Unmanned mining truck, parking method, device and system thereof and storage medium

Abstract

The invention relates to an unmanned mining truck, a parking method, device and system thereof and a storage medium. The unmanned mining truck parking method comprises the steps that parking related data are obtained, and the parking related data at least comprise vehicle current state information, obstacle data, reference parking point data and retaining wall boundary data; according to the reference parking point data and the retaining wall boundary data, parking point sampling is carried out, and sampled parking point information is obtained; calculating a sampling path according to the current state information of the vehicle and the sampling parking point information; performing obstacle collision detection on the sampling paths according to the obstacle data, and selecting an optimal driving path from the sampling paths; and controlling the unmanned mining truck to park according to the optimal driving path. According to the invention, the obstacle avoidance parking path of the unmanned mining truck can be adaptively planned, so that the unmanned mining truck can be accurately parked at the ideal parking space, and the effect and efficiency of parking operation are improved.

Description

Technical Field

[0001] The present disclosure relates to the field of intelligent driving technology, and in particular to an unmanned mining truck and a parking method, device and system, and storage medium thereof. Background Art

[0002] Mining Trucks are core equipment in large-scale open-pit mining. They are mainly responsible for transporting mined ore and earth to crushing stations and dumping sites. Mining trucks have the advantages of large load capacity and high efficiency, which can effectively improve the efficiency of mining operations. At the same time, the professional design and high reliability design of mining trucks enable them to adapt to complex and changeable mining roads with harsh conditions, and meet the needs of stable transportation in various scenarios.

[0003] Given the extreme and harsh environment in mining areas, equipment needs to be able to withstand 24-hour uninterrupted operation intensity. In addition, the large number of mines and high-intensity mining operations have led to frequent safety accidents and hidden dangers in mining areas. The introduction of unmanned driving technology can effectively reduce the number of workers in mining areas, improve transportation efficiency and safety, thereby reducing labor costs and accident rates, and enhancing the economic and social benefits of enterprises. Summary of the invention

[0004] The inventors have discovered through research that in the unmanned transportation operation scenario of an open-pit mine, the related technology may cause obstacles to the vehicle during parking due to scattered materials, wheel tracks, etc. in the operation area.

[0005] In view of at least one of the above technical problems, the present disclosure provides an unmanned mining truck and its parking method, device and system, and storage medium, which can adaptively plan the obstacle avoidance parking path of the unmanned mining truck, so that the unmanned mining truck can be accurately parked at the ideal parking space, thereby improving the effect and efficiency of the parking operation.

[0006] According to one aspect of the present disclosure, there is provided an unmanned mining truck parking method, comprising:

[0007] Acquiring parking-related data, wherein the parking-related data at least includes vehicle current state information, obstacle data, reference parking point data, and retaining wall boundary data;

[0008] Perform parking point sampling according to reference parking point data and retaining wall boundary data to obtain sampled parking point information;

[0009] Calculate the sampling path according to the vehicle's current state information and the sampling parking point information;

[0010] Performing obstacle collision detection on the sampled path according to the obstacle data, and selecting an optimal driving path from the sampled path;

[0011] The unmanned mining truck is controlled to park according to the optimal driving path.

[0012] In some embodiments of the present disclosure, performing obstacle collision detection on the sampled path according to the obstacle data and selecting an optimal driving path from the sampled path includes:

[0013] Performing obstacle collision detection on the sampling paths according to the obstacle data, and selecting a sampling path without obstacle collision from the sampling paths;

[0014] Curvature monitoring is performed on the sampled paths without obstacle collision, and an optimal driving path is selected from the sampled paths without obstacle collision.

[0015] In some embodiments of the present disclosure, the curvature monitoring of the sampled paths without obstacle collision and selecting the optimal driving path from the sampled paths without obstacle collision include:

[0016] Performing curvature monitoring on the sampled paths without obstacle collision, and selecting a drivable path from the sampled paths without obstacle collision;

[0017] Calculating a total cost of each drivable path, wherein the total cost includes at least one of a parking point deviation cost, a reference path deviation cost, and a curvature cost;

[0018] Select the drivable path with the smallest total cost as the optimal driving path.

[0019] In some embodiments of the present disclosure, the parking-related data further includes a path maximum curvature threshold and a path minimum curvature threshold.

[0020] In some embodiments of the present disclosure, the performing curvature monitoring on the sampled paths without obstacle collision and selecting a drivable path from the sampled paths without obstacle collision comprises:

[0021] Determine whether the obstacle-free sampling path satisfies a curvature constraint, wherein the curvature constraint is that the path curvature of the obstacle-free sampling path is between a path maximum curvature threshold and a path minimum curvature threshold;

[0022] Filter out the sampled paths that meet the curvature constraints as drivable paths.

[0023] In some embodiments of the present disclosure, the calculating the total cost of each drivable path includes at least one of the following steps:

[0024] For each drivable path, the parking point deviation cost of the drivable path is calculated according to the heading of the sampled parking point, the heading of the target parking point, the heading error weight between the sampled parking point and the target parking point, the position error weight between the sampled parking point and the target parking point, the coordinates of the sampled parking point and the coordinates of the target parking point;

[0025] For each drivable path, calculating a reference path deviation cost of the drivable path according to the coordinates of each path point in the drivable path, the coordinates of each path point in the reference path, and the reference path deviation weight;

[0026] For each drivable path, the curvature cost of the drivable path is calculated according to the curvature of each path point in the drivable path and the path curvature weight.

[0027] In some embodiments of the present disclosure, the parking-related data further includes vehicle parameters.

[0028] In some embodiments of the present disclosure, performing obstacle collision detection on the sampling path according to the obstacle data, and selecting a sampling path without obstacle collision from the sampling path comprises:

[0029] Calculate the vehicle bounding box and vehicle encirclement according to vehicle parameters;

[0030] For each sampled path, calculate the potential conflicting obstacles and potential conflicting path points whose obstacle contours are less than the radius of the vehicle encirclement from the path points;

[0031] By judging whether the vehicle bounding box at the potential conflict path point intersects with the obstacle outline, it is judged whether the sampling path has a collision conflict, and the sampling path without obstacle collision is screened out.

[0032] In some embodiments of the present disclosure, the parking-related data includes at least map data and obstacle data, wherein:

[0033] The map data is acquired based on real-time data sensing by a data sensing device; the map data includes retaining wall boundary data, the retaining wall boundary data is line data at the connection between the retaining wall and the ground, and the attributes of discrete points on the retaining wall boundary include at least coordinate information and direction angle information, and the direction angle is a direction perpendicular to the retaining wall and pointing to the unloading area;

[0034] The obstacle data is obstacle data sensed by a data sensing device, and the obstacle data is stored in the form of polygons.

[0035] In some embodiments of the present disclosure, the acquiring of parking-related data further includes at least reference path data and a first distance, wherein:

[0036] The reference path data is path data based on the decision-making planning module and is saved in the form of discrete points; the reference path data includes reference parking point data; the end point of the reference path is the reference parking point; the attributes of the discrete points in the reference path include at least coordinates, heading angles and curvature;

[0037] The first distance is the distance between the center of the rear axle of the unmanned mining truck and the boundary of the retaining wall when the truck is precisely parked at the parking point.

[0038] In some embodiments of the present disclosure, performing parking point sampling according to the reference parking point data and the retaining wall boundary data to obtain the sampled parking point information includes:

[0039] According to the reference parking point data and the retaining wall boundary data, a point projection method is applied to obtain the projection point of the reference parking point on the retaining wall boundary;

[0040] Taking the projection point as the base point, the boundary points are sampled at equal intervals on the boundary of the retaining wall, and the sampled parking point information is calculated.

[0041] In some embodiments of the present disclosure, obtaining the projection point of the reference parking point on the retaining wall boundary by applying a point projection method according to the reference parking point data and the retaining wall boundary data includes:

[0042] Displacing the reference parking point by the first distance along the vehicle heading angle to determine a reference boundary point;

[0043] Based on the retaining wall boundary data, the closest point of the reference boundary point to the retaining wall boundary is calculated, and the projection point of the reference boundary point on the retaining wall boundary is calculated using a point projection method.

[0044] In some embodiments of the present disclosure, taking the projection point as a base point, sampling boundary points at equal intervals on the boundary of the retaining wall, and calculating the sampled parking point information includes:

[0045] Taking the projection point as a base point, sampling boundary points at a sampling interval of a second predetermined distance within the range of first predetermined distances to the left and right of the projection point to obtain a plurality of sampling boundary points;

[0046] The sampling boundary point and the projection point are displaced by the first distance along the direction angle to obtain the sampling parking point and obtain the sampling parking point information, wherein the sampling parking point information includes the coordinates and heading angle of the sampling parking point.

[0047] In some embodiments of the present disclosure, calculating the sampling path according to the vehicle current state information and the sampling parking point information includes:

[0048] Taking the reference path as the center line, a first coordinate system is established to calculate the coordinate information of the current position of the vehicle and the coordinate information of the sampled parking point, wherein the coordinate information of the current position of the vehicle in the first coordinate system includes a first coordinate and a second coordinate, the first coordinate being the longitudinal displacement along the road from the starting point of the road to the current position of the vehicle; the second coordinate being the lateral displacement from the center of mass of the vehicle to the center line of the road when the vehicle is at the current position;

[0049] Set up a quintic polynomial equation;

[0050] Setting boundary conditions, wherein the boundary conditions include a starting boundary and an end boundary;

[0051] Solving a quintic polynomial equation according to the boundary conditions to calculate the parking path in equal time intervals;

[0052] The discrete path points are transformed from the first coordinate system to the Cartesian coordinate system.

[0053] In some embodiments of the present disclosure, the independent variable of the quintic polynomial equation is time, and the dependent variable is the lateral displacement.

[0054] In some embodiments of the present disclosure, the boundary conditions include: the lateral displacement of the starting point is the second coordinate of the starting point, the lateral displacement of the end point is the second coordinate of the end point, the lateral velocity of the starting point is the tangent of the vehicle's heading angle at the starting point in the Cartesian coordinate system, the lateral velocity of the end point is the tangent of the vehicle's heading angle at the sampled parking point in the Cartesian coordinate system, and the lateral accelerations of the starting point and the end point are both 0.

[0055] According to another aspect of the present disclosure, there is provided an unmanned mining truck parking device, comprising:

[0056] A data acquisition module is configured to acquire parking-related data, wherein the parking-related data at least includes vehicle current state information, obstacle data, reference parking point data, and retaining wall boundary data;

[0057] The parking point sampling module is configured to perform parking point sampling according to the reference parking point data and the retaining wall boundary data to obtain sampled parking point information;

[0058] A path planning module is configured to calculate a sampling path according to the vehicle current state information and the sampling parking point information;

[0059] A path selection module is configured to perform obstacle collision detection on the sampled path according to the obstacle data, and select an optimal driving path from the sampled path;

[0060] The parking control module is configured to control the unmanned mining truck to park according to the optimal driving path.

[0061] According to another aspect of the present disclosure, there is provided an unmanned mining truck parking device, comprising:

[0062] a memory configured to store instructions;

[0063] The processor is configured to execute the instructions so that the unmanned mining truck parking device implements the unmanned mining truck parking method as described in any of the above embodiments.

[0064] According to another aspect of the present disclosure, an unmanned mining truck parking system is provided, comprising a data sensing device and an unmanned mining truck parking device as described in any of the above embodiments.

[0065] According to another aspect of the present disclosure, an unmanned mining truck is provided, comprising the unmanned mining truck parking device as described in any one of the above embodiments, or comprising the unmanned mining truck parking system as described in any one of the above embodiments.

[0066] According to another aspect of the present disclosure, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores computer instructions, and when the instructions are executed by a processor, the unmanned mining truck parking method as described in any of the above embodiments is implemented.

[0067] According to another aspect of the present disclosure, a computer program product is provided, comprising a computer program, wherein when the computer program is executed by a processor, the unmanned mining truck parking method as described in any of the above embodiments is implemented.

[0068] The present disclosure can adaptively plan an obstacle avoidance parking path for an unmanned mining truck, so that the unmanned mining truck can be accurately parked at an ideal parking space, thereby improving the effect and efficiency of the parking operation. BRIEF DESCRIPTION OF THE DRAWINGS

[0069] In order to more clearly illustrate the embodiments of the present disclosure or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present disclosure. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0070] Figure 1 Schematic diagrams of some embodiments of the unmanned mining truck parking method disclosed herein.

[0071] Figure 2 Schematic diagram of unmanned mining truck parking operation in some embodiments of the present disclosure.

[0072] Figure 3 Schematic diagram of adaptive obstacle avoidance parking for unmanned mining trucks in some embodiments of the present disclosure.

[0073] Figure 4 Schematic diagram of obstacle collision detection for unmanned mining trucks in some embodiments of the present disclosure.

[0074] Figure 5 Schematic diagrams of some embodiments of the unmanned mining truck parking device disclosed in the present invention.

[0075] Figure 6 Schematic diagram of the structure of other embodiments of the unmanned mining truck parking device disclosed in the present invention.

[0076] Figure 7 It is a schematic diagram of the structure of some embodiments of the unmanned mining truck parking system disclosed in the present invention. DETAILED DESCRIPTION

[0077] The technical solutions in the embodiments of the present disclosure will be clearly and completely described below in conjunction with the drawings in the embodiments of the present disclosure. Obviously, the described embodiments are only part of the embodiments of the present disclosure, rather than all of the embodiments. The following description of at least one exemplary embodiment is actually only illustrative and is by no means intended to limit the present disclosure and its application or use. Based on the embodiments in the present disclosure, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present disclosure.

[0078] Unless specifically stated otherwise, the relative arrangement of components and steps, the numerical expressions and numerical values ​​set forth in these embodiments do not limit the scope of the present disclosure.

[0079] At the same time, it should be understood that for the convenience of description, the sizes of the various parts shown in the drawings are not drawn according to the actual proportional relationship.

[0080] Technologies, methods, and apparatus known to ordinary technicians in the relevant field may not be discussed in detail, but where appropriate, such technologies, methods, and apparatus should be considered part of the authorization specification.

[0081] In all examples shown and discussed herein, any specific values ​​should be interpreted as merely exemplary and not as limiting. Therefore, other examples of the exemplary embodiments may have different values.

[0082] It should be noted that like reference numerals and letters refer to similar items in the following figures, and therefore, once an item is defined in one figure, it need not be further discussed in subsequent figures.

[0083] The inventors also found through research that in the unmanned transportation operation scene of open-pit mines, the actual parking operation point deviates from the ideal parking point due to factors such as the continuous bulldozing operation of the bulldozer in the operation area, the continuous unloading operation of the unmanned mining truck, and the inability to update the map in real time. The scattered materials and wheel tracks in the operation area will also cause the vehicle to park at obstacles during the parking process. The above problems will lead to problems such as unmanned mining trucks parking at obstacles and large parking deviations, resulting in interruptions in the parking operation process and inadequate parking, which will directly affect the operation effect and efficiency of the unmanned system.

[0084] The related technology does not involve the unloading and stopping path planning information. The related technology is difficult to adapt to the specific requirements of the unloading terminal state when the retaining wall is unloaded.

[0085] In view of at least one of the above technical problems, the present disclosure provides an unmanned mining truck and a parking method, device and system thereof, and a storage medium. The present disclosure is described below through specific embodiments.

[0086] Figure 1 Schematic diagram of some embodiments of the unmanned mining truck parking method disclosed in the present invention. Preferably, this embodiment can be performed by the unmanned mining truck parking device disclosed in the present invention, the unmanned mining truck parking system disclosed in the present invention, or the unmanned mining truck disclosed in the present invention. Figure 1 As shown, Figure 1 The method of the embodiment may include at least one of steps 100 to 500 .

[0087] Step 100, obtaining parking related data, wherein the parking related data at least includes vehicle current state information, obstacle data, reference parking point data and retaining wall boundary data.

[0088] In some embodiments of the present disclosure, step 100 may include: a data acquisition module, acquiring real-time map data, reference path data, obstacle data, measuring a first distance , wherein the first distance The distance between the center of the rear axle of an unmanned mining truck and the boundary of the retaining wall when the truck is parked accurately at the parking spot.

[0089] In some embodiments of the present disclosure, the first distance may be distance information from the center of the rear axle of the vehicle to the boundary of the retaining wall during precise parking.

[0090] In some embodiments of the present disclosure, the path planning is based on the center of the rear axle of the vehicle. The data acquisition module collects in advance the distance between the center of the rear axle of the vehicle and the boundary of the retaining wall when the vehicle is accurately parked at the parking point, which is recorded as the first distance. ,refer to Figure 2 . Figure 2 Schematic diagram of unmanned mining truck parking operation in some embodiments of the present disclosure.

[0091] In some embodiments of the present disclosure, step 100 may include: a data acquisition module, acquiring map data, reference path data, and obstacle data near a reference parking point, and measuring a first distance, wherein the first distance is the distance from the center of the rear axle of the unmanned mining truck to the boundary of the retaining wall when the truck is precisely parked at the parking point.

[0092] In some embodiments of the present disclosure, the acquired parking related data may include at least map data and obstacle data.

[0093] In some embodiments of the present disclosure, the map data is perceived and acquired in real time based on a data perception device; the map data includes retaining wall boundary data, the retaining wall boundary data is line data at the connection between the retaining wall and the ground, and the discrete point attributes of the retaining wall boundary include at least coordinate information ( and Coordinate information) and direction angle Information, the direction angle is perpendicular to the retaining wall and pointing to the unloading area.

[0094] In some embodiments of the present disclosure, the obstacle data is obstacle data sensed by a data sensing device, and the obstacle data is saved in the form of polygons.

[0095] In some embodiments of the present disclosure, the acquisition of parking related data may further include at least reference path data and a first distance.

[0096] In some embodiments of the present disclosure, the reference path data is path data based on a decision planning module and is stored in the form of discrete points; the reference path data includes reference parking point data; the end point of the reference path is the reference parking point; the attributes of the discrete points in the reference path include at least coordinates ( and Coordinates), heading angle and curvature .

[0097] Step 200: Perform parking point sampling based on reference parking point data and retaining wall boundary data to obtain sampled parking point information.

[0098] In some embodiments of the present disclosure, step 200 may include: a parking point sampling module sampling parking points based on retaining wall boundary data and reference parking points.

[0099] In some embodiments of the present disclosure, step 200 may include: a parking point sampling module, based on the reference parking point and the retaining wall boundary data, applying a point projection method to obtain a projection point of the reference parking point on the retaining wall boundary; taking the projection point as a base point, sampling boundary points at equal intervals on the retaining wall boundary, and angularly shifting the sampled boundary points and the projection points along the direction by the first distance , obtain the sampling parking point.

[0100] Figure 3 Schematic diagram of adaptive obstacle avoidance parking for unmanned mining trucks in some embodiments of the present disclosure. Figure 3 As shown, Figure 1 Step 200 of the embodiment may include at least one of steps 210 to 220 .

[0101] Step 210, based on the reference parking point data and the retaining wall boundary data, a point projection method is used to obtain the projection point of the reference parking point on the retaining wall boundary, such as Figure 3 shown.

[0102] In some embodiments of the present disclosure, step 210 may include at least one of steps 211 to 212 .

[0103] Step 211: angularly displace the reference parking point by the first distance along the vehicle heading. , determine the reference boundary point, such as Figure 3 As shown, the reference boundary point represents the ideal retaining wall boundary point corresponding to the reference parking point where the vehicle stops, such as Figure 2 shown.

[0104] In some embodiments of the present disclosure, step 211 may include: according to formulas (1) and (2), the reference parking point is displaced along the heading , obtain the reference boundary points.

[0105] (1)

[0106] (2)

[0107] In formulas (1) and (2), is the coordinate of the center point of the vehicle's rear axle; is the coordinate of the reference boundary point; is the vehicle heading angle.

[0108] Step 212, based on the retaining wall boundary data, calculate the closest point of the reference boundary point to the retaining wall boundary, and use the point projection method to calculate the projection point of the reference boundary point on the retaining wall boundary, such as Figure 3 shown.

[0109] In some embodiments of the present disclosure, step 210 may include: calculating the projection point of the reference boundary point on the boundary of the retaining wall according to formulas (3) to (5).

[0110] (3)

[0111] (4)

[0112] (5)

[0113] In formulas (3) to (5), is the projection point coordinate; is the coordinate of the nearest point; is the closest point heading angle.

[0114] In some embodiments of the present disclosure, when the vehicle is traveling backward, the heading angle of the boundary point of the barrier wall is rotated 180° from its direction angle.

[0115] Step 220, taking the projection point as a base point, sampling boundary points at equal intervals on the boundary of the retaining wall, and calculating the sampled parking point information.

[0116] In some embodiments of the present disclosure, step 220 may include at least one of steps 221 to 222, such as Figure 3 shown.

[0117] Step 221, taking the projection point as the base point, sampling boundary points at a sampling interval of a second predetermined distance within the range of the first predetermined distance to the left and right of the projection point, to obtain a plurality of sampling boundary points, such as Figure 3 shown.

[0118] In some embodiments of the present disclosure, the first predetermined distance is equal to 1 / 2 of the vehicle width, and the second predetermined distance is equal to 1 / 4 of the vehicle width.

[0119] In some embodiments of the present disclosure, step 221 may include: taking the projection point as the base point, sampling boundary points within the range of 1 / 2 vehicle width on the left and right of the projection point at a sampling interval of 1 / 4 vehicle width to obtain a sampled parking point. ,like Figure 3 shown.

[0120] Step 222: angularly shift the sampling boundary point and the projection point along the direction by the first distance , obtain the sampling parking point, and obtain the sampling parking point information, such as Figure 3 As shown, the sampled parking point information includes the coordinates and heading angle of the sampled parking point.

[0121] In some embodiments of the present disclosure, step 222 may include: angularly shifting the sampling boundary points and the projection points along the direction , similar to the calculation method of step 211 or formula (1) to formula (2), the sample parking point is obtained and recorded as ,in is the sampling parking point number corresponding to the projection point, are the sampling parking point labels corresponding to the sampling boundary points, such as Figure 3 shown.

[0122] Step 300, calculating a sampling path according to the current state information of the vehicle and the sampling parking point information.

[0123] In some embodiments of the present disclosure, step 300 may include: the path planning module plans the sampling path of each sampled parking point using a quintic polynomial algorithm.

[0124] In some embodiments of the present disclosure, step 300 may include: the path planning module applies a quintic polynomial algorithm to plan a driving path of the sampled parking point based on the current state of the vehicle and the sampled parking point information.

[0125] In some embodiments of the present disclosure, step 300 may include at least one of steps 310 to 350 .

[0126] Step 310: Establish a first coordinate system with the reference path as the center line to calculate the coordinate information of the current position of the vehicle. , sample parking point coordinate information , where the coordinate information of the current position of the vehicle in the first coordinate system includes the first coordinate and the second coordinate , the first coordinate is the longitudinal displacement along the road from the starting point of the road to the current position of the vehicle; the second coordinate is the lateral displacement from the center of mass of the vehicle to the center line of the road when the vehicle is at the current position.

[0127] In some embodiments of the present disclosure, the first coordinate system is a moving coordinate system based on a road centerline.

[0128] In some embodiments of the present disclosure, the first coordinate system is a Frenet coordinate system.

[0129] In some embodiments of the present disclosure, step 310 may include: using the reference path as the center line, establishing a Frenet coordinate system, and calculating the current state of the vehicle and the coordinate information of the sampled parking point, respectively, as , .

[0130] Step 320, establish a quintic polynomial equation.

[0131] In some embodiments of the present disclosure, step 320 may include: establishing a quintic polynomial equation according to formula (6).

[0132] (6)

[0133] In formula (6), the independent variable of the fifth-order polynomial equation is time t, and the dependent variable is the lateral displacement ; are the coefficients of the quintic polynomial equation.

[0134] Step 330: setting boundary conditions, wherein the boundary conditions include a starting point boundary and an end point boundary.

[0135] In some embodiments of the present disclosure, the boundary condition may include: the lateral displacement of the starting point is the second coordinate of the starting point , the lateral displacement of the end point is the second coordinate of the end point ; The lateral velocity at the starting point is the tangent of the vehicle's heading angle at the starting point in the Cartesian coordinate system The lateral velocity at the end point is the tangent of the heading angle of the vehicle at the sampled parking point in the Cartesian coordinate system. ,in, , are the heading angles of the vehicle and the parking point in the Cartesian coordinate system (Cartesian coordinate system); the lateral acceleration at the starting point and the end point is 0, , .

[0136] Step 340, solving the quintic polynomial equation according to the boundary conditions, and calculating the parking path in equal time intervals t.

[0137] Step 350 , converting the discrete path points from the first coordinate system to the Cartesian coordinate system.

[0138] Step 400: perform obstacle collision detection on the sampled paths according to the obstacle data, and select an optimal driving path from the sampled paths.

[0139] In some embodiments of the present disclosure, step 400 may include: a path selection module, first performing obstacle collision detection and curvature check on the sampled path to obtain a drivable path; considering parking point deviation, reference path deviation, and path curvature cost to evaluate the drivable path, and select the optimal driving path.

[0140] In some embodiments of the present disclosure, step 400 may include: a path selection module, based on the sampled path information of the path planning module, performs obstacle collision detection and curvature check to screen out a drivable path; considers parking point deviation, reference path deviation, and path curvature cost to evaluate the drivable path and determine the optimal driving path.

[0141] In some embodiments of the present disclosure, step 400 may include: a path selection module, based on the sample path calculated in step 300, performs obstacle collision detection and curvature check to calculate a drivable path; evaluates the drivable path according to the parking point heading and position deviation, reference path deviation, and path curvature cost to determine the optimal driving path.

[0142] In some embodiments of the present disclosure, step 400 may include at least one of steps 410 to 420 .

[0143] Step 410: perform obstacle collision detection on the sampling path according to the obstacle data, and select a sampling path without obstacle collision from the sampling path, such as Figure 4 shown. Figure 4 Schematic diagram of obstacle collision detection for unmanned mining trucks in some embodiments of the present disclosure.

[0144] In some embodiments of the present disclosure, the parking-related data may further include vehicle parameters.

[0145] In some embodiments of the present disclosure, step 410 may include at least one of steps 411 to 413 .

[0146] Step 411, calculate the vehicle bounding box and vehicle encirclement according to the vehicle parameters, such as Figure 4 shown.

[0147] In some embodiments of the present disclosure, step 411 may include: calculating a vehicle bounding box and a vehicle bounding circle based on vehicle parameters; wherein the vehicle bounding box is composed of rectangular corner points , , , The radius of the vehicle encirclement is ; Decisions on obstacles that would cause unmanned mining trucks to stop, such as Figure 4 shown.

[0148] Step 412: For each sampled path, calculate the distance between the obstacle contour and the path point less than the radius of the vehicle encirclement. Potential conflict obstacles and potential conflict path points.

[0149] In some embodiments of the present disclosure, step 412 may be implemented as follows: Figure 4 Step 1 of the embodiment.

[0150] Step 413 , by determining whether the vehicle bounding box at the potential conflict path point intersects with the obstacle outline, it is determined whether the sampling path has a collision conflict, and a sampling path without obstacle collision is screened out.

[0151] In some embodiments of the present disclosure, step 413 may be implemented as follows: Figure 4 Step 2 of the embodiment.

[0152] Step 420 : performing curvature monitoring on the sampled paths without obstacle collisions, and selecting an optimal driving path from the sampled paths without obstacle collisions.

[0153] In some embodiments of the present disclosure, step 420 may include at least one of steps 421 to 422 .

[0154] Step 421 , performing curvature monitoring on the sampled paths without obstacle collision, and selecting a drivable path from the sampled paths without obstacle collision screened out in step 410 .

[0155] In some embodiments of the present disclosure, the parking-related data may further include a path maximum curvature threshold and a path minimum curvature threshold.

[0156] In some embodiments of the present disclosure, step 421 may include: determining whether the sampled path without obstacle collision screened out in step 410 satisfies a curvature constraint, wherein the curvature constraint is that the path curvature of the sampled path without obstacle collision is between a path maximum curvature threshold and a path minimum curvature threshold; and screening out the sampled path that satisfies the curvature constraint as a drivable path.

[0157] Step 422 , calculating the total cost of each drivable path, wherein the total cost includes at least one of a parking point deviation cost, a reference path deviation cost, and a curvature cost.

[0158] In some embodiments of the present disclosure, step 422 may include: determining the total cost of each drivable path according to formula (7): .

[0159] (7)

[0160] In formula (7), is the total cost of the drivable path; is the parking point deviation cost, Reference path deviation cost, is the curvature cost.

[0161] In some embodiments of the present disclosure, the total cost includes a parking point deviation cost, a reference path deviation cost, and a curvature cost. All three costs need to be considered and different weight coefficients are set.

[0162] In some embodiments of the present disclosure, step 422 may include at least one of steps 4221 to 4223 .

[0163] Step 4221, for each drivable path, calculate the parking point deviation cost of the drivable path according to the heading of the sampled parking point, the heading of the target parking point, the heading error weight between the sampled parking point and the target parking point, the position error weight between the sampled parking point and the target parking point, the coordinates of the sampled parking point and the coordinates of the target parking point. .

[0164] In some embodiments of the present disclosure, step 4221 may include: for each drivable path, according to formula (8), according to the heading of the sampled parking point of the drivable path , the heading of the target parking point , the heading error weight between the sampling parking point and the target parking point , the position error weight between the sampling parking point and the target parking point , sampling parking point coordinates and the target parking point coordinates , calculate the parking point deviation cost of the drivable path .

[0165] (8)

[0166] Step 4222, for each drivable path, calculate the reference path deviation cost of the drivable path according to the coordinates of each path point in the drivable path, the coordinates of each path point in the reference path, and the reference path deviation weight. .

[0167] In some embodiments of the present disclosure, step 4222 may include: for each drivable path, according to formula (9), based on the coordinates of each path point in the drivable path, the coordinates of each path point in the reference path, and the reference path deviation weight , calculate the reference path deviation cost of the drivable path .

[0168] (9)

[0169] In formula (9), The sampling path Waypoint coordinates; The reference path The waypoint coordinates.

[0170] Step 4223: For each drivable path, calculate the curvature cost of the drivable path based on the curvature of each path point in the drivable path and the path curvature weight. .

[0171] In some embodiments of the present disclosure, step 4223 may include: for each drivable path, according to formula (10), according to the curvature of each path point in the drivable path, the path curvature weight , calculate the curvature cost of the drivable path .

[0172] (10)

[0173] In formula (10), The sampling path Waypoint curvature.

[0174] Step 423, selecting the drivable path with the minimum total cost as the optimal driving path.

[0175] Step 500: Control the unmanned mining truck to park according to the optimal driving path.

[0176] The above embodiments of the present disclosure provide an operation device, system and method for adaptive obstacle avoidance parking of unmanned mining trucks. The method adopts data collection, parking point sampling, path planning, path inspection and evaluation to achieve obstacle avoidance and precise parking of unmanned mining trucks when obstacles and map data change dynamically, which can effectively improve the effect and efficiency of unmanned mining truck parking operations.

[0177] The above-mentioned embodiments of the present disclosure perform obstacle avoidance parking path planning based on map information collected by the vehicle in real time, and can adapt to scenarios and working conditions where the on-site work area changes dynamically and the map cannot be updated in real time.

[0178] The above-mentioned embodiment of the present disclosure projects the reference parking point on the boundary of the retaining wall and samples it at equal intervals, so that the vehicle can park close to the retaining wall and remain perpendicular to the boundary of the retaining wall, thereby ensuring the parking effect of the unmanned mining truck.

[0179] The above-mentioned embodiments of the present disclosure select the optimal path that satisfies the driving of unmanned mining trucks by performing obstacle collision detection, curvature inspection, and path cost evaluation on the sampled path, thereby ensuring the feasibility and optimality of the driving path of the unmanned mining trucks.

[0180] Figure 5 Schematic diagram of some embodiments of the unmanned mining truck parking device disclosed in the present invention. Figure 5 As shown, the unmanned mining truck parking device disclosed herein may include a data acquisition module 51 , a parking point sampling module 52 , a path planning module 53 , a path selection module 54 and a parking control module 55 .

[0181] The data acquisition module 51 is configured to acquire parking-related data, wherein the parking-related data at least includes vehicle current state information, obstacle data, reference parking point data and retaining wall boundary data.

[0182] In some embodiments of the present disclosure, the data acquisition module 51 may be implemented as a data collection module.

[0183] In some embodiments of the present disclosure, the data acquisition module 51 may be configured to acquire map information, reference parking path information, and obstacle information.

[0184] In some embodiments of the present disclosure, the data acquisition module 51 may be configured to acquire map information, reference path information, obstacle information, and measure the distance information between the center of the rear axle of the vehicle and the boundary of the retaining wall during precise parking.

[0185] In some embodiments of the present disclosure, the parking-related data may include at least map data and obstacle data, wherein: the map data is real-time perception data acquired by a data perception device; the map data includes retaining wall boundary data, the retaining wall boundary data is line data at the connection between the retaining wall and the ground, and the attributes of discrete points of the retaining wall boundary include at least coordinate information and direction angle information, and the direction angle is the direction perpendicular to the retaining wall and pointing to the unloading area; the obstacle data is obstacle data perceived by the data perception device, and the obstacle data is saved in the form of polygons.

[0186] In some embodiments of the present disclosure, the acquisition of parking-related data may also include at least reference path data and a first distance, wherein: the reference path data is path data based on a decision-making planning module and is saved in the form of discrete points; the reference path data includes reference parking point data; the end point of the reference path is the reference parking point; the attributes of the discrete points in the reference path include at least coordinates, heading angles and curvature; the first distance is the distance from the center of the rear axle of the unmanned mining truck to the boundary of the retaining wall when the truck is precisely parked at the parking point.

[0187] The parking point sampling module 52 is configured to perform parking point sampling according to the reference parking point data and the retaining wall boundary data to obtain sampled parking point information.

[0188] In some embodiments of the present disclosure, the parking point sampling module 52 may be configured to sample parking points based on the retaining wall boundary data and reference parking points.

[0189] In some embodiments of the present disclosure, the parking point sampling module 52 may be configured to obtain the projection point of the reference parking point on the retaining wall boundary by applying a point projection method based on the reference parking point data and the retaining wall boundary data; taking the projection point as a base point, sampling boundary points at equal intervals on the retaining wall boundary, and calculating the sampled parking point information.

[0190] In some embodiments of the present disclosure, the parking point sampling module 52, when obtaining the projection point of the reference parking point on the retaining wall boundary by the point projection method based on the reference parking point data and the retaining wall boundary data, can be configured to displace the reference parking point by the first distance along the vehicle heading angle to determine the reference boundary point; based on the retaining wall boundary data, calculate the nearest point of the reference boundary point to the retaining wall boundary, and calculate the projection point of the reference boundary point on the retaining wall boundary by the point projection method.

[0191] In some embodiments of the present disclosure, the parking point sampling module 52, when taking the projection point as the base point, sampling boundary points at equal intervals on the boundary of the retaining wall, and calculating the sampled parking point information, can be configured to take the projection point as the base point, sample boundary points at a sampling interval of a second predetermined distance within the range of the first predetermined distances to the left and right of the projection point, to obtain a plurality of sampled boundary points; and angularly shift the sampled boundary points and the projection points by the first distance along the direction to obtain sampled parking points, and obtain sampled parking point information, wherein the sampled parking point information includes the coordinates and heading angle of the sampled parking point.

[0192] The path planning module 53 is configured to calculate a sampling path according to the current state information of the vehicle and the sampling parking point information.

[0193] In some embodiments of the present disclosure, the path planning module 53 may be implemented as an initial path planning module.

[0194] In some embodiments of the present disclosure, the path planning module 53 may be configured to plan a sampling path for each sampled parking point using a quintic polynomial algorithm.

[0195] In some embodiments of the present disclosure, the sampling path is an initial path of the sampling parking point.

[0196] In some embodiments of the present disclosure, the path planning module 53 may be configured to plan an initial path to the sampled parking points by applying a quintic polynomial algorithm based on the current state of the vehicle and the sampled parking point information.

[0197] In some embodiments of the present disclosure, the path planning module 53 can be configured to establish a first coordinate system with the reference path as the center line, calculate the coordinate information of the current position of the vehicle and the coordinate information of the sampled parking point, wherein the coordinate information of the current position of the vehicle in the first coordinate system includes a first coordinate and a second coordinate, the first coordinate being the longitudinal displacement along the road from the starting point of the road to the current position of the vehicle; the second coordinate being the lateral displacement from the center of mass of the vehicle to the center line of the road when the vehicle is at the current position; establish a quintic polynomial equation; set boundary conditions, wherein the boundary conditions include a starting point boundary and an end point boundary; solve the quintic polynomial equation according to the boundary conditions, and calculate the parking driving path in an equal time interval manner; and convert discrete path points from the first coordinate system to a Cartesian coordinate system.

[0198] In some embodiments of the present disclosure, the independent variable of the quintic polynomial equation may be time, and the dependent variable may be the lateral displacement.

[0199] In some embodiments of the present disclosure, the boundary conditions may include: the lateral displacement of the starting point is the second coordinate of the starting point, the lateral displacement of the end point is the second coordinate of the end point, the lateral velocity of the starting point is the tangent of the vehicle's heading angle at the starting point in the Cartesian coordinate system, the lateral velocity of the end point is the tangent of the vehicle's heading angle at the sampled parking point in the Cartesian coordinate system, and the lateral accelerations of the starting point and the end point are both 0.

[0200] The path selection module 54 is configured to perform obstacle collision detection on the sampled paths according to the obstacle data, and select an optimal driving path from the sampled paths.

[0201] In some embodiments of the present disclosure, the path selection module 54 may be implemented as a path checking and evaluation module.

[0202] In some embodiments of the present disclosure, the path selection module 54 can be configured to first perform obstacle collision detection and curvature check on the sampled path to obtain a drivable path; evaluate the drivable path considering the parking point deviation, reference path deviation, and path curvature cost, and select the optimal driving path.

[0203] In some embodiments of the present disclosure, the path selection module 54 can be configured to perform obstacle collision detection and curvature check based on the sampled path calculated by the path planning module 53, and calculate a drivable path; evaluate the drivable path according to the heading and position deviation of the parking point, the reference path deviation, and the path curvature cost, and determine the optimal driving path.

[0204] In some embodiments of the present disclosure, the path selection module 54 can be configured to perform obstacle collision detection on the sampling path according to the obstacle data, and select a sampling path without obstacle collision from the sampling path; perform curvature monitoring on the sampling path without obstacle collision, and select the optimal driving path from the sampling path without obstacle collision.

[0205] In some embodiments of the present disclosure, the path selection module 54, when performing curvature monitoring on the sampled path without obstacle collision and selecting the optimal driving path from the sampled path without obstacle collision, can be configured to perform curvature monitoring on the sampled path without obstacle collision, select a drivable path from the sampled path without obstacle collision; calculate the total cost of each drivable path, wherein the total cost includes at least one of a parking point deviation cost, a reference path deviation cost and a curvature cost; and select the drivable path with the smallest total cost as the optimal driving path.

[0206] In some embodiments of the present disclosure, the parking-related data may further include a path maximum curvature threshold and a path minimum curvature threshold.

[0207] In some embodiments of the present disclosure, the path selection module 54, when performing curvature monitoring on the sampled path without obstacle collision and selecting a drivable path from the sampled path without obstacle collision, can be configured to determine whether the sampled path without obstacle collision satisfies a curvature constraint, wherein the curvature constraint is that the path curvature of the sampled path without obstacle collision is between a maximum curvature threshold of the path and a minimum curvature threshold of the path; and screen out the sampled path that satisfies the curvature constraint as a drivable path.

[0208] In some embodiments of the present disclosure, the path selection module 54, in the case of calculating the total cost of each drivable path, can be configured to perform at least one of the following operations: for each drivable path, calculate the parking point deviation cost of the drivable path according to the heading of the sampled parking point of the drivable path, the heading of the target parking point, the heading error weight between the sampled parking point and the target parking point, the position error weight between the sampled parking point and the target parking point, the sampled parking point coordinates and the target parking point coordinates; for each drivable path, calculate the reference path deviation cost of the drivable path according to the coordinates of each path point in the drivable path, the coordinates of each path point in the reference path, and the reference path deviation weight; for each drivable path, calculate the curvature cost of the drivable path according to the curvature of each path point in the drivable path and the path curvature weight.

[0209] In some embodiments of the present disclosure, the parking-related data may further include vehicle parameters.

[0210] In some embodiments of the present disclosure, the path selection module 54, when performing obstacle collision detection on the sampling path according to the obstacle data and selecting a sampling path without obstacle collision from the sampling path, can be configured to calculate the vehicle bounding box and the vehicle encirclement according to the vehicle parameters; for each sampling path, calculate the potential conflicting obstacles and potential conflicting path points whose obstacle contours are less than the radius of the vehicle encirclement from the path points; by judging whether the vehicle bounding box at the potential conflicting path point intersects with the obstacle contour, judge whether the sampling path has a collision conflict, and screen out the sampling path without obstacle collision.

[0211] The parking control module 55 is configured to control the unmanned mining truck to park according to the optimal driving path.

[0212] In some embodiments of the present disclosure, the unmanned mining truck parking device of the present disclosure may also be configured to execute the unmanned mining truck parking method described in any of the above embodiments of the present disclosure.

[0213] The technical solution of the above-mentioned embodiment of the present disclosure utilizes a data acquisition module to obtain real-time map data, reference path data, and obstacle data, and measures the distance information between the center of the rear axle of the vehicle and the boundary of the retaining wall during precise parking.

[0214] The technical solution of the above-mentioned embodiment of the present disclosure utilizes a parking point sampling module, based on reference parking points and retaining wall boundary data, and applies a point projection method to obtain projection points of reference parking points on the retaining wall boundary; and samples boundary points at equal intervals on the retaining wall boundary with the projection points as base points.

[0215] The technical solution of the above-mentioned embodiment of the present disclosure utilizes a path planning module, based on the current state of the vehicle and the sampled parking point data, and applies a quintic polynomial algorithm to plan the driving path of the sampled parking point.

[0216] The technical solution of the above-mentioned embodiment of the present disclosure utilizes a path selection module to perform obstacle collision detection and curvature check based on the sampled path information of the path planning module to screen out a drivable path; the drivable path is evaluated by considering the heading and position deviation of the parking point, the deviation from the reference path, and the path curvature cost to determine the optimal driving path.

[0217] The above-mentioned embodiments of the present disclosure aim to solve the problems of parking around obstacles and being unable to accurately park at an ideal parking spot during the parking operation of an unmanned mining truck. Through a data acquisition module, a parking spot sampling module, a path planning module, a path selection module and a parking control module, an obstacle avoidance parking path of the unmanned mining truck is adaptively planned according to map information, reference path information and obstacle information collected in real time by the unmanned mining truck, so that the unmanned mining truck can be accurately parked at an ideal parking spot, thereby improving the effect and efficiency of the parking operation.

[0218] Figure 6 Schematic diagram of the structure of some other embodiments of the unmanned mining truck parking device disclosed in the present invention. Figure 6 As shown, the unmanned mining truck parking device includes a memory 61 and a processor 62 .

[0219] The memory 61 is used to store instructions, the processor 62 is coupled to the memory 61, and the processor 62 is configured to execute the unmanned mining truck parking method described in any of the above embodiments of the present disclosure based on the instructions stored in the memory.

[0220] like Figure 6 As shown, the unmanned mining truck parking device also includes a communication interface 63 for information exchange with other devices. At the same time, the unmanned mining truck parking device also includes a bus 64, and the processor 62, the communication interface 63, and the memory 61 communicate with each other through the bus 64.

[0221] The memory 61 may include a high-speed RAM memory, and may also include a non-volatile memory, such as at least one disk memory. The memory 61 may also be a memory array. The memory 61 may also be divided into blocks, and the blocks may be combined into virtual volumes according to certain rules.

[0222] In addition, the processor 62 may be a central processing unit (CPU), or may be an application specific integrated circuit (ASIC), or may be configured to implement one or more integrated circuits of the embodiments of the present disclosure.

[0223] The above-mentioned embodiments of the present disclosure provide an operating method, device and system for adaptive obstacle avoidance parking of unmanned mining trucks, which realize path planning for obstacle avoidance and precise parking in the parking scenario of unmanned mining trucks.

[0224] Figure 7 Schematic diagram of the structure of some embodiments of the unmanned mining truck parking system disclosed in the present invention. Figure 7 As shown, the unmanned mining truck parking system disclosed herein may include a data sensing device 71 and an unmanned mining truck parking device 72 .

[0225] The data sensing device 71 is configured to sense and acquire parking-related data in real time, wherein the parking-related data at least includes vehicle current status information, obstacle data, reference parking point data and retaining wall boundary data; and send the parking-related data to the unmanned mining truck parking device 72.

[0226] The unmanned mining truck parking device 72 may be an unmanned mining truck parking device as described in any of the above embodiments.

[0227] According to another aspect of the present disclosure, an unmanned mining truck is provided, comprising the unmanned mining truck parking device as described in any one of the above embodiments, or comprising the unmanned mining truck parking system as described in any one of the above embodiments.

[0228] The operating method, device and system for adaptive obstacle avoidance parking of unmanned mining trucks provided in the above embodiments of the present disclosure can adjust the parking path according to map information, reference path information and obstacle information, so that the vehicle can park smoothly and accurately at the parking point while avoiding obstacles.

[0229] According to another aspect of the present disclosure, a computer program product is provided, comprising a computer program, wherein when the computer program is executed by a processor, the unmanned mining truck parking method as described in any of the above embodiments is implemented.

[0230] According to another aspect of the present disclosure, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores computer instructions, and when the instructions are executed by a processor, the unmanned mining truck parking method as described in any of the above embodiments of the present disclosure is implemented.

[0231] In some embodiments of the present disclosure, the computer-readable storage medium may be a non-transitory computer-readable storage medium.

[0232] The above embodiments of the present disclosure provide unmanned mining trucks and parking methods, devices and systems, computer-readable storage media and computer program products thereof. The above embodiments of the present disclosure disclose an operating device, system and method for adaptive obstacle avoidance parking of unmanned mining trucks. The method disclosed herein includes the following steps: constructing a data acquisition module to obtain map data, reference path data and obstacle data near the parking point; adopting point projection and equal interval sampling methods to sample parking points; planning the driving path of the unmanned mining truck to each sampling point based on the quintic polynomial algorithm; performing obstacle collision detection and curvature check on the sampling path to screen the drivable path; considering the parking point deviation, reference path deviation and path curvature cost to evaluate the drivable path and determine the optimal driving path. In the above manner, the above embodiments of the present disclosure can plan the optimal obstacle avoidance parking path according to real-time map data, reference path information and obstacle information, adapt to the scene of dynamic changes in the working area when the unmanned mining truck is parking, and provide strong support for obstacle avoidance and precise parking when the unmanned mining truck is parking.

[0233] Those skilled in the art will appreciate that the embodiments of the present disclosure may be provided as methods, devices, or computer program products. Therefore, the present disclosure may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Furthermore, the present disclosure may take the form of a computer program product implemented on one or more computer-usable non-transient storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0234] The present disclosure is described with reference to flowcharts and / or block diagrams of methods, devices (systems) and computer program products according to embodiments of the present disclosure. It should be understood that each process and / or block in the flowchart and / or block diagram and the combination of processes and / or blocks in the flowchart and / or block diagram can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0235] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0236] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0237] The unmanned mining truck parking device, data acquisition module, parking point sampling module, path planning module, path selection module and parking control module described above can be implemented as a general processor, programmable logic controller (PLC), digital signal processor (DSP), application specific integrated circuit (ASIC), field programmable gate array (FPGA) or other programmable logic device, discrete gate or transistor logic device, discrete hardware component or any appropriate combination thereof for performing the functions described in this application.

[0238] So far, the present disclosure has been described in detail. In order to avoid obscuring the concept of the present disclosure, some details known in the art are not described. Based on the above description, those skilled in the art can fully understand how to implement the technical solution disclosed here.

[0239] A person skilled in the art will understand that all or part of the steps to implement the above embodiments may be accomplished by hardware, or may be accomplished by instructing the relevant hardware through a program, and the program may be stored in a non-transitory computer-readable storage medium, and the above-mentioned storage medium may be a read-only memory, a disk or an optical disk, etc.

[0240] The description of the present disclosure is given for the purpose of illustration and description, and is not intended to be exhaustive or to limit the present disclosure to the disclosed form. Many modifications and variations will be apparent to those of ordinary skill in the art. The embodiments are selected and described in order to better illustrate the principles and practical applications of the present disclosure, and to enable those of ordinary skill in the art to understand the present disclosure and thereby design various embodiments with various modifications suitable for specific uses.

Claims

1. An unmanned mining truck parking method, comprising: Acquiring parking-related data, wherein the parking-related data at least includes vehicle current state information, obstacle data, reference parking point data, and retaining wall boundary data; Perform parking point sampling according to reference parking point data and retaining wall boundary data to obtain sampled parking point information; Calculate the sampling path according to the vehicle's current state information and the sampling parking point information; Performing obstacle collision detection on the sampled path according to the obstacle data, and selecting an optimal driving path from the sampled path; The unmanned mining truck is controlled to park according to the optimal driving path.

2. The unmanned mining truck parking method according to claim 1, wherein: The performing obstacle collision detection on the sampled path according to the obstacle data and selecting the optimal driving path from the sampled path comprises: Performing obstacle collision detection on the sampling paths according to the obstacle data, and selecting a sampling path without obstacle collision from the sampling paths; Curvature monitoring is performed on the sampled paths without obstacle collision, and an optimal driving path is selected from the sampled paths without obstacle collision.

3. The unmanned mining truck parking method according to claim 2, wherein: The curvature monitoring of the sampled paths without obstacle collision and selecting the optimal driving path from the sampled paths without obstacle collision comprises: Performing curvature monitoring on the sampled paths without obstacle collision, and selecting a drivable path from the sampled paths without obstacle collision; Calculating a total cost of each drivable path, wherein the total cost includes at least one of a parking point deviation cost, a reference path deviation cost, and a curvature cost; Select the drivable path with the smallest total cost as the optimal driving path.

4. The unmanned mining truck parking method according to claim 3, wherein: The parking-related data also includes a path maximum curvature threshold and a path minimum curvature threshold; The performing curvature monitoring on the sampled paths without obstacle collision and selecting a drivable path from the sampled paths without obstacle collision comprises: Determine whether the obstacle-free sampling path satisfies a curvature constraint, wherein the curvature constraint is that the path curvature of the obstacle-free sampling path is between a path maximum curvature threshold and a path minimum curvature threshold; Filter out the sampled paths that meet the curvature constraints as drivable paths.

5. The unmanned mining truck parking method according to claim 3 or 4, wherein: The calculating the total cost of each drivable path comprises at least one of the following steps: For each drivable path, the parking point deviation cost of the drivable path is calculated according to the heading of the sampled parking point, the heading of the target parking point, the heading error weight between the sampled parking point and the target parking point, the position error weight between the sampled parking point and the target parking point, the coordinates of the sampled parking point and the coordinates of the target parking point; For each drivable path, calculating a reference path deviation cost of the drivable path according to the coordinates of each path point in the drivable path, the coordinates of each path point in the reference path, and the reference path deviation weight; For each drivable path, the curvature cost of the drivable path is calculated according to the curvature of each path point in the drivable path and the path curvature weight.

6. The unmanned mining truck parking method according to any one of claims 2 to 4, wherein: The parking-related data also includes vehicle parameters; The performing obstacle collision detection on the sampling path according to the obstacle data and selecting a sampling path without obstacle collision from the sampling path comprises: Calculate the vehicle bounding box and vehicle encirclement according to vehicle parameters; For each sampled path, calculate the potential conflicting obstacles and potential conflicting path points whose obstacle contours are less than the radius of the vehicle encirclement from the path points; By judging whether the vehicle bounding box at the potential conflict path point intersects with the obstacle outline, it is judged whether the sampling path has a collision conflict, and the sampling path without obstacle collision is screened out.

7. The unmanned mining truck parking method according to any one of claims 1 to 4, wherein: The parking-related data at least includes map data and obstacle data, wherein: The map data is acquired based on real-time data sensing by a data sensing device; the map data includes retaining wall boundary data, the retaining wall boundary data is line data at the connection between the retaining wall and the ground, and the attributes of discrete points on the retaining wall boundary include at least coordinate information and direction angle information, and the direction angle is a direction perpendicular to the retaining wall and pointing to the unloading area; The obstacle data is obstacle data sensed by a data sensing device, and the obstacle data is stored in the form of polygons.

8. The unmanned mining truck parking method according to claim 7, wherein: The acquisition of parking related data at least includes reference path data and a first distance, wherein: The reference path data is path data based on the decision-making planning module and is saved in the form of discrete points; the reference path data includes reference parking point data; the end point of the reference path is the reference parking point; the attributes of the discrete points in the reference path include at least coordinates, heading angles and curvature; The first distance is the distance between the center of the rear axle of the unmanned mining truck and the boundary of the retaining wall when the truck is precisely parked at the parking point.

9. The unmanned mining truck parking method according to claim 8, wherein: The sampling of parking points according to the reference parking point data and the retaining wall boundary data to obtain the sampled parking point information includes: According to the reference parking point data and the retaining wall boundary data, a point projection method is applied to obtain the projection point of the reference parking point on the retaining wall boundary; Taking the projection point as the base point, the boundary points are sampled at equal intervals on the boundary of the retaining wall, and the sampled parking point information is calculated.

10. The unmanned mining truck parking method according to claim 9, wherein: The step of obtaining the projection point of the reference parking point on the retaining wall boundary by using a point projection method according to the reference parking point data and the retaining wall boundary data includes: Displacing the reference parking point by the first distance along the vehicle heading angle to determine a reference boundary point; Based on the retaining wall boundary data, the closest point of the reference boundary point to the retaining wall boundary is calculated, and the projection point of the reference boundary point on the retaining wall boundary is calculated using a point projection method.

11. The unmanned mining truck parking method according to claim 8, wherein: The method of taking the projection point as the base point, sampling boundary points at equal intervals on the boundary of the retaining wall, and calculating the sampled parking point information includes: Taking the projection point as a base point, sampling boundary points at a sampling interval of a second predetermined distance within the range of first predetermined distances to the left and right of the projection point to obtain a plurality of sampling boundary points; The sampling boundary point and the projection point are displaced by the first distance along the direction angle to obtain the sampling parking point and obtain the sampling parking point information, wherein the sampling parking point information includes the coordinates and heading angle of the sampling parking point.

12. The unmanned mining truck parking method according to any one of claims 1 to 4, wherein: The calculating of the sampling path according to the vehicle current state information and the sampling parking point information includes: Taking the reference path as the center line, a first coordinate system is established to calculate the coordinate information of the current position of the vehicle and the coordinate information of the sampled parking point, wherein the coordinate information of the current position of the vehicle in the first coordinate system includes a first coordinate and a second coordinate, the first coordinate being the longitudinal displacement along the road from the starting point of the road to the current position of the vehicle; the second coordinate being the lateral displacement from the center of mass of the vehicle to the center line of the road when the vehicle is at the current position; Set up a quintic polynomial equation; Setting boundary conditions, wherein the boundary conditions include a starting point boundary and an end point boundary; Solving a quintic polynomial equation according to the boundary conditions to calculate the parking path in equal time intervals; The discrete path points are transformed from the first coordinate system to the Cartesian coordinate system.

13. The unmanned mining truck parking method according to claim 11, wherein: The independent variable of the fifth-order polynomial equation is time, and the dependent variable is the lateral displacement; The boundary conditions include: the lateral displacement of the starting point is the second coordinate of the starting point, the lateral displacement of the end point is the second coordinate of the end point, the lateral speed of the starting point is the tangent of the heading angle of the vehicle at the starting point in the Cartesian coordinate system, the lateral speed of the end point is the tangent of the heading angle of the sampled parking point of the vehicle in the Cartesian coordinate system, and the lateral accelerations of the starting point and the end point are both 0.

14. An unmanned mining truck parking device, comprising: A data acquisition module is configured to acquire parking-related data, wherein the parking-related data at least includes vehicle current state information, obstacle data, reference parking point data, and retaining wall boundary data; The parking point sampling module is configured to perform parking point sampling according to the reference parking point data and the retaining wall boundary data to obtain sampled parking point information; A path planning module is configured to calculate a sampling path according to the vehicle current state information and the sampling parking point information; A path selection module is configured to perform obstacle collision detection on the sampled path according to the obstacle data, and select an optimal driving path from the sampled path; The parking control module is configured to control the unmanned mining truck to park according to the optimal driving path.

15. An unmanned mining truck parking device, comprising: a memory configured to store instructions; The processor is configured to execute the instructions so that the unmanned mining truck parking device implements the unmanned mining truck parking method as described in any one of claims 1-13.

16. An unmanned mining truck parking system, comprising a data sensing device and the unmanned mining truck parking device according to claim 14 or 15.

17. An unmanned mining truck, comprising the unmanned mining truck parking device according to claim 14 or 15, or the unmanned mining truck parking system according to claim 16.

18. A computer-readable storage medium, wherein: The computer-readable storage medium stores computer instructions, and when the instructions are executed by a processor, the unmanned mining truck parking method according to any one of claims 1 to 13 is implemented.

19. A computer program product comprising a computer program, wherein: When the computer program is executed by a processor, the unmanned mining truck parking method according to any one of claims 1 to 13 is implemented.

Images