Snow open-pit mine unmanned mine car obstacle avoidance method and system

Abstract

The application discloses a snow open-pit mine unmanned mine car obstacle avoidance method and system, the method comprises the following steps: real-time sensing the scene in front of the driving path of the unmanned mine car to obtain sensing data information; then, identifying and processing the sensing data information to obtain the type and position information of the obstacle existing in front of the driving path of the unmanned mine car; if the type of the obstacle is rockfall, further extracting the three-dimensional data information of the snow-exposed part of the obstacle from the sensing data information; calculating the estimated size information of the obstacle according to the three-dimensional data information of the snow-exposed part of the obstacle and the real-time monitored snow depth; if the estimated size information of the obstacle meets the preset obstacle avoidance condition, re-planning the driving path of the unmanned mine car based on the position information of the obstacle to avoid the obstacle; the method improves the obstacle identification accuracy of the unmanned mine car in the snow, and effectively reduces the occurrence of safety accidents.

Description

Technical Field

[0001] This invention relates to the field of unmanned driving technology, and more specifically, to an obstacle avoidance method and system for unmanned mining trucks in open-pit mines during snowy weather. Background Technology

[0002] In recent years, with the continuous development of autonomous driving technology, driverless mining trucks have become an important component of intelligent mining solutions. In open-pit mines, material spillage, rockfalls, and axle crushing are frequent occurrences, resulting in various obstacles in the driving areas of driverless mining trucks. These obstacles can affect the normal operation of the trucks. In particular, when a driverless mining truck's tires run over falling rocks, it can cause component failure, tire blowouts, and rollovers, easily leading to safety accidents. To prevent driverless mining trucks from colliding with these obstacles, it is necessary to identify obstacles and plan obstacle avoidance paths. Accurate identification of obstacle size is crucial for obstacle avoidance by driverless mining trucks. Especially in snowy weather, partial snow cover can easily cause driverless mining trucks to misjudge the size of obstacles, mistaking larger obstacles for smaller ones, resulting in failure to avoid them in time and causing safety accidents.

[0003] In summary, there is an urgent need to develop an obstacle avoidance method and system for unmanned mining trucks in open-pit mines during snowy weather in order to solve the aforementioned technical problems. Summary of the Invention

[0004] One objective of this invention is to provide a new technical solution for obstacle avoidance methods and systems for unmanned mining trucks in open-pit mines during snowy weather.

[0005] According to a first aspect of the present invention, obstacle avoidance is provided for unmanned mining trucks in open-pit mines during snowy weather.

[0006] The method includes:

[0007] Step S1: Real-time perception of the scene ahead of the unmanned mining truck's driving path to obtain perception data information;

[0008] Step S2: The perceived data information is processed to obtain the type and location information of obstacles in front of the unmanned mining truck's driving path;

[0009] Step S3: If the obstacle is a rockfall, then further extract the three-dimensional data information of the exposed snow portion of the obstacle from the perception data information;

[0010] Step S4: Calculate the estimated size of the obstacle based on the three-dimensional data of the exposed snow portion of the obstacle and the real-time monitored snow depth;

[0011] Step S5: In a case where it is determined that the estimated size information of the obstacle meets a preset obstacle avoidance condition, re-planning a driving path of the unmanned mine car based on the position information of the obstacle to avoid the obstacle.

[0012] According to the method of the first aspect of the present application, in the step S1, the perception data information comprises visual perception data and radar perception data.

[0013] According to the method of the first aspect of the present application, in the step S2, the perception data information is subjected to identification processing to obtain a type of the obstacle existing in front of the driving path of the unmanned mine car, specifically comprising:

[0014] inputting the visual perception data into a pre-trained obstacle detection model to detect the obstacle existing in front of the driving path of the unmanned mine car and local visual perception data corresponding to a region where the obstacle is located;

[0015] processing the local visual perception data corresponding to the region where the obstacle is located by using a pre-trained category identification model to obtain the type of the obstacle.

[0016] According to the method of the first aspect of the present application, in the step S2, the perception data information is subjected to identification processing to obtain position information of the obstacle existing in front of the driving path of the unmanned mine car, specifically comprising:

[0017] determining the position information of the obstacle based on the local visual perception data corresponding to the region where the obstacle is located and the radar perception data.

[0018] According to the method of the first aspect of the present application, the step S3 specifically comprises:

[0019] graying the local visual perception data corresponding to the region where the obstacle is located;

[0020] processing the local visual perception data corresponding to the region where the obstacle is located after graying by using an edge detection algorithm to obtain contour information of the obstacle;

[0021] extracting three-dimensional data information of a snow-exposed part of the obstacle from the radar perception data based on the contour information.

[0022] According to the method of the first aspect of the present application, the step S4 specifically comprises:

[0023] determining a vertical height and a maximum transverse width of the snow-exposed part of the obstacle based on the three-dimensional data information of the snow-exposed part of the obstacle;

[0024] calculate the actual height of the obstacle based on the vertical height of the snow-exposed part of the obstacle and the real-time monitored snow depth;

[0025] wherein the maximum lateral width of the snow-exposed part of the obstacle and the actual height of the obstacle are taken as the estimated size information of the obstacle.

[0026] According to the method of the first aspect of the present application, in the step S5, the preset obstacle avoidance condition is that the maximum lateral width of the snow-exposed part of the obstacle is greater than or equal to a first size threshold or the actual height of the obstacle is greater than or equal to a second size threshold.

[0027] According to the second aspect of the present application, an obstacle avoidance system for an unmanned mine car in an open-pit mine in snowy weather is provided, the system comprising:

[0028] The acquisition module is configured to perform real-time sensing on a scene in front of a driving path of the unmanned mine car to obtain sensing data information;

[0029] The identification module is configured to perform identification processing on the sensing data information to obtain type and position information of an obstacle existing in front of the driving path of the unmanned mine car;

[0030] The extraction module is configured to further extract three-dimensional data information of a snow-exposed part of the obstacle from the sensing data information if the type of the obstacle is rockfall;

[0031] The calculation module is configured to calculate estimated size information of the obstacle based on the three-dimensional data information of the snow-exposed part of the obstacle and the real-time monitored snow depth;

[0032] The path planning module is configured to, in a case where the estimated size information of the obstacle meets a preset obstacle avoidance condition, re-plan a driving path of the unmanned mine car based on the position information of the obstacle to avoid the obstacle.

[0033] According to the third aspect of the present application, an electronic device is provided, the electronic device comprising a memory and a processor, the memory storing a computer program, and the processor implementing the steps of the obstacle avoidance method for an unmanned mine car in an open-pit mine in snowy weather according to the first aspect of the present application when executing the computer program.

[0034] According to the fourth aspect of the present application, a computer readable storage medium is provided, the computer readable storage medium storing a computer program, and the computer program implementing the steps of the obstacle avoidance method for an unmanned mine car in an open-pit mine in snowy weather according to the first aspect of the present application when executed by a processor.

[0035] According to one embodiment disclosed by the present application, the snow open-pit mine unmanned mine car obstacle avoidance method and system has the following beneficial effects:

[0036] The snow open-pit mine unmanned mine car obstacle avoidance method provided by the present application firstly performs real-time sensing on a scene in front of a driving path of the unmanned mine car to obtain sensing data information; then performs identification processing on the sensing data information to obtain type and position information of an obstacle existing in front of the driving path of the unmanned mine car; if the type of the obstacle is rockfall, further three-dimensional data information of a snow-covered part of the obstacle is extracted from the sensing data information; then estimated size information of the obstacle is calculated according to the three-dimensional data information of the snow-covered part of the obstacle and real-time monitored snow depth; finally, the driving path of the unmanned mine car is re-planned based on the position information of the obstacle to avoid the obstacle, under the condition that the estimated size information of the obstacle meets preset obstacle avoidance conditions. The present application provides an effective obstacle avoidance method for the unmanned mine car in the case that the obstacle is partially covered by snow, the estimated size information of the obstacle is calculated by detecting the three-dimensional data information of the snow-covered part of the obstacle, and then whether the preset obstacle avoidance conditions are met is determined based on the estimated size information of the obstacle, so that the obstacle identification accuracy of the unmanned mine car in the snow is improved, and the occurrence of safety accidents is effectively reduced.

[0037] Other features of the present application, and their advantages, will become apparent in the non-limiting detailed description of the exemplary embodiments of the present application described below. BRIEF DESCRIPTION OF DRAWINGS

[0038] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments of the application and, together with the description, serve to explain the principles of the application.

[0039] Figure 1 A flowchart of a snow open-pit mine unmanned mine car obstacle avoidance method according to an embodiment is shown in the figure;

[0040] Figure 2 A structure diagram of a snow open-pit mine unmanned mine car obstacle avoidance system according to an embodiment is shown in the figure;

[0041] Figure 3 A schematic diagram of an electronic device is shown in the figure. DETAILED DESCRIPTION

[0042] Various exemplary embodiments of the present application will now be described in detail with reference to the accompanying drawings. Note that the relative arrangement, numerical expressions, and numerical values of components and steps set forth in these embodiments are not limiting to the scope of the present application, unless otherwise specifically stated.

[0043] The following description of at least one exemplary embodiment is merely exemplary in nature and is in no way intended to limit the application or its application and uses.

[0044] Techniques, methods, and apparatus known to those of ordinary skill in the relevant art can not be discussed in detail herein. However, where appropriate, such techniques, methods, and apparatus should be considered as part of the description.

[0045] In all of the examples shown and discussed herein, any specific values should be interpreted as merely exemplary, and not as a limitation. Thus, other examples of the exemplary embodiments can have different values.

[0046] Embodiment One:

[0047] Referring to Figure 1 As shown, the embodiment of the present application provides a snow open-pit mine unmanned mine car obstacle avoidance method, which comprises the following steps:

[0048] Step S1: Real-time perception is performed on the scene in front of the driving path of the unmanned mine car to obtain perception data information.

[0049] Optionally, the perception data information in the embodiment comprises visual perception data and radar perception data.

[0050] It should be noted that in order to obtain the environmental information of the scene in front of the driving path of the unmanned mine car, a visual perception device and a radar perception device need to be installed on the unmanned mine car in advance. In the embodiment, a plurality of frames of images of the scene in front of the driving path are obtained by the visual perception device to constitute the visual perception data, and point cloud data of the scene in front of the driving path is obtained by the radar perception device to constitute the radar perception data.

[0051] The number of visual perception devices can be one, two or more. When the number is one, the visual sensor is installed at the middle position of the front end of the unmanned mine car. When the number is two, the two visual sensors are symmetrically installed at the front end of the unmanned mine car. When the number is more, one or two of the visual sensors can be installed on the side of the unmanned mine car to assist the unmanned control of the mine car. The number of radar perception devices is one or more, which are installed at the front end of the unmanned mine car. The radar perception device can be a laser radar sensor, a millimeter wave radar sensor or an ultrasonic radar sensor.

[0052] Step S2: The perception data information is identified and processed to obtain the type and position information of the obstacle existing in front of the driving path of the unmanned mine car.

[0053] In this embodiment, the image of the scene in front of the obtained driving path is detected to determine whether there is an obstacle in front of the driving path of the unmanned mine car, and in the case where the obstacle is detected, the type of the obstacle is identified, and the position of the obstacle is determined based on the radar sensing data.

[0054] It should be noted that the type of the obstacle in this embodiment includes people, auxiliary vehicles, falling rocks, mine trucks, bulldozers, electric shovels, retaining walls and mechanical parts, etc.

[0055] The position information of the obstacle in this embodiment is mainly the spatial position information of the obstacle relative to the front end of the unmanned mine car, including the lateral and vertical distances between the obstacle and the unmanned mine car.

[0056] Optionally, in step S2, the sensing data information is identified to obtain the type of the obstacle existing in front of the driving path of the unmanned mine car, which specifically includes:

[0057] The visual sensing data is input into a pre-trained obstacle detection model to detect the obstacle existing in front of the driving path of the unmanned mine car and the local visual sensing data of the region where the obstacle is located;

[0058] The local visual sensing data of the region where the obstacle is located is processed by using a pre-trained category recognition model to obtain the type of the obstacle.

[0059] It should be noted that the obstacle detection model and the category recognition model in this embodiment are both convolutional neural network models, and the network is trained by pre-establishing corresponding obstacle image training sets and test sets, obstacle image training sets and test sets of different categories until a preset training target is reached.

[0060] Optionally, in step S2, the sensing data information is identified to obtain the position information of the obstacle existing in front of the driving path of the unmanned mine car, which specifically includes:

[0061] The position information of the obstacle is determined based on the local visual sensing data and the radar sensing data of the region where the obstacle is located.

[0062] In this embodiment, the local visual sensing data of the region where the obstacle is located can be calculated based on the pre-calibrated relationship between the visual sensing device and the radar sensing device, and then the position information of the obstacle is determined.

[0063] Step S3: If the type of the obstacle is falling rock, further three-dimensional data information of the snow-exposed part of the obstacle is extracted from the sensing data information.

[0064] It should be noted that step S3 in the method of the embodiment is mainly for the case that the obstacle is not completely covered. For the case that the obstacle is completely covered, the obstacle data detected in a period of time before can be used as the guiding data for the obstacle avoidance operation.

[0065] Optionally, step S3 in the embodiment specifically comprises:

[0066] graying the local visual perception data of the region where the obstacle is located;

[0067] processing the graying local visual perception data of the region where the obstacle is located by using an edge detection algorithm to obtain the contour information of the obstacle;

[0068] extracting the three-dimensional data information of the exposed snow part of the obstacle from the radar perception data based on the contour information.

[0069] It should be noted that the edge detection algorithm in the embodiment can be a Sobel detection algorithm, a Canny detection algorithm, a SUSAN detection algorithm, or a Harris detection algorithm. Among them, Sobel operator image edge detection is one of the most important operators in the field of machine learning, digital media, computer vision, etc., and plays an important role. Sobel edge detection is a gradient-based edge detection method that detects edges by calculating the gradients of an image in the x and y directions. It uses two 3x3 convolution kernels to calculate the gradients in the horizontal and vertical directions, respectively, and then combines the two gradients to obtain the edge strength. Canny edge detection is a multi-stage edge detection algorithm that includes noise filtering, gradient calculation, non-maximum suppression, and double-threshold detection. It aims to find strong edges in an image and remove weak edges; the Canny algorithm uses four masks to detect edges in horizontal, vertical, and diagonal directions. The convolution of the original image with each mask is stored, and for each point, we identify the maximum value at that point and the direction of the generated edge, so we generate a brightness gradient map and the direction of the brightness gradient for each point from the original image. SUSAN (Smallest Univalue Segment Assimilating Nucleus) is a local similarity-based edge detection method. It detects edges and corners by comparing the similarity of a pixel to other pixels in its neighborhood. SUSAN operator is a gray-based feature point acquisition method suitable for edge and corner detection in images, which can remove noise in images. It has the characteristics of simplicity, effectiveness, strong anti-noise ability, and fast calculation speed. Harris corner detection is a gradient-based corner detection algorithm that detects corners by calculating the gradient matrix of an image in the x and y directions. It is commonly used for corner detection in images, but can also be used for edge detection.

[0070] Step S4: The estimated size information of the obstacle is calculated according to the three-dimensional data information of the snow-exposed part of the obstacle and the real-time monitored snow depth.

[0071] Optionally, step S4 of the embodiment specifically comprises:

[0072] determining the vertical height and the maximum transverse width of the snow-exposed part of the obstacle based on the three-dimensional data information of the snow-exposed part of the obstacle;

[0073] calculating the actual height of the obstacle based on the vertical height of the snow-exposed part of the obstacle and the real-time monitored snow depth;

[0074] wherein the maximum transverse width of the snow-exposed part of the obstacle and the actual height of the obstacle are taken as the estimated size information of the obstacle.

[0075] Step S5: If the estimated size information of the obstacle meets the preset obstacle avoidance condition, the driving path of the unmanned mine car is re-planned based on the position information of the obstacle to perform obstacle avoidance.

[0076] Optionally, in the embodiment, the preset obstacle avoidance condition is that the maximum transverse width of the snow-exposed part of the obstacle is greater than or equal to a first size threshold or the actual height of the obstacle is greater than or equal to a second size threshold.

[0077] It should be noted that the values of the first size threshold and the second size threshold in the embodiment are determined according to empirical data and are not specifically limited here. For example, the first size threshold can be 20 cm and the second size threshold can be 30 cm.

[0078] In the embodiment, when the maximum transverse width of the snow-exposed part of the rockfall is greater than or equal to the first size threshold, or the actual height of the rockfall is greater than or equal to the second size threshold, or the maximum transverse width of the snow-exposed part of the rockfall is greater than or equal to the first size threshold and the actual height of the rockfall is greater than or equal to the second size threshold, the rockfall is determined to be an obstacle that needs to be avoided, and then the position information of the obstacle that needs to be avoided is used to re-plan the driving path of the unmanned mine car to perform obstacle avoidance.

[0079] In summary, the obstacle avoidance method of the unmanned mine car in the open-pit mine in snowy weather according to the embodiment of the present application firstly performs real-time sensing on the scene in front of the driving path of the unmanned mine car to obtain sensing data information; then performs identification processing on the sensing data information to obtain the type and position information of the obstacle existing in front of the driving path of the unmanned mine car; if the type of the obstacle is rockfall, further three-dimensional data information of the part of the obstacle exposed to the snow is extracted from the sensing data information; then the estimated size information of the obstacle is calculated according to the three-dimensional data information of the part of the obstacle exposed to the snow and the real-time monitored snow depth; finally, in the case that the estimated size information of the obstacle meets the preset obstacle avoidance condition, the driving path of the unmanned mine car is re-planned based on the position information of the obstacle to avoid the obstacle. The embodiment of the present application provides an effective obstacle avoidance method for the unmanned mine car in the case that part of the obstacle is covered by snow in snowy weather, the estimated size information of the obstacle is calculated by detecting the three-dimensional data information of the part of the obstacle exposed to the snow, and then whether the preset obstacle avoidance condition is met is determined based on the estimated size information of the obstacle, thereby improving the obstacle identification accuracy of the unmanned mine car in snowy weather and effectively reducing the occurrence of safety accidents.

[0080] Embodiment two:

[0081] The embodiment of the present application provides an obstacle avoidance system 100 for an unmanned mine car in an open-pit mine in snowy weather, as shown in the figure, Figure 2 The system comprises:

[0082] The acquisition module 10 is configured to perform real-time sensing on the scene in front of the driving path of the unmanned mine car to obtain sensing data information.

[0083] The identification module 20 is configured to perform identification processing on the sensing data information to obtain the type and position information of the obstacle existing in front of the driving path of the unmanned mine car.

[0084] The extraction module 30 is configured to, if the type of the obstacle is rockfall, further extract three-dimensional data information of the part of the obstacle exposed to the snow from the sensing data information.

[0085] The calculation module 40 is configured to calculate the estimated size information of the obstacle according to the three-dimensional data information of the part of the obstacle exposed to the snow and the real-time monitored snow depth.

[0086] The path planning module 50 is configured to, in the case that the estimated size information of the obstacle meets the preset obstacle avoidance condition, re-plan the driving path of the unmanned mine car based on the position information of the obstacle to avoid the obstacle.

[0087] Optionally, the sensing data information in the obstacle avoidance system for the unmanned mine car in the open-pit mine in snowy weather according to the embodiment of the present application comprises visual sensing data and radar sensing data.

[0088] Optionally, the recognition module 20 in the obstacle avoidance system of the snow open-pit mine unmanned mine car in the embodiment is specifically configured as:

[0089] inputting the visual perception data into a pre-trained obstacle detection model to detect the obstacle existing in front of the driving path of the unmanned mine car and the local visual perception data of the region where the corresponding obstacle is located;

[0090] processing the local visual perception data of the region where the obstacle is located by using a pre-trained category recognition model to obtain the type of the obstacle.

[0091] Optionally, the recognition module 20 in the obstacle avoidance system of the snow open-pit mine unmanned mine car in the embodiment is specifically further configured as: determining the position information of the obstacle based on the local visual perception data of the region where the obstacle is located and the radar perception data.

[0092] Optionally, the extraction module 30 in the obstacle avoidance system of the snow open-pit mine unmanned mine car in the embodiment is specifically configured as:

[0093] graying the local visual perception data of the region where the obstacle is located;

[0094] processing the local visual perception data of the region where the obstacle is located after graying by using an edge detection algorithm to obtain the contour information of the obstacle;

[0095] extracting the three-dimensional data information of the snow-exposed part of the obstacle from the radar perception data based on the contour information.

[0096] Optionally, the measurement module 40 in the obstacle avoidance system of the snow open-pit mine unmanned mine car in the embodiment is specifically configured as:

[0097] determining the vertical height and the maximum transverse width of the snow-exposed part of the obstacle based on the three-dimensional data information of the snow-exposed part of the obstacle;

[0098] calculating the actual height of the obstacle based on the vertical height of the snow-exposed part of the obstacle and the real-time monitored snow depth;

[0099] wherein the maximum transverse width of the snow-exposed part of the obstacle and the actual height of the obstacle are taken as the estimated size information of the obstacle.

[0100] Optionally, the pre-set obstacle avoidance condition in the obstacle avoidance system of the snow open-pit mine unmanned mine car in the embodiment is that the maximum transverse width of the snow-exposed part of the obstacle is greater than or equal to a first size threshold or the actual height of the obstacle is greater than or equal to a second size threshold.

[0101] Embodiment three:

[0102] The application discloses an electronic device. The electronic device comprises a memory and a processor, the memory stores a computer program, and the processor executes the computer program to realize the steps in the obstacle avoidance method of the unmanned mine car in an open-pit mine in a snowy day in any one of the embodiments disclosed by the application.

[0103] Figure 3 A structural diagram of the electronic device according to the embodiment of the application is shown in FIG. 1. Figure 3 As shown in the figure, the electronic device comprises a processor, a memory, a communication interface, a display screen and an input device connected through a system bus. The processor of the electronic device is used to provide computing and control capabilities. The memory of the electronic device comprises a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operating system and the computer program in the non-volatile storage medium to run. The communication interface of the electronic device is used to communicate with external terminals in a wired or wireless manner. The wireless manner can be realized through WIFI, an operator network, near field communication (NFC) or other technologies. The display screen of the electronic device can be a liquid crystal display screen or an electronic ink display screen. The input device of the electronic device can be a touch layer overlaid on the display screen, or a key, trackball or touchpad arranged on the shell of the electronic device, or an external keyboard, touchpad or mouse, etc.

[0104] Those skilled in the art can understand that, Figure 3 The structure shown in the figure is only a structural diagram of part of the technical solution of the present application, and does not constitute a limitation on the electronic device to which the technical solution of the present application is applied. The specific electronic device can comprise more or fewer components than those shown in the figure, or some components can be combined, or have a different component arrangement.

[0105] Embodiment four:

[0106] The embodiment of the application discloses a computer readable storage medium. The computer readable storage medium stores a computer program, and the computer program is executed by a processor to realize the steps in the obstacle avoidance method of the unmanned mine car in an open-pit mine in a snowy day in any one of the embodiments disclosed by the application.

[0107] Please note that the technical features of the above embodiments can be combined in any manner, and for the sake of brevity, not all possible combinations of the technical features in the above embodiments are described, however, as long as the combinations of the technical features do not contradict each other, they shall be considered within the scope of the present disclosure. The above embodiments only express several implementation manners of the present application, which are described in a more specific and detailed manner, but should not be construed as limiting the scope of the patent. It should be noted that for those skilled in the art, without departing from the concept of the present application, a number of modifications and improvements can be made, which are all within the scope of protection of the present application. Therefore, the scope of protection of the patent of the present application shall be subject to the appended claims.

[0108] The above only describes the preferred embodiments of the present application and is not intended to limit the present application. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application shall be included in the scope of protection of the present application.

[0109] Although some specific embodiments of the present application have been described in detail by examples, those skilled in the art should understand that the above examples are only for illustration and are not intended to limit the scope of the present application. Those skilled in the art should understand that the above embodiments can be modified without departing from the scope and spirit of the present application. The scope of the present application is defined by the appended claims.

Claims

1. A snow open-pit mine unmanned mine car obstacle avoidance method, characterized in that, The method comprises: Step S1: Real-time perception is performed on a scene in front of a driving path of the unmanned mine car to obtain perception data information; Step S2: The perception data information is identified to obtain type and position information of an obstacle existing in front of the driving path of the unmanned mine car; Step S3: If the type of the obstacle is rockfall, three-dimensional data information of a snow-covered part of the obstacle is further extracted from the perception data information; Step S4: The estimated size information of the obstacle is calculated according to the three-dimensional data information of the snow-covered part of the obstacle and real-time monitored snow depth; Step S5: In a case where the estimated size information of the obstacle meets a preset obstacle avoidance condition, the driving path of the unmanned mine car is re-planned based on the position information of the obstacle to avoid the obstacle. In the step S1, the perception data information comprises visual perception data and radar perception data.

2. The snow open-pit mine unmanned vehicle obstacle avoidance method according to claim 1, characterized in that, In the step S2, the perception data information is identified to obtain the type of the obstacle existing in front of the driving path of the unmanned mine car, specifically comprising:

3. The snow open-pit mine unmanned vehicle obstacle avoidance method according to claim 2, characterized in that, The visual perception data is input into a pre-trained obstacle detection model to detect the obstacle existing in front of the driving path of the unmanned mine car and local visual perception data of a region where the obstacle is located; The local visual perception data of the region where the obstacle is located is processed by using a pre-trained category identification model to obtain the type of the obstacle. In the step S2, the perception data information is identified to obtain the position information of the obstacle existing in front of the driving path of the unmanned mine car, specifically comprising:

4. The snow open-pit mine unmanned vehicle obstacle avoidance method according to claim 3, characterized in that, The position information of the obstacle is determined based on the local visual perception data of the region where the obstacle is located and the radar perception data. The step S3 specifically comprises:

5. The snow open-pit mine unmanned vehicle obstacle avoidance method according to claim 4, characterized in that, The local visual perception data of the region where the obstacle is located is grayed; The local visual perception data of the region where the obstacle is located after being grayed is processed by using an edge detection algorithm to obtain contour information of the obstacle; The three-dimensional data information of the snow-covered part of the obstacle is extracted from the radar perception data based on the contour information. The step S4 specifically comprises:

6. The snow open-pit mine unmanned vehicle obstacle avoidance method according to claim 5, characterized in that, The vertical height and the maximum transverse width of the snow-covered part of the obstacle are determined based on the three-dimensional data information of the snow-covered part of the obstacle; The actual height of the obstacle is calculated based on the vertical height of the snow-covered part of the obstacle and the real-time monitored snow depth; The maximum transverse width of the snow-covered part of the obstacle and the actual height of the obstacle are taken as the estimated size information of the obstacle. In the step S5, the preset obstacle avoidance condition is that the maximum transverse width of the snow-covered part of the obstacle is greater than or equal to a first size threshold or the actual height of the obstacle is greater than or equal to a second size threshold.

7. The snow open-pit mine unmanned vehicle obstacle avoidance method according to claim 6, characterized in that, The system comprises:

8. A barrier avoidance system for an unmanned mine vehicle in a snow open-pit mine, characterized in that An acquisition module configured to perform real-time perception on a scene in front of a driving path of the unmanned mine car to obtain perception data information; ​ The identification module is configured to perform identification processing on the perception data information to obtain type and position information of an obstacle existing in front of a driving path of the unmanned mine truck; The extraction module is configured to further extract three-dimensional data information of a snow-covered part of the obstacle from the perception data information if the type of the obstacle is rockfall; The measurement module is configured to measure and calculate estimated size information of the obstacle according to the three-dimensional data information of the snow-covered part of the obstacle and real-time monitored snow depth; The path planning module is configured to re-plan a driving path of the unmanned mine truck based on the position information of the obstacle to avoid the obstacle if it is determined that the estimated size information of the obstacle meets a preset obstacle avoidance condition.

9. An electronic device, comprising: The electronic device includes a memory and a processor, the memory stores a computer program, and the processor implements the steps of the obstacle avoidance method of the unmanned mine truck in the snow open-pit mine according to any one of claims 1 to 7 when executing the computer program.

10. A computer-readable storage medium, characterized in that, The computer readable storage medium stores a computer program, and the computer program is executed by the processor to implement the steps of the obstacle avoidance method of the unmanned mine truck in the snow open-pit mine according to any one of claims 1 to 7.

Images