Mine car obstacle avoidance method and system based on vehicle-mounted panel

Abstract

The application provides a mine car obstacle avoidance method and system based on a vehicle-mounted panel, comprising: a vehicle-road cooperation server detecting that a load state of a target mine car changes, and calling a mine image cache library of a mine; querying a target image set in the mine image cache library based on a device identifier of the target mine car; determining actual car size information of the target mine car according to the target image set; updating the actual car size information to a mine car size configuration table; and sending the mine car size configuration table to a vehicle-mounted panel in each mine car, the mine car size configuration table being used for each mine car to perform an obstacle avoidance operation. The application can effectively support precise obstacle avoidance of the mine car and improve safety and efficiency of mine car operation.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of image data processing or the control technology field of power vehicles, and in particular to a mine car obstacle avoidance method and system based on a vehicle-mounted tablet. BACKGROUND

[0002] In a mine area mine car operation scene, the mine car often faces dynamic load changes, such as empty load and load switching, load mass increase and decrease, which leads to the change of the actual car size; the existing obstacle avoidance scheme is difficult to cover the dynamic obstacle avoidance demand of the whole operation cycle of the mine car, and is difficult to meet the demand of real-time updating of the car size information after the load state of the mine car changes and executing the obstacle avoidance operation. SUMMARY

[0003] The present application provides a mine car obstacle avoidance method and system based on a vehicle-mounted tablet, which takes the load state change of the mine car as a trigger point, retrieves the actual car size by multiple node images, and updates it to the configuration table and synchronizes it to all mine cars, realizes the obstacle avoidance in the whole operation cycle, solves the problems of information lag and visual angle blind area in the mine area, effectively supports the accurate obstacle avoidance of the mine car, and improves the operation safety and efficiency.

[0004] In a first aspect, the present application provides a mine car obstacle avoidance method based on a vehicle-mounted tablet, applied to a vehicle-road cooperation server of a mine car navigation system of a mine field, the system further comprising a vehicle-mounted tablet in each mine car of the mine field and a roadside device, and the vehicle-road cooperation server is in communication connection with the vehicle-mounted tablet and the roadside device; the method comprises:

[0005] Detecting that the load state of a target mine car changes, retrieving a mine field image cache library of the mine field, the mine field image cache library containing a target image set corresponding to the target mine car in the mine field, the target image set containing a plurality of vehicle images corresponding to the target mine car taken by at least one node device in the mine field, and the device type of the at least one node device including a roadside device and a mine car;

[0006] Querying the target image set in the mine field image cache library based on the device identifier of the target mine car;

[0007] Determining the actual car size information of the target mine car according to the target image set;

[0008] Updating the actual car size information to a mine car size configuration table;

[0009] Sending the mine car size configuration table to the vehicle-mounted tablet in each mine car, and the mine car size configuration table is used for the each mine car to execute an obstacle avoidance operation.

[0010] In a second aspect, the embodiments of the present application provide a mine car navigation system, comprising a vehicle-road cooperation server, a vehicle-mounted tablet in each mine car in a mine field, and a roadside device, the vehicle-road cooperation server being in communication connection with the vehicle-mounted tablet and the roadside device respectively; wherein the vehicle-road cooperation server is configured to execute the steps of the method of the first aspect.

[0011] In a third aspect, the embodiments of the present application provide an electronic device, comprising a processor, a memory, and one or more programs stored in the memory and configured to be executed by the processor, the program comprising instructions for executing the steps in the first aspect of the embodiments of the present application.

[0012] In a fourth aspect, the embodiments of the present application provide a computer-readable storage medium having stored thereon a computer program or instructions, which are executed by a processor to implement the steps of the method of the first aspect.

[0013] As can be seen, in the embodiments of the present application, the vehicle-road cooperation server detects that the load state of the target mine car changes, and retrieves the mine field image cache library of the mine field; queries the target image set in the mine field image cache library based on the equipment identifier of the target mine car; determines the actual car compartment size information of the target mine car according to the target image set; updates the actual car compartment size information to the mine car size configuration table; and sends the mine car size configuration table to the vehicle-mounted tablet in each mine car, which is used for each mine car to perform obstacle avoidance operation. In this way, compared with the existing obstacle avoidance scheme, the present application takes the change of the load state of the mine car as the trigger point, retrieves the multi-node image to calculate the actual car compartment size and updates it to the configuration table which is synchronized to all mine cars, realizes the obstacle avoidance in the whole operation cycle, solves the problem of mine information lag and visual angle blind area, effectively supports the precise obstacle avoidance of the mine car, and improves the operation safety and efficiency. BRIEF DESCRIPTION OF DRAWINGS

[0014] In order to more clearly illustrate the technical solutions of the embodiments of the present application or the prior art, the following will briefly introduce the drawings needed to be used in the embodiments or prior art description. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can also be obtained by those skilled in the art without creative labor.

[0015] Figure 1 is a system architecture diagram of a mine car navigation system provided by the embodiments of the present application;

[0016] Figure 2 is a step flowchart of a mine car obstacle avoidance method based on a vehicle-mounted tablet provided by the embodiments of the present application;

[0017] Figure 3is a flowchart of a process for determining actual car size information of a mine car provided by an embodiment of the present application;

[0018] Figure 4 is a schematic diagram of an image processing process for determining actual car size information of a mine car provided by an embodiment of the present application;

[0019] Figure 5 is a flowchart of a process for executing obstacle avoidance operation of a mine car provided by an embodiment of the present application;

[0020] Figure 6 is a schematic diagram of a scenario for constructing a flat panel ad hoc network provided by an embodiment of the present application;

[0021] Figure 7 is a schematic diagram of a scenario for calculating car boundary position information of a mine car provided by an embodiment of the present application;

[0022] Figure 8 is a functional unit block diagram of a mine car navigation system provided by an embodiment of the present application;

[0023] Figure 9 is a structural block diagram of an electronic device provided by an embodiment of the present application. DETAILED DESCRIPTION

[0024] In order to make the personnel in the art better understand the present application, the technical solutions in the embodiments of the present application will be described clearly and completely below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor fall within the scope of protection of the present application.

[0025] The terms "first", "second", and the like in the specification and claims of the present application and the above-mentioned drawings are used to distinguish different objects, rather than to describe a specific order. In addition, the terms "include" and "have" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product or device including a series of steps or units is not limited to the listed steps or units, but can optionally include steps or units not listed or can optionally include other steps or units inherent to the process, method, product or device.

[0026] Reference to“an embodiment” herein means that a particular feature, structure, or characteristic described in connection with the embodiment can be included in at least one embodiment of the application. The appearances of the phrase“in an embodiment” in various places in the specification are not necessarily all referring to the same embodiment, nor are they necessarily mutually exclusive of one another. It is expressly understood that any of the embodiments described herein can be incorporated in a combination of embodiments.

[0027] In the embodiments of the present application, “and / or” describes the association relationship of associated objects, which means that there can be three kinds of relationships. For example, A and / or B can represent the following three cases: A exists alone; A and B exist simultaneously; and B exists alone. Wherein, A and B can be singular or plural.

[0028] In the embodiments of the present application, the symbol“ / ” can represent that the associated objects before and after the symbol are in an“or” relationship. In addition, the symbol“ / ” can also represent the division sign, that is, performing division operation. For example, A / B can represent A divided by B.

[0029] In the embodiments of the present application, “at least one” or similar expressions mean any combination of these items, including any combination of single item or multiple items, means one or more, and multiple means two or more. For example, at least one of a, b or c can represent the following seven cases: a, b, c, a and b, a and c, b and c, a, b and c. Wherein, each of a, b and c can be an element or a set containing one or more elements.

[0030] In the embodiments of the present application, “equal to” can be used with greater than, which is applicable to the technical solutions adopted when greater than; or can be used with less than, which is applicable to the technical solutions adopted when less than. When equal to is used with greater than, it is not used with less than; when equal to is used with less than, it is not used with greater than.

[0031] In the mine car operation scene, the mine car often faces dynamic load changes, such as load switching, load mass increase and decrease, which leads to the change of actual car size; the existing obstacle avoidance scheme is difficult to cover the dynamic obstacle avoidance demand of the whole operation cycle of the mine car, and is difficult to meet the demand of updating the car size information in real time and executing the obstacle avoidance operation after the load state of the mine car changes.

[0032] In view of the above problems, the embodiments of the present application provide a mine car obstacle avoidance method and system based on a vehicle-mounted flat plate, which will be described in detail below in combination with the drawings.

[0033] Please refer to Figure 1 , Figure 1 is a system architecture diagram of a mine car navigation system provided by the embodiments of the present application, like Figure 1As shown, the mining truck navigation system 100 includes a vehicle-road cooperative server 110, an on-board tablet 120, and roadside equipment 130. The vehicle-road cooperative server 110 is communicatively connected to the on-board tablet 120 and the roadside equipment 130.

[0034] The vehicle-road cooperative server 110 is typically deployed in a local data center within the mining area, possessing high computing power, high storage capacity, and high reliability. Specifically, it receives images of mining trucks uploaded by roadside equipment 130 and information on the load status and location of mining trucks uploaded by onboard tablets 120, integrating these to form a mining area image cache library and maintaining a mining truck size configuration table. When a change in the load status of a target mining truck is detected (such as changes in weighing data uploaded by onboard tablets 120 or changes in loading status identified by roadside equipment 130), it retrieves images from the image cache library and filters multi-view images to calculate the actual truck dimensions. Furthermore, it synchronously distributes the updated mining truck size configuration table to the onboard tablets 120 of all mining trucks, ensuring that each mining truck can obtain the latest size data of surrounding mining trucks in real time, providing data support for global collaborative obstacle avoidance.

[0035] The vehicle-mounted tablet 120 is deployed in the cab of each mining truck and has touch interaction, data acquisition, and wireless communication functions. Specifically, it is used to connect to the mining truck's on-board positioning device, weighing sensor, etc., to collect real-time positioning information and load status data of the mining truck and upload it to the vehicle-road cooperative server 110; the vehicle-mounted tablet 120 can also capture images of surrounding mining trucks through its built-in camera to supplement the image acquisition blind spots of the roadside equipment 130; it can also be used to form a tablet self-organizing network with the on-board tablets of other mining trucks based on a preset protocol, broadcasting its own mining truck positioning information and vehicle identity information, while receiving broadcast messages from other tablets in the network; and it can receive the "mining truck size configuration table" issued by the vehicle-road cooperative server 110, combine it with the vehicle-end perception information and the basic map of the mine to construct an environmental modeling information set, and then perform obstacle avoidance operations based on the environmental modeling information set.

[0036] Among them, the roadside equipment 130 is an IoT device that is fixedly deployed at key locations in the mining area (such as loading points, unloading points, tunnel entrances, and meeting points). It typically integrates high-definition cameras, millimeter-wave radar, and wireless communication modules, and has stable perception capabilities in all weather and all environments. Specifically, it is used to continuously capture images of mining trucks on key road sections in the mining area, providing key image data; through image recognition technology, it assists in detecting changes in the load status of mining trucks; in addition to data related to mining trucks, it can also collect real-time road conditions at the deployment location (such as whether there are scattered rocks in the tunnels or whether there is water accumulation on the road surface), upload it to the vehicle-road cooperative server 110, and then synchronize it to the vehicle-mounted tablet 120 to supplement the environmental modeling information set with road condition dimension data, further improving obstacle avoidance safety.

[0037] As can be seen, in this embodiment, the roadside device 130 and the vehicle-mounted tablet 120 collect images, status, and positioning data of the mining truck from fixed and moving perspectives, respectively, and upload them to the vehicle-road cooperative server 110. After the vehicle-road cooperative server 110 completes the size calculation and configuration table update, it sends the global size information to all vehicle-mounted tablets 120. The vehicle-mounted tablet 120, as the execution layer, combines the information of nearby mining trucks received by the self-organizing network with local perception data to perform obstacle avoidance operations, thereby achieving precise obstacle avoidance and improving operational safety and efficiency.

[0038] The following is combined with Figure 2 The present application provides a further explanation of the obstacle avoidance method for mining trucks based on vehicle-mounted flatbeds provided in the embodiments of this application.

[0039] Please see Figure 2 , Figure 2 This is a flowchart illustrating the steps of a mine car obstacle avoidance method based on an onboard flatbed, as provided in an embodiment of this application. Figure 2 As shown, the method includes the following steps:

[0040] Step S210: A change in the load status of the target mining truck is detected, and the mining farm image cache library is retrieved.

[0041] The mine image cache library contains a set of target images corresponding to the target mining truck in the mine. The set of target images contains multiple vehicle images corresponding to the target mining truck taken by at least one node device in the mine. The device types of the at least one node device include roadside equipment and mining trucks.

[0042] Among them, roadside equipment is IoT devices that are fixedly deployed at key locations in the mining area (such as loading points, unloading points, tunnel entrances, passing points, etc.). They typically integrate high-definition cameras, millimeter-wave radar, and wireless communication modules, and have stable perception capabilities in all weather and all environments.

[0043] The load status of the target mining truck changes, including: the target mining truck changes from an empty state to a loaded state, or from a loaded state to an empty state, or the load mass changes when it is loaded.

[0044] Specifically, the load status of the target mining truck can be collected by the on-board flatbed, such as by connecting a weighing sensor to the on-board flatbed; and it can also be collected or determined by roadside equipment, such as roadside equipment that can use image recognition technology to help detect changes in the load status of the mining truck.

[0045] In one possible embodiment, before detecting a change in the load state of the target mining truck, the method further includes: detecting that the target mining truck is in a stable driving state; and determining whether the load state of the target mining truck has changed.

[0046] For example, a stable driving state includes, but is not limited to, meeting one or more of the following conditions: the mine car speed is stable above a preset threshold for a duration greater than or equal to a first preset duration; the mine car's parking brake is not activated, the gear is in driving gear (not neutral or reverse), and the vehicle's position continuously moves more than a preset distance; the vehicle load is stable within a preset time. This application does not limit the detection mechanism for the mine car load state, including but not limited to a timed detection mechanism when the mine car is in a stable driving state.

[0047] It is understandable that the actual dimensions of the mine car are strongly correlated with the load status. When detecting changes in the load status of the target mine car, priority should be given to making judgments when the mine car is in a stable driving state. This eliminates invalid detections during the loading (or unloading) process, which can significantly improve the accuracy and timeliness of load change judgments and avoid false triggering caused by temporary load fluctuations during loading, such as ore not being fully settled or materials temporarily stored in the loading machinery.

[0048] As can be seen, in this embodiment, when a change in the load state of the mining truck is detected, subsequent operations are triggered to update the actual dimensions of the mining truck. This enables real-time dynamic updates of the mining truck's dimensions, ensuring the accuracy of subsequent obstacle avoidance decisions and avoiding collision risks caused by mismatch between static dimensions and actual load. Furthermore, by relying on load change triggering, repetitive and redundant operations caused by continuous image retrieval and size calculation can be avoided, balancing obstacle avoidance safety and system operating efficiency.

[0049] Step S220: Based on the equipment identifier of the target mining truck, query the target image set in the mine image cache library.

[0050] The equipment identification of the target mining truck includes, but is not limited to, one or more of the following: a unique code on the mining truck body, a customized visual label, a combination of physical characteristics of the mining truck, and a special license plate for the mining area.

[0051] For example, the mine car body-specific code is a unique number painted on the side, front, or rear of each mine car by the mining area, such as "KC-001" or "MTR-2023"; customized visual labels are exclusive marks pasted or welded to conspicuous positions on the mine car (such as the top of the cab or the side of the car body), such as QR codes and barcodes: containing the unique ID information of the mine car; color block combination labels: composed of color blocks of specific colors and shapes arranged according to preset rules, each combination corresponding to a unique mine car; mine car physical feature combination marks utilize the unique appearance features of the mine car itself as natural identifiers, such as: personalized paint on the side of the cab (such as specific patterns or numbered stickers), modification marks on the car body (such as the shape of the added guardrails, the design of the exclusive unloading port), and the arrangement of the headlight assembly; mining area-specific license plates, such as metal plates printed with "Mining Area A-005".

[0052] Specifically, during system initialization, a mapping relationship between "equipment identifier and image data" is established for each mining truck. When roadside equipment or other mining trucks capture images of vehicles, the system automatically binds the equipment identifier of the captured object (obtained through image recognition of license plate / code or by receiving broadcast information from the captured mining truck) with the image data and stores them together in the mine image cache, forming a database structure of "identifier index and image path". Furthermore, multiple images corresponding to one or more equipment identifiers for the same mining truck are stored in the same dataset. When a target image set needs to be queried, the vehicle-road cooperative server uses the target mining truck's equipment identifier as the search keyword to match it in the index table of the mine image cache to obtain the target image set.

[0053] In addition, if a certain sign cannot be recognized due to a malfunction (such as a license plate being obscured), cross-validation of multiple signs can be used to ensure the accuracy of the query and avoid the loss of the image set due to the failure of a single sign.

[0054] As can be seen, in this embodiment, by clearly defining the multi-equipment identifiers of the mining truck, a "identifier and image" mapping and binding, index query and multi-identifier cross-validation mechanism is constructed. This not only achieves accurate and efficient association between the target mining truck and the exclusive image set, but also avoids image loss caused by the failure of a single identifier, providing reliable data support for subsequent image screening and truck size calculation.

[0055] Step S230: Determine the actual dimensions of the target mining truck based on the target image set.

[0056] The actual carriage size information refers to the actual dimensions of the carriage and its cargo.

[0057] Specifically, the actual dimensions of the carriage include the actual carriage width, actual carriage length, and actual carriage height. The actual carriage width includes the width of the left-side carriage and the width of the right-side carriage.

[0058] Step S240: Update the actual car body size information to the mine car size configuration table.

[0059] In one possible embodiment, the mine car size configuration table includes multiple size configuration parameter groups corresponding to multiple mine cars. Each size configuration parameter group includes an initial car body size parameter and an actual car body size parameter corresponding to a single mine car. The parameter value of the initial car body size parameter is a first preset value, which represents the car body size of the mine car in an unloaded state. The actual car body size parameter includes an actual car body width parameter, an actual car body length parameter, and an actual car body height parameter.

[0060] The actual carriage width parameters also include the width parameters of the left carriage and the right carriage.

[0061] In this case, the actual carriage size parameter is initially set to the first preset value. At this time, the actual carriage size parameter is the same as the initial carriage size parameter, indicating that the carriage is in an empty state.

[0062] In one possible embodiment, updating the actual car body size information to the mine car size configuration table includes: updating the current parameter value of the left car body width parameter according to the left car body width in the actual car body size information; updating the current parameter value of the right car body width parameter according to the right car body width in the actual car body size information; updating the current parameter value of the actual car body length parameter according to the actual car body length in the actual car body size information; and updating the current parameter value of the actual car body height parameter according to the actual car body height in the actual car body size information.

[0063] Understandably, when the load status of a mine car changes, the actual car body size information is calculated and updated in the mine car size configuration table. There are three types of load status changes: first, a change from empty to loaded, in which case the mine car size configuration table is updated as described above; second, a change in the load mass under loaded status, in which case the mine car size configuration table is updated as described above; third, a change from loaded to empty, in which case, in addition to updating the mine car size configuration table as described above, it is also possible to directly update the current parameter value of the actual car body size parameter in the mine car size configuration table to the initial first preset value without retrieving the image cache library, thus simplifying the width update operation.

[0064] Step S250: Send a mine car size configuration table to the onboard flatbed in each mine car. The mine car size configuration table is used by each mine car to perform obstacle avoidance operations.

[0065] The specific methods for sending the mine car size configuration table to the onboard tablet in each mine car include, but are not limited to, targeted push notifications to all onboard tablets in mine cars connected to the system via the main communication network of the mining area. For example, the configuration table can be sent to each tablet in encrypted data packets based on the tablet's MAC address or the mine car's device identifier (such as "KC-001"). Additionally, for onboard tablets that did not receive the initial push due to signal obstruction, temporary offline status, or other reasons, the configuration table can be distributed through a self-organizing network of the tablets. This application does not limit the specific implementation method by which the server sends the mine car size configuration table to the onboard tablet in each mine car.

[0066] Specifically, the vehicle-mounted tablets that have acquired the new configuration table will periodically broadcast configuration table update notifications within the self-organizing network. When offline devices reconnect to the network or approach other mining vehicles (e.g., meeting or traveling on the same route), they can automatically request synchronization of the latest configuration table from neighboring tablets, quickly acquiring data via short-range communication (e.g., LoRa, WiFi mesh). This avoids configuration table synchronization delays caused by single communication link failures. After receiving the configuration table, each vehicle-mounted tablet will verify data integrity through checksum comparison; if it finds that the local configuration table version is lower than the version broadcast by the self-organizing network, it will proactively trigger an update.

[0067] Among them, the self-organizing tablet network refers to a communication network composed of multiple vehicle-mounted tablets of multiple mining trucks in the mine based on preset protocol components.

[0068] As can be seen, in this embodiment, by using the change in the load status of the mining truck as the trigger point, multi-node images are retrieved to calculate the actual size of the truck bed and updated to the configuration table and synchronized to all mining trucks, obstacle avoidance is achieved throughout the entire operation cycle. This solves the problems of information lag and blind spots in the mining area, effectively supports precise obstacle avoidance by mining trucks, and improves operational safety and efficiency.

[0069] The following is combined with Figures 3-4 The specific process and image processing steps for determining the actual dimensions of the mine car are explained.

[0070] Specifically, please refer to Figure 3 , Figure 3 This is a flowchart illustrating a method for determining the actual dimensions of a mining car according to an embodiment of this application. In determining the actual dimensions of a target mining car based on a target image set, the method further includes the following steps:

[0071] Step S310: Determine multiple image entries corresponding to multiple vehicle images in the target image set.

[0072] The image entries include the time of capture, the information of the capturing node device, and the vehicle location. In addition, the image entries may also include basic image attribute information, such as image resolution, image format, image storage path, target mining truck identification association information, shooting angle and shooting environment parameters, image status and verification information, and other data related to the vehicle image.

[0073] Step S320: Determine the first time node based on multiple image entries.

[0074] The first time point represents the starting point at which the load status of the target mining truck changes.

[0075] In one possible embodiment, the image entries include the load status of the mining trucks; determining the first time node based on multiple image entries includes: sorting the multiple image entries in order of their capture times; analyzing whether the load status of the mining trucks changes between adjacent image entries according to the sorting; if so, determining the capture time corresponding to the previous image entry as the first time node; and if not, repeating the steps of analyzing whether the load status of the mining trucks changes between adjacent image entries according to the sorting until the first time node is determined.

[0076] As can be seen, the key to determining the first time point in the above embodiments lies in the fact that the image entry directly includes the load status of the mining truck. If the image entry does not include the load status of the mining truck, it is also necessary to combine image recognition to determine whether the load status of the mining truck represented by the vehicle image has changed, in order to determine the first time point.

[0077] In one possible embodiment, the image entries do not include the load status of the mining truck; determining the first time node based on multiple image entries includes: sorting the multiple vehicle images in order of multiple capture times in the multiple image entries; analyzing whether the load status of the mining truck represented by adjacent vehicle images has changed according to the sorting; if yes, determining the capture time in the image entry of the previous vehicle image in the adjacent vehicle images as the first time node; and if no, repeating the above steps of analyzing whether the load status of the mining truck represented by adjacent vehicle images has changed until the first time node is determined.

[0078] As can be seen, in this embodiment, by efficiently locating the starting point of the load change in the mining truck, a precise time reference is ultimately provided for the subsequent screening of valid images after the load status changes, ensuring a strong match between the actual truck size calculation and the current load status of the mining truck.

[0079] Step S330: Based on multiple image entries, select the first part of vehicle images from multiple vehicle images whose shooting time is later than the first time node.

[0080] Specifically, each vehicle image corresponds to an image entry, and the image entry includes the shooting time. Based on the shooting time, the first part of the vehicle images corresponding to the image entries whose shooting time is later than the first time node are selected.

[0081] Step S340: Select a second part of vehicle images containing a side view of the target mining truck, a third part of vehicle images containing a rear outline image of the target mining truck, and a fourth part of vehicle images containing a vertical outline image of the target mining truck's cargo compartment from the first part of vehicle images.

[0082] The side view image of the target mining truck includes both left and right side views. A second portion of the vehicle image, containing the side view image of the target mining truck, is used to determine the width of the truck bed.

[0083] The third part, the vehicle image, which includes the rear outline of the target mining truck, refers to an image that clearly shows the rear outline of the truck and is used to determine the length of the target mining truck's cargo compartment.

[0084] The fourth part, vehicle images, which include the vertical outline of the target mining car, refers to images that clearly show the outline of the car's height (mainly the top of the car), and are used to determine the height of the target mining car.

[0085] Step S341: Determine the actual width of the carriage based on the second part of the vehicle image.

[0086] The actual width of the carriage includes the width of the left carriage and the width of the right carriage.

[0087] In one possible embodiment, determining the actual car body width based on the second part of the vehicle image includes: dividing the second part of the vehicle image into a left-side vehicle image and a right-side vehicle image according to the left and right side views of the target mining car; merging the left-side vehicle image to obtain a left-side global image corresponding to the target mining car; and determining the left-side car body width of the target mining car based on the left-side global image; merging the right-side vehicle image to obtain a right-side global image corresponding to the target mining car; and determining the right-side car body width of the target mining car based on the right-side global image; and obtaining the actual car body width of the target mining car based on the left-side car body width and the right-side car body width.

[0088] In the image merging process, duplicate images are processed based on the latest time.

[0089] The mine car is equipped with a vehicle-mounted positioning device at the top of its front end. A three-dimensional coordinate system is constructed with the first position of the vehicle-mounted positioning device as the origin, and the X-axis along the vehicle body direction, the Y-axis along the vehicle body width direction, and the Z-axis along the vehicle body height direction are obtained. The width of the left side of the car body and the width of the right side of the car body refer to the two projection distances corresponding to the two projection points that are farthest from the X-axis after the projection of the car body and its load on the XOY plane is divided by the X-axis.

[0090] Specifically, please refer to Figure 4 , Figure 4 This is a schematic diagram of an image processing procedure for determining the actual dimensions of a mine car, as provided in an embodiment of this application. Figure 4As shown, firstly, a first batch of vehicle images with a capture time later than the first time node is selected from multiple vehicle images; then, a second batch of vehicle images containing the side view of the target mining truck is selected from the first batch of vehicle images; next, the second batch of vehicle images is divided into left-side vehicle images and right-side vehicle images according to the left and right side view of the target mining truck; then, the left-side vehicle images are merged to obtain the left-side global image, and the width of the left-side truck is determined; and the right-side vehicle images are merged to obtain the right-side global image, and the width of the right-side truck is determined; finally, the actual truck width is determined based on the left-side and right-side truck widths.

[0091] As can be seen, in this embodiment, the width measurement of asymmetric loading is realized through side processing and global synthesis mechanism, and the visual information is accurately converted into physical size by using the three-dimensional coordinate system. This provides fine width data with "different left and right sides" for mine truck obstacle avoidance, avoiding the limitation that the traditional "single body width" parameter cannot reflect the actual loading deviation.

[0092] Step S342: Determine the actual length of the carriage based on the third part of the vehicle image.

[0093] In one possible embodiment, determining the actual car body length based on the third part of the vehicle image includes: merging the third part of the vehicle image to obtain a complete rear outline image of the target mining truck, and determining the actual car body length of the target mining truck based on the complete rear outline image.

[0094] The mine car is equipped with a vehicle-mounted positioning device at the top of its front end. A three-dimensional coordinate system is constructed with the first position of the vehicle-mounted positioning device as the origin, resulting in the X-axis along the vehicle body direction, the Y-axis along the vehicle body width direction, and the Z-axis along the vehicle body height direction. The length of the car body refers to the projection distance of the car body and its load on the XOY plane corresponding to the projection point farthest from the Y-axis. The projection portion on the XOY plane is located on one side of the Y-axis.

[0095] Step S343: Determine the actual carriage height based on the vehicle image in Part 4.

[0096] In one possible embodiment, determining the actual car height based on the fourth part of the vehicle image includes: merging the fourth part of the vehicle image to obtain a complete vertical outline image of the car corresponding to the target mining car, and determining the actual car height of the target mining car based on the complete vertical outline image of the car.

[0097] Among them, a vehicle-mounted positioning device is deployed at the top of the front of the mining car. A three-dimensional coordinate system is constructed with the first position of the vehicle-mounted positioning device as the origin, and the X-axis along the vehicle body direction, the Y-axis along the vehicle body width direction, and the Z-axis along the vehicle body height direction are obtained. The height of the car body refers to the projection distance corresponding to the projection point farthest from the X-axis in the projection part of the car body and its load in the XOZ plane.

[0098] It should be noted that this application does not limit the specific image merging method or the specific algorithm for determining the size of the carriage based on vehicle images.

[0099] As can be seen, in this embodiment, the effective image after the loading state of the mine car is accurately locked first, and then key images such as the side, rear, and vertical contours are extracted and optimized. Finally, the actual width, length and height of the mine car are accurately calculated, providing accurate size data that is strongly adapted to the real-time load for mine car obstacle avoidance.

[0100] Please see Figure 5 , Figure 5 This is a schematic flowchart illustrating a mining truck performing obstacle avoidance operations according to an embodiment of this application. Regarding the obstacle avoidance operation performed by each mining truck, the method further includes the following steps performed by the onboard flatbed of each mining truck:

[0101] Step S510: The onboard tablet of the current mining truck obtains the broadcast message broadcast by the onboard tablet in the tablet self-organizing network.

[0102] The broadcast message includes the mine truck's location information and vehicle identification information.

[0103] The onboard positioning device deployed on the top of the mine truck's cab is used to locate the mine truck and determine its position information. Specifically, it uses GNSS and RTK technologies to achieve centimeter-level positioning, combined with a gyroscope to detect vehicle tilt and calibrate the positioning, ultimately achieving precise positioning of the mine truck in complex mining environments.

[0104] Specifically, GNSS (Global Navigation Satellite System) obtains the initial positioning coordinates (such as longitude, latitude, and altitude) of the mining truck in the global coordinate system by receiving satellite signals from BeiDou, GPS, and other satellites. However, GNSS alone is greatly affected by the mining environment. For example, if the mining truck travels to a roadway intersection or near tall equipment, the satellite signal is easily blocked, and the positioning accuracy will drop from meters to more than 10 meters, or even experience signal interruption. RTK (Real-Time Kinematics) deploys a "base station" at a fixed location in the mine and receives differential data of satellite signals from the base station and the mining truck's positioning device in real time. This eliminates errors such as ionospheric delay and satellite clock bias, improving the GNSS positioning accuracy from "meter-level" to "centimeter-level". Furthermore, based on GNSS and RTK technologies, the initial position of the onboard positioning device can be accurately determined, providing a reliable origin reference for subsequent "cargo truck boundary calculation".

[0105] Specifically, gyroscopes are used to detect the tilt state of the mining truck, such as pitch and roll angles, and can then calibrate the positioning results based on the tilt data. By collecting the pitch and roll angle data of the mining truck in real time, the gyroscope can dynamically adjust the attitude of the three-dimensional coordinate system, such as correcting the X-axis from the "horizontal direction" to the "actual longitudinal direction of the tilted vehicle body," ensuring that the coordinate system with the positioning device as the origin always matches the actual attitude of the mining truck, avoiding boundary calculation errors caused by tilt. In addition, when the mining truck enters a closed tunnel or the shadow area of ​​a tall ore pile, GNSS satellite signals are severely blocked, and RTK differential data cannot be transmitted, causing GNSS and RTK positioning to fail. At this time, the gyroscope, as the core component of the inertial measurement unit (IMU), can detect the angular velocity and acceleration of the mining truck, and combine this with the last accurate coordinates before the failure, to calculate the driving trajectory of the mining truck during the signal blockage, avoiding positioning interruption.

[0106] Among them, the self-organizing tablet network refers to a communication network composed of multiple vehicle-mounted tablets of multiple mining trucks in a mining farm based on preset protocol components.

[0107] Specifically, please refer to Figure 6 , Figure 6 This is a schematic diagram illustrating a scenario for constructing a self-organizing flat-panel network, as provided in an embodiment of this application. Figure 6 As shown, there are four mining cars (namely, the first, second, third, and fourth mining cars) traveling along the main transportation road in the mine. Each mining car has a vehicle-mounted tablet above the center console in the driver's cab, which serves as a self-organizing network communication node; multiple vehicle-mounted tablets form a communication network.

[0108] As can be seen, in this embodiment, by clearly defining the broadcast message containing the mine truck's location and identity information obtained from the tablet's self-organizing network by the current mine truck's onboard tablet, and combining it with... Figure 6The invention vividly presents a self-organizing network scenario in a mining farm, with onboard tablets as nodes. This not only enables real-time interaction of dynamic data between the mining workshops, but also ensures the coverage and reliability of data transmission in the complex environment of the mining farm by relying on the self-organizing network architecture. This lays a key data communication foundation for the subsequent construction of environmental modeling information sets and support for obstacle avoidance operations of mining trucks.

[0109] Step S520: Construct an environmental modeling information set based on the current vehicle-side perception information of the mining truck, the basic map information of the mine, broadcast messages, and the mining truck size configuration table.

[0110] Among them, the vehicle-side perception information refers to the dynamic data related to the surrounding environment and other mining vehicles that the mining truck collects in real time through its onboard sensors. Specifically, this includes distance perception data, such as distance data collected by lidar, millimeter-wave radar, and ultrasonic sensors; visual perception data, such as real-time images of surrounding mining vehicles and the environment collected by onboard cameras; status perception data, such as its own driving speed, steering angle, and acceleration; and sensor status data.

[0111] The environmental modeling information set is a structured dataset that comprehensively describes the current operating environment around the mining truck. Specifically, it includes basic static information, such as the location coordinates of fixed equipment (e.g., loading machinery, unloading platforms) and the location of road markings (e.g., the boundaries of driving lanes); as well as dynamic distance information and information about neighboring mining trucks (e.g., the location of the truck's boundary).

[0112] In one possible embodiment, constructing an environmental modeling information set based on the current mine truck's on-board perception information, the mine's basic map information, the broadcast message, and the mine truck size configuration table includes: constructing an environmental modeling information set based on the current mine truck's on-board perception information and the mine's basic map information, wherein the environmental modeling information set includes a first distance to perceived neighboring mine trucks, the first distance being the distance between the current mine truck and the neighboring mine trucks determined based on the on-board perception information; determining the vehicle identity information of the mine truck that matches the first distance from the plurality of mine trucks; querying the mine truck size configuration table based on the vehicle identity information to obtain the actual car body size of the neighboring mine truck; and updating the environmental modeling information set based on the actual car body size of the neighboring mine truck and the mine truck positioning information in the broadcast message.

[0113] The mining truck size configuration table includes multiple size configuration parameter groups corresponding to multiple mining trucks, and the vehicle identity information of a single mining truck corresponds to a unique size configuration parameter group.

[0114] In one possible embodiment, determining the vehicle identity information of the mining truck that matches the first distance from the plurality of mining trucks includes: determining a second distance between the current mining truck and other mining trucks based on the current location information of the mining truck and the mining truck positioning information; obtaining the positioning information of the mining truck that matches the first distance by comparing the second distance and the first distance; and extracting the vehicle identity information from the broadcast message to which the matched mining truck positioning information belongs.

[0115] Understandably, during mining operations, there may be multiple mining trucks that are close to the current mining truck in terms of the first distance. If the identity of the mining truck is determined directly based on the first distance, it is impossible to distinguish whether it is the first mining truck or the second mining truck. However, the second distance is labeled with an identity tag. By comparing the "first distance" with the "second distance of each mining truck", the neighboring mining trucks can be located.

[0116] Furthermore, vehicle-mounted sensing devices (such as radar) are susceptible to interference from mine dust, strong light, and ore piles, leading to inaccuracies in the initial distance measurement. The location information from broadcast messages may also be inaccurate due to signal issues. Comparing the initial and second distance measurements verifies the consistency of these two types of data: if the difference is within a reasonable threshold, the mine car corresponding to the second distance is identified as a neighboring mine car detected by the first distance measurement. Simultaneously, comparing the initial and second distance measurements also eliminates the possibility of misidentifying non-mine car obstacles.

[0117] In one possible embodiment, updating the environmental modeling information set based on the actual dimensions of the adjacent mining truck and the mining truck location information in the broadcast message includes: obtaining the first position of the on-board positioning device of the adjacent mining truck based on the mining truck location information in the broadcast message, wherein the on-board positioning device refers to a positioning acquisition device deployed on the top of the front of the mining truck; determining the boundary position information of the adjacent mining truck based on the first position and the actual dimensions of the truck; and updating the environmental modeling information set based on the boundary position information of the truck.

[0118] Among them, vehicle positioning devices include positioning boxes, USB positioning devices, and other vehicle positioning data acquisition equipment.

[0119] The actual dimensions of the carriage include the actual carriage length, the width of the left carriage, the width of the right carriage, and the actual carriage height.

[0120] In one possible embodiment, determining the boundary position information of the adjacent mining car based on the first position and the actual car dimensions includes: constructing a three-dimensional coordinate system with the first position as the origin to obtain the X-axis along the vehicle body direction, the Y-axis along the vehicle body width direction, and the Z-axis along the vehicle body height direction; determining the first boundary position information of the adjacent mining car based on the actual car body length and the three-dimensional coordinate system, wherein the actual car body length refers to the projection distance corresponding to the projection point farthest from the Y-axis in the projection portion of the car body and its load in the XOY plane, and the projection portion in the XOY plane is located on one side of the Y-axis; and determining the first boundary position information of the adjacent mining car based on the left car body width, the right car body width, and the... The second boundary position information of the adjacent mining car is determined by a three-dimensional coordinate system. The width of the left car and the width of the right car refer to the two projection distances corresponding to the two projection points farthest from the X-axis in the projection of the car and its load on the XOY plane after being divided by the X-axis. The third boundary position information of the adjacent mining car is determined based on the actual car height and the three-dimensional coordinate system. The actual car height refers to the projection distance corresponding to the projection point farthest from the X-axis in the projection of the car and its load on the XOZ plane. The car boundary position information of the adjacent mining car is determined based on the first boundary position information, the second boundary position information, and the third boundary position information.

[0121] Specifically, please refer to Figure 7 , Figure 7 This application provides a schematic diagram of a scenario for calculating the boundary position information of a mine car, as illustrated in an embodiment of the present application. Figure 7 As shown, the current mining truck senses a neighboring mining truck, and the two vehicles establish a communication connection via their onboard tablets. The current mining truck obtains the vehicle identity information of the neighboring mining truck, then queries the mining truck size configuration table to obtain the actual dimensions of the neighboring mining truck's cargo compartment. Finally, using the first position of the neighboring mining truck's onboard positioning device as the origin O(0,0,0), a three-dimensional coordinate system of X (vehicle direction), Y (width direction), and Z (height direction) is constructed to determine the boundary position information of the neighboring mining truck's cargo compartment.

[0122] Furthermore, the calculation logic for the carriage boundary position information can be intuitively presented based on the aforementioned three-dimensional coordinate system. For example, based on the actual length of the carriage being 8 meters, the carriage length direction boundary L is formed by extending along the positive X-axis from O(0,0,0) to (8,0,0), and its projection on the XOY plane is within the range of 0-8 meters on the X-axis; based on the width of the left carriage being 1.8 meters and the width of the right carriage being 1.6 meters, the carriage width direction boundary D is formed by extending along the negative Y-axis from O(0,0,0) to (0,-1.8,0) (left boundary) and along the positive Y-axis to (0,1.6,0) (right boundary), and its projection on the XOY plane is within the range of -1.8 meters to 1.6 meters on the Y-axis; based on the actual height of the carriage being 3.2 meters, the carriage height direction boundary H is formed by extending along the positive Z-axis from O(0,0,0) to (0,0,3.2), and its projection on the XOZ plane is within the range of 0-3.2 meters on the Z-axis.

[0123] As can be seen, in this embodiment, the boundaries of the X, Y, and Z axes together constitute a transparent cuboid (the three-dimensional spatial occupancy of the car and its load), with a boundary range of 0-8 meters on the X axis, -1.8 meters to 1.6 meters on the Y axis, and 0-3.2 meters on the Z axis. This fully presents the car boundary position information of the adjacent mining cars, providing a spatial quantitative basis for subsequent updates to the environmental modeling information set.

[0124] Furthermore, the environmental modeling information set is updated based on the car boundary position information, including directly adding the car boundary positions of neighboring mining cars to the environmental modeling information set; or updating the initial neighboring mining car position information in the environmental modeling information set to accurately determine the three-dimensional spatial occupancy status of neighboring mining car cars, providing accurate environmental data support for subsequent mining car obstacle avoidance and path planning, and avoiding decision-making deviations or safety risks caused by information ambiguity.

[0125] As can be seen, in this embodiment, by integrating vehicle-side perception, basic map, broadcast messages and size configuration table, the identities of nearby mining trucks are accurately matched and their actual sizes are obtained by comparing the first distance and the second distance. Then, the sizes are transformed into concrete truck boundary position information by combining the three-dimensional coordinate system. Finally, the environmental modeling information set is updated. This not only solves the problems of mining truck identity confusion, perception bias and misidentification of non-mining trucks in the complex environment of the mine, but also supplements the environmental modeling with the three-dimensional spatial occupancy data of nearby mining trucks. This provides accurate and reliable environmental basis for subsequent mining truck obstacle avoidance and path planning, avoiding decision bias and safety risks.

[0126] Step S530: Perform obstacle avoidance operations during the driving process based on the environmental modeling information set, the current position of the mining truck, and the vehicle speed.

[0127] Among them, the obstacle avoidance operation during the driving process based on the environmental modeling information set, the current position and speed of the mining truck is the core decision-making link of the autonomous operation of the mining truck. Its essence is the process of environmental risk identification, safety strategy generation and execution command output, which transforms the environmental data built in the early stage into specific driving control actions to ensure that the mining truck avoids collision risks in dynamic operation scenarios.

[0128] Specifically, the current mining truck dynamically generates an optimal obstacle avoidance strategy based on the environmental modeling information set, its own position, and speed. The obstacle avoidance strategy includes a target travel path and a target travel speed. This strategy can be shared and circulated based on broadcast information from various onboard tablets in the tablet ad hoc network. After receiving the obstacle avoidance strategy from the current mining truck, other mining trucks can perform collaborative path planning. This application does not limit the specific implementation method of performing obstacle avoidance operations during the driving process based on the environmental modeling information set, the current mining truck's own position, and speed, including but not limited to dynamically planning obstacle avoidance paths and speeds.

[0129] As can be seen, in this embodiment, by using the change in the load status of the mining truck as the trigger point, multi-node images are retrieved to calculate the actual size of the truck bed and updated to the configuration table and synchronized to all mining trucks, obstacle avoidance is achieved throughout the entire operation cycle. This solves the problems of information lag and blind spots in the mining area, effectively supports precise obstacle avoidance by mining trucks, and improves operational safety and efficiency.

[0130] Please see Figure 8 , Figure 8 A functional unit block diagram of a mine truck navigation system provided in this application embodiment is shown below. Figure 8 As shown, the mine truck navigation system 100 includes the following units:

[0131] The detection unit 810 is used to detect a change in the load status of the target mining truck and retrieve the mine image cache library of the mine. The mine image cache library contains a set of target images corresponding to the target mining truck in the mine. The set of target images contains multiple vehicle images corresponding to the target mining truck taken by at least one node device in the mine. The device types of the at least one node device include roadside equipment and mining trucks.

[0132] The processing unit 820 is configured to query the target image set in the mine image cache based on the device identifier of the target mining truck; determine the actual car body size information of the target mining truck according to the target image set; update the actual car body size information to the mining truck size configuration table; and send the mining truck size configuration table to the on-board flatbed in each mining truck, wherein the mining truck size configuration table is used by each mining truck to perform obstacle avoidance operations.

[0133] In one embodiment, the actual car body size information includes the actual car body width, actual car body length, and actual car body height. Determining the actual car body size information of the target mining truck based on the target image set includes: determining multiple image entries corresponding to the multiple vehicle images in the target image set, each image entry including the capture time, capture node device information, and vehicle position; determining a first time node based on the multiple image entries, the first time node representing the starting point of a change in the load state of the target mining truck; filtering out a first portion of vehicle images from the multiple vehicle images based on the multiple image entries, with a capture time later than the first time node; and filtering out a second portion of vehicle images containing a side view image of the target mining truck, a third portion of vehicle images containing a rear outline image of the target mining truck, and a fourth portion of vehicle images containing a vertical outline image of the target mining truck's car body from the first portion of vehicle images; determining the actual car body width based on the second portion of vehicle images; determining the actual car body length based on the third portion of vehicle images; and determining the actual car body height based on the fourth portion of vehicle images.

[0134] In one embodiment, determining the actual car body width based on the second portion of the vehicle images includes: dividing the second portion of the vehicle images into a left-side vehicle image and a right-side vehicle image according to the left and right side views of the target mining truck; merging the left-side vehicle images to obtain a left-side global image corresponding to the target mining truck, and determining the left-side car body width of the target mining truck based on the left-side global image; merging the right-side vehicle images to obtain a right-side global image corresponding to the target mining truck, and determining the right-side car body width of the target mining truck based on the right-side global image; and obtaining the actual car body width of the target mining truck based on the left-side car body width and the right-side car body width.

[0135] In one embodiment, the obstacle avoidance operation performed by each mining truck includes the following steps performed by the on-board tablet of each mining truck: the on-board tablet of the current mining truck obtains a broadcast message broadcast by the on-board tablet in the tablet self-organizing network, the broadcast message including mining truck positioning information and vehicle identity information, the tablet self-organizing network being a communication network composed of multiple on-board tablets of multiple mining trucks in the mine based on a preset protocol component; constructs an environmental modeling information set based on the current mining truck's vehicle-end perception information, the mine's basic map information, the broadcast message, and the mining truck size configuration table; and performs obstacle avoidance operation during driving based on the environmental modeling information set, the current mining truck's own position, and speed.

[0136] In one embodiment, constructing an environmental modeling information set based on the current mine truck's on-board perception information, the mine's basic map information, the broadcast message, and the mine truck size configuration table includes: constructing an environmental modeling information set based on the current mine truck's on-board perception information and the mine's basic map information, wherein the environmental modeling information set includes a first distance to perceived neighboring mine trucks, the first distance being the distance between the current mine truck and the neighboring mine trucks determined based on the on-board perception information; determining the vehicle identity information of the mine truck that matches the first distance from the plurality of mine trucks; querying the mine truck size configuration table based on the vehicle identity information to obtain the actual car body size of the neighboring mine truck; and updating the environmental modeling information set based on the actual car body size of the neighboring mine truck and the mine truck positioning information in the broadcast message.

[0137] In one embodiment, determining the vehicle identity information of the mining truck that matches the first distance from the plurality of mining trucks includes: determining a second distance between the current mining truck and other mining trucks based on the current location information of the mining truck and the mining truck positioning information; obtaining the positioning information of the mining truck that matches the first distance by comparing the second distance and the first distance; and extracting the vehicle identity information from the broadcast message to which the matched mining truck positioning information belongs.

[0138] In one embodiment, updating the environmental modeling information set based on the actual dimensions of the adjacent mining truck and the mining truck location information in the broadcast message includes: obtaining the first position of the on-board positioning device of the adjacent mining truck based on the mining truck location information in the broadcast message, wherein the on-board positioning device refers to a positioning acquisition device deployed on the top of the front of the mining truck; determining the boundary position information of the adjacent mining truck based on the first position and the actual dimensions of the truck; and updating the environmental modeling information set based on the boundary position information of the truck.

[0139] In one embodiment, the actual car dimensions include the actual car length, the left car width, the right car width, and the actual car height; determining the car boundary position information of the adjacent mining car based on the first position and the actual car dimensions includes: constructing a three-dimensional coordinate system with the first position as the origin to obtain the X-axis along the vehicle body direction, the Y-axis along the vehicle body width direction, and the Z-axis along the vehicle body height direction; determining the first boundary position information of the adjacent mining car based on the actual car length and the three-dimensional coordinate system, wherein the actual car length refers to the projection distance corresponding to the projection point farthest from the Y-axis in the projection portion of the car body and its load in the XOY plane, and the projection portion in the XOY plane is located on one side of the Y-axis; based on the left The width of the side carriage, the width of the right carriage, and the three-dimensional coordinate system determine the second boundary position information of the adjacent mining car. The width of the left carriage and the width of the right carriage refer to the two projection distances corresponding to the two projection points farthest from the X-axis in the projection of the carriage and its load on the XOY plane after being divided by the X-axis. The third boundary position information of the adjacent mining car is determined according to the actual carriage height and the three-dimensional coordinate system. The actual carriage height refers to the projection distance corresponding to the projection point farthest from the X-axis in the projection of the carriage and its load on the XOZ plane. The carriage boundary position information of the adjacent mining car is determined according to the first boundary position information, the second boundary position information, and the third boundary position information.

[0140] In one embodiment, the mine car size configuration table includes multiple size configuration parameter groups corresponding to multiple mine cars. Each size configuration parameter group includes an initial car body size parameter and an actual car body size parameter corresponding to a single mine car. The parameter value of the initial car body size parameter is a first preset value, which represents the car body size of the mine car in an unloaded state. The actual car body size parameter includes an actual car body width parameter, an actual car body length parameter, and an actual car body height parameter.

[0141] As can be seen, in this embodiment, by using the change in the load status of the mining truck as the trigger point, multi-node images are retrieved to calculate the actual size of the truck bed and updated to the configuration table and synchronized to all mining trucks, obstacle avoidance is achieved throughout the entire operation cycle. This solves the problems of information lag and blind spots in the mining area, effectively supports precise obstacle avoidance by mining trucks, and improves operational safety and efficiency.

[0142] Please see Figure 9 , Figure 9 This is a structural block diagram of an electronic device provided in an embodiment of this application, such as... Figure 9As shown, the electronic device 900 may include one or more of the following components: a processor 910 and a memory 920 coupled to the processor 910, wherein the memory 920 may store one or more computer programs, which may be configured to implement the methods described in the above embodiments when executed by one or more processors 910.

[0143] Processor 910 may include one or more processing cores. Processor 910 connects to various parts within the electronic device 900 using various interfaces and lines, and performs various functions and processes data of the electronic device 900 by running or executing instructions, programs, code sets, or instruction sets stored in memory 920, and by calling data stored in memory 920. Optionally, processor 910 may be implemented using at least one hardware form of Digital Signal Processing (DSP), Field-Programmable Gate Array (FPGA), or Programmable Logic Array (PLA). Processor 910 may integrate one or more of the following: Central Processing Unit (CPU), Graphics Processing Unit (GPU), and modem. The CPU primarily handles the operating system, user interface, and applications; the GPU is responsible for rendering and drawing the displayed content; and the modem handles wireless communication. It is understood that the modem may also not be integrated into processor 910 and may be implemented separately through a communication chip.

[0144] The memory 920 may include random access memory (RAM) or read-only memory (ROM). The memory 920 can be used to store instructions, programs, code, code sets, or instruction sets. The memory 920 may include a program storage area and a data storage area. The program storage area may store instructions for implementing an operating system, instructions for implementing at least one function (such as touch functionality, sound playback functionality, image playback functionality, etc.), and instructions for implementing the various method embodiments described above. The data storage area may also store data created by the electronic device 900 during use.

[0145] It is understood that the electronic device 900 may include more or fewer structural elements than those shown in the above block diagram, such as a power module, physical buttons, a Wi-Fi module, a speaker, a Bluetooth module, sensors, etc., without limitation.

[0146] Furthermore, this application embodiment also provides a computer storage medium that stores a computer program that can be loaded by a processor and executed as described above for the obstacle avoidance method of a mining truck based on an on-board tablet. The computer-readable storage medium includes, for example, various media capable of storing program code, such as a USB flash drive, a portable hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk.

[0147] It should be noted that, for the sake of simplicity, the foregoing method embodiments are all described as a series of actions. However, those skilled in the art should understand that this application is not limited to the described order of actions, as some steps may be performed in other orders or simultaneously according to this application. Furthermore, those skilled in the art should also understand that the embodiments described in the specification are preferred embodiments, and the actions and modules involved are not necessarily essential to this application.

[0148] In the several embodiments provided in this application, it should be understood that the disclosed methods, apparatuses, and systems can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for example, the division of units is merely a logical functional division, and other division methods may exist in actual implementation; for example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces, and the indirect coupling or communication connection between devices or units may be electrical, mechanical, or other forms.

[0149] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0150] Furthermore, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can be physically comprised separately, or two or more units can be integrated into one unit. The integrated unit described above can be implemented in hardware or in the form of hardware plus software functional units.

[0151] The integrated units implemented as software functional units described above can be stored in a computer-readable storage medium. These software functional units, stored in a storage medium, include several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute some steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes: a USB flash drive, a portable hard drive, a magnetic disk, an optical disk, volatile memory, or non-volatile memory. The non-volatile memory can be read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), or flash memory. The volatile memory can be random access memory (RAM), which is used as an external cache. By way of example, but not limitation, many forms of random access memory (RAM) are available, such as static random access memory (SRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate synchronous dynamic random access memory (DDRSDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous linked dynamic random access memory (SLDRAM), and direct rambus RAM (DRRAM), etc., which are various media that can store program code.

[0152] In the above embodiments, the descriptions of each embodiment have different focuses. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions in other embodiments.

[0153] The embodiments of this application have been described in detail above. Specific examples have been used to illustrate the principles and implementation methods of this application. The description of the above embodiments is only for the purpose of helping to understand the method and core ideas of this application. At the same time, for those skilled in the art, there will be changes in the specific implementation methods and application scope based on the ideas of this application. Therefore, the content of this specification should not be construed as a limitation of this application.

[0154] While this application discloses the above information, it is not limited thereto. Any person skilled in the art can easily conceive of variations or substitutions without departing from the spirit and scope of this application, and can make various alterations and modifications, including combinations of the different functions and implementation steps described above, as well as software and hardware implementation methods, all of which are within the protection scope of this application.

Claims

1. A method for obstacle avoidance in mining trucks based on an onboard flatbed, characterized in that, A vehicle-road cooperative server for a mine truck navigation system applied in a mine, the system further including an on-board tablet and roadside equipment in each mine truck in the mine, the vehicle-road cooperative server being communicatively connected to the on-board tablet and the roadside equipment respectively; the method includes: If a change in the load status of the target mining truck is detected, the mine image cache library of the mine is retrieved. The mine image cache library contains a set of target images corresponding to the target mining truck in the mine. The set of target images contains multiple vehicle images corresponding to the target mining truck taken by at least one node device in the mine. The device types of the at least one node device include roadside equipment and mining trucks. Based on the equipment identifier of the target mining truck, the target image set in the mine image cache is retrieved; The actual dimensions of the target mining truck are determined based on the target image set. Update the actual car body size information to the mine car size configuration table; The mine car size configuration table is sent to the on-board flatbed of each mine car, and the mine car size configuration table is used by each mine car to perform obstacle avoidance operation.

2. The method according to claim 1, characterized in that, The actual carriage dimensions include the actual carriage width, actual carriage length, and actual carriage height; Determining the actual dimensions of the target mining truck based on the target image set includes: Determine multiple image entries corresponding to the multiple vehicle images in the target image set, wherein the image entries include the shooting time, shooting node device information, and vehicle location; A first time node is determined based on the multiple image entries, and the first time node represents the starting point of time when the load state of the target mining truck changes; Based on the multiple image entries, a first portion of vehicle images with a shooting time later than the first time node are selected from the multiple vehicle images; and a second portion of vehicle images containing a side view of the target mining truck, a third portion of vehicle images containing a rear outline image of the target mining truck, and a fourth portion of vehicle images containing a vertical outline image of the target mining truck are selected from the first portion of vehicle images. The actual width of the vehicle compartment is determined based on the second part of the vehicle image; the actual length of the vehicle compartment is determined based on the third part of the vehicle image; and the actual height of the vehicle compartment is determined based on the fourth part of the vehicle image.

3. The method according to claim 2, characterized in that, Determining the actual width of the vehicle compartment based on the second part of the vehicle image includes: The second part of the vehicle image is divided into left-side vehicle image and right-side vehicle image according to the left and right side views of the target mining truck. The images of vehicles in the left-side orientation are merged to obtain a global image of the left-side orientation corresponding to the target mining truck; and the width of the left-side carriage of the target mining truck is determined based on the global image of the left-side orientation; and, The vehicle images on the right side are merged to obtain a global image of the right side corresponding to the target mining truck, and the width of the right side carriage of the target mining truck is determined based on the global image of the right side. The actual width of the target mining car is obtained based on the width of the left and right car compartments.

4. The method according to claim 1, characterized in that, The obstacle avoidance operation performed by each mining truck includes the following steps performed by the onboard flatbed of each mining truck: The onboard tablet of the mining truck obtains broadcast messages broadcast by the onboard tablet in the self-organizing tablet network. The broadcast messages include the mining truck's location information and vehicle identity information. The self-organizing tablet network refers to a communication network composed of multiple onboard tablets of multiple mining trucks in the mine based on preset protocol components. An environmental modeling information set is constructed based on the current vehicle-side perception information of the mining truck, the basic map information of the mine, the broadcast message, and the mining truck size configuration table; Based on the environmental modeling information set, the current position and speed of the mining truck, obstacle avoidance operations are performed during the driving process.

5. The method according to claim 4, characterized in that, The construction of an environmental modeling information set based on the current vehicle-side perception information of the mining truck, the basic map information of the mine, the broadcast message, and the mining truck size configuration table includes: An environmental modeling information set is constructed based on the vehicle-side perception information of the current mining truck and the basic map information of the mine. The environmental modeling information set includes the first distance of the perceived neighboring mining trucks. The first distance is the distance between the current mining truck and the neighboring mining trucks determined based on the vehicle-side perception information. The vehicle identity information of the mining truck that matches the first distance is determined from the plurality of mining trucks; Based on the vehicle identity information, query the mining car size configuration table to obtain the actual car body size of the adjacent mining car; The environmental modeling information set is updated based on the actual dimensions of the nearby mining trucks and the mining truck location information in the broadcast message.

6. The method according to claim 5, characterized in that, The step of determining the vehicle identity information of the mining truck that matches the first distance from the plurality of mining trucks includes: Based on the current location information of the mining truck and the positioning information of the mining truck, a second distance between the current mining truck and other mining trucks is determined; By comparing the second distance and the first distance, the positioning information of the mining truck that matches the first distance is obtained; Extract the vehicle identity information from the broadcast message to which the matched mining truck location information belongs.

7. The method according to claim 5, characterized in that, The step of updating the environmental modeling information set based on the actual dimensions of the nearby mining trucks and the mining truck location information in the broadcast message includes: The first position of the vehicle-mounted positioning device of the nearby mine car is obtained based on the mine car positioning information in the broadcast message. The vehicle-mounted positioning device refers to the positioning acquisition device deployed on the top of the front of the mine car. The boundary position information of the adjacent mining car is determined based on the first position and the actual car size; The environmental modeling information set is updated based on the carriage boundary location information.

8. The method according to claim 7, characterized in that, The actual car dimensions include the actual car length, the width of the left car, the width of the right car, and the actual car height; determining the car boundary position information of the adjacent mining car based on the first position and the actual car dimensions includes: A three-dimensional coordinate system is constructed with the first position as the origin, and the X-axis along the vehicle body direction, the Y-axis along the vehicle body width direction, and the Z-axis along the vehicle body height direction are obtained. The first boundary position information of the adjacent mining car is determined based on the actual car length and the three-dimensional coordinate system. The actual car length refers to the projection distance corresponding to the projection point farthest from the Y axis in the projection part of the car and its load in the XOY plane. The projection part in the XOY plane is located on one side of the Y axis. The second boundary position information of the adjacent mine car is determined based on the width of the left car, the width of the right car, and the three-dimensional coordinate system. The width of the left car and the width of the right car refer to the two projection distances corresponding to the two projection points that are farthest from the X-axis after the projection of the car and its load on the XOY plane is divided by the X-axis. The third boundary position information of the adjacent mining car is determined based on the actual car height and the three-dimensional coordinate system. The actual car height refers to the projection distance corresponding to the projection point farthest from the X-axis in the projection part of the car and its load in the XOZ plane. The car boundary position information of the adjacent mining car is determined based on the first boundary position information, the second boundary position information, and the third boundary position information.

9. The method according to claim 1, characterized in that, The mine car size configuration table includes multiple size configuration parameter groups corresponding to multiple mine cars. Each size configuration parameter group includes the initial car body size parameter and the actual car body size parameter corresponding to a single mine car. The parameter value of the initial car body size parameter is a first preset value, which represents the car body size of the mine car in an unloaded state. The actual carriage dimensions include the actual carriage width, actual carriage length, and actual carriage height.

10. A mine car navigation system, characterized in that, The method includes a vehicle-road cooperative server, an onboard tablet in each mining truck in the mine, and roadside equipment, wherein the vehicle-road cooperative server is communicatively connected to the onboard tablet and the roadside equipment respectively; wherein the vehicle-road cooperative server is used to perform the steps in the method as described in any one of claims 1-9.

Images