Automatic driving vehicle control method, device and system and automatic driving vehicle

Abstract

The invention discloses an automatic driving vehicle control method and device and an automatic driving vehicle, and belongs to the field of automatic driving. The control method comprises the following steps: after acquiring vehicle information and a non-driving track of a target vehicle and acquiring road information and system delay time, firstly determining a target obstacle based on the size of the vehicle and the non-driving track, and calculating a relative distance based on motion information of the target obstacle; the minimum braking distance of the target vehicle is calculated based on the road information, the system delay time and the vehicle speed, when the relative distance is smaller than or equal to the minimum braking distance, it is indicated that the collision risk exists, and therefore the target vehicle needs to be controlled according to a preset control strategy. According to the scheme, the minimum braking distance is calculated from multiple dimensions, when to conduct braking control can be accurately judged in combination with the relative distance, and driving safety of the automatic driving vehicle in complex environments such as mines can be ensured.

Description

Technical Field

[0001] The present application relates to the field of autonomous driving technology, and in particular, to an autonomous driving vehicle control method, device and system, and an autonomous driving vehicle. Background Art

[0002] In today's autonomous vehicle applications, especially in complex environments such as mining areas, the braking safety of the vehicle is crucial to whether the vehicle can stop safely in advance without collision. The challenge lies in calculating the braking distance of the vehicle under complex conditions. The existing technology calculates the braking distance of the vehicle inaccurately, which easily causes late braking and brings safety hazards. Summary of the invention

[0003] In order to overcome the shortcomings of the relevant technology, the present application provides an autonomous driving vehicle control method, device and system and an autonomous driving vehicle to solve the problem in the prior art that the vehicle braking distance is inaccurately calculated, which easily causes late braking and brings safety hazards.

[0004] The technical solution adopted by this application to solve its technical problem is:

[0005] In a first aspect, a method for controlling an autonomous driving vehicle is provided, comprising:

[0006] Acquiring vehicle information and untraveled tracks of the target vehicle, as well as road information and system delay time, wherein the vehicle information includes vehicle speed and vehicle size, and the road information includes road slope and road adhesion coefficient; the untraveled tracks are used to characterize the untraveled routes in the trajectory planning of the target vehicle;

[0007] Determine a target obstacle based on the vehicle size and the untraveled trajectory, calculate a relative distance from the target vehicle to the target predicted position based on motion information of the target obstacle, and calculate a minimum braking distance of the target vehicle based on the vehicle speed, the road slope, the road adhesion coefficient, and the system delay time, the motion information including a motion direction and a motion speed, and the target predicted position is a predicted position where the target vehicle meets the target obstacle;

[0008] When the relative distance is less than or equal to the minimum braking distance, the target vehicle is controlled according to a preset control strategy, and the preset control strategy includes at least one of the following: deceleration with maximum braking and changing the driving direction.

[0009] Further, the calculating the minimum braking distance of the target vehicle based on the vehicle speed, the road slope, the road adhesion coefficient and the system delay time includes:

[0010] The minimum braking distance is calculated using the following formula:

[0011]

[0012] Among them, S is the minimum braking distance, v0 is the vehicle speed, f is the road adhesion coefficient, g is the gravity acceleration, α is the road slope, t systemdelay The system delay time.

[0013] Further, the calculating the minimum braking distance of the target vehicle based on the vehicle speed, the road slope, the road adhesion coefficient and the system delay time includes:

[0014] The minimum braking distance is calculated using the following formula:

[0015]

[0016] Where S is the minimum braking distance, v0 is the vehicle speed, f is the road adhesion coefficient, g is the gravitational acceleration, α is the road slope, C is the braking response time, and the braking response time is the time from braking 0 to maximum braking, t systemdelay The system delay time.

[0017] Furthermore, it also includes:

[0018] Obtaining an average curvature of a trajectory from the target vehicle to the predicted position;

[0019] determining a curvature coefficient based on the average curvature;

[0020] When the relative distance is less than or equal to the product of the minimum braking distance and the curvature coefficient, the target vehicle is controlled according to a preset control strategy.

[0021] Furthermore, it also includes:

[0022] Collecting point cloud data of an adjacent area of ​​the target vehicle, wherein the adjacent area is an area whose distance to the current position of the target vehicle is less than a preset distance;

[0023] Performing plane fitting on the point cloud data of the adjacent area; if the number of point clouds in the fitting plane is greater than a preset number, taking the fitting plane as a candidate fitting plane;

[0024] Calculating an angle difference between the angle of the candidate fitting plane and the road surface slope, and determining the candidate fitting plane whose angle difference is smaller than a preset angle difference as a road surface;

[0025] Acquire point cloud data of the road surface, identify the category of the point cloud data of the road surface, and obtain the road surface type;

[0026] The road adhesion coefficient is determined based on a preset corresponding relationship, in which each road surface type corresponds to a road adhesion coefficient.

[0027] Furthermore, the acquiring the point cloud data of the road surface, identifying the category of the point cloud data of the road surface, and obtaining the road surface type includes:

[0028] taking points whose distance to the road surface is less than a threshold as point cloud data of the road surface;

[0029] Dividing the point cloud data of the road surface into point cloud blocks of a preset size;

[0030] Connecting every three points in each point cloud block into a triangle, and deleting all triangles that do not meet a preset condition; the preset condition is that there are no other points in the circumscribed circle of the triangle;

[0031] The outline of the point cloud block is determined based on the connecting lines of all triangles, and the road surface type is determined based on the outline of the point cloud block.

[0032] Further, the determining of the target obstacle based on the vehicle size and the untraveled track includes:

[0033] Obtaining the shortest distance from the obstacle to the untraveled track;

[0034] If the shortest distance is smaller than the shortest width, the obstacle is determined as a target obstacle, and the shortest width is determined according to the size of the vehicle.

[0035] In a second aspect, an automatic driving vehicle control device is provided, comprising:

[0036] An information acquisition module, used to acquire vehicle information and untraveled tracks of the target vehicle, as well as road information and system delay time, wherein the vehicle information includes vehicle speed and vehicle size, and the road information includes road slope and road adhesion coefficient; the untraveled tracks are used to characterize the untraveled routes in the trajectory planning of the target vehicle;

[0037] a distance calculation module, configured to determine a target obstacle based on the size of the vehicle and the untraveled trajectory, calculate a relative distance from the target vehicle to the target obstacle based on motion information of the target obstacle, and calculate a minimum braking distance of the target vehicle based on the vehicle speed, the road slope, the road adhesion coefficient, and the system delay time, wherein the motion information includes a motion direction and a motion speed, and the relative distance is a distance from a predicted position where the target vehicle meets the target obstacle to the target vehicle;

[0038] The vehicle control module is used to control the target vehicle according to a preset control strategy when the relative distance is less than or equal to the minimum braking distance, and the preset control strategy includes at least one of the following: deceleration with maximum braking and changing the driving direction.

[0039] In a third aspect, a computer-readable storage medium is provided, on which a computer program or instruction is stored. When the computer program or instruction is executed by a processor, the steps of the automatic driving vehicle control method provided by the technical solution of the first aspect are implemented.

[0040] In a fourth aspect, an autonomous driving vehicle control system is provided, comprising:

[0041] at least one processor and at least one memory;

[0042] The memory stores executable instructions of the processor;

[0043] The processor is configured to execute the autonomous driving vehicle control method provided by the technical solution of the first aspect.

[0044] In a fifth aspect, an autonomous driving vehicle is provided, which applies the autonomous driving vehicle control method provided by the technical solution of the first aspect.

[0045] Beneficial effects:

[0046] The technical solution of the present application provides a control method, device and system for an autonomous driving vehicle and an autonomous driving vehicle. The control method includes: after obtaining the vehicle information and untraveled track of the target vehicle and obtaining the road information and system delay time, first determine the target obstacle based on the vehicle size and untraveled track, calculate the relative distance based on the motion information of the target obstacle, and calculate the minimum braking distance of the target vehicle based on the road information, system delay time and vehicle speed. When the relative distance is less than or equal to the minimum braking distance, it indicates that there is a collision risk, so the target vehicle needs to be controlled according to the preset control strategy. The solution of the present application calculates the minimum braking distance from multiple dimensions, and can accurately determine when to perform braking control in combination with the relative distance, which can ensure the driving safety of autonomous driving vehicles in complex environments such as mines. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the related technologies, the drawings required for use in the embodiments or the related technical descriptions are briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0048] Figure 1is a flow chart of an autonomous driving vehicle control method provided in an embodiment of the present application;

[0049] Figure 2 is a flow chart of a method for determining a road adhesion coefficient provided in an embodiment of the present application;

[0050] Figure 3 is a flow chart of a method for determining a road surface type provided in an embodiment of the present application;

[0051] Figure 4 is a flow chart of a specific autonomous driving vehicle control method provided in an embodiment of the present application;

[0052] Figure 5 is a schematic diagram of a fitting curve of vehicle speed and minimum braking distance provided in an embodiment of the present application;

[0053] Figure 6 It is a schematic diagram of the structure of an autonomous driving vehicle control device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0054] In order to make the purpose, technical scheme and advantages of the present application clearer, the technical scheme of the present application is described in detail below in conjunction with the accompanying drawings and embodiments. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all of the embodiments. Based on the embodiments in the present application, all other implementation methods obtained by ordinary technicians in the field without making creative work belong to the scope of protection of the present application.

[0055] Conventional technical solutions generally calculate the minimum braking distance based only on vehicle speed. Because the driving environment of conventional vehicles is relatively simple, the minimum braking distance can be determined more accurately by only using vehicle speed calculation, and then the vehicle can be controlled. However, in complex environments such as mines, there are many factors affecting the minimum braking distance. Considering only vehicle speed will lead to inaccurate judgment of the minimum braking distance, which is very likely to cause a vehicle collision and pose a safety hazard.

[0056] Therefore, in order to solve the above problems, the present application scheme combines parameters of multiple dimensions to accurately determine the minimum braking distance, prevent vehicle collisions, and ensure vehicle driving safety.

[0057] Reference Figure 1 , the embodiment of the present application provides an automatic driving vehicle control method, comprising:

[0058] S11: Acquire vehicle information and untraveled trajectory of the target vehicle, as well as road information and system delay time, wherein the vehicle information includes vehicle speed and vehicle size, and the road information includes road slope and road adhesion coefficient; the untraveled trajectory is used to characterize the untraveled route in the trajectory planning of the target vehicle.

[0059] The vehicle speed is obtained by the sensors on the vehicle. The vehicle size is determined by the vehicle model. The untraveled trajectory is determined by the vehicle's trajectory planning and current position.

[0060] In addition, the system delay time refers to the time from when the vehicle acquires data to when a control instruction is generated based on the data or when the control instruction is sent to the execution unit. In one embodiment, the system delay time can be pre-set for each vehicle or each vehicle type based on advance testing. In another embodiment, the system delay time can be measured by the vehicle itself in real time, such as recording the first time of acquiring data and the second time of generating a control instruction based on the data or sending the control instruction to the execution unit. The system delay time is determined based on the difference between the second time and the first time.

[0061] Furthermore, the road slope can be determined based on the elevation difference and horizontal distance between two points.

[0062] In one embodiment, the road surface adhesion coefficient is determined according to the road surface type. The adhesion coefficients of different road surfaces (such as ice, snow, dirt road-wet, gravel, dirt road-dry) are different. Please refer to Table 1 for the corresponding relationship.

[0063] Table 1

[0064] Road surface type Road adhesion coefficient (no load) gravel 0.6 Dirt road (dry) 0.68 Dirt road (wet) 0.55 Snow (compacted) 0.2 ice 0.1

[0065] Therefore, once the road surface type is determined, the road adhesion coefficient can be determined according to the corresponding relationship shown in Table 1.

[0066] In one embodiment, a road surface photo is obtained by using a sensor such as a camera on a vehicle, and then a recognition model is trained to determine the road surface type according to the recognition model. However, the training cost of the recognition model is relatively high.

[0067] Therefore, in another embodiment, the road type is determined by combining data obtained by multiple sensors (such as lidar, cameras) on the vehicle.

[0068] Preferably, if Figure 2 As shown:

[0069] S21: collecting point cloud data of an adjacent area of ​​the target vehicle, where the adjacent area is an area whose distance to the current position of the target vehicle is less than a preset distance; that is, obtaining point cloud data around the target vehicle.

[0070] S22: plane fitting is performed on the point cloud data of the adjacent area; if the number of point clouds in the fitting plane is greater than a preset number, the fitting plane is used as a candidate fitting plane; since the acquired point cloud data includes not only the road surface, but also point cloud data outside the road surface, such as obstacles. However, since the number of point clouds of the road surface is the largest, candidate fitting planes with more point cloud data are determined through plane fitting. These candidate fitting planes include the road surface.

[0071] S23: Calculate the angle difference between the candidate fitting plane and the road surface slope, and determine the candidate fitting plane whose angle difference is less than the preset angle difference as the road surface; because in practice, if there is a high earth pile or enclosure on one side of the road, its point cloud data is relatively large, and at this time, a candidate fitting plane will also be determined based on the point cloud data of the earth pile or enclosure. Therefore, it is also necessary to determine a road surface in the candidate fitting plane based on the angle of the road surface slope.

[0072] S24: Obtain the point cloud data of the road surface, identify the category of the point cloud data of the road surface, and obtain the road surface type; the shape of the point cloud on the road surface can be obtained according to the point cloud data of the road surface, and the road surface type can be determined based on the shape. For some shapes that are relatively similar, the grayscale value of the image is combined to determine the type of the road surface. For example, the grayscale value of snow is different from the grayscale value of soil, and the grayscale value of dry soil and wet soil is also different.

[0073] S25: Determine the road surface adhesion coefficient based on a preset corresponding relationship, wherein each road surface type in the preset corresponding relationship corresponds to a road surface adhesion coefficient.

[0074] As a preferred implementation method of the present application, Figure 3 As shown, obtaining the point cloud data of the road surface, identifying the category of the point cloud data of the road surface, and obtaining the road surface type include:

[0075] S31: The points whose distance to the road surface is less than a threshold are regarded as point cloud data of the road surface; the shape cannot be determined only based on the point cloud on the fitting plane, so the point cloud of the entire road surface is required. During processing, the points whose distance to the road surface is less than a threshold are regarded as points on the road surface.

[0076] S32: dividing the point cloud data of the road surface into point cloud blocks of a preset size; dividing into point cloud blocks of a preset size can be processed in parallel, thereby improving processing efficiency.

[0077] S33: Connect every three points in each point cloud block into a triangle, and delete all triangles that do not meet the preset condition; the preset condition is that there are no other points in the circumscribed circle of the triangle; the triangles that do not meet the preset condition are deleted because the connection lines of these triangles will exceed the range of the point cloud block. This will cause great interference in the subsequent recognition of the point cloud contour.

[0078] S34: Determine the outline of the point cloud block based on the lines connecting all triangles, and determine the road surface type based on the outline of the point cloud block. Since the three vertices in the triangle are all points in the point cloud, the adjacent points are basically connected (the lines of distant points will be deleted due to the deletion of some triangles). The point cloud outline in the point cloud block can be identified based on the lines, and the road surface type is determined based on the shape and size of the outline.

[0079] The solution of this embodiment does not require a special image recognition model, and the road type can be determined based on the vehicle's original sensors, thereby reducing costs.

[0080] In another embodiment, the adhesion coefficient is determined based on the road surface type and the vehicle weight. The vehicle weight is divided into two conditions: empty and heavy. Because during the use of the mine, the vehicle generally only includes two conditions: empty and fully loaded. Therefore, in the embodiment of the present application, the road adhesion coefficient when fully loaded is used as the adhesion coefficient when heavy loaded. The corresponding relationship can be referred to in Table 2.

[0081] Table 2

[0082]

[0083]

[0084] S12: Determine a target obstacle based on the vehicle size and the untraveled trajectory, calculate a relative distance from the target vehicle to the target predicted position based on the motion information of the target obstacle, and calculate a minimum braking distance of the target vehicle based on the vehicle speed, the road slope, the road adhesion coefficient, and the system delay time, the motion information including the motion direction and the motion speed, and the target predicted position is the predicted position where the target vehicle meets the target obstacle.

[0085] As a preferred implementation of the embodiment of the present application, the determining of the target obstacle based on the vehicle size and the untraveled track includes:

[0086] The shortest distance from the obstacle to the untraveled track is obtained.

[0087] If the shortest distance is less than the shortest width, the obstacle is determined as a target obstacle, and the shortest width is determined according to the size of the vehicle. In one embodiment, the larger the vehicle, the larger the shortest width. The specific value is set as needed. In another embodiment, the driving direction of the target vehicle at the target prediction position is determined based on trajectory planning, and the shortest width is determined based on the driving direction and the length and width of the vehicle. For example, when traveling straight along the road, the shortest width is half the width of the target vehicle.

[0088] In addition, the target predicted position is related to the motion state of the target vehicle and the target obstacle. Exemplarily, if the target obstacle is stationary, the target predicted position is the current position of the target obstacle. If the target obstacle is moving, the target predicted position is related to the motion speed and motion direction of the target obstacle. Among them, the motion direction is divided into the same as the motion direction of the target vehicle and the opposite to the motion direction of the target vehicle. When the motion directions are opposite, the target predicted position is determined based on the speed of the target vehicle and the target obstacle. When the motion directions are the same, the magnitude of the motion speed of the target obstacle and the target vehicle is compared. If the motion speed of the target obstacle is greater than or equal to the motion speed of the target vehicle, it is predicted that the two will not meet. At this time, the relative distance is infinite, and the motion speed of the target obstacle is less than the motion speed of the target vehicle. The target predicted position is determined according to the motion speed of the target obstacle and the target vehicle.

[0089] In one embodiment, the calculating the minimum braking distance of the target vehicle based on the vehicle speed, the road slope, the road adhesion coefficient, and the system delay time includes:

[0090] The minimum braking distance is calculated using the following formula:

[0091]

[0092] Among them, S is the minimum braking distance, v0 is the vehicle speed, f is the road adhesion coefficient, g is the gravity acceleration, α is the road slope, t systemdelay The system delay time.

[0093] However, when testing vehicles with different loads, it was found that the minimum braking distance calculated above is not accurate for the same vehicle with different loads. This is because the time from braking to maximum braking is different when the vehicle is unloaded and heavily loaded. When the vehicle is heavily loaded, the time (brake response time) is longer than when the vehicle is unloaded. When the vehicle is unloaded or heavily loaded, the brake response time is the same, so the time can be fitted into the system delay time.

[0094] Therefore, in another embodiment, the calculating the minimum braking distance of the target vehicle based on the vehicle speed, the road slope, the road adhesion coefficient and the system delay time includes:

[0095] The minimum braking distance is calculated using the following formula:

[0096]

[0097] Where S is the minimum braking distance, v0 is the vehicle speed, f is the road adhesion coefficient, g is the gravitational acceleration, α is the road slope, C is the braking response time, and the braking response time is the time from braking 0 to maximum braking, t systemdelay The system delay time.

[0098] The braking response time selects different parameters according to whether the vehicle is unloaded or loaded.

[0099] S13: When the relative distance is less than or equal to the minimum braking distance, the target vehicle is controlled according to a preset control strategy, wherein the preset control strategy includes at least one of the following: deceleration with maximum braking and changing the driving direction.

[0100] In addition, in actual tests, the inventors found that if the target vehicle is traveling in a straight line, the braking distance calculated by the above embodiment has a small deviation from the actual braking distance. However, if the target vehicle brakes on a curve, the calculated braking distance is always smaller than the actual braking distance, and the deviation is large. Therefore, in order to control more accurately. The embodiment of the present application also provides a solution for controlling according to the trajectory of the target vehicle, which is as follows:

[0101] The average curvature of the trajectory from the target vehicle to the predicted position is obtained; the average curvature represents the curvature; the curvature coefficient is determined based on the average curvature; the greater the curvature, the greater the average curvature, and the greater the curvature coefficient.

[0102] When the relative distance is less than or equal to the product of the minimum braking distance and the curvature coefficient, the target vehicle is controlled according to a preset control strategy.

[0103] In addition, it should be noted that the preset control strategy includes at least one of the following: decelerating with maximum braking and changing the driving direction. That is, the vehicle may decelerate with maximum braking only, change the driving direction only, or change the driving direction while decelerating with maximum braking.

[0104] Optionally, when the relative distance is greater than the minimum braking distance, or when the relative distance is greater than the product of the minimum braking distance and the curvature coefficient, a safety distance may be set, and the safety distance is greater than the minimum braking distance. When the relative distance is greater than the safety distance, no control is performed. When the relative distance is less than or equal to the safety distance, the maximum speed of the target vehicle is limited, that is, the speed of the target vehicle is not allowed to exceed the set maximum speed.

[0105] As a specific implementation method of this application, Figure 2 As shown, the following steps are included:

[0106] 1. Map the position of the obstacle to the trajectory, calculate the collision point, and the relative distance S_obs relative to the vehicle box collision;

[0107] 2. According to the vehicle status information (vehicle speed, load status), slope information, adhesion coefficient of the mining area road surface, system delay and other input information and the braking distance model, the minimum braking distance S_emergency_stop is calculated. The braking distance model is:

[0108]

[0109] Where:

[0110] f empty (μ), f full (μ) represents the coefficients related to road adhesion when the vehicle is unloaded and fully loaded, respectively. The lower the road adhesion, the smaller the coefficient; C empty , C full They represent the time parameters of the vehicle under no-load and full-load conditions respectively, are related to the braking response time, and are generally constants.

[0111] t systemdelay Indicates system delay;

[0112] g represents the acceleration due to gravity, usually 9.8m / s^2;

[0113] α represents the climbing grade, v0 represents the initial vehicle speed;

[0114] S empty ,S full Respectively represent the braking distance under no-load and full-load output.

[0115] The derivation process is as follows:

[0116] Based on automobile theory, the wheel ground braking force is determined by two parts:

[0117] One part is the vehicle's own braking capacity (mechanical braking torque + motor braking torque), calculated as follows:

[0118] a1=-(T w / r w / m+gsinα+fgcosα)

[0119] Where, a1: braking deceleration, T w : braking torque of the tire; r w : Radius of tire g: Acceleration due to gravity (usually 9.81 m / s 2 )α: slope angle (usually the angle between the ground and the horizontal plane), where α=arctan(h / s); h is the elevation difference between the two points, s is the horizontal distance difference between the two points, and f is the friction coefficient related to the vehicle mass (which may represent the friction performance between the ground and the tire).

[0120] The other part is the constraint of the road adhesion parameter, that is, the deceleration constraint, and the calculation formula is as follows:

[0121] a2=-(gsinα+μgcosα)

[0122] In the formula, a2 is the deceleration and μ is the "comprehensive road adhesion coefficient".

[0123] It should be noted that the "comprehensive adhesion coefficient of the road surface" needs to be combined with the influence of factors related to wheel sliding state, wheel vertical load, tire stiffness, and ground conditions. Generally, it is necessary to establish a tire model, a body model, a vertical load model / a longitudinal vehicle speed and wheel speed model. The calculation process is relatively complex, with many input parameters and accuracy requirements. The calculation process is generally implemented through TruckSim commercial software. This document preliminarily evaluates the wheel braking distance. The wheel's ground force and adhesion are constantly changing. It is also limited to adjust the braking force at any time and make it exactly the same as the adhesion. Therefore, the "comprehensive adhesion coefficient of the road surface" <= the actual adhesion coefficient of the road surface.

[0124] Based on the force analysis and kinematic relationship of the vehicle, as well as the "rolling and sliding" state of the vehicle during braking, the calculation model for the unloaded and heavily loaded braking distances can be obtained as shown in the following formula. The braking distance is determined by the various coefficients f empty (μ), C empty 、f full (μ), C full , the initial vehicle speed v0 and α, and the system delay buffer also needs to be added.

[0125]

[0126] Where:

[0127] f empty (μ), f full (μ) represents the coefficients related to road adhesion when the vehicle is unloaded and loaded, respectively. The lower the road adhesion, the smaller the coefficient;

[0128] C empty , C full They represent the vehicle's no-load and heavy-load conditions respectively, and are related to the braking response time, and are generally constants.

[0129] t systemdelay Indicates system delay;

[0130] g represents the acceleration due to gravity, usually 9.8m / s^2;

[0131] α represents the climbing grade.

[0132] Referring to the empirical data under different road conditions, the adhesion coefficients under different road conditions are shown in Table 2 above.

[0133] Due to the different adhesion coefficients on different road surfaces (ice, snow, dirt road-wet, gravel, dirt road-dry) (see table above), the corresponding f empty (μ), f full The values ​​of (μ) are all different.

[0134] According to the test data fitting, various coefficients under different road adhesion conditions are obtained. The curves of vehicle speed and minimum braking distance obtained based on various coefficients are as follows: Figure 5 shown.

[0135] in Figure 5 The upper curve is the fitting curve when no load is applied. Figure 5 The lower curve in the middle is the fitting curve when overloaded.

[0136] The specific testing process is provided below.

[0137] Among them, the control braking data is shown in Table 3, and the full-load braking data is shown in Table 4.

[0138] Table 3

[0139]

[0140] Table 4

[0141]

[0142] In Table 3 and Table 4, -5.5m / s / s is the maximum braking deceleration. Kph is the speed unit of kilometers per hour. Taking the plane as an example, the first column is the initial movement speed, and the second column is -5.5m / s / s is the minimum braking distance at the maximum braking deceleration.

[0143] Minimum braking distance fitting:

[0144] According to the braking distance formula: (Where t0 is the braking response time, ignoring the change in vehicle speed during the response time when there is no braking). System delay does not exist during simulation and only needs to be added in actual vehicle testing.

[0145] Based on the data in Table 3, the no-load fitting curve is as follows Figure 5 The curve in the upper middle part, where f+gα=5.17 and t0=0.751.

[0146] Based on the data in Table 4, the overload fitting curve is as follows Figure 5 The lower middle curve. Among them, f+gα=2.417, t0=0.5301.

[0147] Data Validation:

[0148] The no-load fitting formula is verified by the measured data of 4° downhill slope. The verification results are shown in Table 5:

[0149] Table 5

[0150]

[0151] The heavy load fitting formula is verified by the measured data of 4° uphill slope. The verification results are shown in Table 6:

[0152] Table 6

[0153]

[0154] 3. Determine the obstacle information and the minimum safe distance. When the distance obtained with maximum braking is less than the distance to the obstacle, it is determined that there is a safety risk. At this time, the vehicle needs to be issued an emergency stop and emergency braking.

[0155] Based on the same inventive concept, Figure 6 As shown, the present application also provides an automatic driving vehicle control device 60, comprising:

[0156] The information acquisition module 61 is used to obtain the vehicle information and untraveled trajectory of the target vehicle, as well as the road information and system delay time. The vehicle information includes the vehicle speed and vehicle size, and the road information includes the road slope and road adhesion coefficient; the untraveled trajectory is used to characterize the untraveled route in the trajectory planning of the target vehicle.

[0157] Optionally, collecting point cloud data of an adjacent area of ​​the target vehicle, the adjacent area being an area whose distance to the current position of the target vehicle is less than a preset distance;

[0158] Performing plane fitting on the point cloud data of the adjacent area; if the number of point clouds in the fitting plane is greater than a preset number, taking the fitting plane as a candidate fitting plane;

[0159] Calculating an angle difference between the angle of the candidate fitting plane and the road surface slope, and determining the candidate fitting plane whose angle difference is smaller than a preset angle difference as a road surface;

[0160] Acquire point cloud data of the road surface, identify the category of the point cloud data of the road surface, and obtain the road surface type;

[0161] The road adhesion coefficient is determined based on a preset corresponding relationship, in which each road surface type corresponds to a road adhesion coefficient.

[0162] Preferably, acquiring the point cloud data of the road surface, identifying the category of the point cloud data of the road surface, and obtaining the road surface type includes:

[0163] taking points whose distance to the road surface is less than a threshold as point cloud data of the road surface;

[0164] Dividing the point cloud data of the road surface into point cloud blocks of a preset size;

[0165] Connecting every three points in each point cloud block into a triangle, and deleting all triangles that do not meet a preset condition; the preset condition is that there are no other points in the circumscribed circle of the triangle;

[0166] The outline of the point cloud block is determined based on the connecting lines of all triangles, and the road surface type is determined based on the outline of the point cloud block.

[0167] The distance calculation module 62 is used to determine the target obstacle based on the vehicle size and the untraveled trajectory, and calculate the relative distance from the target vehicle to the target obstacle based on the motion information of the target obstacle, and calculate the minimum braking distance of the target vehicle based on the vehicle speed, the road slope, the road adhesion coefficient and the system delay time, the motion information includes the motion direction and the motion speed, and the relative distance is the distance from the predicted position where the target vehicle meets the target obstacle to the target vehicle.

[0168] Wherein, determining the target obstacle based on the vehicle size and the untraveled track includes:

[0169] Obtaining the shortest distance from the obstacle to the untraveled track;

[0170] If the shortest distance is smaller than the shortest width, the obstacle is determined as a target obstacle, and the shortest width is determined according to the size of the vehicle.

[0171] In one embodiment, calculating the minimum braking distance of the target vehicle based on the vehicle speed, the road slope, the road adhesion coefficient, and the system delay time includes:

[0172] The minimum braking distance is calculated using the following formula:

[0173]

[0174] Among them, S is the minimum braking distance, v0 is the vehicle speed, f is the road adhesion coefficient, g is the gravity acceleration, α is the road slope, t systemdelay The system delay time.

[0175] In another embodiment, calculating the minimum braking distance of the target vehicle based on the vehicle speed, the road slope, the road adhesion coefficient, and the system delay time includes:

[0176] The minimum braking distance is calculated using the following formula:

[0177]

[0178] Where S is the minimum braking distance, v0 is the vehicle speed, f is the road adhesion coefficient, g is the gravity acceleration, Δ is the road slope, C is the braking response time, and the braking response time is the time from braking 0 to maximum braking, t systemdelay The system delay time.

[0179] The vehicle control module 63 is used to control the target vehicle according to a preset control strategy when the relative distance is less than or equal to the minimum braking distance. The preset control strategy includes at least one of the following: deceleration with maximum braking and changing the driving direction.

[0180] As a preferred implementation method of the embodiment of the present application, an average curvature of the trajectory of the target vehicle to the predicted position is obtained;

[0181] determining a curvature coefficient based on the average curvature;

[0182] When the relative distance is less than or equal to the product of the minimum braking distance and the curvature coefficient, the target vehicle is controlled according to a preset control strategy.

[0183] Based on the same inventive concept, the present application provides a computer-readable storage medium on which a computer program or instruction is stored. When the computer program or instruction is executed by a processor, the steps of the autonomous driving vehicle control method provided in any of the above embodiments are implemented.

[0184] Based on the same inventive concept, the present application provides an autonomous driving vehicle control system, comprising:

[0185] at least one processor and at least one memory;

[0186] The memory stores executable instructions of the processor;

[0187] The processor is configured to execute the autonomous driving vehicle control method provided in any of the above embodiments.

[0188] Based on the same inventive concept, the present application provides an autonomous driving vehicle, applying the autonomous driving vehicle control method provided by any of the above embodiments.

[0189] The autonomous driving vehicle provided in the embodiment of the present application, after obtaining the vehicle information and untraveled track of the target vehicle and obtaining the road information and system delay time, first determines the target obstacle based on the vehicle size and untraveled track, calculates the relative distance based on the motion information of the target obstacle, and calculates the minimum braking distance of the target vehicle based on the road information and system delay time and vehicle speed. When the relative distance is less than or equal to the minimum braking distance, it indicates that there is a collision risk, so the target vehicle needs to be controlled according to the preset control strategy. The present application solution calculates the minimum braking distance from multiple dimensions, and combined with the relative distance, it can accurately determine when to perform braking control, which can ensure the driving safety of autonomous driving vehicles in complex environments such as mines.

[0190] It can be understood that the same or similar parts of the above embodiments can be referenced to each other, and the contents not described in detail in some embodiments can refer to the same or similar contents in other embodiments.

[0191] It should be noted that, in the description of this application, the terms "first", "second", etc. are only used for descriptive purposes and cannot be understood as indicating or implying relative importance. In addition, in the description of this application, unless otherwise specified, the meaning of "plurality" refers to at least two.

[0192] Any process or method description in a flowchart or otherwise described herein may be understood to represent a module, segment or portion of code that includes one or more executable instructions for implementing the steps of a specific logical function or process, and the scope of the preferred embodiments of the present application includes alternative implementations in which functions may not be performed in the order shown or discussed, including performing functions in a substantially simultaneous manner or in the reverse order depending on the functions involved, which should be understood by technicians in the technical field to which the embodiments of the present application belong.

[0193] It should be understood that the various parts of the present application can be implemented by hardware, software, firmware or a combination thereof. In the above-mentioned embodiments, multiple steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or their combination: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0194] A person skilled in the art may understand that all or part of the steps in the method for implementing the above-mentioned embodiment may be completed by instructing related hardware through a program, and the program may be stored in a computer-readable storage medium, which, when executed, includes one or a combination of the steps of the method embodiment.

[0195] In addition, each functional unit in each embodiment of the present application may be integrated into a processing module, or each unit may exist physically separately, or two or more units may be integrated into one module. The above-mentioned integrated module may be implemented in the form of hardware or in the form of a software functional module. If the integrated module is implemented in the form of a software functional module and sold or used as an independent product, it may also be stored in a computer-readable storage medium.

[0196] The storage medium mentioned above can be a read-only memory, a magnetic disk or an optical disk, etc.

[0197] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present application. In this specification, the schematic representation of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner.

[0198] Although the embodiments of the present application have been shown and described above, it can be understood that the above embodiments are exemplary and cannot be understood as limitations on the present application. Ordinary technicians in this field can change, modify, replace and modify the above embodiments within the scope of the present application.

Claims

1. A method for controlling an automatic driving vehicle, characterized in that: include: Acquiring vehicle information and untraveled tracks of the target vehicle, as well as road information and system delay time, wherein the vehicle information includes vehicle speed and vehicle size, and the road information includes road slope and road adhesion coefficient; The untraveled trajectory is used to represent the untraveled route in the trajectory planning of the target vehicle; Determine a target obstacle based on the vehicle size and the untraveled trajectory, calculate a relative distance from the target vehicle to the target predicted position based on motion information of the target obstacle, and calculate a minimum braking distance of the target vehicle based on the vehicle speed, the road slope, the road adhesion coefficient, and the system delay time, the motion information including a motion direction and a motion speed, and the target predicted position is a predicted position where the target vehicle meets the target obstacle; When the relative distance is less than or equal to the minimum braking distance, the target vehicle is controlled according to a preset control strategy, and the preset control strategy includes at least one of the following: deceleration with maximum braking and changing the driving direction.

2. The method according to claim 1, characterized in that The calculating the minimum braking distance of the target vehicle based on the vehicle speed, the road slope, the road adhesion coefficient, and the system delay time includes: The minimum braking distance is calculated using the following formula: Among them, S is the minimum braking distance, v0 is the vehicle speed, f is the road adhesion coefficient, g is the gravity acceleration, α is the road slope, t systemdelay The system delay time.

3. The method according to claim 1, characterized in that The calculating the minimum braking distance of the target vehicle based on the vehicle speed, the road slope, the road adhesion coefficient, and the system delay time includes: The minimum braking distance is calculated using the following formula: Where S is the minimum braking distance, v0 is the vehicle speed, f is the road adhesion coefficient, g is the gravitational acceleration, α is the road slope, C is the braking response time, and the braking response time is the time from braking 0 to maximum braking, t systemdelay The system delay time.

4. The method according to claim 1, characterized in that: Also includes: Obtaining an average curvature of a trajectory from the target vehicle to the predicted position; determining a curvature coefficient based on the average curvature; When the relative distance is less than or equal to the product of the minimum braking distance and the curvature coefficient, the target vehicle is controlled according to a preset control strategy.

5. The method according to claim 1, characterized in that Also includes: Collecting point cloud data of an adjacent area of ​​the target vehicle, wherein the adjacent area is an area whose distance to the current position of the target vehicle is less than a preset distance; Performing plane fitting on the point cloud data of the adjacent area; if the number of point clouds in the fitting plane is greater than a preset number, taking the fitting plane as a candidate fitting plane; Calculating an angle difference between the angle of the candidate fitting plane and the road surface slope, and determining the candidate fitting plane whose angle difference is smaller than a preset angle difference as a road surface; Acquire point cloud data of the road surface, identify the category of the point cloud data of the road surface, and obtain the road surface type; The road adhesion coefficient is determined based on a preset corresponding relationship, in which each road surface type corresponds to a road adhesion coefficient.

6. The method according to claim 5, characterized in that The step of acquiring the point cloud data of the road surface, identifying the category of the point cloud data of the road surface, and obtaining the road surface type includes: taking points whose distance to the road surface is less than a threshold as point cloud data of the road surface; Dividing the point cloud data of the road surface into point cloud blocks of a preset size; Connecting every three points in each point cloud block into a triangle, and deleting all triangles that do not meet a preset condition; the preset condition is that there are no other points in the circumscribed circle of the triangle; The outline of the point cloud block is determined based on the connecting lines of all triangles, and the road surface type is determined based on the outline of the point cloud block.

7. The method according to claim 1, characterized in that The determining of the target obstacle based on the vehicle size and the untraveled track comprises: Obtaining the shortest distance from the obstacle to the untraveled track; If the shortest distance is smaller than the shortest width, the obstacle is determined as a target obstacle, and the shortest width is determined according to the size of the vehicle.

8. An automatic driving vehicle control device, characterized in that: include: An information acquisition module, used to acquire vehicle information and untraveled tracks of the target vehicle, as well as road information and system delay time, wherein the vehicle information includes vehicle speed and vehicle size, and the road information includes road slope and road adhesion coefficient; The untraveled trajectory is used to represent the untraveled route in the trajectory planning of the target vehicle; a distance calculation module, configured to determine a target obstacle based on the size of the vehicle and the untraveled trajectory, calculate a relative distance from the target vehicle to the target obstacle based on motion information of the target obstacle, and calculate a minimum braking distance of the target vehicle based on the vehicle speed, the road slope, the road adhesion coefficient, and the system delay time, wherein the motion information includes a motion direction and a motion speed, and the relative distance is a distance from a predicted position where the target vehicle meets the target obstacle to the target vehicle; The vehicle control module is used to control the target vehicle according to a preset control strategy when the relative distance is less than or equal to the minimum braking distance. The preset control strategy includes at least one of the following: deceleration with maximum braking and changing the driving direction.

9. An automatic driving vehicle control system, characterized in that: include: at least one processor and at least one memory; The memory stores executable instructions of the processor; The processor is configured to execute the method according to any one of claims 1 to 7.

10. An autonomous driving vehicle, characterized in that: The method according to any one of claims 1 to 7 is used.

Images