an IGV navigation warning system, comprising:

[0025] A task receiving module, used to receive a transport task, and extract a planned path generated based on a satellite map from the transport task, wherein the planned path includes a coordinate sequence to reach the location of the target object;

[0026] The first acquisition module is used to obtain its own positioning coordinates and posture data through a pre-deployed sensor combination;

[0027] A second acquisition module is used to acquire 360° laser point cloud data and construct a grid map based on the laser point cloud data using a map construction algorithm;

[0028] A path processing module, used for overlaying the planned path onto the grid map, generating an avoidance route for an obstacle area on the planned path, and updating the planned path based on the avoidance route to obtain an execution path;

[0029] The warning generation module is used to calculate the similarity between the execution path and the planned path, and if the similarity does not reach a preset threshold, generate warning prompt information of the path change.

[0030] In an optional implementation, the first acquisition module includes:

[0031] A posture acquisition unit, used to acquire speed, acceleration and rotation angle through a velocity sensor, an acceleration sensor and a gyroscope;

[0032] The positioning acquisition unit is used to obtain the positioning coordinates using the positioning chip.

[0033] In an optional implementation, the second acquisition module includes:

[0034] A communication monitoring unit, used to monitor the communication quality with the cloud computing platform;

[0035] A first processing unit is configured to send the laser point cloud data to a cloud computing platform if the communication quality reaches a preset quality level, and obtain a raster map and walking posture data returned by the cloud computing platform;

[0036] The second processing unit is used to delete the laser point cloud data if the communication quality does not reach the quality level, and update the grid map and walking posture data based on the deleted laser point cloud data.

[0037] In an optional embodiment, the system further includes:

[0038] A first arrangement module, used to arrange the posture data into a first posture sequence in chronological order according to the acquisition time;

[0039] A second arrangement module, used for arranging the walking posture data into a second posture sequence according to the generation time;

[0040] A sequence alignment module, for aligning the second pose sequence with the first pose sequence;

[0041] A delay calculation module is used to obtain the number of new pose data that is more than the second pose sequence in the first pose sequence, and calculate the delay time of laser point cloud data processing based on the number of new pose data and the interval value of adjacent pose data;

[0042] The delay processing module is used to compare the delay time with a preset time threshold. If the delay time reaches the time threshold, the walking mechanism is controlled to pause until the pause time reaches a preset time limit.

[0043] In a third aspect, a terminal is provided, including:

[0044] processor, memory, wherein:

[0045] The memory is used to store the IGV navigation warning program.

[0046] The processor is used to call and run the IGV navigation warning program from the memory to implement the steps of the IGV navigation warning method provided in the first aspect.

[0047] In a fourth aspect, a computer storage medium is provided, wherein the computer-readable storage medium stores an IGV navigation warning program, and when the IGV navigation warning program is executed by a processor, the steps of the IGV navigation warning method provided in the first aspect are implemented.

[0048] The beneficial effect of the present invention is that the IGV navigation warning method, system, terminal and storage medium provided by the present invention can effectively reduce the processing frequency of high-computation laser point cloud data by integrating the planned path pre-generated by the satellite map and the avoidance route formulated by the point cloud data collected in real time by the laser radar. This strategy not only significantly reduces the overall computational burden of the system, but also ensures that the accuracy of navigation is maintained. At the same time, the introduction of the path similarity calculation mechanism can monitor and evaluate the degree of deviation between the execution path and the preset path in real time. Once a large-scale path modification is detected, the system will immediately trigger a warning prompt message to remind the operator to intervene in the review and verification in time, thereby ensuring the safety and efficiency of the IGV operation.

[0049] In addition, the invention has a reliable design principle, a simple structure and a very broad application prospect. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0051] Figure 1 is a schematic flow chart of a method according to an embodiment of the present invention.

[0052] Figure 2 is a schematic block diagram of a system according to an embodiment of the present invention.

[0053] Figure 3 A schematic diagram of the structure of a terminal provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0054] In order to enable those skilled in the art to better understand the technical solutions in the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0055] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art of the present invention. The terms used in the specification of the present invention herein are only for the purpose of describing specific embodiments and are not intended to limit the present invention.

[0056] The IGV navigation warning method provided in the embodiment of the present invention is executed by a computer device, and accordingly, the IGV navigation warning system runs in the computer device.

[0057] Figure 1 is a schematic flow chart of a method according to an embodiment of the present invention. Figure 1 The execution subject may be an IGV navigation warning system. According to different requirements, the order of the steps in the flow chart may be changed, and some may be omitted.

[0058] like Figure 1 As shown, the method includes:

[0059] Step 110, receiving a transport task, and extracting a planned path generated based on a satellite map from the transport task, wherein the planned path includes a coordinate sequence to reach a location of a target object;

[0060] Step 120, obtaining its own positioning coordinates and posture data through a pre-deployed sensor combination;

[0061] Step 130, acquiring 360° laser point cloud data, and constructing a raster map based on the laser point cloud data using a map construction algorithm;

[0062] Step 140, overlaying the planned path onto the grid map, generating an avoidance route for the obstacle area on the planned path, and updating the planned path based on the avoidance route to obtain an execution path;

[0063] Step 150, calculating the similarity between the execution path and the planned path, and if the similarity does not reach a preset threshold, generating a warning prompt message of the path change.

[0064] To facilitate understanding of the present invention, the IGV navigation warning method provided by the present invention is further described below based on the principle of the IGV navigation warning method of the present invention and in combination with the process of navigating the IGV in the embodiment.

[0065] Specifically, the IGV navigation warning method includes:

[0066] S1. Receive a transport task, and extract a planned path generated based on a satellite map from the transport task, wherein the planned path includes a coordinate sequence to reach a location of a target object.

[0067] The management center obtains the positioning coordinates of the IGV and the position coordinates of the target object (such as a vehicle). A feasible path is generated based on the satellite map, and the shortest path algorithm is used to select the planned path from the positioning coordinates of the IGV to the target object from the feasible path.

[0068] Specifically, the process includes the following:

[0069] Positioning coordinate acquisition: The management center first establishes a connection with the automatic guided vehicle (IGV) through wireless communication technology (such as Wi-Fi, Zigbee, LoRa, 5G, etc.) to receive the current position coordinates of the IGV in real time. These coordinates are usually provided by the GPS module, inertial navigation system (INS), or laser / visual navigation system on the IGV to ensure high-precision positioning.

[0070] Target location acquisition: At the same time, the management center also needs to obtain the location coordinates of the target (such as vehicles, goods, etc.). This may be achieved through RFID tags, QR code scanning, or GPS devices on the target. For static targets, their locations may have been pre-entered into the system; for dynamic targets, their location information needs to be updated in real time.

[0071] Fusion of satellite maps and indoor maps: The management center uses high-precision satellite maps as the basis to build a complete navigation environment for the port.

[0072] Environmental perception and updating: The system also needs to have environmental perception capabilities and be able to detect and update changes in the map in real time, such as temporary obstacles, road repairs, etc., to ensure that the planned path is always valid.

[0073] Generate feasible paths: Use image recognition technology to identify feasible roads from satellite images.

[0074] Apply the shortest path algorithm:

[0075] Among all feasible paths, the shortest path algorithm (such as Dijkstra algorithm) is used to select the best path. This path will take into account factors such as path length, number of turns, IGV speed and capacity to ensure efficient and safe arrival at the destination.

[0076] Specifically, the feasible paths in the satellite map are structured and converted into a weighted graph with positive weights. The starting point and end point of the path are used as points, the path is used as an edge, and the length of the path is used as the weight of the edge. A two-dimensional array is used to store the weight of each edge. A boolean array is also required to determine which points have the shortest length determined and which points have not been determined. The int array records the distance (which may be updated multiple times during the execution of the algorithm). A priority queue is required to add the surrounding points of the determined points. Each time the shortest path is determined, the one that is determined is thrown out and the shortest is determined until the shortest path is determined for all points.

[0077] Instruction sending: Once the optimal path is planned, the management center will send the path information to the IGV and instruct it to drive along this path.

[0078] S2. Obtain its own positioning coordinates and posture data through the pre-deployed sensor combination.

[0079] The speed, acceleration and rotation angle are collected through the speed sensor, acceleration sensor and gyroscope; the positioning coordinates are obtained using the positioning chip.

[0080] S3. Acquire 360° laser point cloud data, and use a map construction algorithm to construct a grid map based on the laser point cloud data.

[0081] S301, monitor the communication quality with the cloud computing platform; if the communication quality reaches a preset quality level, send the laser point cloud data to the cloud computing platform, and obtain the raster map and walking posture data returned by the cloud computing platform; if the communication quality does not reach the quality level, delete the laser point cloud data, and update the raster map and walking posture data based on the deleted laser point cloud data.

[0082] The specific process includes:

[0083] (1) Real-time monitoring and evaluation of communication quality:

[0084] Enable real-time monitoring mechanism to continuously measure key indicators such as communication delay, packet loss rate, bandwidth utilization, etc. between monitoring devices and cloud computing platforms.

[0085] Adopting adaptive threshold algorithm, the preset communication quality level threshold is dynamically adjusted according to the historical data and current status of the network environment to more accurately reflect the actual communication status.

[0086] (2) Data preprocessing and sending strategy:

[0087] If the communication quality reaches the preset quality level, perform the following steps:

[0088] The laser point cloud data is encrypted to ensure the security during data transmission.

[0089] The encrypted laser point cloud data is sent to the cloud computing platform through an optimized network protocol to reduce transmission time and error rate.

[0090] Receive the raster map and walking posture data returned by the cloud computing platform and verify them to ensure the integrity and accuracy of the data.

[0091] If the communication quality does not reach the preset quality level, then:

[0092] Intelligently delete the laser point cloud data, giving priority to retaining key feature points and obstacle information to reduce the amount of data transmission.

[0093] Apply local algorithms or lightweight models to quickly update local grid maps and walking posture data based on the deleted laser point cloud data to ensure the system's immediate responsiveness.

[0094] Among them, the method for deleting laser point cloud data is as follows:

[0095] Key point detection: Use algorithms (such as SIFT, SURF, etc.) to extract key points from the point cloud. These points usually represent significant features in the scene, such as corner points, edge points, etc. These key points are crucial for subsequent processing and recognition.

[0096] Feature descriptor calculation: Although directly calculating the descriptor will increase the amount of calculation, the descriptors of key points can be selectively calculated to facilitate subsequent matching and recognition. Alternatively, a more efficient feature description method can be used, such as ORB (Oriented FAST and Rotated BRIEF), which reduces the amount of calculation while ensuring recognition accuracy.

[0097] Dynamic point cloud removal: Using dynamic point cloud removal algorithms, such as dynamic point detection and removal methods based on label consistency, dynamic points (such as pedestrians, vehicles, etc.) in the scan can be quickly identified and removed, thereby retaining static obstacle information. This method can reduce the amount of data transmission while ensuring map accuracy.

[0098] Obstacle identification and marking: Use machine learning or deep learning algorithms to classify point cloud data, identify obstacles (such as trees, buildings, walls, etc.), and mark them. When transmitting data, point cloud data marked as obstacles can be transmitted first.

[0099] Data downsampling: Through point cloud data downsampling techniques, such as voxel grid downsampling and random downsampling, the number of data points can be reduced while maintaining the basic shape and features of the point cloud.

[0100] Octree compression: Use the octree data structure to compress the point cloud, divide the point cloud space into a series of nested cubes (octree nodes), and only store the cube information containing the point, thereby greatly reducing the amount of data storage.

[0101] Background modeling and subtraction: By building a background model, static background points (such as the ground, buildings, etc.) in the point cloud data are separated from dynamic points (such as pedestrians, vehicles, etc.). During data transmission, only dynamic points or point cloud data processed by background subtraction can be transmitted to reduce the amount of data transmission.

[0102] Intelligent pre-processing algorithm: Integrating intelligent pre-processing algorithms on the lidar device side, such as the dynamic point cloud removal and background subtraction mentioned above, can perform preliminary data processing and simplification while collecting data, thereby reducing the burden of subsequent data transmission and processing.

[0103] In one embodiment of the present invention, a local algorithm or a lightweight model is applied to quickly update the local grid map and walking posture data based on the deleted laser point cloud data to ensure the instant response capability of the system. The specific implementation method is as follows:

[0104] The LOAM (Lidar Odometry And Mapping) model is used as a lightweight model. The LOAM algorithm mainly includes four nodes: point cloud extraction (scan registration), radar odometry (lidar odometry), radar mapping (lidar mapping) and transform integration (transform integration).

[0105] Point cloud extraction: Receive point cloud data released by the LiDAR driver, calculate the curvature of the points, and classify the point clouds into different categories (edge ​​points, plane points, etc.) based on the curvature.

[0106] Radar odometer: The scan-to-scan matching method is used to calculate the relative pose transformation between two adjacent frame point clouds to obtain a high-frequency coarse odometer.

[0107] Radar mapping: Use the scan-to-map matching method to match the current frame point cloud with the historical point cloud in the map, optimize the low-frequency accurate pose estimation, and update the map.

[0108] Pose integration: Integrate the pose estimates obtained by the radar odometer and radar mapping to obtain the final pose output.

[0109] This lightweight model requires less input data and only requires feature points.

[0110] (3) Data backup and security:

[0111] Regularly back up important information such as laser point cloud data, raster maps, and walking posture data to local or cloud storage to prevent data loss.

[0112] Encryption technology is used to protect data security during data transmission and storage, ensuring that user privacy and sensitive information are not leaked.

[0113] In addition, the method of generating raster maps and walking posture data based on laser point cloud data includes:

[0114] The laser radar detects the surrounding environment data to form 360° two-dimensional point cloud data, and collects odometer information at the same time; the laser radar detection data and odometer data are collected for preprocessing, and then the extended information filtering algorithm is used to estimate and update the pose, and the data is uploaded to the map construction unit. The map construction unit uses the SLAM algorithm to build a grid map. SLAM is the abbreviation of Simultaneous Localization And Mapping. The SLAM algorithm is mainly used to solve the problems of positioning, navigation and map construction when mobile robots are running in unknown environments. The SLAM algorithm usually includes the following parts: feature extraction, data association, state estimation, state update and feature update. The specific processing steps of the laser point cloud are not the invention of the present invention, and there are related technologies, so it is not described in detail.

[0115] S302. Arrange the posture data collected by the sensor into a first posture sequence in chronological order according to the collection time; arrange the walking posture data generated based on the laser point cloud data into a second posture sequence in chronological order according to the generation time; align the second posture sequence with the first posture sequence; obtain the number of new posture data that is more than the second posture sequence in the first posture sequence, and calculate the delay time for laser point cloud data processing based on the number of new posture data and the interval value of adjacent posture data; compare the delay time with a preset time threshold, and if the delay time reaches the time threshold, control the walking mechanism to pause until the pause time reaches a preset time limit.

[0116] Specifically, in order to compare the two sequences, it is necessary to compare the posture data of the second posture sequence with the first posture sequence. The latest 5 walking posture data are intercepted from the second posture sequence, and the 5 sequentially arranged walking posture data are converted into sample vectors. The latest 5 posture data are intercepted from the first posture sequence, and the intercepted 5 sequentially arranged posture data are converted into comparison vectors, and the similarity between the sample vector and the comparison vector is calculated, which is the first similarity; 5 posture data one time step earlier than the latest 5 posture data are intercepted from the first posture sequence, and the intercepted data are converted into comparison vectors, and the similarity with the sample vector is calculated again to obtain the second similarity; determine whether the second similarity is higher than the first similarity. If the second similarity is higher than the first similarity, continue to intercept the posture data one time step earlier from the first posture sequence, and perform vector similarity comparison. If the second similarity is lower than the first similarity, confirm that the posture data corresponding to the first similarity and the running posture data corresponding to the sample vector are in an aligned state, and use this as the positioning point to achieve alignment of the two sequences.

[0117] After alignment, by comparing the two sequences, it is possible to determine the number of new pose data segments in the first pose sequence that are more than in the second pose sequence. These extra data reflect the delay in the laser point cloud data processing process.

[0118] Next, based on the number of new pose data and the time interval between adjacent pose data (i.e., sampling rate or update frequency), the total delay time required for the laser point cloud data to be acquired and processed and generate pose data can be calculated. This calculation takes into account the complexity of data processing and the utilization of system resources.

[0119] The calculated delay time is compared with the preset time threshold. This threshold is set according to the specific needs of the application scenario to ensure the real-time and security of the system.

[0120] If the delay time reaches or exceeds the preset time threshold, it means that the processing speed of the laser point cloud data cannot meet the real-time requirements of the current system, which may affect the navigation and control accuracy of the mobile platform. At this time, the system will trigger the control mechanism to suspend the movement of the walking mechanism.

[0121] This can effectively avoid untimely obstacle avoidance due to processing delays in laser point cloud data.

[0122] S4. Overlaying the planned path onto the grid map, generating an avoidance route for the obstacle area on the planned path, and updating the planned path based on the avoidance route to obtain an execution path.

[0123] (1) Integration of planning path and grid map:

[0124] First, ensure that the planned path is expressed in an appropriate coordinate system (such as the global coordinate system) and has been preliminarily calculated or optimized based on the target position and the starting position.

[0125] Map each point (or key point) of the planned path to a raster map. This usually involves converting the coordinates of the path points to indices or pixel locations in the raster map.

[0126] On a grid map, the planned path will be represented as a series of continuous points or line segments that may cross multiple grid cells.

[0127] (2) Identification and marking of obstacle areas:

[0128] The obstacle information marked in the grid map (such as the grid cells occupied by the obstacles) is used to identify the obstacle areas that may intersect with the planned path.

[0129] Accurately define the boundaries of these obstacle areas so that when generating avoidance routes later, you can clearly know which areas need to be avoided.

[0130] (3) Generation of avoidance routes:

[0131] Design avoidance strategies based on the layout of the obstacle area and the direction of the planned path, including detouring, finding narrow passages to pass through, or using path planning algorithms (such as A algorithm, RRT, etc.) to find the optimal avoidance path.

[0132] When generating an avoidance route, it is necessary to consider the smoothness, safety (avoiding getting too close to obstacles), and efficiency (minimizing the path length).

[0133] If there are multiple obstacle areas on the planned path, it may be necessary to generate multiple avoidance routes and connect them seamlessly to form a complete avoidance path.

[0134] (4) Update of planning path and determination of execution path:

[0135] The generated avoidance route is merged with the original planned path to replace the part of the planned path that is inaccessible due to obstacles.

[0136] Perform necessary optimization on the updated path, such as removing redundant points and adjusting the path shape to improve driving efficiency.

[0137] The final path is the execution path, which will serve as the input of the navigation system or controller to guide the IGV to follow the established route.

[0138] S5. Calculate the similarity between the execution path and the planned path. If the similarity does not reach a preset threshold, generate warning information of path change.

[0139] When calculating the similarity between the executed path and the pre-set planned path, we use advanced algorithms to compare every key point, direction change, and overall shape of the two paths in detail. This comparison process not only considers the difference in straight-line distance of the paths, but also covers multiple dimensions such as curve smoothness, turning angles and frequency to ensure a comprehensive assessment of the similarity of the paths.

[0140] If after rigorous calculation, it is found that the similarity between the executed path and the planned path does not reach the preset threshold of the system, this usually means that unforeseen obstacles, environmental changes or internal system failures have been encountered during the actual operation, causing the IGV to deviate from the original driving route. At this time, the system will immediately activate the early warning mechanism and automatically generate a clear and unambiguous path change early warning prompt message.

[0141] This warning message will record the specific content, time, location and possible reasons of the route change in detail, and notify the operator in a conspicuous way (such as sound alarm, screen pop-up window, etc.). After receiving the warning, the operator will quickly review and verify the route change to determine whether manual intervention or adjustment of the IGV's subsequent operation strategy is required to ensure that it can continue to perform its tasks safely and accurately. Through this mechanism, we can ensure the efficient operation of the IGV while minimizing the risks that may be caused by route deviation.

[0142] In some embodiments, the IGV navigation warning system may include a plurality of functional modules composed of computer program segments. The computer programs of the various program segments in the IGV navigation warning system may be stored in a memory of a computer device and executed by at least one processor to perform (see Figure 1 Description) Function of IGV navigation warning.

[0143] In this embodiment, the IGV navigation warning system can be divided into multiple functional modules according to the functions it performs, such as Figure 2 As shown. The functional modules of the system 200 may include: a task receiving module 210, a first acquisition module 220, a second acquisition module 230, a path processing module 240 and an early warning generation module 250. The module referred to in the present invention refers to a series of computer program segments that can be executed by at least one processor and can complete fixed functions, which are stored in a memory. In this embodiment, the functions of each module will be described in detail in subsequent embodiments.

[0144] A task receiving module, used to receive a transport task, and extract a planned path generated based on a satellite map from the transport task, wherein the planned path includes a coordinate sequence to reach the location of the target object;

[0145] The first acquisition module is used to obtain its own positioning coordinates and posture data through a pre-deployed sensor combination;

[0146] A second acquisition module is used to acquire 360° laser point cloud data and construct a grid map based on the laser point cloud data using a map construction algorithm;

[0147] A path processing module, used for overlaying the planned path onto the grid map, generating an avoidance route for an obstacle area on the planned path, and updating the planned path based on the avoidance route to obtain an execution path;

[0148] The warning generation module is used to calculate the similarity between the execution path and the planned path, and if the similarity does not reach a preset threshold, generate warning prompt information of the path change.

[0149] Optionally, as an embodiment of the present invention, the first acquisition module includes:

[0150] A posture acquisition unit, used to acquire speed, acceleration and rotation angle through a velocity sensor, an acceleration sensor and a gyroscope;

[0151] The positioning acquisition unit is used to obtain the positioning coordinates using the positioning chip.

[0152] Optionally, as an embodiment of the present invention, the second acquisition module includes:

[0153] A communication monitoring unit, used to monitor the communication quality with the cloud computing platform;

[0154] A first processing unit is configured to send the laser point cloud data to a cloud computing platform if the communication quality reaches a preset quality level, and obtain a raster map and walking posture data returned by the cloud computing platform;

[0155] The second processing unit is used to delete the laser point cloud data if the communication quality does not reach the quality level, and update the grid map and walking posture data based on the deleted laser point cloud data.

[0156] Optionally, as an embodiment of the present invention, the system further includes:

[0157] A first arrangement module, used to arrange the posture data into a first posture sequence in chronological order according to the acquisition time;

[0158] A second arrangement module, used for arranging the walking posture data into a second posture sequence according to the generation time;

[0159] A sequence alignment module, for aligning the second pose sequence with the first pose sequence;

[0160] A delay calculation module is used to obtain the number of new pose data that is more than the second pose sequence in the first pose sequence, and calculate the delay time of laser point cloud data processing based on the number of new pose data and the interval value of adjacent pose data;

[0161] The delay processing module is used to compare the delay time with a preset time threshold. If the delay time reaches the time threshold, the walking mechanism is controlled to pause until the pause time reaches a preset time limit.

[0162] Figure 3 The present invention is a schematic diagram of the structure of a terminal 300 provided in an embodiment of the present invention. The terminal 300 can be used to execute the IGV navigation warning method provided in an embodiment of the present invention.

[0163] The terminal 300 may include: a processor 310, a memory 320 and a communication unit 330. These components communicate via one or more buses. Those skilled in the art will appreciate that the server structure shown in the figure does not limit the present invention, and it may be a bus structure or a star structure, and may include more or fewer components than shown in the figure, or combine certain components, or arrange the components differently.

[0164] The memory 320 can be used to store the execution instructions of the processor 310, and the memory 320 can be implemented by any type of volatile or non-volatile storage terminal or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk or optical disk. When the execution instructions in the memory 320 are executed by the processor 310, the terminal 300 can perform some or all of the steps in the following method embodiments.

[0165] The processor 310 is the control center of the storage terminal, and uses various interfaces and lines to connect various parts of the entire electronic terminal. It runs or executes software programs and / or modules stored in the memory 320, and calls data stored in the memory to perform various functions of the electronic terminal and / or process data. The processor can be composed of an integrated circuit (IC), for example, it can be composed of a single packaged IC, or it can be composed of multiple packaged ICs with the same or different functions. For example, the processor 310 can only include a central processing unit (CPU). In the embodiment of the present invention, the CPU can be a single computing core or multiple computing cores.

[0166] The communication unit 330 is used to establish a communication channel so that the storage terminal can communicate with other terminals, receive user data sent by other terminals or send user data to other terminals.

[0167] The present invention also provides a computer storage medium, wherein the computer storage medium may store a program, and when the program is executed, the program may include some or all of the steps in each embodiment provided by the present invention. The storage medium may be a magnetic disk, an optical disk, a read-only memory (ROM) or a random access memory (RAM).

[0168] Those skilled in the art can clearly understand that the technology in the embodiments of the present invention can be implemented by means of software plus a necessary general hardware platform. Based on this understanding, the technical solution in the embodiments of the present invention, in essence or in other words, the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a disk or an optical disk, and other media that can store program codes, including several instructions for enabling a computer terminal (which can be a personal computer, a server, or a second terminal, a network terminal, etc.) to execute all or part of the steps of the methods described in each embodiment of the present invention.

[0169] In this specification, the same or similar parts between the various embodiments can be referred to each other. In particular, for the terminal embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the description in the method embodiment.

[0170] In the several embodiments provided by the present invention, it should be understood that the disclosed systems and methods can be implemented in other ways. For example, the system embodiments described above are only schematic. For example, the division of the modules is only a logical function division. There may be other division methods in actual implementation, such as multiple modules or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of systems or modules, which can be electrical, mechanical or other forms.

[0171] The modules described as separate components may or may not be physically separated, and the components shown as modules may or may not be physical modules, that is, they may be located in one place or distributed on multiple network modules. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0172] In addition, each functional module in each embodiment of the present invention may be integrated into one processing module, or each module may exist physically separately, or two or more modules may be integrated into one module.

[0173] Although the present invention has been described in detail by referring to the accompanying drawings and in combination with the preferred embodiments, the present invention is not limited thereto. Without departing from the spirit and essence of the present invention, a person skilled in the art may make various equivalent modifications or substitutions to the embodiments of the present invention, and these modifications or substitutions shall be within the scope of the present invention. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed by the present invention, and they shall be within the scope of protection of the present invention.

Claims

1. An IGV navigation warning method, characterized in that: include: receiving a transport task, and extracting a planned path generated based on a satellite map from the transport task, wherein the planned path includes a coordinate sequence to reach a location of a target object; Obtain its own positioning coordinates and posture data through a combination of pre-deployed sensors; Acquire 360° laser point cloud data, and construct a raster map based on the laser point cloud data using a map construction algorithm; Overlaying the planned path onto the grid map, generating an avoidance route for an obstacle area on the planned path, and updating the planned path based on the avoidance route to obtain an execution path; Calculating the similarity between the execution path and the planned path, and generating a warning prompt message of path change if the similarity does not reach a preset threshold; Acquire 360° laser point cloud data, and use a map construction algorithm to construct a grid map based on the laser point cloud data, including: Monitor the quality of communication with the cloud computing platform; If the communication quality reaches a preset quality level, the laser point cloud data is sent to the cloud computing platform to obtain the raster map and walking posture data returned by the cloud computing platform; If the communication quality does not reach the quality level, the laser point cloud data is deleted, and the grid map and walking posture data are updated based on the deleted laser point cloud data; Also includes: Arrange the posture data in order of collection time into a first posture sequence; Arranging the walking posture data into a second posture sequence according to the generation time; Aligning the second pose sequence with the first pose sequence; Obtain the number of new pose data that is greater than the number of new pose data in the first pose sequence than in the second pose sequence, and calculate the delay time of laser point cloud data processing based on the number of new pose data and the interval value of adjacent pose data; The delay time is compared with a preset time threshold, and if the delay time reaches the time threshold, the walking mechanism is controlled to pause until the pause time reaches a preset time limit; The posture data of the second posture sequence is compared with that of the first posture sequence, and the latest 5 walking posture data are intercepted from the second posture sequence, and the 5 sequentially arranged walking posture data are converted into sample vectors; the latest 5 posture data are intercepted from the first posture sequence, and the intercepted 5 sequentially arranged posture data are converted into comparison vectors, and the similarity between the sample vector and the comparison vector is calculated, which is the first similarity; 5 posture data one time step earlier than the latest 5 posture data are intercepted from the first posture sequence, and the intercepted data are converted into comparison vectors, and the similarity with the sample vector is calculated again to obtain the second similarity; it is determined whether the second similarity is higher than the first similarity. If the second similarity is higher than the first similarity, the posture data one time step earlier is continued to be intercepted from the first posture sequence, and vector similarity comparison is performed. If the second similarity is lower than the first similarity, it is confirmed that the posture data corresponding to the first similarity and the running posture data corresponding to the sample vector are in an aligned state, and the alignment of the two sequences is achieved using this as the positioning point.

2. The method according to claim 1, characterized in that The system obtains its own positioning coordinates and posture data through a combination of pre-deployed sensors, including: The speed, acceleration and rotation angle are collected through the speed sensor, acceleration sensor and gyroscope; Use the positioning chip to obtain the positioning coordinates.

3. An IGV navigation warning system, characterized in that: include: A task receiving module, used to receive a transport task, and extract a planned path generated based on a satellite map from the transport task, wherein the planned path includes a coordinate sequence to reach the location of the target object; The first acquisition module is used to obtain its own positioning coordinates and posture data through a pre-deployed sensor combination; A second acquisition module is used to acquire 360° laser point cloud data and construct a grid map based on the laser point cloud data using a map construction algorithm; A path processing module, used for overlaying the planned path onto the grid map, generating an avoidance route for an obstacle area on the planned path, and updating the planned path based on the avoidance route to obtain an execution path; An early warning generation module is used to calculate the similarity between the execution path and the planned path, and if the similarity does not reach a preset threshold, generate early warning prompt information of the path change; The second acquisition module includes: A communication monitoring unit, used to monitor the communication quality with the cloud computing platform; A first processing unit is configured to send the laser point cloud data to a cloud computing platform and obtain a raster map and walking posture data returned by the cloud computing platform if the communication quality reaches a preset quality level; A second processing unit is used for deleting the laser point cloud data if the communication quality does not reach the quality level, and updating the grid map and walking posture data based on the deleted laser point cloud data; Also includes: A first arrangement module, used to arrange the posture data into a first posture sequence in chronological order according to the acquisition time; A second arrangement module, used for arranging the walking posture data into a second posture sequence according to the generation time; A sequence alignment module, for aligning the second pose sequence with the first pose sequence; A delay calculation module is used to obtain the number of new pose data that is more than the second pose sequence in the first pose sequence, and calculate the delay time of laser point cloud data processing based on the number of new pose data and the interval value of adjacent pose data; A delay processing module, used for comparing the delay time with a preset time threshold, and if the delay time reaches the time threshold, controlling the walking mechanism to pause until the pause time reaches a preset time limit; The posture data of the second posture sequence is compared with that of the first posture sequence, and the latest 5 walking posture data are intercepted from the second posture sequence, and the 5 sequentially arranged walking posture data are converted into sample vectors; the latest 5 posture data are intercepted from the first posture sequence, and the intercepted 5 sequentially arranged posture data are converted into comparison vectors, and the similarity between the sample vector and the comparison vector is calculated, which is the first similarity; 5 posture data one time step earlier than the latest 5 posture data are intercepted from the first posture sequence, and the intercepted data are converted into comparison vectors, and the similarity with the sample vector is calculated again to obtain the second similarity; it is determined whether the second similarity is higher than the first similarity. If the second similarity is higher than the first similarity, the posture data one time step earlier is continued to be intercepted from the first posture sequence, and vector similarity comparison is performed. If the second similarity is lower than the first similarity, it is confirmed that the posture data corresponding to the first similarity and the running posture data corresponding to the sample vector are in an aligned state, and the alignment of the two sequences is achieved using this as the positioning point.

4. The system according to claim 3, characterized in that The first acquisition module includes: A posture acquisition unit, used to acquire speed, acceleration and rotation angle through a velocity sensor, an acceleration sensor and a gyroscope; The positioning acquisition unit is used to obtain the positioning coordinates using the positioning chip.

5. A terminal, characterized in that: include: A memory, used for storing an IGV navigation warning program; A processor is used to implement the steps of the IGV navigation warning method according to any one of claims 1-2 when executing the IGV navigation warning program.

6. A computer-readable storage medium storing a computer program, characterized in that: The readable storage medium stores an IGV navigation warning program, which, when executed by a processor, implements the steps of the IGV navigation warning method according to any one of claims 1 to 2.

Images