Disclosure of Invention
Technical problem to be solved
Aiming at the defects of the prior art, the invention provides a waiting position generation method and a waiting position generation device for an unmanned mine vehicle to be loaded, which solve the problem of distributing the waiting positions of the vehicle to be loaded to ensure the safe and ordered loading of the vehicle.
(II) technical scheme
In order to achieve the purpose, the invention is realized by the following technical scheme:
in a first aspect, a waiting space generation method for a to-be-loaded vehicle used for mine unmanned driving is provided, and the method comprises the following steps:
acquiring an available search space of a waiting position based on a track that a vehicle drives out of a loading area from a current loading position and a minimum parking safety distance;
acquiring candidate waiting positions and coordinates and optimal orientations of the candidate waiting positions based on the available search space;
and acquiring the weight of each candidate waiting bit based on the track entering the candidate waiting bit from the entrance of the loading area and the track entering the target loading bit from the candidate waiting bit, and selecting the waiting bit corresponding to the optimal weight as the optimal waiting bit.
Further, the obtaining of the available search space of the waiting space based on the track of the vehicle driving out of the loading area from the current loading position and the minimum parking safety distance comprises:
obtaining the space occupied by the track of the vehicle driving out of the loading area from the current loading position and the space occupied by the area taking the current loading position as the center and the minimum parking safety distance as the radius to jointly form a search forbidding space;
and taking the loading area with the forbidden search space deleted as an available search space.
Further, the obtaining the available search space of the wait bit further includes:
and acquiring a region which is subjected to outward expansion at a preset distance based on the boundary of the search prohibiting space in the available search space as an optimal available search space.
Further, the obtaining of the candidate waiting position and the coordinates and the optimal orientation of the candidate waiting position based on the available search space includes:
acquiring a rasterized available search space;
taking the coordinates of the central point of each grid as the coordinates of candidate waiting positions;
and calculating the optimal orientation of each candidate waiting position based on the turning radius of the vehicle and an automatic driving motion planning algorithm.
Further, the calculating of the optimal orientation of each waiting position candidate based on the turning radius and the automatic driving movement of the vehicle includes:
for any candidate wait bit:
discretizing 0-360 degrees into n discrete orientations;
taking the n candidate waiting positions as a starting point and the target loading position as an end point, and acquiring a track curve of the vehicle entering the loading position from the candidate waiting positions by utilizing an automatic driving motion planning algorithm;
and acquiring the direction with the shortest distance in the n track curves as the optimal direction corresponding to the central point of the grid.
Further, if the trajectory curve corresponding to the optimal orientation of the candidate waiting bit contains a commutation trajectory, the candidate waiting bit is deleted.
Further, the obtaining the weight of each candidate waiting bit based on the trajectory entering the candidate waiting bit from the entry of the loading area and the trajectory entering the target loading bit from the candidate waiting bit, and selecting the waiting bit corresponding to the optimal weight as the optimal waiting bit includes:
acquiring a track of a vehicle entering a candidate waiting position from an entrance of a loading area and a track of the vehicle entering a target loading position from the candidate waiting position, and acquiring the corresponding reversing times of the tracks and the driving distance of the vehicle;
the weight of each candidate waiting bit is calculated, and the calculation formula is as follows:
wherein J represents the weight of the candidate wait bit;
a distance weight representing an incoming candidate wait bit;
indicating a distance into a candidate wait bit;
a weight representing the number of commutations into the candidate wait bit;
indicating the number of commutations into the candidate wait bit;
a distance weight representing a candidate waiting position is driven;
indicating a distance to exit the candidate waiting space;
representing a commutation time weight of the candidate waiting position;
representing the number of commutations of the candidate waiting position;
and selecting the candidate waiting bit with the minimum weight as the optimal waiting bit.
Further, the method for acquiring the target loading position comprises the following steps:
acquiring the coordinate and the orientation of a current loading position of the excavator and the coordinate and the orientation of a historical loading position of the excavator;
when the historical loading positions are distributed on two sides of the excavator, calculating the average orientation of all the historical loading positions
As the orientation of the target load site;
rotating the coordinate axis XOY of the historical loading position counterclockwise
Obtaining a new coordinate axis X 'OY';
based on the average orientation
Calculating the coordinates of all historical loading positions and the current loading position on the coordinate axis X 'OY', wherein the calculation method comprises the following steps:
wherein X 'and y' are two components of coordinates in X 'OY', and X and y are two components of coordinates in XOY;
acquiring X ' components of all historical loading positions and current loading positions on a coordinate axis X ' OY ', clustering by a clustering algorithm, and dividing all historical loading positions into two types according to the left side and the right side of the average orientation of the historical loading positions;
and taking the center coordinates of the class where the non-current loading position is located as the coordinates of the target loading position.
Further, when all the historical loading positions are positioned at one side of the excavator or no historical loading positions exist,
calculating the side of the current loading position relative to the excavator, wherein the side of the loading position relative to the excavator comprises the left side or the right side of the excavator;
taking the current loading position as a reference, translating the current loading position to the other side of the current loading position relative to the excavator to obtain the coordinate of the target loading position;
and if the orientation of the excavator and the orientation of the target loading position are collinear, randomly generating the direction as the orientation of the target loading position, and otherwise, taking the orientation of the current loading position as the orientation of the target loading position.
In a second aspect, there is provided a waiting space generation device for a vehicle to be loaded in a mine unmanned plane, the device comprising:
the available search space acquisition module is used for acquiring an available search space of the waiting position based on the track that the vehicle drives out of the loading area from the current loading position and the minimum parking safety distance;
a candidate waiting bit obtaining module for obtaining candidate waiting bits and coordinates and an optimal orientation of the candidate waiting bits based on an available search space;
and the optimal waiting position determining module is used for acquiring the weight of each candidate waiting position based on a track entering the candidate waiting position from the entrance of the loading area and a track entering the target loading position from the candidate waiting position, and selecting the waiting position corresponding to the optimal weight as the optimal waiting position.
In a third aspect, a computer-readable storage medium is provided, which stores a computer program for generating a waiting space for a mine unmanned vehicle to be loaded, wherein the computer program causes a computer to execute the above-described waiting space generation method for a mine unmanned vehicle to be loaded.
In a fourth aspect, an electronic device includes:
one or more processors;
a memory; and
one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the one or more processors, the programs comprising instructions for performing the above-described waiting space generation method for a mine unmanned vehicle.
(III) advantageous effects
The invention provides a waiting position generation method and device for a to-be-loaded vehicle in unmanned mine. Compared with the prior art, the method has the following beneficial effects:
according to the invention, based on the track that the vehicle is driven out of the loading area from the current loading position and the minimum parking safety distance, the available search space of the waiting position is obtained, the loading vehicle can be ensured to smoothly leave the loading position after the loading is finished, and the condition that a plurality of vehicles are jammed when entering the same loading position is prevented. And then, acquiring candidate waiting positions and coordinates and optimal orientations of the candidate waiting positions based on the available search space, acquiring the weight of each candidate waiting position based on a track entering the candidate waiting positions from the entrance of the loading area and a track entering the target loading position from the candidate waiting positions, and selecting the waiting position corresponding to the optimal weight as the optimal waiting position, so that safe and orderly loading of the vehicle can be ensured, and the loading efficiency can be effectively improved.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention are clearly and completely described, and it is obvious that the described embodiments are a part of the embodiments of the present invention, but not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
The embodiment of the application provides a waiting position generation method and device for the unmanned mine vehicle to be loaded, and solves the problem that how to distribute the waiting positions of the vehicle to be loaded to ensure safe and orderly loading of the vehicle.
In order to solve the technical problems, the general idea of the embodiment of the application is as follows:
the available search space of the waiting position is obtained based on the track that the vehicle drives out of the loading area from the current loading position and the minimum parking safety distance, the loading vehicle can be guaranteed to smoothly leave the loading position after the loading is finished, and the situation that congestion occurs when a plurality of vehicles enter the same loading position is prevented. And then acquiring candidate waiting positions and coordinates and optimal orientations of the candidate waiting positions based on the available search space, acquiring the weight of each candidate waiting position based on a track entering the candidate waiting positions from the entrance of the loading area and a track entering the target loading position from the candidate waiting positions, and selecting the waiting position corresponding to the optimal weight as the optimal waiting position, thereby effectively improving the loading efficiency.
In order to better understand the technical solution, the technical solution will be described in detail with reference to the drawings and the specific embodiments.
Example 1:
as shown in fig. 1, the invention provides a waiting space generation method for a to-be-loaded vehicle in mine unmanned operation, which comprises the following steps:
acquiring an available search space of a waiting position based on a track that a vehicle drives out of a loading area from a current loading position and a minimum parking safety distance;
acquiring candidate waiting positions and coordinates and optimal orientations of the candidate waiting positions based on the available search space;
and acquiring the weight of each candidate waiting bit based on the track entering the candidate waiting bit from the entrance of the loading area and the track entering the target loading bit from the candidate waiting bit, and selecting the waiting bit corresponding to the optimal weight as the optimal waiting bit.
The beneficial effect of this embodiment does:
according to the embodiment of the invention, the available search space of the waiting position is obtained based on the track that the vehicle is driven out of the loading area from the current loading position and the minimum parking safety distance, the loading vehicle can be ensured to smoothly leave the loading position after the loading is finished, and the condition that a plurality of vehicles are jammed when entering the same loading position is prevented. And then acquiring candidate waiting positions and coordinates and optimal orientations of the candidate waiting positions based on the available search space, acquiring the weight of each candidate waiting position based on a track entering the candidate waiting positions from the entrance of the loading area and a track entering the target loading position from the candidate waiting positions, and selecting the waiting position corresponding to the optimal weight as the optimal waiting position, thereby effectively improving the loading efficiency.
The following describes the implementation process of the embodiment of the present invention in detail:
as shown in the loading area diagram of fig. 2, the maximum search space of the waiting bit is the whole loading area, but for a scenario with a large loading area, it is very time-consuming to perform a global search.
The principles and constraints for waiting space generation for a waiting vehicle are as follows:
(1) the route of the vehicle at the current loading position out of the loading position cannot be shielded;
(2) keeping a certain safety distance with the vehicle at the current loading position;
therefore, a search space in which the wait bit is appropriate needs to be determined.
S1, acquiring an available search space of the waiting space based on the track that the vehicle drives out of the loading area from the current loading position and the minimum parking safety distance;
specifically, it is first necessary to determine a search forbidden space, which mainly consists of two regions:
one of the space occupied by the track of the vehicle which is driven out of the loading area from the current loading position;
the other is the space occupied by the area taking the current loading position as the center and the minimum parking safety distance as the radius;
thus, as shown in FIG. 3, the available search space for the wait bit is the area of the entire load region that remains after the area of the search space is removed.
In the actual process of searching for the waiting space, if the available search space is still very large after the forbidden search space is removed, in order to reduce the search space, the region near the intersection (including the exit and the entrance) of the loading area can be removed by expanding the forbidden search space boundary, so as to obtain the optimal available search space shown in fig. 4.
The specific extended preset distance generally considers the sum of the maximum width of the two vehicles and a certain safety distance, and the purpose is to ensure that when one vehicle is to be loaded and parked, the other vehicle can safely enter the loading position.
The optimal available search space is a continuous two-dimensional space, and discrete candidate waiting bits need to be acquired in the space.
And S2, acquiring the candidate waiting position and the coordinate and the optimal orientation of the candidate waiting position based on the available search space.
The optimal available search space can be rasterized, the rasterized optimal available search space is composed of a plurality of grids, and coordinates of center points of all the grids completely in the optimal available search space are taken as coordinates of candidate waiting bits. After the coordinates are determined, the orientation of the candidate wait bits also needs to be determined.
The orientation of each candidate waiting bit can be any orientation between 0-360 degrees, and when searching is carried out, only one orientation on the coordinates of each candidate waiting bit is considered to be optimal.
To determine this optimal orientation, the optimal orientation for each candidate waiting position may be calculated based on the turning radius of the vehicle and the automated driving motion planning algorithm.
Specifically, the following method can be used to obtain the optimal orientation:
(1) discretizing 0-360 degrees, and dividing the discretized data into n discrete angles (if one sample is obtained every 10 degrees, n is 36), so that each grid central point will obtain n discretized candidate waiting bits with different orientations.
(2) The Reeds-Shepp curve is calculated with the n candidate wait bits as the starting point and the target load bit as the end point (simulating the trajectory of the incoming load bit).
(3) And taking the orientation with the shortest distance of the Reeds-Shepp curve from the n candidate waiting bits as the optimal orientation corresponding to the central point of the grid.
(4) And if the optimal orientation corresponding to the Reeds-Shepp curve contains a reversing track, the reversing track is a track of the vehicle in the processes of starting, accelerating, decelerating and restarting. For example, if the vehicle moves forward and then moves backward, the candidate waiting space is eliminated. And ensuring that the candidate waiting position to the target loading position only needs to be backed by the vehicle for one time, otherwise, the efficiency is low.
After the operation, the improper candidate waiting positions (namely, the entering target loading positions need to be reversed) are further removed, and each remaining candidate waiting position obtains an optimal angle.
And obtaining a complete candidate waiting position list through the screening of the candidate waiting positions and the determination of the angle. All candidate wait bits need to be sorted next to determine the optimal wait bit and its weight.
S4, acquiring the weight of each candidate waiting position based on the track entering the candidate waiting position from the entrance of the loading area and the track entering the target loading position from the candidate waiting position, and selecting the waiting position corresponding to the optimal weight as the optimal waiting position.
Specifically, the target reprint bit may be obtained by any method, the present invention is not limited, and only one feasible specific implementation flow is given below:
acquiring the coordinate and the orientation of a current loading position of the excavator and the coordinate and the orientation of a historical loading position of the excavator; after obtaining, there are three distribution situations of the historical loading bits:
the first method comprises the following steps: when the historical loading positions are distributed on two sides of the excavator:
calculating the average orientation of all historical load bits
As the orientation of the target load site;
rotating the coordinate axis XOY of the historical loading position counterclockwise
Obtaining a new coordinate axis X 'OY';
based on the average orientation
Calculating the coordinates of all historical loading positions and the current loading position on the coordinate axis X 'OY', wherein the calculation method comprises the following steps:
wherein X 'and y' are two components of coordinates in X 'OY', and X and y are two components of coordinates in XOY;
acquiring X ' components of all historical loading positions and current loading positions on a coordinate axis X ' OY ', and clustering by using a clustering algorithm, for example, a K-Means clustering algorithm can be adopted:
t1, randomly initializing K (two in this example) cluster centers (cluster centers) for a given set of data;
t2, calculating the distance from each data to the center of the cluster, and classifying the data as the cluster closest to the data;
t3, recalculating the cluster center according to the obtained cluster;
t4, iterating T2, T3 until the cluster center no longer changes or is less than a specified threshold.
Dividing all historical loading positions into two types according to the left side and the right side of the average orientation of the historical loading positions;
and taking the center coordinates of the class where the non-current loading position is located as the coordinates of the target loading position.
And the second method comprises the following steps: when all the historical loading positions are positioned at one side of the excavator;
and the third is that: when there is no historical load bit;
the second and third cases may employ the following methods:
calculating the side of the current loading position relative to the excavator, wherein the side of the loading position relative to the excavator comprises the left side or the right side of the excavator;
as shown in fig. 5, with the current loading position as a reference, translating the current loading position to the other side of the current loading position relative to the excavator to obtain a coordinate of the target loading position; the distance of translation is set according to the lateral safety interval to be installed and the width of the unmanned vehicle.
And if the orientation of the excavator and the orientation of the target loading position are collinear, randomly generating the direction as the orientation of the target loading position, and otherwise, taking the orientation of the current loading position as the orientation of the target loading position.
In order to ensure the accuracy of the historical loading bits, only a certain amount of historical loading bit data is taken for analysis. Meanwhile, when the distance or orientation deviation between the latest current loading position and the historical loading position exceeds a certain threshold value, the excavator is considered to have changed the loading position, and therefore all the historical loading positions are emptied.
The optimal waiting position is defined to meet the safety constraint of the waiting position, and meanwhile, the track of the vehicle entering the target loading position from the waiting position and the track weight of the vehicle entering the waiting position from the intersection of the loading area are comprehensively optimal.
In consideration of the actual driving process, the weight of the vehicle track mainly takes two factors into consideration, namely the number of commutations of the vehicle and the driving distance of the vehicle,
therefore, the weight calculation formula of the candidate wait bit is:
wherein J represents the weight of the candidate wait bit;
a distance weight representing an incoming candidate wait bit;
indicating a distance into a candidate wait bit;
a weight representing the number of commutations into the candidate wait bit;
indicating the number of commutations into the candidate wait bit;
a distance weight representing a candidate waiting position is driven;
indicating a distance to exit the candidate waiting space;
representing a commutation time weight of the candidate waiting position;
indicating the number of commutations to drive out of the candidate waiting position.
Generally, the commutation times weight needs to be much larger than the distance weight for preventing commutation of the vehicle into and out of the waiting space.
In the actual operation process, the reversing times and the traveling distance in the formula need to be determined.
Because the actual vehicle is constrained by information such as obstacles and loading area boundaries when driving in the loading area, a specific calculation algorithm is not provided here, and is generally obtained directly by directly adopting a global path planning algorithm of the vehicle, and the specific algorithm includes Dijkstra, a, mixed a, RRT and the like, and is not expanded here.
And after the reversing times and the distance of the vehicle are obtained by utilizing the global path planning algorithm, the weights of all candidate waiting positions can be obtained by substituting the formula, and after all the candidate waiting positions are sorted from low to high according to the weights, the candidate waiting position with the minimum weight is selected as the optimal waiting position.
Example 2:
a waiting space generation device for a mine unmanned vehicle to be loaded, the device comprising:
the available search space acquisition module is used for acquiring an available search space of the waiting position based on the track that the vehicle drives out of the loading area from the current loading position and the minimum parking safety distance;
a candidate waiting bit obtaining module for obtaining candidate waiting bits and coordinates and an optimal orientation of the candidate waiting bits based on an available search space;
and the optimal waiting position determining module is used for acquiring the weight of each candidate waiting position based on a track entering the candidate waiting position from the entrance of the loading area and a track entering the target loading position from the candidate waiting position, and selecting the waiting position corresponding to the optimal weight as the optimal waiting position.
It can be understood that the device for generating the waiting space for the vehicle to be loaded for the unmanned mine provided in the embodiment of the present invention corresponds to the method for generating the waiting space for the vehicle to be loaded for the unmanned mine, and the explanation, the example, and the beneficial effects of the relevant contents thereof may refer to the corresponding contents in the method for generating the waiting space for the vehicle to be loaded for the unmanned mine, and are not repeated herein.
Example 3:
a computer-readable storage medium storing a computer program for generating a waiting space for a mine unmanned vehicle to be loaded, wherein the computer program causes a computer to execute the steps of:
acquiring an available search space of a waiting position based on a track that a vehicle drives out of a loading area from a current loading position and a minimum parking safety distance;
acquiring candidate waiting positions and coordinates and optimal orientations of the candidate waiting positions based on the available search space;
and acquiring the weight of each candidate waiting bit based on the track entering the candidate waiting bit from the entrance of the loading area and the track entering the target loading bit from the candidate waiting bit, and selecting the waiting bit corresponding to the optimal weight as the optimal waiting bit.
Example 4:
an electronic device, comprising:
one or more processors;
a memory; and
one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the one or more processors, the programs comprising instructions for performing the steps of:
acquiring an available search space of a waiting position based on a track that a vehicle drives out of a loading area from a current loading position and a minimum parking safety distance;
acquiring candidate waiting positions and coordinates and optimal orientations of the candidate waiting positions based on the available search space;
and acquiring the weight of each candidate waiting bit based on the track entering the candidate waiting bit from the entrance of the loading area and the track entering the target loading bit from the candidate waiting bit, and selecting the waiting bit corresponding to the optimal weight as the optimal waiting bit.
In summary, compared with the prior art, the invention has the following beneficial effects:
according to the embodiment of the invention, the available search space of the waiting position is obtained based on the track that the vehicle is driven out of the loading area from the current loading position and the minimum parking safety distance, the loading vehicle can be ensured to smoothly leave the loading position after the loading is finished, and the condition that a plurality of vehicles are jammed when entering the same loading position is prevented. And then acquiring candidate waiting positions and coordinates and optimal orientations of the candidate waiting positions based on the available search space, acquiring the weight of each candidate waiting position based on a track entering the candidate waiting positions from the entrance of the loading area and a track entering the target loading position from the candidate waiting positions, and selecting the waiting position corresponding to the optimal weight as the optimal waiting position, thereby effectively improving the loading efficiency.
It should be noted that, through the above description of the embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by software plus a necessary general hardware platform. With this understanding in mind, the above-described technical solutions may be embodied in the form of a software product, which can be stored in a computer-readable storage medium such as ROM/RAM, magnetic disk, optical disk, etc., and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute the methods described in the embodiments or some parts of the embodiments. In this document, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other identical elements in a process, method, article, or apparatus that comprises the element.
The above examples are only intended to illustrate the technical solution of the present invention, but not to limit it; although the present invention has been described in detail with reference to the foregoing embodiments, it will 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; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present invention.