Multi-source construction method, device and equipment for strip mine area map
The construction of open-pit mining area maps through multi-source data, including static, editable and dynamic map layers, solves the problem that the existing technology cannot adapt to mining scenarios, realizes effective data support for mine unmanned driving, and improves the operational safety and efficiency of unmanned equipment.
Patent Information
- Application Number
- CN202411606214.3
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-11-12
- Publication Date
- 2025-03-18
AI Technical Summary
The existing map construction method is not suitable for mining scenarios and cannot effectively provide data support for mine unmanned driving.
Use multi-source data to build an open-pit mining area map, including building static map layers, editable map layers and dynamic map layers, collecting multi-source data through unmanned collection vehicles and unmanned mining cards, filtering dynamic obstacles, editing regional pass attributes, and dynamically updating the map.
The generated open-pit mining area map can reflect real mine scenes, meet the positioning, navigation and control needs of unmanned vehicles, provide a solid data foundation, and improve the operational safety and efficiency of unmanned equipment.
Smart Images
Figure CN119648933A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of intelligent transportation technology, and in particular to a method, device and equipment for constructing a multi-source open-pit mine map. Background Art
[0002] With the introduction of intelligent mining policies, more and more intelligent technologies are being transferred to mines. As a typical representative of mines, open-pit mines have the characteristics of high resource utilization, low mining costs, and relatively safe operations. Related unmanned driving technologies are also relatively easy to develop. As the basic factor of unmanned driving, the importance of maps is self-evident. Accurate maps are crucial to the positioning, navigation, control, and safety of unmanned vehicles. For mining scenarios, the on-site operating environment is complex and changeable, and there may be map elements that cannot be collected by non-contact sensors. Therefore, the maps relied on by mine unmanned driving must not only be able to reflect the real terrain scenes on site, but also need to be customized according to the needs of people and vehicles. Existing map construction methods often do not combine mining scenarios and cannot better meet the needs of mine unmanned driving. Summary of the invention
[0003] The purpose of the present invention is to overcome the deficiencies in the prior art and provide a method, device and equipment for constructing a multi-source map of an open-pit mine area, so as to solve the technical problem that the existing map construction method is not suitable for mining scenes and cannot provide strong data support for unmanned driving in mines.
[0004] To achieve the above object, the present invention is implemented by adopting the following technical solutions: In a first aspect, the present invention provides a method for constructing a multi-source open-pit mine map, comprising: Acquire global multi-source data of the open-pit mine area, filter point cloud data of dynamic obstacles in the multi-source data, and construct a static map layer of the target map based on the filtered multi-source data; After the static map layer is constructed, the regional traffic attributes of the static map layer are edited according to the requirements, and an editable map layer of the target map is constructed based on the editing results; During the use of the static map layer, point cloud data of static obstacles appearing in the traversable area of the static map layer are obtained, and a dynamic map layer of the target map is constructed based on the point cloud data of the static obstacles; A final open-pit mine map is generated based on the static map layer, the editable map layer and the dynamic map layer.
[0005] Optionally, the obtaining of global multi-source data of the open-pit mine area includes: The open-pit mine area is collected globally through the camera, radar and odometer on the unmanned collection vehicle to obtain the corresponding image data, point cloud data and posture data.
[0006] Optionally, filtering the point cloud data of dynamic obstacles in the multi-source data includes: The observation time difference method is used to compare the point cloud data at different time points. If the point cloud data at the location of the obstacle changes, the obstacle is determined to be a dynamic obstacle and its point cloud data is removed.
[0007] Optionally, constructing a static map layer of a target map based on the filtered multi-source data includes: Perform time alignment processing on image data, point cloud data and pose data; At the same time point, the image data is subjected to an image recognition algorithm to extract image knowledge, the point cloud data is subjected to voxel filtering to perform noise reduction and downsampling to extract sparse point cloud data, and the image knowledge is added as a annotation to the sparse point cloud data to generate enhanced point cloud data; The enhanced point cloud data is converted from the radar coordinate system to the world coordinate system based on the posture data, and a static map layer of the target map is constructed according to the enhanced point cloud data in the world coordinate system.
[0008] Optionally, the unmanned data collection vehicle is also provided with a positioning system, which is used for collecting position data and correcting the posture data collected by the odometer.
[0009] Optionally, the area traffic attributes include a prohibited traffic area, a speed-limited traffic area, and a dynamic traffic area.
[0010] Optionally, the step of acquiring point cloud data of static obstacles appearing in the traversable area of the static map layer includes: When the unmanned mining truck is traveling in the passable area, the radar on the unmanned mining truck collects data of the passable area to obtain corresponding point cloud data; The point cloud data at different time points are compared using the observation time difference method. If the point cloud data at the location of the obstacle does not change, the obstacle is determined to be a static obstacle.
[0011] Optionally, after acquiring the point cloud data of the static obstacle uploaded by the unmanned mining truck in the cloud, the point cloud data of the static obstacle is searched in the database according to the location of the static obstacle. If there is point cloud data of the static obstacle, the difference between the two is calculated. If the difference is greater than a preset difference threshold, the point cloud data of the two are fused.
[0012] In a second aspect, the present invention provides a multi-source construction device for an open-pit mine map, the device comprising: A static map layer module is used to obtain multi-source data of the open-pit mine area, filter the point cloud data of dynamic obstacles in the multi-source data, and construct a static map layer of the target map based on the filtered multi-source data; The editable map layer module is used to edit the regional traffic attributes of the static map layer according to the requirements after the static map layer is built, and to build the editable map layer of the target map based on the editing results; The dynamic map layer module is used to obtain point cloud data of static obstacles appearing in the traversable area of the static map layer during the use of the static map layer, and to construct the dynamic map layer of the target map based on the point cloud data of the static obstacles; A map summary module is used to generate a final open-pit mine map based on the static map layer, the editable map layer and the dynamic map layer.
[0013] In a third aspect, the present invention provides an electronic device, including a processor and a storage medium; The storage medium is used to store instructions; The processor is used to operate according to the instructions to execute the steps according to the above method.
[0014] Compared with the prior art, the present invention has the following beneficial effects: The present invention provides a method, device and equipment for constructing a multi-source map of an open-pit mine area. The method, device and equipment are constructed by constructing three layers: a static map layer, a dynamic map layer and an editable map layer. The construction process of the static map layer only requires the participation of a single unmanned data collection vehicle, which can solve the differences in establishing a global map among multiple vehicles, such as differences in sensors among multiple workshops, differences in network quality and other issues. The construction process of the dynamic map layer can involve multiple unmanned mining trucks operating in the open-pit mine, which can describe static obstacles to the greatest extent and provide good auxiliary effects on the operation of unmanned mining trucks. The editable map layer can customize map elements according to on-site needs, which can make up for the shortcomings of the first two layers. In summary, the construction of the unmanned mining truck operation map in the open-pit mine area through a multi-source method can draw a map that meets the needs of multiple parties, reflects the real scene of the mining area, and provides a solid and stable data foundation for the operation of unmanned equipment. BRIEF DESCRIPTION OF THE DRAWINGS
[0015] Figure 1 It is a flow chart of a multi-source construction method of an open-pit mine area map provided by an embodiment of the present invention; Figure 2 It is a schematic diagram of the point cloud fusion of a single static obstacle in the dynamic map layer provided by an embodiment of the present invention. DETAILED DESCRIPTION
[0016] The present invention will be further described below in conjunction with the accompanying drawings. The following embodiments are only used to more clearly illustrate the technical solution of the present invention, and cannot be used to limit the protection scope of the present invention.
[0017] Embodiment 1:
[0018] like Figure 1 As shown, the present invention provides a method for constructing a multi-source open-pit mine map, comprising the following steps: Step S1, obtaining global multi-source data of the open-pit mine area, filtering the point cloud data of dynamic obstacles in the multi-source data, and constructing a static map layer of the target map based on the filtered multi-source data.
[0019] Specifically in this embodiment, obtaining global multi-source data of the open-pit mine area includes: The open-pit mine area is collected globally through the camera, radar, odometer and positioning system on the unmanned collection vehicle to obtain the corresponding image data, point cloud data, posture data and position data.
[0020] The static map layer is the base layer of the target map. In order to obtain a static map layer without interference from dynamic obstacles, it is necessary to filter the point cloud data of dynamic obstacles in the multi-source data. For moving objects, the observation time of their point clouds is either earlier or later than the ground point clouds at their locations. The specific methods include: The observation time difference method is used to compare the point cloud data at different time points. If the point cloud data of the obstacle location changes, the obstacle is determined to be a dynamic obstacle and its point cloud data is removed.
[0021] Specifically in this embodiment, constructing a static map layer of a target map based on filtered multi-source data includes: Perform time alignment processing on image data, point cloud data, pose data and position data; At the same time point, image recognition algorithms are used to extract image knowledge from image data, voxel filtering is used to reduce noise and downsample point cloud data to extract sparse point cloud data, and image knowledge is added as annotations to the sparse point cloud data to generate enhanced point cloud data; The position in the pose data is corrected based on the position data, and the enhanced point cloud data is converted from the radar coordinate system to the world coordinate system based on the corrected pose data. The static map layer of the target map is constructed according to the enhanced point cloud data in the world coordinate system.
[0022] Step S2: After the static map layer is constructed, edit the regional access attributes of the static map layer according to the requirements, and construct the editable map layer of the target map based on the editing results. The regional access attributes include: No-travel areas: There are areas on site where unmanned mining vehicles are prohibited from entering, such as cable areas. No-travel areas are added at the corresponding locations. Speed limit areas: For example, if there is a cable bridge on the path of the unmanned vehicle, or when the vehicle is going uphill or downhill, the unmanned mining vehicle needs to travel at a limited speed. Add speed limit areas at the corresponding locations; Dynamic traffic area: The on-site intersection needs to realize the alternating driving of unmanned vehicles and manned vehicles. Dynamic traffic areas are added at the corresponding positions, and the state of the area is changed by enabling conditions. For example, when the red light is on, the area is a prohibited area, and when the green light is on, the area is a allowed area.
[0023] Step S3: during the use of the static map layer, the point cloud data of the static obstacles appearing in the traversable area of the static map layer are obtained, and the dynamic map layer of the target map is constructed based on the point cloud data of the static obstacles.
[0024] The dynamic map layer is an automatic maintenance layer of the target map. After the static map layer is built, the dynamic map layer has no content by default. The dynamic map layer is collected and constructed by unmanned mining trucks running in open-pit mines. During the operation of the open-pit mining trucks, the point cloud of static obstacles that are different from the static map layer is annotated. For the same obstacle, multiple vehicles are used to annotate to enrich the boundary of the obstacle, height changes and other details, thereby improving the confidence of the obstacle.
[0025] Specifically in this embodiment, obtaining point cloud data of static obstacles appearing in the traversable area of the static map layer includes: When the unmanned mining truck is traveling in the passable area, the radar on the unmanned mining truck collects data of the passable area to obtain corresponding point cloud data; The observation time difference method is used to compare the point cloud data at different time points. If the point cloud data at the obstacle location does not change, the obstacle is determined to be a static obstacle.
[0026] Furthermore, after obtaining the point cloud data of the static obstacles uploaded by the unmanned mining truck in the cloud, the location of the static obstacles is used to search in the database to see whether the point cloud data of the static obstacles already exists. If there is point cloud data of a static obstacle, the difference between the two is calculated. If the difference is greater than the preset difference threshold, the point cloud data of the two are fused. Figure 2 As shown, the confidence of the static obstacles is improved by fusing the point cloud data of the static obstacles.
[0027] Step S4: generating a final open-pit mine map based on the static map layer, the editable map layer and the dynamic map layer.
[0028] Embodiment 2:
[0029] An embodiment of the present invention provides a multi-source construction device for an open-pit mine map, the device comprising: The static map layer module is used to obtain the global multi-source data of the open-pit mine area, filter the point cloud data of dynamic obstacles in the multi-source data, and build the static map layer of the target map based on the filtered multi-source data; The editable map layer module is used to edit the regional traffic attributes of the static map layer according to the requirements after the static map layer is built, and to build the editable map layer of the target map based on the editing results; The dynamic map layer module is used to obtain the point cloud data of static obstacles appearing in the passable area of the static map layer during the use of the static map layer, and to construct the dynamic map layer of the target map based on the point cloud data of the static obstacles; The map summary module is used to generate the final open-pit mine area map based on the static map layer, the editable map layer and the dynamic map layer.
[0030] Embodiment three:
[0031] An embodiment of the present invention provides an electronic device, including a processor and a storage medium; The storage medium is used to store instructions; The processor is used to operate according to the instructions to execute the steps of the multi-source construction method of the open-pit mine map provided according to an embodiment.
[0032] It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.
[0033] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.
[0034] These computer program instructions may also be stored in a computer readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture including an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.
[0035] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process in the computer or other programmable device. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.
[0036] The above is only a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the technical principles of the present invention. These improvements and modifications should also be regarded as the scope of protection of the present invention.
Claims
1. A multi-source construction method for an open-pit mine map, characterized in that: include: Acquire global multi-source data of the open-pit mine area, filter point cloud data of dynamic obstacles in the multi-source data, and construct a static map layer of the target map based on the filtered multi-source data; After the static map layer is constructed, the regional traffic attributes of the static map layer are edited according to the requirements, and an editable map layer of the target map is constructed based on the editing results; During the use of the static map layer, point cloud data of static obstacles appearing in the traversable area of the static map layer are obtained, and a dynamic map layer of the target map is constructed based on the point cloud data of the static obstacles; A final open-pit mine map is generated based on the static map layer, the editable map layer and the dynamic map layer.
2. The multi-source construction method of an open-pit mine area map according to claim 1, characterized in that: The acquisition of global multi-source data of the open-pit mine area includes: The open-pit mine area is collected globally through the camera, radar and odometer on the unmanned collection vehicle to obtain the corresponding image data, point cloud data and posture data.
3. The multi-source construction method of an open-pit mine area map according to claim 2, characterized in that: The filtering of the point cloud data of the dynamic obstacles in the multi-source data includes: The observation time difference method is used to compare the point cloud data at different time points. If the point cloud data at the location of the obstacle changes, the obstacle is determined to be a dynamic obstacle and its point cloud data is removed.
4. The multi-source construction method of an open-pit mine area map according to claim 2, characterized in that: The static map layer of the target map is constructed based on the filtered multi-source data, including: Perform time alignment processing on image data, point cloud data and pose data; At the same time point, the image data is subjected to an image recognition algorithm to extract image knowledge, the point cloud data is subjected to voxel filtering to perform noise reduction and downsampling to extract sparse point cloud data, and the image knowledge is added as a annotation to the sparse point cloud data to generate enhanced point cloud data; The enhanced point cloud data is converted from the radar coordinate system to the world coordinate system based on the posture data, and a static map layer of the target map is constructed according to the enhanced point cloud data in the world coordinate system.
5. The multi-source construction method of an open-pit mine area map according to claim 2, characterized in that: The unmanned data collection vehicle is also provided with a positioning system, which is used for collecting position data and correcting the posture data collected by the odometer.
6. The multi-source construction method of an open-pit mine area map according to claim 1, characterized in that: The area traffic attributes include a prohibited traffic area, a speed-limited traffic area, and a dynamic traffic area.
7. The multi-source construction method of an open-pit mine area map according to claim 1, characterized in that: The step of obtaining point cloud data of static obstacles appearing in the traversable area of the static map layer includes: When the unmanned mining truck is traveling in the passable area, the radar on the unmanned mining truck collects data of the passable area to obtain corresponding point cloud data; The point cloud data at different time points are compared using the observation time difference method. If the point cloud data at the location of the obstacle does not change, the obstacle is determined to be a static obstacle.
8. The multi-source construction method of an open-pit mine area map according to claim 7, characterized in that: After obtaining the point cloud data of the static obstacle uploaded by the unmanned mining truck in the cloud, the point cloud data of the static obstacle is searched in the database according to the location of the static obstacle. If there is point cloud data of the static obstacle, the difference between the two is calculated. If the difference is greater than a preset difference threshold, the point cloud data of the two are fused.
9. A multi-source construction device for an open-pit mine map, characterized in that: The device comprises: A static map layer module is used to obtain multi-source data of the open-pit mine area, filter the point cloud data of dynamic obstacles in the multi-source data, and construct a static map layer of the target map based on the filtered multi-source data; The editable map layer module is used to edit the regional traffic attributes of the static map layer according to the requirements after the static map layer is built, and to build the editable map layer of the target map based on the editing results; The dynamic map layer module is used to obtain point cloud data of static obstacles appearing in the traversable area of the static map layer during the use of the static map layer, and to construct the dynamic map layer of the target map based on the point cloud data of the static obstacles; A map summary module is used to generate a final open-pit mine map based on the static map layer, the editable map layer and the dynamic map layer.
10. An electronic device, characterized in that: including processor and storage medium; The storage medium is used to store instructions; The processor is configured to operate according to the instructions to execute the steps of the method according to any one of claims 1-8.