Vehicle control method, device, equipment and readable storage medium

Abstract

A vehicle control method, device, equipment and readable storage medium, the vehicle control method includes: obtaining three-dimensional point cloud data through a vehicle-mounted laser radar; extracting a drivable area and obstacles based on the three-dimensional point cloud data; obtaining the motion state of the extracted obstacle, the relative motion state between the obstacle and the vehicle, and the vehicle characteristics, and using a risk field strength model to calculate the risk field strength of the obstacle in the drivable area; determining the risk level of the obstacle according to the risk field strength of the obstacle in the drivable area; and controlling the vehicle to travel in the drivable area using a control strategy corresponding to the risk level of the obstacle. This application calculates the risk field strength of the obstacle in the drivable area, determines the risk level of the obstacle according to the risk field strength, and controls the vehicle to travel in the drivable area using a control strategy corresponding to the risk level of the obstacle, thereby making the risk assessment of the obstacle more accurate and the control of the vehicle safer.

Description

Technical Field

[0001] The present application relates to the field of intelligent driving technology, and specifically to a vehicle control method, device, equipment and readable storage medium. Background Art

[0002] In the complex scenarios underground in a mine, an autonomous driving vehicle determines whether the vehicle and the road environment are in a safe state based on its own vehicle information and underground environmental characteristics, and enables the vehicle to make correct and safe behavioral decisions, so that the vehicle can pass through the narrow roads in the mine safely and efficiently and complete autonomous driving operations underground in the mine. However, the current control solutions for autonomous driving vehicles are not safe enough. Summary of the invention

[0003] The present application provides a vehicle control method, device, equipment and readable storage medium, which can solve the technical problem that the current control scheme for autonomous driving vehicles underground in mining areas is not safe enough.

[0004] In a first aspect, an embodiment of the present application provides a vehicle control method, the vehicle control method comprising:

[0005] Acquire 3D point cloud data through vehicle-mounted laser radar;

[0006] Extract drivable areas and obstacles based on 3D point cloud data;

[0007] Obtain the motion state of the extracted obstacle, the relative motion state between the obstacle and the vehicle, and the vehicle characteristics, and use the risk field strength model to calculate the risk field strength of the obstacle in the drivable area;

[0008] Determine the risk level of the obstacle based on the risk field strength of the obstacle in the drivable area;

[0009] A control strategy corresponding to the risk level of the obstacle is used to control the vehicle to travel within the drivable area.

[0010] Optionally, extracting the drivable area based on the three-dimensional point cloud data includes:

[0011] Divide the 3D point cloud data into grids in the polar coordinate system and determine the height of each grid unit;

[0012] By traversing the grid cells, the slope between the current grid cell and the adjacent grid cells is calculated, and the height difference between the current grid cell and the adjacent grid cells is obtained;

[0013] If the slope is less than the preset slope and the height difference is less than the preset height difference, the adjacent grid cells are taken as the ground to obtain all the ground grid cells;

[0014] All ground grid cells are removed from all grid cells to obtain all left and right wall grid cells, and the projections of all left and right wall grid cells are fitted to obtain left and right boundary lines;

[0015] Project the left and right boundary lines onto the map to obtain the drivable area.

[0016] Optionally, determining the height of each grid unit includes:

[0017] The median value of the height of each point in each grid cell is used as the initial height of each grid cell;

[0018] If the initial height of the grid unit is greater than the preset maximum value, the preset maximum value is used as the height of the grid unit, otherwise the initial height of the grid unit is used as the height of the grid unit, and the preset maximum value is the installation height of the laser radar.

[0019] Optionally, before the step of traversing the grid cells to calculate the slope between the current grid cell and the adjacent grid cells to obtain the height difference between the current grid cell and the adjacent grid cells, the step includes:

[0020] If the height information of a grid cell is missing, the median of the heights of the adjacent grid cells is used as its height;

[0021] The height of each grid cell is smoothed using a Gaussian smoothing filter.

[0022] Optionally, the motion state of the obstacle includes the acceleration of the obstacle, the relative motion state between the obstacle and the vehicle includes the speed difference between the vehicle and the obstacle and the angle between the center of mass of the vehicle and the center of mass of the obstacle, the vehicle characteristics include the vehicle load, and the acquisition of the extracted motion state of the obstacle, the relative motion state between the obstacle and the vehicle, and the vehicle characteristics, and the use of the risk field strength model to calculate the risk field strength of the obstacle in the drivable area includes:

[0023] Obtain the acceleration of the extracted obstacle, the speed difference between the vehicle and the obstacle, the angle between the center of mass of the vehicle and the center of mass of the obstacle, and the vehicle load;

[0024] The acceleration of the obstacle, the speed difference between the vehicle and the obstacle, the angle between the center of mass of the vehicle and the center of mass of the obstacle, and the vehicle load are substituted into the risk field strength model to calculate the risk field strength of the obstacle in the drivable area. The risk field strength model is:

[0025]

[0026] Among them, E S,ij Indicates that the i ,y i ) is located at point (xj ,y j ), K is the weight coefficient, M is the vehicle load, and σ is the field strength at point (x j ,y j ) is the Gaussian distribution variance of the field strength at , r ij =(x i -x j ,y i -y j ) means located at (x i ,y i ) and the obstacle i at point (x j ,y j ), μ is the distance between the point (x j ,y j ), Δv is the speed difference between the vehicle and the obstacle, γ is the calibration coefficient, a is the acceleration of the obstacle, and θ is the angle between the center of mass of the vehicle and the center of mass of the obstacle.

[0027] Optionally, the risk level of the obstacle includes level one, level two and level three, and the use of a control strategy corresponding to the risk level of the obstacle to control the vehicle to travel within the drivable area includes:

[0028] When the risk level of the obstacle is level one, the vehicle is controlled to maintain the current speed and follow the obstacle within the drivable area;

[0029] When the risk level of the obstacle is level 2, if the current speed of the vehicle is greater than the speed of the obstacle, the vehicle is controlled to decelerate to the speed of the obstacle and follow the obstacle within the drivable area;

[0030] When the risk level of the obstacle is level three, if the vehicle is in motion, the vehicle is controlled to slow down and stop; if the vehicle is not in motion, the vehicle is controlled to be unable to drive and an audible and visual alarm is issued.

[0031] In a second aspect, an embodiment of the present application provides a vehicle control device, the vehicle control device comprising:

[0032] An acquisition module is used to acquire three-dimensional point cloud data through a vehicle-mounted laser radar;

[0033] An extraction module, used to extract drivable areas and obstacles based on 3D point cloud data;

[0034] A calculation module is used to obtain the motion state of the extracted obstacle, the relative motion state between the obstacle and the vehicle, and the vehicle characteristics, and use the risk field strength model to calculate the risk field strength of the obstacle in the drivable area;

[0035] A determination module, used to determine the risk level of the obstacle according to the risk field strength of the obstacle in the drivable area;

[0036] The control module is used to control the vehicle to travel within the drivable area by adopting a control strategy corresponding to the risk level of the obstacle.

[0037] Optionally, the extraction module is used to:

[0038] Divide the 3D point cloud data into grids in the polar coordinate system and determine the height of each grid unit;

[0039] By traversing the grid cells, the slope between the current grid cell and the adjacent grid cells is calculated, and the height difference between the current grid cell and the adjacent grid cells is obtained;

[0040] If the slope is less than the preset slope and the height difference is less than the preset height difference, the adjacent grid cells are taken as the ground to obtain all the ground grid cells;

[0041] All ground grid cells are removed from all grid cells to obtain all left and right wall grid cells, and the projections of all left and right wall grid cells are fitted to obtain left and right boundary lines;

[0042] Project the left and right boundary lines onto the map to obtain the drivable area.

[0043] In the third aspect, an embodiment of the present application provides a vehicle control device, which includes a processor, a memory, and a vehicle control program stored in the memory and executable by the processor, wherein when the vehicle control program is executed by the processor, the steps of the vehicle control method described above are implemented.

[0044] In a fourth aspect, an embodiment of the present application provides a readable storage medium, on which a vehicle control program is stored, wherein when the vehicle control program is executed by a processor, the steps of the vehicle control method as described above are implemented.

[0045] The beneficial effects brought by the technical solution provided by the embodiments of the present application include:

[0046] In the embodiment of the present application, three-dimensional point cloud data is acquired through a vehicle-mounted laser radar; based on the three-dimensional point cloud data, the drivable area and obstacles are extracted; the motion state of the extracted obstacle, the relative motion state between the obstacle and the vehicle, and the vehicle characteristics are acquired, and the risk field strength model is used to calculate the risk field strength of the obstacle in the drivable area; the risk level of the obstacle is determined based on the risk field strength of the obstacle in the drivable area; and a control strategy corresponding to the risk level of the obstacle is used to control the vehicle to travel in the drivable area. The embodiment of the present application calculates the risk field strength of the obstacle in the drivable area after extracting the drivable area and the obstacle, determines the risk level of the obstacle based on the risk field strength, and uses a control strategy corresponding to the risk level of the obstacle to control the vehicle to travel in the drivable area, thereby making the risk assessment of the obstacle more accurate and the control of the vehicle safer. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] Figure 1 This is a flow chart of an embodiment of a vehicle control method of the present application;

[0048] Figure 2 For this application Figure 1 Detailed flow chart of step S20;

[0049] Figure 3 For this application Figure 1 Detailed flow chart of step S30;

[0050] Figure 4 For this application Figure 1 A detailed flow chart of step S50;

[0051] Figure 5 This is a functional module diagram of an embodiment of a vehicle control device of the present application;

[0052] Figure 6 This is a schematic diagram of the hardware structure of the vehicle control device involved in the embodiment of the present application. DETAILED DESCRIPTION

[0053] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0054] The terms "including" and "having" and any variations thereof in the specification and claims of this application and the above-mentioned drawings are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or units is not limited to the listed steps or units, but optionally includes steps or units that are not listed, or optionally includes other steps or units inherent to these processes, methods, products or devices. The terms "first", "second" and "third" are used to distinguish different objects, etc., and do not represent a sequence, nor do they limit "first", "second" and "third" to different types.

[0055] In the description of the embodiments of the present application, "exemplary", "for example" or "for example" are used to indicate examples, illustrations or descriptions. Any embodiment or design described as "exemplary", "for example" or "for example" in the embodiments of the present application should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of words such as "exemplary", "for example" or "for example" is intended to present related concepts in a specific way.

[0056] In the description of the embodiments of the present application, unless otherwise specified, “ / ” means or, for example, A / B can mean A or B; the “and / or” in the text is merely a description of the association relationship of associated objects, indicating that three relationships may exist, for example, A and / or B can mean: A exists alone, A and B exist at the same time, and B exists alone. In addition, in the description of the embodiments of the present application, “multiple” refers to two or more than two.

[0057] In some processes described in the embodiments of the present application, multiple operations or steps that appear in a specific order are included, but it should be understood that these operations or steps may not be executed in the order in which they appear in the embodiments of the present application or in parallel, and the sequence number of the operation is only used to distinguish the different operations, and the sequence number itself does not represent any execution order. In addition, these processes may include more or fewer operations, and these operations or steps may be executed in sequence or in parallel, and these operations or steps may be combined.

[0058] In order to make the objectives, technical solutions and advantages of the present application clearer, the implementation methods of the present application will be further described in detail below with reference to the accompanying drawings.

[0059] In a first aspect, an embodiment of the present application provides a vehicle control method.

[0060] In one embodiment, referring to Figure 1 , Figure 1 This is a flow chart of an embodiment of the vehicle control method of the present application. Figure 1 As shown, the vehicle control method includes:

[0061] Step S10, acquiring three-dimensional point cloud data through a vehicle-mounted laser radar.

[0062] In this embodiment, the environment in the underground mining scene is complex and changeable, with narrow mine caves, up and down ramps, and ultra-high loads, which have a serious impact on the driving safety of the vehicle. First, the road environment is scanned by a laser radar sensor mounted on the vehicle to obtain three-dimensional point cloud data about the road environment. The three-dimensional point cloud data is a data set of spatial points obtained by scanning the laser radar. Each point in the point cloud contains information such as three-dimensional coordinates (XYZ) and laser reflection intensity (Intensity).

[0063] Step S20: extracting drivable areas and obstacles based on the three-dimensional point cloud data.

[0064] In this embodiment, by processing the three-dimensional point cloud data, the drivable area of ​​the road and obstacles are extracted therefrom. The obstacle extraction can use a fusion algorithm to extract information such as the type, location, size, shape and orientation of the obstacle.

[0065] Step S30, obtaining the extracted motion state of the obstacle, the relative motion state between the obstacle and the vehicle, and the vehicle characteristics, and using the risk field strength model to calculate the risk field strength of the obstacle in the drivable area.

[0066] In this embodiment, after the obstacle is extracted, the motion state of the obstacle, the relative motion state between the obstacle and the vehicle, and the vehicle characteristics are further obtained, and the motion state of the obstacle, the relative motion state between the obstacle and the vehicle, and the vehicle characteristics are input into the risk field strength model, and the risk field strength of the obstacle in the drivable area is obtained by calculation.

[0067] Step S40, determining the risk level of the obstacle according to the risk field strength of the obstacle in the drivable area.

[0068] In this embodiment, the risk field strength actually represents the risk of the obstacle. The larger the value of the risk field strength, the greater the risk of the corresponding obstacle. The risk level of the obstacle can be divided into level one, level two and level three according to the size of the risk field strength value. The risk level of the corresponding obstacle is determined according to the value of the risk field strength of the obstacle in the drivable area.

[0069] Step S50: Control the vehicle to travel within the drivable area using a control strategy corresponding to the risk level of the obstacle.

[0070] In this embodiment, according to different risk levels of obstacles, corresponding control strategies should be adopted to control the vehicle to improve the safety of the vehicle in the drivable area.

[0071] In this embodiment, in the underground mining scene, the road environment is first scanned by a lidar sensor mounted on the vehicle to obtain three-dimensional point cloud data about the road environment. After extracting the drivable area and obstacles, the risk field strength of the obstacle in the drivable area is calculated. According to the risk field strength, the risk level of the obstacle is determined, and a control strategy corresponding to the risk level of the obstacle is used to control the vehicle to travel within the drivable area, thereby making the risk assessment of the obstacle more accurate and making the control of the vehicle safer in the absence of lane lines and road markings underground in the mine.

[0072] Further, in one embodiment, referring to Figure 2 , Figure 2 For this application Figure 1 The detailed flow chart of step S20 is as follows: Figure 2 As shown, step S20 includes:

[0073] Step S201, gridding the three-dimensional point cloud data in a polar coordinate system, and determining the height of each grid unit;

[0074] Step S202, by traversing the grid cells, calculating the slope between the current grid cell and the adjacent grid cells, and obtaining the height difference between the current grid cell and the adjacent grid cells;

[0075] Step S203, if the slope is less than the preset slope and the height difference is less than the preset height difference, the adjacent grid cells are taken as the ground to obtain all the ground grid cells;

[0076] Step S204, removing all ground grid cells from all grid cells to obtain all left and right wall grid cells, and fitting the projections of all left and right wall grid cells to obtain left and right boundary lines;

[0077] Step S205: Project the left and right boundary lines onto the map to obtain a drivable area.

[0078] In this embodiment, the three-dimensional point cloud data is grid-divided in the polar coordinate system, and the vehicle is used as the coordinate origin to establish a mapping between the point cloud coordinates and the grid coordinates to determine the height of each grid unit. The grid units can be traversed in sequence according to the order of the vehicle's driving direction. The slope between the current grid unit and the adjacent grid unit is calculated by pairwise comparison, and the height difference between the current grid unit and the adjacent grid unit is calculated by combining the distance between the current grid unit and the adjacent grid unit. If the slope is less than the preset slope and the height difference between the two is less than the preset height difference, it means that the adjacent grid unit is the ground. All ground grid units can be obtained by traversing, and all ground grid units can be removed from all grid units to obtain all left and right wall grid units. The projections of all left and right wall grid units are fitted to obtain left and right boundary lines, and the left and right boundary lines are placed in the SLAM (Simultaneous Localization And Mapping, real-time positioning and map construction) map is projected to obtain the drivable area. In the scenario of underground mining, the wall is actually the mine wall. Since the mine wall is uneven and has many inclinations, it poses a great safety risk to vehicle driving. By removing the ground and using the left and right mine wall projections to determine the left and right boundary lines and the drivable area, the safety of vehicle driving can be greatly improved.

[0079] Further, in one embodiment, determining the height of each grid unit includes:

[0080] The median value of the height of each point in each grid cell is used as the initial height of each grid cell;

[0081] If the initial height of the grid unit is greater than the preset maximum value, the preset maximum value is used as the height of the grid unit, otherwise the initial height of the grid unit is used as the height of the grid unit, and the preset maximum value is the installation height of the laser radar.

[0082] In this embodiment, the grid cell generally includes multiple points, and the median of the heights of each point in each grid cell is used as the initial height of each grid cell to better characterize the height of the grid cell. The range of ground height can be pre-defined [preset minimum value, preset maximum value], the preset minimum value can be set to 0, and the preset maximum value is the installation height of the laser radar. If the initial height of the grid cell is greater than the preset maximum value, that is, the installation height of the laser radar, the installation height of the laser radar is used as the height of the grid cell, otherwise the initial height of the grid cell is used as the height of the grid cell.

[0083] Furthermore, in one embodiment, before calculating the slope between the current grid cell and the adjacent grid cell by traversing the grid cells to obtain the height difference between the current grid cell and the adjacent grid cell, the method further includes:

[0084] If the height information of a grid cell is missing, the median of the heights of the adjacent grid cells is used as its height;

[0085] The height of each grid cell is smoothed using a Gaussian smoothing filter.

[0086] In this embodiment, in order to better expand the ground and improve the accuracy of ground extraction, before identifying the ground grid cells, for the grid cells with missing height information, the median of the heights of adjacent grid cells is used as their height to solve the problem of data loss. A Gaussian smoothing filter is used to smooth the height of each grid cell, that is, the height of each grid cell uses the weighted average of the heights of adjacent grid cells as its height. The height of each grid cell is adjusted to remove noise in data processing.

[0087] Furthermore, in one embodiment, the motion state of the obstacle includes the acceleration of the obstacle, the relative motion state between the obstacle and the vehicle includes the speed difference between the vehicle and the obstacle and the angle between the center of mass of the vehicle and the center of mass of the obstacle, and the vehicle characteristics include the vehicle load. Figure 3 , Figure 3 For this application Figure 1 The detailed flow chart of step S30 is as follows: Figure 3 As shown, step S30 includes:

[0088] Step S301, obtaining the extracted acceleration of the obstacle, the speed difference between the vehicle and the obstacle, the angle between the center of mass of the vehicle and the center of mass of the obstacle, and the vehicle load;

[0089] Step S302: Substitute the acceleration of the obstacle, the speed difference between the vehicle and the obstacle, the angle between the center of mass of the vehicle and the center of mass of the obstacle, and the vehicle load into the risk field strength model to calculate the risk field strength of the obstacle in the drivable area. The risk field strength model is:

[0090]

[0091] Among them, E S,ij Indicates that the i ,y i ) is located at point (x j ,y j ), K is the weight coefficient, M is the vehicle load, and σ is the field strength at point (x j ,y j ) is the Gaussian distribution variance of the field strength at , r ij =(x i -x j ,y i -y j ) means located at (xi ,y i ) and the obstacle i at point (x j ,y j ), μ is the distance between the point (x j ,y j ), Δv is the speed difference between the vehicle and the obstacle, γ is the calibration coefficient, a is the acceleration of the obstacle, and θ is the angle between the center of mass of the vehicle and the center of mass of the obstacle.

[0092] In this embodiment, the input factors for calculating the risk field strength of an obstacle in the drivable area through the risk field strength model include the acceleration of the obstacle, the speed difference between the vehicle and the obstacle, the angle between the center of mass of the vehicle and the center of mass of the obstacle, and the vehicle load, that is, the factors that affect the risk field strength. The equivalent mass (mass, speed) can be used to characterize the driving risk. The larger the equivalent mass, the greater the driving risk.

[0093] Furthermore, in one embodiment, the risk level of the obstacle includes level one, level two and level three. Figure 4 , Figure 4 For this application Figure 1 The detailed flow chart of step S50 is as follows: Figure 4 As shown, step S50 includes:

[0094] Step S501, when the risk level of the obstacle is level one, the vehicle is controlled to maintain the current speed and follow the obstacle in the drivable area;

[0095] Step S502, when the risk level of the obstacle is level 2, if the current speed of the vehicle is greater than the speed of the obstacle, the vehicle is controlled to decelerate to the speed of the obstacle and follow the obstacle within the drivable area;

[0096] Step S503, when the risk level of the obstacle is level three, if the vehicle is in motion, the vehicle is controlled to slow down and stop; if the vehicle is not in motion, the vehicle is controlled to be unable to drive and an audible and visual alarm is issued.

[0097] In this embodiment, the first, second and third levels of the risk level of the obstacle are divided according to the numerical value of the risk field strength of the obstacle in the drivable area obtained by calculation. The obstacle may be a vehicle in front and a mine wall, etc. When the risk level of the obstacle is level one, the risk is relatively small, and the vehicle can be controlled to maintain the current speed and follow the obstacle in the drivable area. When the risk level of the obstacle is level two, the risk is relatively large. If the speed of the vehicle exceeds the speed of the obstacle at this time, it is necessary to control the vehicle to decelerate to the speed of the obstacle and follow the obstacle in the drivable area. When the risk level of the obstacle is level three, the risk is the greatest. At this time, if the vehicle is in motion, it is necessary to control the vehicle to decelerate and stop. If the vehicle is not in motion, the vehicle is controlled not to start and drive, and an audible and visual alarm is issued until the risk of the obstacle is eliminated. The vehicle can start and drive, thereby realizing autonomous obstacle avoidance of the vehicle according to the risk field strength of the obstacle. By calculating the risk field strength of the obstacle in the drivable area and dividing the risk levels of different obstacles, the vehicle is controlled by adopting a corresponding strategy, the risk caused by the obstacle to the vehicle driving is accurately evaluated, and the safety of vehicle driving is improved by adopting a targeted control strategy.

[0098] In a second aspect, an embodiment of the present application also provides a vehicle control device.

[0099] In one embodiment, referring to Figure 5 , Figure 5 This is a functional module diagram of an embodiment of a vehicle control device of the present application, such as Figure 5 As shown, the vehicle control device includes:

[0100] An acquisition module 10 is used to acquire three-dimensional point cloud data through a vehicle-mounted laser radar;

[0101] An extraction module 20, for extracting drivable areas and obstacles based on the three-dimensional point cloud data;

[0102] The calculation module 30 is used to obtain the motion state of the extracted obstacle, the relative motion state between the obstacle and the vehicle, and the vehicle characteristics, and use the risk field strength model to calculate the risk field strength of the obstacle in the drivable area;

[0103] A determination module 40, for determining a risk level of an obstacle according to a risk field strength of the obstacle in a drivable area;

[0104] The control module 50 is used to control the vehicle to travel within the drivable area by adopting a control strategy corresponding to the risk level of the obstacle.

[0105] Furthermore, in one embodiment, the extraction module 20 includes:

[0106] Determine the unit, which is used to grid the three-dimensional point cloud data in the polar coordinate system and determine the height of each grid unit;

[0107] A traversal unit is used to calculate the slope between the current grid cell and the adjacent grid cell by traversing the grid cells, and obtain the height difference between the current grid cell and the adjacent grid cell;

[0108] A comparison unit, used for taking the adjacent grid cells as the ground if the slope is less than a preset slope and the height difference is less than a preset height difference, to obtain all ground grid cells;

[0109] A fitting unit is used to remove all ground grid cells from all grid cells to obtain all left and right wall grid cells, and fit the projections of all left and right wall grid cells to obtain left and right boundary lines;

[0110] The projection unit is used to project the left and right boundary lines onto the map to obtain a drivable area.

[0111] Furthermore, in one embodiment, the determining unit is configured to:

[0112] The median value of the height of each point in each grid cell is used as the initial height of each grid cell;

[0113] If the initial height of the grid unit is greater than the preset maximum value, the preset maximum value is used as the height of the grid unit, otherwise the initial height of the grid unit is used as the height of the grid unit, and the preset maximum value is the installation height of the laser radar.

[0114] Furthermore, in one embodiment, the vehicle control device further includes a smoothing module, which is used to:

[0115] If the height information of a grid cell is missing, the median of the heights of the adjacent grid cells is used as its height;

[0116] The height of each grid cell is smoothed using a Gaussian smoothing filter.

[0117] Further, in one embodiment, the motion state of the obstacle includes the acceleration of the obstacle, the relative motion state between the obstacle and the vehicle includes the speed difference between the vehicle and the obstacle and the angle between the center of mass of the vehicle and the center of mass of the obstacle, and the vehicle characteristics include the vehicle load. The calculation module 30 is used to:

[0118] Obtain the acceleration of the extracted obstacle, the speed difference between the vehicle and the obstacle, the angle between the center of mass of the vehicle and the center of mass of the obstacle, and the vehicle load;

[0119] The acceleration of the obstacle, the speed difference between the vehicle and the obstacle, the angle between the center of mass of the vehicle and the center of mass of the obstacle, and the vehicle load are substituted into the risk field strength model to calculate the risk field strength of the obstacle in the drivable area. The risk field strength model is:

[0120]

[0121] Among them, E S,ij Indicates that the i ,y i ) is located at point (x j ,y j ), K is the weight coefficient, M is the vehicle load, and σ is the field strength at point (x j ,y j ) is the Gaussian distribution variance of the field strength at , r ij =(x i -x j ,y i -y j ) means located at (x i ,y i ) and the obstacle i at point (x j ,y j ), μ is the distance between the point (x j ,y j ), Δv is the speed difference between the vehicle and the obstacle, γ is the calibration coefficient, a is the acceleration of the obstacle, and θ is the angle between the center of mass of the vehicle and the center of mass of the obstacle.

[0122] Furthermore, in one embodiment, the risk level of the obstacle includes level one, level two and level three, and the control module 50 is used to:

[0123] When the risk level of the obstacle is level one, the vehicle is controlled to maintain the current speed and follow the obstacle within the drivable area;

[0124] When the risk level of the obstacle is level 2, if the current speed of the vehicle is greater than the speed of the obstacle, the vehicle is controlled to decelerate to the speed of the obstacle and follow the obstacle within the drivable area;

[0125] When the risk level of the obstacle is level three, if the vehicle is in motion, the vehicle is controlled to slow down and stop; if the vehicle is not in motion, the vehicle is controlled to be unable to drive and an audible and visual alarm is issued.

[0126] Among them, the functional implementation of each module in the above-mentioned vehicle control device corresponds to the various steps in the above-mentioned vehicle control method embodiment, and its functions and implementation processes will not be repeated here one by one.

[0127] In a third aspect, an embodiment of the present application provides a vehicle control device.

[0128] Reference Figure 6 , Figure 6 Schematic diagram of the hardware structure of the vehicle control device involved in the embodiment of the present application. In the embodiment of the present application, the vehicle control device may include a processor, a memory, a communication interface and a communication bus.

[0129] The communication bus may be of any type and is used to interconnect the processor, the memory, and the communication interface.

[0130] The communication interface includes input / output (I / O) interfaces, physical interfaces, and logical interfaces, which are used to interconnect the devices inside the vehicle control device, and interfaces used to interconnect the vehicle control device with other devices (such as other computing devices or user devices). The physical interface can be an Ethernet interface, a fiber optic interface, an ATM interface, etc.; the user device can be a display, a keyboard, etc.

[0131] The memory can be various types of storage media, such as random access memory (RAM), read-only memory (ROM), non-volatile RAM (NVRAM), flash memory, optical storage, hard disk, programmable ROM (PROM), erasable PROM (EPROM), electrically erasable PROM (EEPROM), etc.

[0132] The processor may be a general-purpose processor, which may call the vehicle control program stored in the memory and execute the vehicle control method provided in the embodiment of the present application. For example, the general-purpose processor may be a central processing unit (CPU). The method executed when the vehicle control program is called may refer to the various embodiments of the vehicle control method of the present application, which will not be described in detail here.

[0133] Those skilled in the art will understand that Figure 6 The hardware structure shown in the figure does not constitute a limitation on the present application, and may include more or less components than shown in the figure, or combine certain components, or arrange the components differently.

[0134] In a fourth aspect, an embodiment of the present application also provides a readable storage medium.

[0135] A vehicle control program is stored on the readable storage medium of the present application, wherein when the vehicle control program is executed by the processor, the steps of the vehicle control method as described above are implemented.

[0136] Among them, the method implemented when the vehicle control program is executed can refer to the various embodiments of the vehicle control method of the present application, and will not be repeated here.

[0137] It should be noted that the serial numbers of the above-mentioned embodiments of the present application are only for description and do not represent the advantages or disadvantages of the embodiments.

[0138] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present application is essentially or the part that contributes to the prior art can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, disk, CD) as described above, and includes a number of instructions for a terminal device to execute the methods described in each embodiment of the present application.

[0139] The above are only preferred embodiments of the present application, and are not intended to limit the patent scope of the present application. Any equivalent structure or equivalent process transformation made using the contents of the present application specification and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present application.

Claims

1. A vehicle control method, characterized in that: The vehicle control method comprises: Acquire 3D point cloud data through vehicle-mounted laser radar; Extract drivable areas and obstacles based on 3D point cloud data; Obtain the motion state of the extracted obstacle, the relative motion state between the obstacle and the vehicle, and the vehicle characteristics, and use the risk field strength model to calculate the risk field strength of the obstacle in the drivable area; Determine the risk level of the obstacle based on the risk field strength of the obstacle in the drivable area; A control strategy corresponding to the risk level of the obstacle is used to control the vehicle to travel within the drivable area; The motion state of the obstacle includes the acceleration of the obstacle, the relative motion state between the obstacle and the vehicle includes the speed difference between the vehicle and the obstacle and the angle between the center of mass of the vehicle and the center of mass of the obstacle, the vehicle characteristics include the vehicle load, and the motion state of the obstacle, the relative motion state between the obstacle and the vehicle, and the vehicle characteristics are obtained and extracted, and the risk field strength of the obstacle in the drivable area is calculated using the risk field strength model, including: Obtain the acceleration of the extracted obstacle, the speed difference between the vehicle and the obstacle, the angle between the center of mass of the vehicle and the center of mass of the obstacle, and the vehicle load; The acceleration of the obstacle, the speed difference between the vehicle and the obstacle, the angle between the center of mass of the vehicle and the center of mass of the obstacle, and the vehicle load are substituted into the risk field strength model to calculate the risk field strength of the obstacle in the drivable area. The risk field strength model is: Among them, E S,ij Indicates that the i ,y i ) is located at point (x j ,y j ), K is the weight coefficient, M is the vehicle load, and σ is the field strength at point (x j ,y j ) is the Gaussian distribution variance of the field strength at , r ij =(x i -x j ,y i -y j ) means located at (x i ,y i ) and the obstacle i at point (x j ,y j ), μ is the distance between the point (x j ,y j ), Δv is the speed difference between the vehicle and the obstacle, γ is the calibration coefficient, a is the acceleration of the obstacle, and θ is the angle between the center of mass of the vehicle and the center of mass of the obstacle.

2. The vehicle control method according to claim 1, characterized in that: The extracting of the drivable area based on the three-dimensional point cloud data includes: Divide the 3D point cloud data into grids in the polar coordinate system and determine the height of each grid unit; By traversing the grid cells, the slope between the current grid cell and the adjacent grid cells is calculated, and the height difference between the current grid cell and the adjacent grid cells is obtained; If the slope is less than the preset slope and the height difference is less than the preset height difference, the adjacent grid cells are taken as the ground to obtain all the ground grid cells; All ground grid cells are removed from all grid cells to obtain all left and right wall grid cells, and the projections of all left and right wall grid cells are fitted to obtain left and right boundary lines; Project the left and right boundary lines onto the map to obtain the drivable area.

3. The vehicle control method according to claim 2, characterized in that: Determining the height of each grid cell includes: The median value of the height of each point in each grid cell is used as the initial height of each grid cell; If the initial height of the grid unit is greater than the preset maximum value, the preset maximum value is used as the height of the grid unit, otherwise the initial height of the grid unit is used as the height of the grid unit, and the preset maximum value is the installation height of the laser radar.

4. The vehicle control method according to claim 2, characterized in that: Before calculating the slope between the current grid cell and the adjacent grid cell by traversing the grid cells and obtaining the height difference between the current grid cell and the adjacent grid cell, the method includes: If the height information of a grid cell is missing, the median of the heights of the adjacent grid cells is used as its height; The height of each grid cell is smoothed using a Gaussian smoothing filter.

5. The vehicle control method according to claim 1, characterized in that: The risk levels of the obstacles include level one, level two and level three. The control strategy corresponding to the risk level of the obstacles is used to control the vehicle to travel within the drivable area, including: When the risk level of the obstacle is level one, the vehicle is controlled to maintain the current speed and follow the obstacle within the drivable area; When the risk level of the obstacle is level 2, if the current speed of the vehicle is greater than the speed of the obstacle, the vehicle is controlled to decelerate to the speed of the obstacle and follow the obstacle within the drivable area; When the risk level of the obstacle is level three, if the vehicle is in motion, the vehicle is controlled to slow down and stop; if the vehicle is not in motion, the vehicle is controlled to be unable to drive and an audible and visual alarm is issued.

6. A vehicle control device, characterized in that: The vehicle control device comprises: An acquisition module is used to acquire three-dimensional point cloud data through a vehicle-mounted laser radar; An extraction module, used to extract drivable areas and obstacles based on 3D point cloud data; A calculation module is used to obtain the motion state of the extracted obstacle, the relative motion state between the obstacle and the vehicle, and the vehicle characteristics, and use the risk field strength model to calculate the risk field strength of the obstacle in the drivable area; A determination module, used to determine the risk level of the obstacle according to the risk field strength of the obstacle in the drivable area; A control module, used to control the vehicle to travel within a drivable area using a control strategy corresponding to the risk level of the obstacle; The motion state of the obstacle includes the acceleration of the obstacle, the relative motion state between the obstacle and the vehicle includes the speed difference between the vehicle and the obstacle and the angle between the center of mass of the vehicle and the center of mass of the obstacle, and the vehicle characteristics include the vehicle load. The calculation module is used for: Obtain the acceleration of the extracted obstacle, the speed difference between the vehicle and the obstacle, the angle between the center of mass of the vehicle and the center of mass of the obstacle, and the vehicle load; The acceleration of the obstacle, the speed difference between the vehicle and the obstacle, the angle between the center of mass of the vehicle and the center of mass of the obstacle, and the vehicle load are substituted into the risk field strength model to calculate the risk field strength of the obstacle in the drivable area. The risk field strength model is: Among them, E S,ij Indicates that the i ,y i ) is located at point (x j ,y j ), K is the weight coefficient, M is the vehicle load, and σ is the field strength at point (x j ,y j ) is the Gaussian distribution variance of the field strength at , r ij =(x i -x j ,y i -y j ) means located at (x i ,y i ) and the obstacle i at point (x j ,y j ), μ is the distance between the point (x j ,y j ), Δv is the speed difference between the vehicle and the obstacle, γ is the calibration coefficient, a is the acceleration of the obstacle, and θ is the angle between the center of mass of the vehicle and the center of mass of the obstacle.

7. The vehicle control device according to claim 6, characterized in that: The extraction module is used to: Divide the 3D point cloud data into grids in the polar coordinate system and determine the height of each grid unit; By traversing the grid cells, the slope between the current grid cell and the adjacent grid cells is calculated, and the height difference between the current grid cell and the adjacent grid cells is obtained; If the slope is less than the preset slope and the height difference is less than the preset height difference, the adjacent grid cells are taken as the ground to obtain all the ground grid cells; All ground grid cells are removed from all grid cells to obtain all left and right wall grid cells, and the projections of all left and right wall grid cells are fitted to obtain left and right boundary lines; Project the left and right boundary lines onto the map to obtain the drivable area.

8. A vehicle control device, characterized in that: The vehicle control device includes a processor, a memory, and a vehicle control program stored in the memory and executable by the processor, wherein when the vehicle control program is executed by the processor, the steps of the vehicle control method as described in any one of claims 1 to 5 are implemented.

9. A readable storage medium, characterized in that: The readable storage medium stores a vehicle control program, wherein when the vehicle control program is executed by a processor, the steps of the vehicle control method according to any one of claims 1 to 5 are implemented.

Images