CN115346385B - Unmanned mine car automatic obstacle avoidance method based on complex road conditions - Google Patents
Unmanned mine car automatic obstacle avoidance method based on complex road conditions Download PDFInfo
- Publication number
- CN115346385B CN115346385B CN202211276249.6A CN202211276249A CN115346385B CN 115346385 B CN115346385 B CN 115346385B CN 202211276249 A CN202211276249 A CN 202211276249A CN 115346385 B CN115346385 B CN 115346385B
- Authority
- CN
- China
- Prior art keywords
- mine car
- unmanned mine
- unmanned
- ore body
- target grid
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/09—Arrangements for giving variable traffic instructions
- G08G1/0962—Arrangements for giving variable traffic instructions having an indicator mounted inside the vehicle, e.g. giving voice messages
- G08G1/0968—Systems involving transmission of navigation instructions to the vehicle
- G08G1/096805—Systems involving transmission of navigation instructions to the vehicle where the transmitted instructions are used to compute a route
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/762—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using clustering, e.g. of similar faces in social networks
- G06V10/763—Non-hierarchical techniques, e.g. based on statistics of modelling distributions
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/764—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using classification, e.g. of video objects
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/56—Context or environment of the image exterior to a vehicle by using sensors mounted on the vehicle
- G06V20/58—Recognition of moving objects or obstacles, e.g. vehicles or pedestrians; Recognition of traffic objects, e.g. traffic signs, traffic lights or roads
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/09—Arrangements for giving variable traffic instructions
- G08G1/0962—Arrangements for giving variable traffic instructions having an indicator mounted inside the vehicle, e.g. giving voice messages
- G08G1/0968—Systems involving transmission of navigation instructions to the vehicle
- G08G1/096833—Systems involving transmission of navigation instructions to the vehicle where different aspects are considered when computing the route
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/16—Anti-collision systems
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Software Systems (AREA)
- Multimedia (AREA)
- Health & Medical Sciences (AREA)
- Remote Sensing (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Computing Systems (AREA)
- Databases & Information Systems (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Radar, Positioning & Navigation (AREA)
- Mathematical Physics (AREA)
- Probability & Statistics with Applications (AREA)
- Control Of Position, Course, Altitude, Or Attitude Of Moving Bodies (AREA)
Abstract
The invention relates to the technical field of unmanned mine car driving, in particular to an automatic obstacle avoidance method of an unmanned mine car based on complex road conditions, which comprises the following steps: acquiring a road image of a mining area, and calculating the traffic rate of the unmanned mine car corresponding to the pixel position of the ore body according to depth information in the image; rasterizing the road image of the mining area, and calculating the movement loss corresponding to the unmanned mine car moving to the target grid according to the traffic rate; obtaining distance loss corresponding to the target grid according to the distance between the target grid and the end point position of the unmanned mine car; and obtaining a planned path of the unmanned mine car for automatic obstacle avoidance according to the movement loss and the distance loss corresponding to the target grid. The invention can directly complete automatic obstacle avoidance through partial obstacles while ensuring the driving safety, ensures the operating efficiency of unmanned mine cars in a mining area and reduces the possibility of blockage.
Description
Technical Field
The invention relates to the technical field of unmanned mine cars, in particular to an automatic obstacle avoidance method for an unmanned mine car based on complex road conditions.
Background
When the unmanned tramcar runs, the unmanned tramcar runs forward according to a given route, and the road surface is complex due to the fact that the road on the mine is narrow and the ore bodies are arranged on two sides of the road on the mine, but the unmanned tramcar is not beneficial to safe running of the unmanned tramcar on the road on the mine due to the fact that the road surface of the road on the mine is complex due to the fact that part of the ore bodies slide. Therefore, the automatic obstacle avoidance of the unmanned mine car is particularly important when the unmanned mine car needs to avoid road surface obstacles in the route planning.
In the existing obstacle avoidance method, an unmanned mine car acquires road condition data through a radar and a camera, the condition of obstacles on the road surface is obtained, the obstacles are marked, namely the obstacles exist, the obstacles are marked as impassable areas, new path planning is carried out again, and automatic obstacle avoidance of the unmanned mine car is realized. However, it is not possible for unmanned tramcars to pass all obstacles. The method does not consider the situation that some obstacles are small so that the unmanned mine car can pass through, and due to the fact that the road on the mine is narrow, the road condition is complex after part of ore bodies slide, all the obstacles are marked as the regions where the mine cannot pass through, road congestion can be caused due to the fact that the avoidance range is too large, and the operation of the road on the mine is affected.
Disclosure of Invention
In order to solve the technical problems, the invention aims to provide an automatic obstacle avoidance method for an unmanned mine car based on complex road conditions, and the adopted technical scheme is as follows:
acquiring a mine road image, acquiring the height of an ore body and the position of an ore body pixel according to depth information of pixel points in the mine road image, and acquiring the chassis height of the unmanned mine car; obtaining the passing rate of the unmanned mine car corresponding to the pixel position of the ore body according to the chassis height and the height of the ore body;
rasterizing the road image of the mining area, and calculating the movement loss corresponding to the unmanned mine car moving to the target grid according to the passing rate of pixel points in the grid;
obtaining distance loss corresponding to the target grid according to the distance between the target grid and the end point position of the unmanned mine car; and obtaining a planned path of the unmanned mine car for automatically avoiding the obstacle according to the movement loss and the distance loss corresponding to the target grid.
Preferably, the method for acquiring the height of the ore body and the pixel position of the ore body specifically comprises the following steps:
carrying out outlier detection on the depth information of the pixel points in the mine road image to obtain the outlier degree of the depth information of the pixel points; classifying the pixel points by using a density clustering algorithm according to the outlier degree and the pixel coordinates of the pixel points to obtain a plurality of categories; and taking the region formed by the pixels in the category corresponding to the outlier data as an ore body region, obtaining the height of the ore body according to the depth information of the pixels in the ore body region, and obtaining the pixel position of the ore body according to the pixel coordinates of the pixels in the ore body region.
Preferably, the method for acquiring the traffic rate of the unmanned tramcar corresponding to the ore body pixel position specifically comprises the following steps:
wherein the content of the first and second substances,
the passing rate of the unmanned mine car at the position of the ith ore body is shown, H is the chassis height of the unmanned mine car,
the height of the ith ore body is expressed, a and b are both hyper-parameters,
an exponential function with a natural constant e as the base is shown.
Preferably, the method for acquiring the movement loss corresponding to the unmanned mine car moving to the target grid specifically comprises the following steps:
recording the minimum value of the pass rates corresponding to all pixel points in the grid as the pass rate of the grid, and calculating the variance of the pass rates of the grid in which the tire area of the unmanned tramcar is located; and acquiring the minimum value of the traffic rates of all grids except the tire area in the area where the unmanned tramcar is located, and calculating the movement loss corresponding to the unmanned tramcar moving to the target grid according to the minimum value and the variance.
Preferably, the method for acquiring the distance loss corresponding to the target grid specifically includes: and obtaining the distance loss corresponding to the target grid according to the Euclidean distance between the central position of the target grid and the terminal position of the unmanned mine car.
Preferably, the obtaining of the planned path of the unmanned mine car for automatic obstacle avoidance according to the movement loss and the distance loss corresponding to the target grid further includes:
when the target grid moved by the unmanned mine car is selected, for the target grid moved in the planned path belonging to other unmanned mine cars, obtaining the difference of the running time according to the difference between the time when the current unmanned mine car reaches the target grid and the time when other unmanned mine cars reach the target grid; and when the running time difference is smaller than or equal to the time threshold, the target grid needs to be reselected to carry out the path planning of the current unmanned mine car.
The embodiment of the invention at least has the following beneficial effects:
the method calculates the passing rate of each ore body position by acquiring the height of the ore body and the chassis height of the unmanned mine car, can intuitively reflect the possibility that the unmanned mine car can pass at the ore body position, determines the passing rate of pixel points in the grid in an image according to the passing rate of the ore body position, further calculates the movement loss corresponding to the unmanned mine car moving to a target grid according to the passing rate in the grid, reflects the passing condition of the unmanned mine car reaching the grid when moving, and compared with conventional mark avoidance, the method can directly finish automatic obstacle avoidance through partial obstacles while ensuring the driving safety; meanwhile, the final planned route of the unmanned mine car is obtained by combining the distance loss, the running efficiency of the unmanned mine car in the mining area is guaranteed, and the possibility of blockage is reduced.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions and advantages of the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and other drawings can be obtained by those skilled in the art without creative efforts.
FIG. 1 is a flow chart of the method for automatically avoiding obstacles of the unmanned mine car based on complex road conditions.
Detailed Description
In order to further explain the technical means and effects of the present invention adopted to achieve the predetermined invention, the following detailed description, with reference to the accompanying drawings and the preferred embodiments, of the unmanned mine car automatic obstacle avoidance method based on complex road conditions according to the present invention, the specific implementation, structure, features and effects thereof are described in detail as follows. In the following description, different "one embodiment" or "another embodiment" refers to not necessarily the same embodiment. Furthermore, the particular features, structures, or characteristics may be combined in any suitable manner in one or more embodiments.
Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.
The following specifically describes a specific scheme of the unmanned mine car automatic obstacle avoidance method based on complex road conditions, which is provided by the invention, with reference to the accompanying drawings.
Example (b):
referring to fig. 1, a flowchart of a method for automatically avoiding obstacles for an unmanned mine car based on complex road conditions according to an embodiment of the present invention is shown, where the method includes the following steps:
acquiring a mine area road image, acquiring the height of an ore body and the position of an ore body pixel according to depth information of pixel points in the mine area road image, and acquiring the chassis height of an unmanned mine car; and obtaining the passing rate of the unmanned mine car corresponding to the pixel position of the ore body according to the chassis height and the height of the ore body.
Firstly, a millimeter wave radar and a camera are arranged on the unmanned mine car and used for acquiring road condition information of a current mine road, point cloud data is acquired by the millimeter wave radar, RGB images of the mine road are acquired by the camera, the coordinate relation between the point cloud data and the RGB images is calibrated, and depth information corresponding to each pixel point in the mine road image can be acquired by the millimeter wave radar. The depth information refers to height information of the unmanned mine car from different road surfaces, namely if the road surfaces have ore bodies with different heights, the depth information is different.
Although the roads in the mining area are composed of the broken stones, the roads in the mining area are relatively smooth roads, the broken stones on the road surface are not large under the general condition, and the difference between the depth information of the road surface is not large.
In this embodiment, the depth information of the pixel points in the mine road image is processed by using an outlier detection method, an outlier of the depth information of each pixel point is obtained, the outlier of the pixel point is further determined according to the outlier, the pixel points are classified by using a density clustering algorithm according to the outlier and the pixel coordinates of the pixel points, a plurality of categories are obtained, the pixel coordinates of the pixel points in the same category are similar, and the outliers are the same or similar. And then the classification can be used for representing ore bodies on the roads of the mining area, the depth information of the pixel points in each classification is used as the height of the ore bodies, and the pixel points belonging to the same classification can be the same ore body. And simultaneously, marking the position where the ore body exists, and acquiring the pixel coordinates of the ore body to obtain the pixel position of the ore body.
It should be noted that, processing data by using an outlier detection method is a known technique, and not described herein too much, and an implementer may also select another suitable method according to the actual situation to obtain the height of the ore body on the mine road and the location information where the ore body is located.
And then, acquiring the height of a chassis of the unmanned mine car, wherein the height of the chassis is the height from the chassis of the unmanned mine car to the road surface of the mining area. Because the distribution condition of ore body on the current mining area road can be represented to ore body height and ore body pixel position, to the ore body that highly is lower, unmanned mine car can easily pass through, and to the ore body that highly is higher, unmanned mine car probably need dodge. On the basis, the difference between the chassis height of the unmanned mine car and the height of the ore body is obtained, and the larger the difference is, the lower the height of the ore body is, and the chassis of the unmanned mine car is away from the ore body by a part of distance, so that the unmanned mine car can easily pass through; the smaller the difference, the higher the height of the ore body, the closer the chassis of the unmanned tramcar is to the ore body, and the risk that the unmanned tramcar directly passes through the ore body is certain, so the avoidance of the ore body needs to be considered. Therefore, the difference between the chassis height of the unmanned mine car and the height of the ore body is used as an influence index of the traffic rate of the unmanned mine car corresponding to the pixel position of the ore body.
That is, when the height of the ore body is greater than the height of the chassis of the unmanned mine car, the unmanned mine car cannot pass through the ore body at all, and the passing rate of the position where the ore body which cannot pass through is placed is infinitesimal. When the height of the ore body is smaller than the chassis height of the unmanned mine car, but the values of the ore body and the unmanned mine car are close to each other, the passing rate of the position of the ore body is low, and due to the fact that errors may exist in the acquired information, the closer the values of the ore body and the unmanned mine car are, the lower the passing rate of the position of the ore body is, and meanwhile, the avoidance of the ore body should be considered. The ore body height is less than the chassis height of unmanned mine car, and the ore body height is lower, and unmanned mine car can directly grind this ore body, and then the traffic rate of corresponding ore body position department is higher.
And finally, obtaining the passing rate of the unmanned mine car corresponding to the pixel position of the ore body according to the chassis height and the height of the ore body, and expressing the passing rate as follows by a formula:
wherein the content of the first and second substances,
the passing rate of the unmanned mine car at the position of the ith ore body is shown, H is the chassis height of the unmanned mine car,
represents the ithThe height of the ore body, a and b are both hyper-parameters,
an exponential function with a natural constant e as the base is shown.
And secondly, rasterizing the road image of the mining area, and calculating the movement loss corresponding to the movement of the unmanned mine car to the target grid according to the passing rate of the pixel points in the grid.
It should be noted that, after the passing rate of the unmanned mine car at the position of the ore body on the current mine road is obtained, since the wheel width and the wheel distance of the unmanned mine car are known, when the planned route of the unmanned mine car is obtained, if the ore body exists in the route, it should be ensured that the unmanned mine car can pass through all the ore bodies existing in the route. For example, if an ore body with a large volume or a large height exists in front of the current position of the unmanned mine car, the unmanned mine car cannot continuously pass along the front road, the problem of shielding between the front and the rear of the ore body is not needed to be considered, and even if the road behind the ore body with the large volume or the large height can pass, the unmanned mine car does not need to be considered to run along the front road.
Because the unmanned mine car passes through the area where all ore bodies are located integrally, the unmanned mine car is simplified into a rectangle, the area where the tires of the unmanned mine car are located is marked in the rectangle, and an implementer can simplify the graph of the unmanned mine car according to the specific type of the unmanned mine car. Meanwhile, when the path of the unmanned mine car is planned, the unmanned mine car has the maximum steering angle limit, the maximum steering angle is a parameter of the unmanned mine car, and in order to enable the unmanned mine car to have a higher safety factor, an implementer can adjust the maximum steering angle according to the actual situation. In this embodiment, the maximum steering angle of the unmanned mining vehicle is set to 45 degrees.
Meanwhile, the chassis of the unmanned mine car passing through the ore body is higher than the road surface, so that the height of the ore body passing through the ore body is higher, but the unmanned mine car runs on the ore body at a certain risk, and in order to reduce the running risk of the unmanned mine car, the situation that the unmanned mine car passes through the ore body is not considered, and the unmanned mine car is only ensured to run according to the passing rate obtained by the road surface height.
In this embodiment, the driving route of the unmanned mine car is planned by using an a-algorithm, wherein the a-algorithm is a direct search method that is most effective in solving the shortest path in a static road network. The mine road image needs to be rasterized, in order to ensure that the unmanned mine car can safely run according to the specified points after rasterization, the embodiment makes the pixel length of the rasterized grid 5cm relative to the length and width of the real world, and the implementer can adjust the length and width according to actual conditions.
In the mine area road image, the passing rate of the unmanned mine car marked as the corresponding pixel point in the area where the ore body is located is the passing rate of the unmanned mine car at the position where the ore body is located, and other pixel points without marks are the area without the ore body, so that the unmanned mine car at the position where the area without the ore body is located can directly and safely pass, namely the passing rate of the pixel points in the area is a first numerical value, in the embodiment, the value of the first numerical value is 1, and the passing rate of the unmanned mine car corresponding to each pixel point in the area without the ore body is 1. And in the rasterized mine area road image, taking the minimum value of the traffic rate corresponding to the pixel point in each grid as the traffic rate corresponding to the grid.
When the unmanned mine car passes through all ore bodies, the unmanned mine car is required to cover an area which cannot contain ore bodies with infinitesimal pass rate, the minimum value of the pass rate corresponding to grids in the area covered by the unmanned mine car is larger, the better the minimum value is, and the height of the ore body corresponding to the maximum value of the pass rate corresponding to grids in the area covered by the unmanned mine car is smaller, the better the maximum value is. That is, if there is a high-height ore body in the area covered by the unmanned mine car during running, the current area is not accessible, and the corresponding passing rate is lower.
When the driving route of the unmanned mine car is planned by the A-x algorithm, the target grid for setting the movement of the unmanned mine car can be selected only in the direction with the maximum steering angle of 45 degrees. The target grid moved by the unmanned tramcar is not a grid, but all grids covered by the whole rectangle corresponding to the unmanned tramcar after moving form the moved target grid, and the moved target grid comprises the former grid and the newly covered grid.
When the unmanned tramcar moves to a new position, the corresponding rectangle moves to a target grid, the traffic rates of all grids corresponding to the tire areas of the unmanned tramcar represented by the rectangle are obtained, the traffic rates in the tire areas of the unmanned tramcar are stable in the running process of the unmanned tramcar, and therefore the traffic rates of the tire areas are the same or close to each other, the variance of the traffic rates of all grids corresponding to the tire areas is calculated, the fluctuation condition of the traffic rates of all grids corresponding to the tire areas can be represented, if the variance is large, the fluctuation of the traffic rates corresponding to the tire areas is large, the traffic rates are not stable, the unmanned tramcar moves to the target grid, accidents can happen due to the fact that the vehicles are not stable, and the target grid is prevented from being selected.
And the traffic rate of all grids in other areas except the tire areas of the unmanned mine car is preferably larger, and if one grid with a smaller traffic rate exists in the current target grid, the traffic rate of the current target grid is lower as a whole. For example, the passage rates of the grids in the other areas than the tire area of the unmanned mine car are 0.8,0.9,0.7 and 0.1, and although there are several grids having a large passage rate, if there is one grid having an extremely low passage rate, the overall passage rate of the current target grid is extremely low, and the target grid should be avoided from being selected.
Calculating the movement loss corresponding to the movement of the unmanned mine car to the target grid, and expressing the movement loss as follows by using a formula:
wherein, the first and the second end of the pipe are connected with each other,
the movement loss corresponding to the unmanned tramcar moving to the target grid a,
representing the variance of the traffic rates of all grids in the tire zone when the unmanned tram moves to the target grid,
represents the minimum value of the passage rate of the grid in the region other than the tire region when the unmanned mine car moves to the target grid,
representing an exponential function with a natural constant e as the base.
It should be noted that, since the speed of the unmanned tramcar is fixed, the speed of the unmanned tramcar can be appropriately decelerated when passing through the ore body regardless of the change distance of the position of the unmanned tramcar before and after the movement indicated by the rectangle, and the decelerated speed is adjusted by the operator according to the specific scene, and in this embodiment, the decelerated speed is 20km/h.
Step three, obtaining distance loss corresponding to the target grid according to the distance between the target grid and the end point position of the unmanned mine car; and obtaining a planned path of the unmanned mine car for automatically avoiding the obstacle according to the movement loss and the distance loss corresponding to the target grid.
First, the final loss in the a-algorithm is composed of two parts, and the original algorithm formula of the final loss is F = G + H, where F denotes the final loss, G denotes the moving loss moving from the start point to the specified position, and H denotes the expected loss moving from the specified position to the end point. The embodiment has obtained the moving loss of the unmanned tramcar to the target grid, so it is also necessary to obtain the distance loss of the unmanned tramcar from the target grid to the end position.
Specifically, in this embodiment, the distance loss of the target grid moving to the end point is obtained by obtaining the euclidean distance between the center position of the center point of the target grid and the end point position of the unmanned tramcar, or may be calculated by obtaining the euclidean distance between the centroid position of the rectangle corresponding to the target grid and the end point position of the unmanned tramcar. The implementer can also select other suitable methods to obtain the distance from the target grid to the end point position according to actual conditions. Meanwhile, when the loss of the unmanned mine car from the target grid to the terminal is calculated, the passing rate is not considered because the target grid closer to the terminal is selected only through the distance loss possibility, and whether the unmanned mine car can pass or not is not considered, and whether the unmanned mine car can pass or not is determined by the moving loss of the unmanned mine car from the target grid to the terminal.
Then, when a target grid for each movement of the unmanned mine car is selected, in order to ensure that the unmanned mine car can safely and quickly travel to the end point, no vehicle comes from the opposite direction in the travel route of other unmanned mine cars, no ore body exists on the road surface, or the ore body easily passes through the road, the current unmanned mine car can be considered to travel by lane. Whether the vehicle can be borrowed for running depends on the distance value between the current unmanned mine car and the unmanned mine car on the road route when the current unmanned mine car runs for borrowing the road, and the speed of the unmanned mine car is constant and the same, so that whether the current unmanned mine car runs for borrowing the road or not can be judged by considering the time of other cars arriving at the place when the unmanned mine car runs for borrowing the road.
Specifically, the running route of each unmanned mine car is acquired through a GPS signal module loaded in each unmanned mine car, when a target grid moved by the current unmanned mine car is selected, if the target grid is a grid in the running routes of other unmanned mine cars, the time required for the current unmanned mine car to reach the target grid from the starting point is acquired, the time for the unmanned mine car corresponding to the running route of the target grid to reach the target grid is acquired, and the absolute value of the difference between the two times is calculated to obtain the running time difference.
The greater the running time difference is, the smaller the collision probability between the current unmanned mine car and other unmanned mine cars is, and the smaller the meeting probability is, and the smaller the running time difference is, the greater the collision probability between the current unmanned mine car and other unmanned mine cars is, and the greater the meeting probability is.
And setting a time threshold, and when the running time difference is greater than the time threshold, indicating that the road route of the current unmanned mine car borrowed by other unmanned mine cars is safe, selecting the target grid to plan the running route of the current unmanned mine car. When the running time difference is smaller than or equal to the time threshold, the situation that the road route of the current unmanned mine car borrows other unmanned mine cars is dangerous is shown, and in order to prevent the collision event, the target grid should be avoided from being selected, and the target grid needs to be selected again to plan the running route of the current unmanned mine car. In this embodiment, the value of the time threshold is 20s, and an implementer can adjust the value of the time threshold according to an actual situation, and in order to prevent a collision, the value of the time threshold should be made as large as possible.
And finally, obtaining the current global loss of the unmanned mine car moving to a target grid as W = X + Y according to the original algorithm formula of the final loss in the A-algorithm, wherein W represents the global loss corresponding to the unmanned mine car moving to the target grid, X represents the moving loss of the unmanned mine car moving to the target grid, and Y represents the distance loss of the unmanned mine car moving from the target grid to the end position. The larger the value of the global loss is, the larger the cost paid by the unmanned mine car when the unmanned mine car runs on the current planned path is. And then, according to the global loss, the A-star algorithm is used for carrying out iteration to plan the running route of the unmanned tramcar.
When planning the driving route of the unmanned mine car, the starting point of the unmanned mine car is the camp position of the unmanned mine car, the end point is the position with the distance of 10m from the ore body area, and the implementer can set the starting point and the end point according to the specific implementation scene.
When a new planned route cannot be iterated through the A-algorithm or infinite global loss values are contained in the iteration process of planning the new route, the current unmanned mine car should stop advancing. And the unmanned mine car behind is warned through the data center, and the advance is stopped. And if the current unmanned mine car can normally pass, the rear unmanned mine car runs according to the planned route of the current unmanned mine car. And if the rear vehicle runs by means of the road according to the current planned route of the unmanned mine car, and the borrowed road route has a vehicle coming, entering a waiting state, and running after a new passable route is available, so that the unmanned mine car automatically avoiding the obstacle is completed under the current complex road condition. Wherein, once detect ore body after, need to feed back ore body regional position through wireless transmission's mode to the maintenance of mining area road.
The above-mentioned embodiments are only used to illustrate the technical solutions of the present application, and not to limit the same; although the present application has been described in detail with reference to the foregoing embodiments, it should be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; such modifications or substitutions do not cause the essential features of the corresponding technical solutions to depart from the scope of the technical solutions of the embodiments of the present application, and are intended to be included within the scope of the present application.
Claims (6)
1. An automatic obstacle avoidance method for an unmanned mine car based on complex road conditions is characterized by comprising the following steps:
acquiring a mine road image, acquiring the height of an ore body and the position of an ore body pixel according to depth information of pixel points in the mine road image, and acquiring the chassis height of the unmanned mine car; obtaining the passing rate of the unmanned mine car corresponding to the pixel position of the ore body according to the chassis height and the height of the ore body;
rasterizing the road image of the mining area, and calculating the movement loss corresponding to the movement of the unmanned mine car to the target grid according to the passing rate of pixel points in the grid;
obtaining distance loss corresponding to the target grid according to the distance between the target grid and the end point position of the unmanned mine car; and obtaining a planned path of the unmanned mine car for automatically avoiding the obstacle according to the movement loss and the distance loss corresponding to the target grid.
2. The automatic obstacle avoidance method for the unmanned mine car based on the complex road condition as claimed in claim 1, wherein the method for obtaining the height of the ore body and the pixel position of the ore body is specifically as follows:
carrying out outlier detection on the depth information of the pixel points in the mine road image to obtain the outlier degree of the depth information of the pixel points; classifying the pixel points by using a density clustering algorithm according to the outlier degree and the pixel coordinates of the pixel points to obtain a plurality of categories; and taking the region formed by the pixels in the category corresponding to the outlier data as an ore body region, obtaining the height of the ore body according to the depth information of the pixels in the ore body region, and obtaining the pixel position of the ore body according to the pixel coordinates of the pixels in the ore body region.
3. The automatic obstacle avoidance method for the unmanned mine car based on the complex road condition as claimed in claim 1, wherein the obtaining method of the traffic rate of the unmanned mine car corresponding to the pixel position of the ore body is specifically as follows:
wherein the content of the first and second substances,
the passing rate of the unmanned mine car at the position of the ith ore body is shown, H is the chassis height of the unmanned mine car,
the height of the ith ore body is shown, a and b are both hyper-parameters,
an exponential function with a natural constant e as the base is shown.
4. The automatic obstacle avoidance method for the unmanned mine car based on the complex road condition as claimed in claim 1, wherein the method for acquiring the movement loss corresponding to the unmanned mine car moving to the target grid specifically comprises:
recording the minimum value of the pass rates corresponding to all pixel points in the grid as the pass rate of the grid, and calculating the variance of the pass rates of the grid in which the tire area of the unmanned tramcar is located; and acquiring the minimum value of the traffic rates of all grids except the tire area in the area where the unmanned tramcar is located, and calculating the movement loss corresponding to the movement of the unmanned tramcar to the target grid according to the minimum value and the variance.
5. The method for automatically avoiding obstacles of the unmanned tramcar according to claim 1, wherein the method for obtaining the distance loss corresponding to the target grid comprises the following specific steps: and obtaining the distance loss corresponding to the target grid according to the Euclidean distance between the central position of the target grid and the terminal position of the unmanned mine car.
6. The method according to claim 1, wherein obtaining the planned path of the unmanned mine car for automatic obstacle avoidance according to the movement loss and the distance loss corresponding to the target grid further comprises:
when the target grid moved by the unmanned mine car is selected, for the target grid moved in the planned path belonging to other unmanned mine cars, obtaining the difference of the running time according to the difference between the time when the current unmanned mine car reaches the target grid and the time when other unmanned mine cars reach the target grid; and when the running time difference is smaller than or equal to the time threshold, the target grid needs to be reselected to carry out the path planning of the current unmanned mine car.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211276249.6A CN115346385B (en) | 2022-10-19 | 2022-10-19 | Unmanned mine car automatic obstacle avoidance method based on complex road conditions |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211276249.6A CN115346385B (en) | 2022-10-19 | 2022-10-19 | Unmanned mine car automatic obstacle avoidance method based on complex road conditions |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115346385A CN115346385A (en) | 2022-11-15 |
| CN115346385B true CN115346385B (en) | 2023-01-03 |
Family
ID=83957160
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211276249.6A Active CN115346385B (en) | 2022-10-19 | 2022-10-19 | Unmanned mine car automatic obstacle avoidance method based on complex road conditions |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115346385B (en) |
Families Citing this family (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115880674B (en) * | 2023-03-01 | 2023-05-23 | 上海伯镭智能科技有限公司 | Obstacle avoidance steering correction method based on unmanned mine car |
| CN116300973B (en) * | 2023-05-18 | 2023-08-04 | 上海伯镭智能科技有限公司 | Autonomous obstacle avoidance method for unmanned mine car in complex weather |
| CN117315992B (en) * | 2023-10-07 | 2024-05-07 | 北京中航天佑科技有限公司 | Mining shuttle car automatic driving obstacle avoidance device and obstacle avoidance system |
| CN117148848B (en) * | 2023-10-27 | 2024-01-26 | 上海伯镭智能科技有限公司 | Intelligent obstacle avoidance method and system for unmanned vehicle |
Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105620409A (en) * | 2014-11-24 | 2016-06-01 | 福特全球技术公司 | Vehicle underside impact avoidance |
| CN105825712A (en) * | 2016-03-22 | 2016-08-03 | 乐视网信息技术（北京）股份有限公司 | Vehicle alarm method and device |
| JP2017182498A (en) * | 2016-03-30 | 2017-10-05 | トヨタ自動車株式会社 | Drive support apparatus |
| CN107480638A (en) * | 2017-08-16 | 2017-12-15 | 北京京东尚科信息技术有限公司 | Vehicle obstacle-avoidance method, controller, device and vehicle |
| CN108919803A (en) * | 2018-07-04 | 2018-11-30 | 北京踏歌智行科技有限公司 | A kind of cooperative control method and device of mining automatic driving vehicle |
| CN110799400A (en) * | 2017-06-28 | 2020-02-14 | 奥迪股份公司 | Method for at least partially automatically operating a motor vehicle |
| CN113147789A (en) * | 2021-05-08 | 2021-07-23 | 银隆新能源股份有限公司 | Control method and control device for unmanned vehicle and unmanned vehicle |
| CN113536849A (en) * | 2020-04-20 | 2021-10-22 | 安徽小眯当家信息技术有限公司 | Crowd gathering identification method and device based on image identification |
| CN113807571A (en) * | 2021-08-12 | 2021-12-17 | 合肥中科智驰科技有限公司 | Real-time planning system for unmanned vehicle path |
| JP2022073083A (en) * | 2020-10-30 | 2022-05-17 | 国立研究開発法人物質・材料研究機構 | Image processing method, image processing device, x-ray diffraction device, and program |
| CN115077556A (en) * | 2022-07-26 | 2022-09-20 | 中国电子科技集团公司第二十八研究所 | Unmanned vehicle field operation path planning method based on multi-dimensional map |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106662021B (en) * | 2014-09-19 | 2019-12-03 | 日立汽车系统株式会社 | Controller of vehicle and control method for vehicle |
-
2022
- 2022-10-19 CN CN202211276249.6A patent/CN115346385B/en active Active
Patent Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105620409A (en) * | 2014-11-24 | 2016-06-01 | 福特全球技术公司 | Vehicle underside impact avoidance |
| CN105825712A (en) * | 2016-03-22 | 2016-08-03 | 乐视网信息技术（北京）股份有限公司 | Vehicle alarm method and device |
| JP2017182498A (en) * | 2016-03-30 | 2017-10-05 | トヨタ自動車株式会社 | Drive support apparatus |
| CN110799400A (en) * | 2017-06-28 | 2020-02-14 | 奥迪股份公司 | Method for at least partially automatically operating a motor vehicle |
| CN107480638A (en) * | 2017-08-16 | 2017-12-15 | 北京京东尚科信息技术有限公司 | Vehicle obstacle-avoidance method, controller, device and vehicle |
| CN108919803A (en) * | 2018-07-04 | 2018-11-30 | 北京踏歌智行科技有限公司 | A kind of cooperative control method and device of mining automatic driving vehicle |
| CN113536849A (en) * | 2020-04-20 | 2021-10-22 | 安徽小眯当家信息技术有限公司 | Crowd gathering identification method and device based on image identification |
| JP2022073083A (en) * | 2020-10-30 | 2022-05-17 | 国立研究開発法人物質・材料研究機構 | Image processing method, image processing device, x-ray diffraction device, and program |
| CN113147789A (en) * | 2021-05-08 | 2021-07-23 | 银隆新能源股份有限公司 | Control method and control device for unmanned vehicle and unmanned vehicle |
| CN113807571A (en) * | 2021-08-12 | 2021-12-17 | 合肥中科智驰科技有限公司 | Real-time planning system for unmanned vehicle path |
| CN115077556A (en) * | 2022-07-26 | 2022-09-20 | 中国电子科技集团公司第二十八研究所 | Unmanned vehicle field operation path planning method based on multi-dimensional map |
Non-Patent Citations (2)
| Title |
|---|
| Path Planning for Mobile Robots on Rough Terrain;Alexandre S. Santos 等;《2018 Latin American Robotic Symposium, 2018 Brazilian Symposium on Robotics (SBR) and 2018 Workshop on Robotics in Education (WRE)》;20181227;265-270 * |
| 非结构化场景下地面无人平台环境感知及三维路径规划研究;张旋;《中国优秀硕士学位论文全文数据库工程科技Ⅱ辑》;20211215;55-58 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115346385A (en) | 2022-11-15 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN115346385B (en) | Unmanned mine car automatic obstacle avoidance method based on complex road conditions | |
| US11685360B2 (en) | Planning for unknown objects by an autonomous vehicle | |
| CN112204633B (en) | Probabilistic object tracking and prediction framework | |
| US11034346B2 (en) | Navigation at alternating merge zones | |
| CN110667578B (en) | Lateral decision making system and lateral decision making determination method for automatic driving vehicle | |
| CN111383474B (en) | Decision making system and method for automatically driving vehicle | |
| US11532167B2 (en) | State machine for obstacle avoidance | |
| US10703362B2 (en) | Autonomous driving autonomous system, automated driving assistance method, and computer program | |
| US10982961B2 (en) | Vehicle control system and vehicle control device | |
| US20190232957A1 (en) | Planning for unknown objects by an autonomous vehicle | |
| US11433894B2 (en) | Driving assistance method and driving assistance device | |
| US11938926B2 (en) | Polyline contour representations for autonomous vehicles | |
| US20180259967A1 (en) | Planning for unknown objects by an autonomous vehicle | |
| US20190027036A1 (en) | Driving Assistance Method and Device | |
| JP2023106554A (en) | Automatic driving device, automatic driving method, and control program | |
| US11842430B2 (en) | Methods and systems for ground segmentation using graph-cuts | |
| CN116457853A (en) | Vehicle track planning method and device and vehicle | |
| CN113734191A (en) | Artificially spoofing sensor data to initiate safety actions for autonomous vehicles | |
| US20230056589A1 (en) | Systems and methods for generating multilevel occupancy and occlusion grids for controlling navigation of vehicles | |
| EP3975137A1 (en) | Road-perception system configured to estimate a belief and plausibility of lanes in a road model | |
| US20220105940A1 (en) | Methods and systems for performing outlet inference by an autonomous vehicle to determine feasible paths through an intersection | |
| CN113178088A (en) | Infrastructure component for broadcasting to vehicles | |
| US11433920B2 (en) | Map-based prediction and mitigation of performance limitations for autonomous vehicles | |
| CN113819920A (en) | Automatic driving non-autonomous navigation method for congested road section | |
| CN117799633A (en) | Prediction method and device and intelligent driving equipment |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |