Automatic driving method, device and storage medium

Abstract

The present application relates to an automatic driving method, device and storage medium, the method comprising: obtaining data collected by sensors, the data including point cloud data in front of the vehicle and acceleration data of the vehicle in a direction perpendicular to the road surface; determining a characteristic value based on the point cloud data, the characteristic value being used to indicate the degree of undulation of the road surface in front of the vehicle; and determining the automatic driving strategy of the vehicle based at least on the acceleration data and / or the characteristic value. According to the embodiments of the present application, the current uneven road surface can be accurately identified, the impact of unexpected steering caused by the uneven road surface on the precise control of the vehicle can be reduced, and the safety and comfort of the vehicle during the automatic driving process can be improved. At the same time, the structural damage caused by vibration to the vehicle, the sensors on the vehicle, etc. can be reduced, thereby improving its reliability and life durability.

Description

Technical Field

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

[0002] With the development of autonomous driving technology, vehicles not only need to achieve autonomous driving on flat roads, but also need to deal with uneven road conditions such as potholes, damaged roads, and roads with speed bumps.

[0003] At present, relevant technologies focus on dealing with obstacles on the road, such as pedestrians and traffic lights. As for uneven road conditions, the vehicle usually relies on the delayed relief of the vehicle's own suspension system after the vehicle vibrates, resulting in low vehicle safety and comfort. Summary of the invention

[0004] In view of this, an automatic driving method, device and storage medium are proposed.

[0005] In a first aspect, an embodiment of the present application provides an autonomous driving method, the method comprising: acquiring data collected by a sensor, the data comprising point cloud data in front of a vehicle and acceleration data of the vehicle in a direction perpendicular to the road surface; determining a characteristic value based on the point cloud data, the characteristic value being used to indicate the degree of undulation of the road surface in front of the vehicle; and determining an autonomous driving strategy for the vehicle based at least on the acceleration data and / or the characteristic value.

[0006] According to the embodiments of the present application, by acquiring the data in front of the vehicle collected by the sensor and determining the characteristic value based on the point cloud data, the current uneven road condition can be accurately identified. By determining the automatic driving strategy of the vehicle based on the acceleration data of the vehicle in the direction perpendicular to the road surface and / or the characteristic value, the impact of unexpected steering caused by uneven road surface on the precise control of the vehicle can be reduced, and the safety and comfort of the vehicle during the automatic driving process can be improved. At the same time, the structural damage caused by vibration to the vehicle, sensors on the vehicle, etc. can be reduced, thereby improving its reliability and life durability.

[0007] According to the first aspect, in a first possible implementation of the autonomous driving method, the feature value is determined based on the coordinate value of the point cloud data in a direction perpendicular to the road surface.

[0008] The coordinate value of the point cloud data in the direction perpendicular to the road surface can reflect the undulation of the road surface. According to the embodiment of the present application, the characteristic value can better measure the unevenness of the road surface.

[0009] According to the first aspect, in a second possible implementation of the autonomous driving method, determining a characteristic value based on the point cloud data includes: determining at least one of a first characteristic value, a second characteristic value and a third characteristic value based on the point cloud data, the first characteristic value being used to indicate the degree of undulation of a local area in each lane in the road surface in front of the vehicle, the second characteristic value being used to indicate the degree of undulation of a road surface in each lane in the road surface in front of the vehicle, and the third characteristic value being used to indicate the degree of undulation of a road surface in all lanes in the road surface in front of the vehicle.

[0010] According to an embodiment of the present application, by determining at least one of the first eigenvalue, the second eigenvalue and the third eigenvalue, and the first eigenvalue, the second eigenvalue and the third eigenvalue respectively indicate the degree of undulation of the road surface from three perspectives: point, line and surface. The unevenness of the road surface can be more accurately and comprehensively reflected, thereby providing a targeted basis for the subsequent determination of the autonomous driving strategy.

[0011] According to the second possible implementation manner of the first aspect, in a third possible implementation manner of the autonomous driving method, the autonomous driving strategy of the vehicle is determined at least based on the acceleration data and / or the eigenvalue, including: determining, based on the second eigenvalue, a target lane corresponding to the smallest second eigenvalue; and determining a strategy for the vehicle to switch to the target lane.

[0012] According to an embodiment of the present application, by determining the target lane corresponding to the smallest second eigenvalue based on the second eigenvalue, and determining the strategy for the vehicle to switch to the target lane, the vehicle can avoid lanes with large undulations to avoid uneven road surfaces, thereby improving the safety and comfort of the vehicle and reducing related structural damage.

[0013] According to the second or third possible implementation manner of the first aspect, in a fourth possible implementation manner of the autonomous driving method, the autonomous driving strategy of the vehicle is determined at least based on the acceleration data and / or the eigenvalue, including: determining, based on the first eigenvalue, a target local area corresponding to the first eigenvalue exceeding a threshold; and determining a strategy for the vehicle to avoid the target local area.

[0014] According to an embodiment of the present application, by determining, based on the first eigenvalue, a target local area corresponding to a first eigenvalue exceeding a threshold value, and determining a basis for a vehicle target avoidance local strategy, the vehicle can bypass local uneven road surfaces such as potholes in the lane to avoid uneven road surfaces, thereby improving the safety and comfort of the vehicle and reducing related structural damage.

[0015] According to the second or third or fourth possible implementation manner of the first aspect, in a fifth possible implementation manner of the autonomous driving method, the autonomous driving strategy of the vehicle is determined at least based on the acceleration data and / or the eigenvalue, including: determining a strategy for limiting the vehicle's driving speed based on at least one of the first eigenvalue, the second eigenvalue, and the third eigenvalue, wherein an upper limit value of the vehicle's limited driving speed is negatively correlated with a maximum value of at least one of the first eigenvalue, the second eigenvalue, and the third eigenvalue.

[0016] According to an embodiment of the present application, by determining a strategy for limiting the vehicle's driving speed based on at least one of the first eigenvalue, the second eigenvalue, and the third eigenvalue, it is possible to achieve early deceleration of the vehicle before encountering an uneven road. By making the upper limit value of the vehicle's limited driving speed negatively correlated with the maximum value of at least one of the first eigenvalue, the second eigenvalue, and the third eigenvalue when determining the strategy for limiting the vehicle's driving speed, it is possible to achieve that when the greater the degree of road undulation, the smaller the upper limit value of the vehicle's speed limit is, thereby further reducing the vibration amplitude of the vehicle, improving the safety and comfort of the vehicle, and reducing related structural damage.

[0017] According to the first aspect or the first or second or third or fourth or fifth possible implementation of the first aspect, in a sixth possible implementation of the autonomous driving method, the autonomous driving strategy of the vehicle is determined at least based on the acceleration data and / or the characteristic value, including: when the characteristic value exceeds a threshold value, or the rate of change of the acceleration data exceeds a threshold value, determining a strategy for adjusting parameters of the active suspension of the vehicle.

[0018] According to an embodiment of the present application, by determining a strategy for indicating adjustment of the parameters of the vehicle's active suspension when a characteristic value exceeds a threshold, or the rate of change of acceleration data exceeds a threshold, it is possible to adjust the parameters of the active suspension in advance before the vehicle passes over an uneven road, thereby reducing the vibration amplitude of the vehicle when passing over an uneven road, improving the safety and comfort of the vehicle, and reducing related structural damage.

[0019] According to the first aspect, in a seventh possible implementation of the autonomous driving method, determining a characteristic value based on the point cloud data includes: when the rate of change of the acceleration data exceeds a predetermined threshold, adjusting the determined characteristic value to obtain an adjusted characteristic value, wherein the adjusted characteristic value is greater than the characteristic value before adjustment.

[0020] According to an embodiment of the present application, by adjusting the determined characteristic value when the rate of change of the acceleration data exceeds a threshold value, the adjusted characteristic value can more realistically reflect the current uneven road condition, so that a more accurate autonomous driving strategy can be generated based on the adjusted characteristic value, thereby further improving the safety and comfort of the vehicle during the autonomous driving process and reducing related structural damage.

[0021] According to the first aspect or the first or second or third or fourth or fifth or sixth or seventh possible implementation of the first aspect, in an eighth possible implementation of the autonomous driving method, determining a characteristic value based on the point cloud data includes: dividing an area of ​​interest in the road surface in front of the vehicle into grids; deleting point cloud data corresponding to obstacles in the point cloud data within the area of ​​interest to obtain processed point cloud data; and determining the characteristic value based on at least one of the processed point cloud data in the grids.

[0022] According to an embodiment of the present application, by dividing the area of ​​interest in the road surface in front of the vehicle into grids and deleting the point cloud data corresponding to obstacles in the point cloud data in the area of ​​interest, the influence of obstacles such as other vehicles and pedestrians on the judgment of the unevenness of the road surface can be reduced. By determining the eigenvalue based on the processed point cloud data in at least one of the grids, the eigenvalue can more accurately reflect the unevenness of the road surface, thereby better assisting in generating relevant autonomous driving strategies.

[0023] According to the eighth possible implementation manner of the first aspect, in a ninth possible implementation manner of the autonomous driving method, determining characteristic values ​​based on the point cloud data includes: determining characteristic values ​​of a local area corresponding to one or a group of grid data in any lane based on coordinate values ​​of the point cloud data in a direction perpendicular to the road surface, to obtain the first characteristic value; and / or determining characteristic values ​​corresponding to any lane based on coordinate values ​​of the point cloud data in one or more columns of grids in the direction of any lane in a direction perpendicular to the road surface, to obtain the second characteristic value; and / or determining the third characteristic value based on coordinate values ​​of the point cloud data in all grids in a direction perpendicular to the road surface.

[0024] According to an embodiment of the present application, by determining the first eigenvalue, the second eigenvalue, and the third eigenvalue based on the coordinate values ​​of the point cloud data in the relevant grid in the direction perpendicular to the road surface, the unevenness of the road surface can be measured more accurately from the perspective of points, lines, and surfaces.

[0025] According to the first aspect or the first or second or third or fourth or fifth or sixth or seventh or eighth or ninth possible implementation of the first aspect, in the tenth possible implementation of the autonomous driving method, the characteristic value is determined based on one or more of the z value of the highest point, the z value of the lowest point, the z value difference between the highest point and the lowest point, the average value of the z value, and the variance of the z value in the processed point cloud data, and the z value represents the coordinate value of the point cloud data in a direction perpendicular to the road surface.

[0026] According to the embodiments of the present application, it is possible to flexibly select a method for determining characteristic values ​​according to needs, so that the degree of road undulation indicated by the characteristic values ​​can be more consistent with the actual situation of the vehicle during automatic driving.

[0027] According to the first aspect or the first or second or third or fourth or fifth or sixth or seventh or eighth or ninth or tenth possible implementation of the first aspect, in an eleventh possible implementation of the autonomous driving method, the method further includes: generating prompt information on the undulation of the road surface in front of the vehicle and / or the autonomous driving strategy of the vehicle based on the strategy, the prompt information including at least one of text, image, audio and video.

[0028] According to the embodiment of the present application, by generating prompt information, the driver and passengers can timely understand the current road conditions and the relevant strategies adopted by the vehicle, thereby improving the driver and passengers' sense of trust.

[0029] In a second aspect, an embodiment of the present application provides an autonomous driving device, comprising: an acquisition module for acquiring data collected by a sensor, the data comprising point cloud data in front of a vehicle and acceleration data of the vehicle in a direction perpendicular to the road surface; a first determination module for determining a characteristic value based on the point cloud data, the characteristic value being used to indicate the degree of undulation of the road surface in front of the vehicle; and a second determination module for determining an autonomous driving strategy for the vehicle based at least on the acceleration data and / or the characteristic value.

[0030] According to the second aspect, in a first possible implementation of the automatic driving device, the characteristic value is determined according to the coordinate value of the point cloud data in a direction perpendicular to the road surface.

[0031] According to the second aspect, in a second possible implementation of the automatic driving device, determining a eigenvalue based on the point cloud data includes: determining at least one of a first eigenvalue, a second eigenvalue and a third eigenvalue based on the point cloud data, the first eigenvalue being used to indicate the degree of undulation of a local area in each lane in the road surface in front of the vehicle, the second eigenvalue being used to indicate the degree of undulation of a road surface in each lane in the road surface in front of the vehicle, and the third eigenvalue being used to indicate the degree of undulation of a road surface in all lanes in the road surface in front of the vehicle.

[0032] According to a second possible implementation manner of the second aspect, in a third possible implementation manner of the autonomous driving device, the autonomous driving strategy of the vehicle is determined at least based on the acceleration data and / or the eigenvalue, including: determining a target lane corresponding to the smallest second eigenvalue based on the second eigenvalue; and determining a strategy for the vehicle to switch to the target lane.

[0033] According to the second or third possible implementation manner of the second aspect, in a fourth possible implementation manner of the autonomous driving device, the autonomous driving strategy of the vehicle is determined at least based on the acceleration data and / or the eigenvalue, including: determining, based on the first eigenvalue, a target local area corresponding to the first eigenvalue exceeding a threshold; and determining a strategy for the vehicle to avoid the target local area.

[0034] According to the second or third or fourth possible implementation manner of the second aspect, in a fifth possible implementation manner of the autonomous driving device, the autonomous driving strategy of the vehicle is determined at least based on the acceleration data and / or the eigenvalue, including: determining a strategy for limiting the vehicle's driving speed based on at least one of the first eigenvalue, the second eigenvalue, and the third eigenvalue, wherein the upper limit value of the vehicle's limited driving speed is negatively correlated with the maximum value of at least one of the first eigenvalue, the second eigenvalue, and the third eigenvalue.

[0035] According to the second aspect or the first or second or third or fourth or fifth possible implementation of the second aspect, in a sixth possible implementation of the autonomous driving device, the autonomous driving strategy of the vehicle is determined at least based on the acceleration data and / or the characteristic value, including: when the characteristic value exceeds a threshold value, or the rate of change of the acceleration data exceeds a threshold value, determining a strategy for adjusting parameters of the active suspension of the vehicle.

[0036] According to the second aspect, in a seventh possible implementation of the autonomous driving device, determining a characteristic value based on the point cloud data includes: when the rate of change of the acceleration data exceeds a predetermined threshold, adjusting the determined characteristic value to obtain an adjusted characteristic value, wherein the adjusted characteristic value is greater than the characteristic value before adjustment.

[0037] According to the second aspect or the first or second or third or fourth or fifth or sixth or seventh possible implementation manner of the second aspect, in an eighth possible implementation manner of the automatic driving device, determining a characteristic value based on the point cloud data includes: dividing an area of ​​interest in the road surface in front of the vehicle into grids; deleting point cloud data corresponding to obstacles in the point cloud data within the area of ​​interest to obtain processed point cloud data; and determining the characteristic value based on at least one of the processed point cloud data in the grids.

[0038] According to the eighth possible implementation manner of the second aspect, in a ninth possible implementation manner of the automatic driving device, determining characteristic values ​​according to the point cloud data includes: determining characteristic values ​​of a local area corresponding to one or a group of grid data in any lane according to the coordinate values ​​of the point cloud data in a direction perpendicular to the road surface, to obtain the first characteristic value; and / or determining the characteristic value corresponding to any lane according to the coordinate values ​​of the point cloud data in one or more columns of grids in the direction of any lane in a direction perpendicular to the road surface, to obtain the second characteristic value; and / or determining the third characteristic value according to the coordinate values ​​of the point cloud data in all grids in a direction perpendicular to the road surface.

[0039] According to the second aspect or the first or second or third or fourth or fifth or sixth or seventh or eighth or ninth possible implementation of the second aspect, in the tenth possible implementation of the automatic driving device, the characteristic value is determined based on one or more of the z value of the highest point, the z value of the lowest point, the z value difference between the highest point and the lowest point, the average value of the z value, and the variance of the z value in the processed point cloud data, and the z value represents the coordinate value of the point cloud data in a direction perpendicular to the road surface.

[0040] According to the second aspect or the first or second or third or fourth or fifth or sixth or seventh or eighth or ninth or tenth possible implementation of the second aspect, in an eleventh possible implementation of the automatic driving device, the device also includes: a generation module, used to generate prompt information on the undulation of the road surface in front of the vehicle and / or the automatic driving strategy of the vehicle according to the strategy, and the prompt information includes at least one of text, image, audio and video.

[0041] In a third aspect, an embodiment of the present application provides a simulated autonomous driving device, comprising: a processor; a memory for storing processor executable instructions; wherein the processor is configured to implement the above-mentioned first aspect or one or more of the multiple possible implementation methods of the first aspect when executing the instructions.

[0042] In a fourth aspect, an embodiment of the present application provides a non-volatile computer-readable storage medium having computer program instructions stored thereon, which, when executed by a processor, implement the above-mentioned first aspect or one or more of the multiple possible implementation methods of the first aspect.

[0043] In a fifth aspect, an embodiment of the present application provides a terminal device that can execute one or more of the autonomous driving methods of the above-mentioned first aspect or multiple possible implementation methods of the first aspect.

[0044] In the sixth aspect, an embodiment of the present application provides a computer program product, including a computer-readable code, or a non-volatile computer-readable storage medium carrying a computer-readable code. When the computer-readable code is running in an electronic device, the processor in the electronic device executes the above-mentioned first aspect or one or more of the multiple possible implementation methods of the first aspect.

[0045] These and other aspects of the present application will become more apparent from the following description of the embodiment(s). BRIEF DESCRIPTION OF THE DRAWINGS

[0046] The accompanying drawings, which are incorporated in and constitute a part of the specification, illustrate exemplary embodiments, features, and aspects of the present application and, together with the description, serve to explain the principles of the present application.

[0047] Figure 1 A schematic diagram showing an application scenario according to an embodiment of the present application.

[0048] Figure 2 A schematic diagram of the architecture of an automatic driving device according to an embodiment of the present application is shown.

[0049] Figure 3 A flow chart of an autonomous driving method according to an embodiment of the present application is shown.

[0050] Figure 4 A schematic diagram of determining point, line, and surface features according to an embodiment of the present application is shown.

[0051] Figure 5 A schematic diagram of determining an autonomous driving strategy according to an embodiment of the present application is shown.

[0052] Figure 6A schematic diagram showing a visual icon prompt on a human-machine interface HMI according to an embodiment of the present application is shown.

[0053] Figure 7 A flow chart of an autonomous driving method according to an embodiment of the present application is shown.

[0054] Figure 8 A flow chart of an autonomous driving method according to an embodiment of the present application is shown.

[0055] Fig. 9 A flow chart of an autonomous driving method according to an embodiment of the present application is shown.

[0056] Fig.10 A flow chart of an autonomous driving method according to an embodiment of the present application is shown.

[0057] Fig.11 A structural diagram of an automatic driving device according to an embodiment of the present application is shown.

[0058] Fig.12 A structural diagram of an automatic driving device according to an embodiment of the present application is shown. DETAILED DESCRIPTION

[0059] Various exemplary embodiments, features and aspects of the present application will be described in detail below with reference to the accompanying drawings. The same reference numerals in the accompanying drawings represent elements with the same or similar functions. Although various aspects of the embodiments are shown in the accompanying drawings, the drawings are not necessarily drawn to scale unless otherwise specified.

[0060] The word “exemplary” is used exclusively herein to mean “serving as an example, example, or illustration.” Any embodiment described herein as “exemplary” is not necessarily to be construed as preferred or advantageous over other embodiments.

[0061] In addition, in order to better illustrate the present application, numerous specific details are given in the following specific embodiments. It should be understood by those skilled in the art that the present application can also be implemented without certain specific details. In some examples, methods, means, components and circuits well known to those skilled in the art are not described in detail in order to highlight the subject matter of the present application.

[0062] Figure 1 A schematic diagram of an application scenario according to an embodiment of the present application is shown. The method of an embodiment of the present application can be used in a process in which a vehicle performs automatic driving on a road, wherein the vehicle may encounter an uneven road surface when driving, such as Figure 1As shown, uneven road conditions may include roads with raised manhole covers, roads with speed bumps, and roads with potholes. In one possible implementation, in the above scenario, the autonomous driving method of the embodiment of the present application can use sensors to detect the characteristics of uneven road surfaces, generate relevant strategies from three angles: lateral, longitudinal, and vertical, and implement autonomous driving of the vehicle according to the relevant strategies to enable the vehicle to pass through uneven roads, thereby reducing or avoiding the impact of uneven road conditions on the vehicle, so as to improve the safety and comfort of the vehicle during the autonomous driving process, while reducing structural fatigue damage to sensors and vehicles, and improving their reliability and stability.

[0063] It should be noted that Figure 1 The uneven road surface shown in is only an example. The uneven road surface may also include other conditions such as uneven road surface, damaged road surface, gravel road, joint road surface, etc. The autonomous driving method of the embodiment of the present application may also be used in other scenarios.

[0064] Figure 2 FIG. 1 is a schematic diagram showing the architecture of an automatic driving device according to an embodiment of the present application. Figure 2 As shown, the automatic driving device may include a vehicle, and the vehicle may be a vehicle with a wireless communication function, wherein the wireless communication function may be provided in a vehicle-mounted terminal, a vehicle-mounted module, a vehicle-mounted unit, a chip (system) or other parts or components of the vehicle. The vehicle in the embodiment of the present application may be in an automatic driving state, that is, the vehicle is fully autonomously driven without the need for driver control or with only a small amount of driver control.

[0065] The vehicle may be provided with at least one sensor, such as an on-board radar (such as millimeter-wave radar, lidar, ultrasonic radar, etc.), a rain sensor, a camera, a vehicle posture sensor (such as a gyroscope), an inertial measurement unit (IMU), a global navigation satellite system (GNSS), etc. The vehicle may also be provided with other sensors. The above sensors may be provided on one vehicle or on multiple vehicles. Through the at least one sensor provided on the vehicle, point cloud data of the road surface and vertical acceleration of the vehicle (i.e., acceleration data of the vehicle in a direction perpendicular to the road surface) and other data may be collected.

[0066] The vehicle may also be provided with an automatic driving system, which can be used to generate an automatic driving strategy for dealing with uneven road conditions based on data collected by sensors, and realize automatic driving of the vehicle based on the generated strategy, so as to enable the vehicle to pass through uneven roads.

[0067] A human machine interface (HMI) can also be set up on the vehicle. The HMI can be used to broadcast the current road conditions and the strategies adopted by the autonomous driving system for the vehicle through visual icons and voice broadcasts to remind relevant drivers and passengers.

[0068] In a possible implementation, the automatic driving device of the present application may also include a server, which may be located on the above-mentioned vehicle as an on-board computing unit, or may be located in the cloud, may be a physical device, or may be a virtual device such as a virtual machine, a container, etc., and may have a wireless communication function, wherein the wireless communication function may be provided in the chip (system) or other parts or components of the server. The server and the vehicle may communicate via a wireless connection, for example, via mobile communication technologies such as 2G / 3G / 4G / 5G, as well as wireless communication methods such as Wi-Fi, Bluetooth, frequency modulation (FM), digital radio, and satellite communication. For example, in a test, the server may be carried on a vehicle and communicate with the vehicle via a wireless connection. Through the communication between the vehicle and the server, the server may collect data collected by sensors on one or more vehicles or installed on the road or elsewhere for calculation, and transmit the calculation results back to the corresponding vehicle.

[0069] The following Figure 2 Taking the architecture in as an example, the process of the autonomous driving method in an embodiment of the present application is explained.

[0070] Figure 3 FIG. 1 is a flow chart showing an automatic driving method according to an embodiment of the present application. Figure 3 As shown, the process of the automatic driving method may include:

[0071] Step S301: The vehicle obtains data collected by sensors.

[0072] The data collected by the sensor may include point cloud data collected by the laser radar and vertical acceleration data of the vehicle collected by the IMU. The point cloud data may be point cloud data in front of the vehicle during the vehicle's driving process, and the vertical acceleration of the vehicle may refer to the acceleration of the vehicle in a direction perpendicular to the road surface, and the vertical acceleration of the vehicle may be used to indicate the degree of vertical vibration of the vehicle on a certain road section.

[0073] The sensor can be set on one or more vehicles, and the data collected by the sensor can be obtained by one vehicle. For example, the sensor can be set on one vehicle, and the sensor can also be set on other vehicles other than the one vehicle to assist the one vehicle in autonomous driving. For example, the point cloud data collected by the sensors on other vehicles can supplement the point cloud data collected by the one vehicle. In a possible implementation, the sensor can also be set in other places, for example, the sensor can be set on both sides of the road, and can be used to collect point cloud data to supplement the point cloud data collected by the sensor on the vehicle.

[0074] Step S302: The autonomous driving system determines the point, line, and surface features of the road surface based on the data collected by the sensor.

[0075] Among them, the point, line and surface features of the road surface can respectively represent the degree of undulation of the road surface from three feature dimensions.

[0076] Figure 4 FIG. 2 is a schematic diagram showing a method for determining point, line, and surface features according to an embodiment of the present application. Figure 4 As shown in FIG. 1 , after the vehicle obtains the point cloud data collected by the laser radar, the automatic driving system can first perform coordinate conversion on the obtained point cloud data to obtain the three-dimensional coordinates of each point in the point cloud data in a Cartesian coordinate system with the center point of the rear axle of the vehicle as the origin, such as (x, y, z), where x, y, and z can represent the coordinate values ​​of the corresponding point on the x-axis, y-axis, and z-axis, respectively. For example, Figure 4 In, P i , P i+1 and P i+2 The three points in the point cloud data under the Cartesian coordinate system can be represented respectively. After obtaining the three-dimensional coordinates corresponding to the point cloud data, the reference reference road surface can be calibrated. The reference reference road surface can be determined by filtering the point cloud data, for example, and can represent the horizontal reference plane of the road surface. The more each point in the point cloud data deviates from the reference reference road surface in the z-axis direction, the greater the road surface undulation corresponding to the point. It should be noted that the reference reference road surface can also be determined by other methods.

[0077] Next, the point cloud data of the road surface in the area of ​​interest can be screened from the point cloud data. The area of ​​interest can include the road surface in front of the vehicle (i.e., the lane in front of the vehicle), and the point cloud data corresponding to the stationary or moving obstacles on the road surface in the area of ​​interest can be screened out. Among them, the acquired point cloud data can be fitted by a random sample consensus algorithm (RANSAC) to determine the lane, thereby determining the boundary of the area of ​​interest. The range of the area of ​​interest can also be pre-set. For example, the area of ​​interest can be the leftmost lane line and the rightmost lane line in the driving direction as the left and right boundaries, and the front of the vehicle and the preset distance in front of the front of the vehicle (for example, 30 meters) as the front and rear boundaries. The area of ​​interest can include all lanes in the driving direction, or part of the lanes (for example, lanes other than emergency lanes, or lanes other than prohibited lanes). Obstacles can include other vehicles, pedestrians, cones, traffic lights, etc. on the road surface. For example, the area corresponding to the point whose z-axis value in the three-dimensional coordinates corresponding to the point cloud data is outside the predetermined threshold range (for example, outside 50cm) can be used as an obstacle to be screened out.

[0078] The autonomous driving system can also grid the area of ​​interest in front of the vehicle. The resolution of the grid can be fixed. For example, the size of the area of ​​interest can be 30m*10m, and the resolution of each grid is 1m*1m, then the area of ​​interest can be divided into 300 grids of the same size; the resolution of the grid can also be variable. For example, in the x-axis direction, as the distance of the road surface from the vehicle increases, the corresponding point cloud becomes sparser, and the resolution of the grid can gradually increase from 1m*1m, for example, gradually change to 2m*1m.

[0079] Based on the point cloud data in each grid, the eigenvalue corresponding to each grid can be determined. The eigenvalue of each grid can be, for example, the z value of the highest point in the point cloud data in the grid (i.e., the value on the z-axis), the z value of the lowest point, the difference between the z values ​​of the highest point and the lowest point, the average of the z values ​​corresponding to all points, the variance of the z values ​​corresponding to all points, etc. The present application does not impose any restrictions on this, as long as the eigenvalue of each grid can represent the degree of undulation of the road surface corresponding to the grid.

[0080] Point, line and surface features of the road surface may be determined respectively according to at least one grid in the region of interest and the point cloud data in the grid.

[0081] Among them, the point feature can correspond to one or a group of grids, a group of grids may include several adjacent grids, and the point feature can correspond to a square area composed of four adjacent grids, or it can correspond to an area composed of three adjacent grids. The present application does not limit the selection method and number of several adjacent grids. For example, the value of the point feature can be the z-value difference between the highest point and the lowest point of all point cloud data in one or a group of grids. When the value of the point feature exceeds a predetermined threshold (for example, 10cm), it can be determined that the road surface corresponding to a grid or a group of grids is uneven, such as the presence of a raised manhole cover, a pothole, a speed bump, etc. on the road surface. In one possible case, when it is determined that the road surface corresponding to the grid is uneven, a virtual obstacle can be set at the one or a group of grids corresponding to the point feature to assist in the determination of subsequent strategies. For example, the range of a grid or a group of grids whose point feature value exceeds the predetermined threshold can be set as the range where the virtual obstacle is located.

[0082] The line feature may correspond to one or more consecutive grids along the lane direction, and may represent the degree of road undulation on a lane. For example, the value of the line feature may be the variance of the z values ​​corresponding to all points in one or more consecutive grids along the lane direction. If the value of the line feature exceeds a predetermined threshold (e.g., 10 cm 2 ), it can be determined that the corresponding lane road surface is undulating, for example, it may be a gravel road, etc.

[0083] The surface feature may correspond to all grids in the region of interest. For example, the value of the surface feature may be the variance of the z values ​​corresponding to all points in all grids in the region of interest. When the value of the surface feature exceeds a predetermined threshold (e.g., 10 cm 2 ), it can be determined that the road surface of all lanes in front of the vehicle is undulating.

[0084] The values ​​of point features, line features, and surface features may also be other values ​​than those mentioned above, for example, they may be determined based on one or more of the z value of the highest point (i.e., the value on the z axis), the z value of the lowest point, the difference between the highest and lowest points, the average z value corresponding to all points, the variance of the z value corresponding to all points, etc., among all points of the corresponding grid. For example, the value of a point feature may also be the variance of the z value of all point cloud data in one or a group of grids. The values ​​of point, line, and surface features may be calculated directly based on the point cloud data in the corresponding grid, or may be calculated based on the feature value of the corresponding grid, which is not limited in this application. For example, when the surface feature value is the average z value corresponding to all points, the surface feature value may be determined based on the average z value corresponding to each grid.

[0085] In one possible implementation, since the point cloud data corresponds to the road surface in front of the vehicle, the vertical acceleration is obtained after the vehicle passes the current road surface. That is to say, for a certain section of the road surface, the corresponding vehicle vertical acceleration data is obtained with a lag relative to the point cloud data. Therefore, when determining the point, line, and surface features of the road surface, the point, line, and surface features of the corresponding road surface can be first obtained based on the acquired point cloud data, and then the obtained point, line, and surface features of the corresponding road surface can be corrected based on the acquired vertical acceleration.

[0086] After obtaining the vertical acceleration data of the vehicle on the corresponding grid, the values ​​of the point features, line features, and surface features can be corrected according to the vertical acceleration of the vehicle. For example, in the case where the vertical acceleration of the vehicle changes dramatically (such as when the rate of change of the vertical acceleration exceeds a predetermined threshold, such as more than 1 m / s 3 ), the value of the corresponding point feature, line feature or surface feature can be modified so that the modified value can more realistically describe the undulation of the road surface. For example, when the larger the value of the point feature, line feature or surface feature, the greater the undulation of the road surface, when the rate of change of the vertical acceleration exceeds a predetermined threshold, the value of the corresponding point feature, line feature or surface feature is proportionally enlarged according to the degree to which the rate of change exceeds the threshold.

[0087] Step S303, the automatic driving system generates relevant strategies from three angles: lateral, longitudinal and vertical, based on the determined features and vertical acceleration data. The lateral direction corresponds to the direction perpendicular to the driving direction (Y direction) on the road surface, the longitudinal direction corresponds to the driving direction (X direction), and the vertical direction corresponds to the direction perpendicular to the road surface (Z direction).

[0088] Based on the vertical acceleration data obtained in step S301 and the characteristic values ​​corresponding to the point features, line features and surface features determined in step S302, without violating traffic regulations and avoiding obstacles on the road normally, the autonomous driving system can generate relevant autonomous driving strategies from the lateral, longitudinal and vertical dimensions to cope with possible uneven road conditions, thereby improving safety and comfort during the autonomous driving process and reducing structural fatigue damage to the vehicle caused by vibration.

[0089] Figure 5 FIG. 1 is a schematic diagram showing a method for determining an automatic driving strategy according to an embodiment of the present application. Figure 5 As shown, in the lateral dimension, uneven road conditions can be dealt with by changing lanes and avoiding lanes.

[0090] Among them, according to the line features of the point cloud data corresponding to different lanes, it can be determined to drive in the lane with the flattest corresponding road surface (i.e., change lanes). For example, when the eigenvalue of the line feature is the variance of all points in one or more consecutive grids along the lane direction, the lane with the smallest corresponding eigenvalue can be selected for driving.

[0091] After determining the lane to travel in, it is possible to determine whether there are virtual obstacles on the lane (such as virtual obstacles within the range of a grid or a group of grids whose values ​​of the corresponding point features exceed a predetermined threshold) based on the point features on the lane. In the case of a virtual obstacle, the vehicle is made to bypass the virtual obstacle in the lane (i.e., avoid the vehicle in the lane). For example, an optimization method can be used to plan the path in the lane. In the absence of other real obstacles (such as other vehicles, pedestrians, cones, etc.), the distance between the path and the virtual obstacle is used as a constraint to make the generated path as far away from the virtual obstacle as possible. In the presence of other real obstacles, the real obstacles are avoided first. The present application can also use other methods for avoiding the vehicle in the lane.

[0092] like Figure 5 As shown, in the longitudinal dimension, after obtaining the path corresponding to the vehicle according to the above path planning, it is possible to determine whether there is an uneven road surface on the path based on the point features, line features, and surface features. For example, when the value of the corresponding point feature / line feature / surface feature exceeds a predetermined threshold, it can be determined that the corresponding road surface on the path has an uneven road surface, and the current speed limit of the vehicle is determined based on the point features, line features, surface features, and the vehicle's driving speed range under uneven road conditions, as a speed constraint for the vehicle during automatic driving.

[0093] The method for determining the current speed limit of the vehicle can be shown as formula (1):

[0094] speed limit =max((1-∝)*speed max ,speed min )

[0095] Where ∝=max(T1,T2,T3), 0<∝<1 Formula (1)

[0096] Among them, speed limit Can indicate the current speed limit of the vehicle, speed max and speed minIt can be pre-set to represent the upper and lower limits of the vehicle's driving speed range when the road surface is uneven. T1, T2, and T3 can represent the normalized point feature value, line feature value, and surface feature value, respectively. The value range of T1, T2, and T3 is 0-1. The larger the maximum value of T1, T2, and T3, that is, the larger the ∝, the greater the degree of undulation of the road surface, and the smaller 1-∝, so that (1-∝)*speed max , the smaller, if (1-∝)*speed max Greater than speed min , the obtained speed limit = (1-∝)*speed max , its value becomes smaller as the road surface becomes more undulating (i.e., the larger the ∝), if (1-∝)*speed max Less than speed min , the obtained speed limit speed min . In this way, the vibration of the vehicle body on uneven road surfaces can be further reduced.

[0097] It should be noted that the present application does not impose any restrictions on the method of determining the current speed limit of the vehicle, as long as the greater the undulation of the road surface, the smaller the upper limit value of the corresponding current speed limit of the vehicle. For example, in formula (1), only one of T1, T2, and T3 or any two of T1, T2, and T3 can be used to determine the value of ∝.

[0098] like Figure 5 As shown, in the vertical dimension, it is possible to determine whether the vehicle is on an uneven road surface based on the vertical acceleration obtained by the inertial measurement unit IMU. When it is determined that the vehicle is on an uneven road surface, the parameters of the vehicle's active suspension, such as the suspension kinematic K (kinematic) characteristics and the suspension elastic kinematic C (compliance) characteristics, can be adjusted to alleviate the vertical vibration of the vehicle when the road surface is uneven. For example, when the rate of change of the vertical acceleration exceeds a predetermined threshold, it can be determined that the vehicle is on an uneven road surface (such as passing through a bumpy section), and the active suspension's K characteristics and C characteristics can be adjusted by adjusting the stiffness and damping of the active suspension, thereby suppressing the movement of the vehicle body and maintaining the stability of the vehicle body. The present application does not limit the method for adjusting the stiffness and damping of the dynamic suspension.

[0099] In one possible implementation, it is also possible to determine whether the vehicle is in an uneven road condition based on point features, line features, and surface features. For example, when the point features, line features, or surface features exceed corresponding thresholds, it is determined that the vehicle is in an uneven road condition, thereby adjusting the K characteristics and C characteristics of the vehicle's active suspension.

[0100] It should be noted that the autonomous driving system can simultaneously determine whether there is uneven road surface in the lateral, longitudinal and vertical dimensions and execute relevant strategies in the above dimensions, or it can only determine and execute one or two of them; there can also be a priority relationship in the lateral, longitudinal and vertical dimensions, for example, the lateral dimension has the highest priority and the vertical dimension has the lowest priority. The autonomous driving system can determine whether there is uneven road surface in the corresponding dimension in sequence according to the priority between dimensions, and execute relevant strategies in the dimension.

[0101] Step S304: The automatic driving system controls the vehicle to perform automatic driving according to the generated strategy and displays it on the human-machine interface HMI.

[0102] Based on the strategy in the lateral dimension, the autonomous driving system can plan the vehicle's driving path during autonomous driving. Based on the strategy in the longitudinal dimension, the autonomous driving system can constrain the vehicle's speed during autonomous driving. Based on the strategy in the vertical dimension, the autonomous driving system can adjust the K and C characteristics of the vehicle's active suspension during autonomous driving.

[0103] After generating relevant strategies, the autonomous driving system can send control signals to the vehicle to achieve autonomous driving of the vehicle on uneven roads.

[0104] Among them, when the vehicle adopts relevant strategies due to uneven road conditions, it can be displayed on the human-machine interface HMI to remind the driver and passengers, so that the driver and passengers can timely understand the current road conditions and the automatic driving strategies adopted, so as to improve the driver and passengers' sense of trust.

[0105] Figure 6 FIG. 1 is a schematic diagram showing a visual icon prompt on a human-machine interface HMI according to an embodiment of the present application. Figure 6 As shown, when the vehicle adopts relevant strategies due to uneven road surface, the icon of uneven road surface can change from gray to a highlighted prompt.

[0106] In a possible implementation, a text prompt of “uneven road surface” may be directly displayed on the screen.

[0107] Table 1 shows an example of voice broadcasting on a human-machine interface HMI according to an embodiment of the present application.

[0108] Table 1

[0109] Priority Autonomous driving strategy Broadcast content 1 Lateral lane change The road ahead is uneven, please change lanes and take a detour 2 Avoidance in the lateral lane The road ahead is uneven, please detour in the lane 3 Longitudinal deceleration The road ahead is uneven, slow down.

[0110] Among them, the smaller the corresponding value of the priority, the higher the priority of voice broadcast when executing the corresponding automatic driving strategy. For example, when the automatic driving strategies of lateral lane change and lateral lane avoidance need to be executed at the same time, the HMI priority voice broadcast content is "The road surface of the lane ahead is uneven, change lanes and detour". In a possible implementation method, after the broadcast, "The road surface of the lane ahead is uneven, detour within the lane" can be broadcast.

[0111] The above voice broadcast process is only an example, and other methods or other broadcast contents may also be adopted.

[0112] In addition to the above-mentioned visual icon prompts and voice broadcast methods, other methods can also be used to display on the HMI, such as prompting by playing a video.

[0113] Figure 7 1 shows a flow chart of an automatic driving method according to an embodiment of the present application. The method can be used on the above-mentioned vehicle, for example, it can be executed by an automatic driving system in the vehicle. Figure 7 As shown, the method includes:

[0114] Step S701, acquiring data collected by the sensor, the data including point cloud data in front of the vehicle and acceleration data of the vehicle in a direction perpendicular to the road surface;

[0115] Step S702, determining a characteristic value according to the point cloud data, wherein the characteristic value is used to indicate the degree of undulation of the road surface in front of the vehicle;

[0116] Step S703: Determine the automatic driving strategy of the vehicle at least based on the acceleration data and / or the characteristic value.

[0117] According to the embodiments of the present application, by acquiring the data in front of the vehicle collected by the sensor and determining the characteristic value based on the point cloud data, the current uneven road condition can be accurately identified. By determining the automatic driving strategy of the vehicle based on the acceleration data of the vehicle in the direction perpendicular to the road surface and / or the characteristic value, the impact of unexpected steering caused by uneven road surface on the precise control of the vehicle can be reduced, and the safety and comfort of the vehicle during the automatic driving process can be improved. At the same time, the structural damage caused by vibration to the vehicle, sensors on the vehicle, etc. can be reduced, thereby improving its reliability and life durability.

[0118] The data collected by the sensor can be obtained by the vehicle from the sensor, or sent by the sensor to the server and obtained from the server. The acceleration data of the vehicle in the direction perpendicular to the road surface can be the vertical acceleration data mentioned above. The larger the characteristic value, the greater the undulation of the road surface in front of the vehicle.

[0119] The example of step S701 can refer to Figure 3 The examples of step S301 and step S702 can refer to Figure 3 The examples of step S302 and step S703 can refer to Figure 3 Step S303.

[0120] In a possible implementation manner, the characteristic value is determined according to a coordinate value of the point cloud data in a direction perpendicular to the road surface.

[0121] The coordinate value of the point cloud data in the direction perpendicular to the road surface can reflect the undulation of the road surface. According to the embodiment of the present application, the characteristic value can better measure the unevenness of the road surface.

[0122] The coordinate value in the direction perpendicular to the road surface may be, for example, the value in the Z direction mentioned above.

[0123] In one possible implementation, the characteristic value is determined based on one or more of the z value of the highest point, the z value of the lowest point, the z value difference between the highest point and the lowest point, the average z value, and the variance of the z value in the processed point cloud data, and the z value represents the coordinate value of the point cloud data in a direction perpendicular to the road surface.

[0124] According to the embodiments of the present application, it is possible to flexibly select a method for determining characteristic values ​​according to needs, so that the degree of road undulation indicated by the characteristic values ​​can be more consistent with the actual situation of the vehicle during automatic driving.

[0125] In one possible implementation, determining eigenvalues ​​based on the point cloud data includes: determining at least one of a first eigenvalue, a second eigenvalue, and a third eigenvalue based on the point cloud data, the first eigenvalue being used to indicate the degree of undulation of a local area in each lane in the road surface in front of the vehicle, the second eigenvalue being used to indicate the degree of undulation of a road surface in each lane in the road surface in front of the vehicle, and the third eigenvalue being used to indicate the degree of undulation of a road surface in all lanes in the road surface in front of the vehicle.

[0126] According to an embodiment of the present application, by determining at least one of the first eigenvalue, the second eigenvalue and the third eigenvalue, and the first eigenvalue, the second eigenvalue and the third eigenvalue respectively indicate the degree of undulation of the road surface from three perspectives: point, line and surface. The unevenness of the road surface can be more accurately and comprehensively reflected, thereby providing a targeted basis for the subsequent determination of the autonomous driving strategy.

[0127] The first eigenvalue may be the value of the point feature described above, the second eigenvalue may be the value of the line feature described above, and the third eigenvalue may be the value of the surface feature described above. The local area may include an area of ​​any size within the lane, and the present application does not limit the size of the local area, each lane, and the entire road surface, nor does it limit the method for determining the range of each lane road surface corresponding to the first eigenvalue, each local area corresponding to the second eigenvalue, and the entire lane road surface corresponding to the third eigenvalue.

[0128] Figure 8 FIG. 1 is a flow chart showing an automatic driving method according to an embodiment of the present application. Figure 8 As shown, determining the automatic driving strategy of the vehicle at least according to the acceleration data and / or the characteristic value includes:

[0129] Step S801, determining a target lane corresponding to a minimum second eigenvalue according to the second eigenvalue;

[0130] Step S802, determining a strategy for the vehicle to switch to the target lane.

[0131] According to an embodiment of the present application, by determining the target lane corresponding to the smallest second eigenvalue based on the second eigenvalue, and determining the strategy for the vehicle to switch to the target lane, the vehicle can avoid lanes with large undulations to avoid uneven road surfaces, thereby improving the safety and comfort of the vehicle and reducing related structural damage.

[0132] Among them, the second eigenvalue is the smallest, which can indicate that the undulation degree of the corresponding lane is the smallest, and the target lane can be the lane within the region of interest mentioned above.

[0133] The examples of steps S801-S802 can be found in the above Figure 3 In step S303, there is a description of generating an autonomous driving strategy from a horizontal dimension.

[0134] Fig. 9 FIG. 1 is a flow chart showing an automatic driving method according to an embodiment of the present application. Fig. 9 As shown, determining the automatic driving strategy of the vehicle at least according to the acceleration data and / or the characteristic value includes:

[0135] Step S901, determining, according to the first eigenvalue, a target local area corresponding to the first eigenvalue exceeding a threshold;

[0136] Step S902, determining a strategy for the vehicle to avoid the target local area.

[0137] According to an embodiment of the present application, by determining, based on the first eigenvalue, a target local area corresponding to a first eigenvalue exceeding a threshold value, and determining a basis for a vehicle target avoidance local strategy, the vehicle can bypass local uneven road surfaces such as potholes in the lane to avoid uneven road surfaces, thereby improving the safety and comfort of the vehicle and reducing related structural damage.

[0138] Among them, the threshold value can be pre-set as needed. If the first eigenvalue exceeds the threshold value, it can indicate that the fluctuation degree of the target local area is greater than the preset range. The target local area can, for example, correspond to the area of ​​the virtual obstacle mentioned above. The present application does not limit the way in which the vehicle avoids the target local area. For example, the optimization method described above can be performed with the distance between the planned path and the virtual obstacle as a constraint.

[0139] The examples of steps S901-S902 can be found in the above Figure 3 In step S303, there is a description of generating an autonomous driving strategy from a horizontal dimension.

[0140] In one possible implementation, the autonomous driving strategy of the vehicle is determined based at least on the acceleration data and / or the eigenvalue, including: determining a strategy for limiting the vehicle's driving speed based on at least one of the first eigenvalue, the second eigenvalue, and the third eigenvalue, wherein an upper limit value of the vehicle's limited driving speed is negatively correlated with a maximum value of at least one of the first eigenvalue, the second eigenvalue, and the third eigenvalue.

[0141] According to an embodiment of the present application, by determining a strategy for limiting the vehicle's driving speed based on at least one of the first eigenvalue, the second eigenvalue, and the third eigenvalue, it is possible to achieve early deceleration of the vehicle before encountering an uneven road. By making the upper limit value of the vehicle's limited driving speed negatively correlated with the maximum value of at least one of the first eigenvalue, the second eigenvalue, and the third eigenvalue when determining the strategy for limiting the vehicle's driving speed, it is possible to achieve that when the greater the degree of road undulation, the smaller the upper limit value of the vehicle's speed limit is, thereby further reducing the vibration amplitude of the vehicle, improving the safety and comfort of the vehicle, and reducing related structural damage.

[0142] The present application does not limit the method for determining the upper limit of the vehicle's restricted speed. For example, reference may be made to the above formula (1).

[0143] The above examples can be found in the above Figure 3 In step S303, there is a description of generating an autonomous driving strategy from a longitudinal dimension.

[0144] In one possible implementation, a strategy for instructing the vehicle to perform autonomous driving is generated based on the acceleration data and / or the characteristic value, including: when the characteristic value exceeds a threshold value, or the rate of change of the acceleration data exceeds a threshold value, determining a strategy for instructing adjustment of parameters of the active suspension of the vehicle.

[0145] According to an embodiment of the present application, by determining a strategy for indicating adjustment of the parameters of the vehicle's active suspension when a characteristic value exceeds a threshold, or the rate of change of acceleration data exceeds a threshold, it is possible to adjust the parameters of the active suspension in advance before the vehicle passes over an uneven road, thereby reducing the vibration amplitude of the vehicle when passing over an uneven road, improving the safety and comfort of the vehicle, and reducing related structural damage.

[0146] The characteristic value exceeding the threshold value may be that at least one of the first characteristic value, the second characteristic value, and the third characteristic value exceeds the corresponding threshold value. The present application does not limit the manner of adjusting the parameters of the active suspension of the vehicle.

[0147] The above examples can be found in the above Figure 3 In step S303, there is a description of generating an autonomous driving strategy from a vertical dimension.

[0148] In a possible implementation, determining a characteristic value based on the point cloud data includes: when the rate of change of the acceleration data exceeds a predetermined threshold, adjusting the determined characteristic value to obtain an adjusted characteristic value, wherein the adjusted characteristic value is greater than the characteristic value before adjustment.

[0149] According to an embodiment of the present application, by adjusting the determined characteristic value when the rate of change of the acceleration data exceeds a threshold value, the adjusted characteristic value can more realistically reflect the current uneven road condition, so that a more accurate autonomous driving strategy can be generated based on the adjusted characteristic value, thereby further improving the safety and comfort of the vehicle during the autonomous driving process and reducing related structural damage.

[0150] The present application does not limit the manner of adjusting the determined eigenvalue. The determined eigenvalue may be adjusted by adjusting at least one of the first eigenvalue, the second eigenvalue, and the third eigenvalue.

[0151] Fig.10 FIG. 1 is a flow chart showing an automatic driving method according to an embodiment of the present application. Fig.10 As shown, determining the characteristic value according to the point cloud data includes:

[0152] Step S1001, dividing the area of ​​interest in the road surface in front of the vehicle into grids;

[0153] Step S1002, deleting the point cloud data corresponding to the obstacle in the point cloud data within the region of interest to obtain processed point cloud data;

[0154] Step S1003: determining the characteristic value according to the processed point cloud data in at least one of the grids.

[0155] According to an embodiment of the present application, by dividing the area of ​​interest in the road surface in front of the vehicle into grids and deleting the point cloud data corresponding to obstacles in the point cloud data in the area of ​​interest, the influence of obstacles such as other vehicles and pedestrians on the judgment of the unevenness of the road surface can be reduced. By determining the eigenvalue based on the processed point cloud data in at least one of the grids, the eigenvalue can more accurately reflect the unevenness of the road surface, thereby better assisting in generating relevant autonomous driving strategies.

[0156] Among them, the present application does not limit the size of the divided grid, for example, it can be determined based on the density of the point cloud data. Obstacles can be stationary or moving objects in the area of ​​interest, such as other vehicles, pedestrians, cones, traffic lights, etc. on the road.

[0157] For examples of steps S1001 to S1003, please refer to the above Figure 3 The relevant description in step S302.

[0158] In one possible implementation, determining characteristic values ​​based on the point cloud data includes: determining characteristic values ​​of a local area corresponding to one or a group of grid data in any lane based on coordinate values ​​of the point cloud data in a direction perpendicular to the road surface, to obtain the first characteristic value; and / or determining characteristic values ​​corresponding to any lane based on coordinate values ​​of the point cloud data in one or more columns of grids in the direction of any lane in a direction perpendicular to the road surface, to obtain the second characteristic value; and / or determining the third characteristic value based on coordinate values ​​of the point cloud data in all grids in a direction perpendicular to the road surface.

[0159] According to an embodiment of the present application, by determining the first eigenvalue, the second eigenvalue, and the third eigenvalue based on the coordinate values ​​of the point cloud data in the relevant grid in the direction perpendicular to the road surface, the unevenness of the road surface can be measured more accurately from the perspective of points, lines, and surfaces.

[0160] In a possible implementation, the method further includes: generating prompt information on the undulation of the road surface in front of the vehicle and / or the automatic driving strategy of the vehicle according to the strategy, wherein the prompt information includes at least one of text, image, audio, and video.

[0161] According to the embodiment of the present application, by generating prompt information, the driver and passengers can timely understand the current road conditions and the relevant strategies adopted by the vehicle, thereby improving the driver and passengers' sense of trust.

[0162] Among them, the present application does not limit the method of generating prompt information. For example, the prompt can be provided in methods other than the above-mentioned text, image, video, and audio. The present application also does not limit the content included in the prompt information.

[0163] An example of the above process can be found in Figure 3 Step S304.

[0164] Fig.11 FIG. 1 shows a structural diagram of an automatic driving device according to an embodiment of the present application. Fig.11 As shown, the device 1100 includes:

[0165] An acquisition module 1101 is used to acquire data collected by a sensor, wherein the data includes point cloud data in front of the vehicle and acceleration data of the vehicle in a direction perpendicular to the road surface;

[0166] A first determination module 1102, configured to determine a characteristic value according to the point cloud data, wherein the characteristic value is used to indicate the degree of undulation of the road surface in front of the vehicle;

[0167] The second determination module 1103 is used to determine the automatic driving strategy of the vehicle at least based on the acceleration data and / or the characteristic value.

[0168] According to the embodiments of the present application, by acquiring the data in front of the vehicle collected by the sensor and determining the characteristic value based on the point cloud data, the current uneven road condition can be accurately identified. By determining the automatic driving strategy of the vehicle based on the acceleration data of the vehicle in the direction perpendicular to the road surface and / or the characteristic value, the impact of unexpected steering caused by uneven road surface on the precise control of the vehicle can be reduced, and the safety and comfort of the vehicle during the automatic driving process can be improved. At the same time, the structural damage caused by vibration to the vehicle, sensors on the vehicle, etc. can be reduced, thereby improving its reliability and life durability.

[0169] In a possible implementation manner, the characteristic value is determined according to a coordinate value of the point cloud data in a direction perpendicular to the road surface.

[0170] The coordinate value of the point cloud data in the direction perpendicular to the road surface can reflect the undulation of the road surface. According to the embodiment of the present application, the characteristic value can better measure the unevenness of the road surface.

[0171] In one possible implementation, the characteristic value is determined based on one or more of the z value of the highest point, the z value of the lowest point, the z value difference between the highest point and the lowest point, the average z value, and the variance of the z value in the processed point cloud data, and the z value represents the coordinate value of the point cloud data in a direction perpendicular to the road surface.

[0172] According to the embodiments of the present application, it is possible to flexibly select a method for determining characteristic values ​​according to needs, so that the degree of road undulation indicated by the characteristic values ​​can be more consistent with the actual situation of the vehicle during automatic driving.

[0173] In one possible implementation, determining eigenvalues ​​based on the point cloud data includes: determining at least one of a first eigenvalue, a second eigenvalue, and a third eigenvalue based on the point cloud data, the first eigenvalue being used to indicate the degree of undulation of a local area in each lane in the road surface in front of the vehicle, the second eigenvalue being used to indicate the degree of undulation of a road surface in each lane in the road surface in front of the vehicle, and the third eigenvalue being used to indicate the degree of undulation of a road surface in all lanes in the road surface in front of the vehicle.

[0174] According to an embodiment of the present application, by determining at least one of the first eigenvalue, the second eigenvalue and the third eigenvalue, and the first eigenvalue, the second eigenvalue and the third eigenvalue respectively indicate the degree of undulation of the road surface from three perspectives: point, line and surface. The unevenness of the road surface can be more accurately and comprehensively reflected, thereby providing a targeted basis for the subsequent determination of the autonomous driving strategy.

[0175] In one possible implementation, the autonomous driving strategy of the vehicle is determined at least based on the acceleration data and / or the eigenvalue, including: determining a target lane corresponding to the smallest second eigenvalue based on the second eigenvalue; and determining a strategy for the vehicle to switch to the target lane.

[0176] According to an embodiment of the present application, by determining the target lane corresponding to the smallest second eigenvalue based on the second eigenvalue, and determining the strategy for the vehicle to switch to the target lane, the vehicle can avoid lanes with large undulations to avoid uneven road surfaces, thereby improving the safety and comfort of the vehicle and reducing related structural damage.

[0177] In one possible implementation, the autonomous driving strategy of the vehicle is determined at least based on the acceleration data and / or the eigenvalue, including: determining, based on the first eigenvalue, a target local area corresponding to the first eigenvalue exceeding a threshold; and determining a strategy for the vehicle to avoid the target local area.

[0178] According to an embodiment of the present application, by determining, based on the first eigenvalue, a target local area corresponding to a first eigenvalue exceeding a threshold value, and determining a basis for a vehicle target avoidance local strategy, the vehicle can bypass local uneven road surfaces such as potholes in the lane to avoid uneven road surfaces, thereby improving the safety and comfort of the vehicle and reducing related structural damage.

[0179] In one possible implementation, the autonomous driving strategy of the vehicle is determined based at least on the acceleration data and / or the eigenvalue, including: determining a strategy for limiting the vehicle's driving speed based on at least one of the first eigenvalue, the second eigenvalue, and the third eigenvalue, wherein an upper limit value of the vehicle's limited driving speed is negatively correlated with a maximum value of at least one of the first eigenvalue, the second eigenvalue, and the third eigenvalue.

[0180] According to an embodiment of the present application, by determining a strategy for limiting the vehicle's driving speed based on at least one of the first eigenvalue, the second eigenvalue, and the third eigenvalue, it is possible to achieve early deceleration of the vehicle before encountering an uneven road. By making the upper limit value of the vehicle's limited driving speed negatively correlated with the maximum value of at least one of the first eigenvalue, the second eigenvalue, and the third eigenvalue when determining the strategy for limiting the vehicle's driving speed, it is possible to achieve that when the greater the degree of road undulation, the smaller the upper limit value of the vehicle's speed limit is, thereby further reducing the vibration amplitude of the vehicle, improving the safety and comfort of the vehicle, and reducing related structural damage.

[0181] In one possible implementation, the autonomous driving strategy of the vehicle is determined based at least on the acceleration data and / or the characteristic value, including: when the characteristic value exceeds a threshold value, or the rate of change of the acceleration data exceeds a threshold value, determining a strategy for adjusting parameters of the active suspension of the vehicle.

[0182] According to an embodiment of the present application, by determining a strategy for indicating adjustment of the parameters of the vehicle's active suspension when a characteristic value exceeds a threshold, or the rate of change of acceleration data exceeds a threshold, it is possible to adjust the parameters of the active suspension in advance before the vehicle passes over an uneven road, thereby reducing the vibration amplitude of the vehicle when passing over an uneven road, improving the safety and comfort of the vehicle, and reducing related structural damage.

[0183] In a possible implementation, determining a characteristic value based on the point cloud data includes: when the rate of change of the acceleration data exceeds a predetermined threshold, adjusting the determined characteristic value to obtain an adjusted characteristic value, wherein the adjusted characteristic value is greater than the characteristic value before adjustment.

[0184] According to an embodiment of the present application, by adjusting the determined characteristic value when the rate of change of the acceleration data exceeds a threshold value, the adjusted characteristic value can more realistically reflect the current uneven road condition, so that a more accurate autonomous driving strategy can be generated based on the adjusted characteristic value, thereby further improving the safety and comfort of the vehicle during the autonomous driving process and reducing related structural damage.

[0185] In one possible implementation, determining a characteristic value based on the point cloud data includes: dividing an area of ​​interest in the road surface in front of the vehicle into grids; deleting point cloud data corresponding to obstacles in the point cloud data in the area of ​​interest to obtain processed point cloud data; and determining the characteristic value based on at least one of the processed point cloud data in the grids.

[0186] According to an embodiment of the present application, by dividing the area of ​​interest in the road surface in front of the vehicle into grids and deleting the point cloud data corresponding to obstacles in the point cloud data in the area of ​​interest, the influence of obstacles such as other vehicles and pedestrians on the judgment of the unevenness of the road surface can be reduced. By determining the eigenvalue based on the processed point cloud data in at least one of the grids, the eigenvalue can more accurately reflect the unevenness of the road surface, thereby better assisting in generating relevant autonomous driving strategies.

[0187] In one possible implementation, determining characteristic values ​​based on the point cloud data includes: determining characteristic values ​​of a local area corresponding to one or a group of grid data in any lane based on coordinate values ​​of the point cloud data in a direction perpendicular to the road surface, to obtain the first characteristic value; and / or determining characteristic values ​​corresponding to any lane based on coordinate values ​​of the point cloud data in one or more columns of grids in the direction of any lane in a direction perpendicular to the road surface, to obtain the second characteristic value; and / or determining the third characteristic value based on coordinate values ​​of the point cloud data in all grids in a direction perpendicular to the road surface.

[0188] According to an embodiment of the present application, by determining the first eigenvalue, the second eigenvalue, and the third eigenvalue based on the coordinate values ​​of the point cloud data in the relevant grid in the direction perpendicular to the road surface, the unevenness of the road surface can be measured more accurately from the perspective of points, lines, and surfaces.

[0189] In one possible implementation, the device also includes: a generation module, which is used to generate prompt information on the undulation of the road surface in front of the vehicle and / or the automatic driving strategy of the vehicle according to the strategy, and the prompt information includes at least one of text, image, audio, and video.

[0190] According to the embodiment of the present application, by generating prompt information, the driver and passengers can timely understand the current road conditions and the relevant strategies adopted by the vehicle, thereby improving the driver and passengers' sense of trust.

[0191] Fig.12 The structure diagram of the automatic driving device according to one embodiment of the present application is shown. The automatic driving device can be applied to Figure 1 In the vehicle shown, the above Figure 3-Figure 10 The functions of the autonomous driving method shown in any one of the above. For example, the autonomous driving device can be the above-mentioned vehicle, or a chip (system) or other parts or components that can be arranged inside the vehicle. For another example, the autonomous driving device can also be the above-mentioned autonomous driving device 1100.

[0192] like Fig.12 As shown, the autonomous driving device 1200 may include a processor 1201 and a transceiver 1202. Optionally, the autonomous driving device 1200 may include a memory 1203. The processor 1201 is coupled with the transceiver 1202 and the memory 1203, such as being connected via a communication bus.

[0193] Combine the following Fig.12 The various components of the automatic driving device 1200 are introduced in detail.

[0194] The processor 1201 is the control center of the autonomous driving device 1200, and may be a processor or a general term for multiple processing elements. For example, the processor 1201 is one or more central processing units (CPUs), or may be an application specific integrated circuit (ASIC), or may be configured to implement one or more integrated circuits of the embodiments of the present application, such as one or more microprocessors (digital signal processors, DSPs), or one or more field programmable gate arrays (FPGAs).

[0195] Optionally, the processor 1201 can perform various functions of the automatic driving device 1200 by running or executing a software program stored in the memory 1203 and calling data stored in the memory 1203.

[0196] In a specific implementation, as an embodiment, the processor 1201 may include one or more CPUs, such as Fig.12 CPU0 and CPU1 are shown in FIG.

[0197] In a possible implementation, the automatic driving device 1200 may also include multiple processors, such as Fig.12 1 and 1204. Each of these processors may be a single-CPU or a multi-CPU. A processor herein may refer to one or more communication devices, circuits, and / or processing cores for processing data (e.g., computer program instructions).

[0198] The transceiver 1202 is used for communication with other devices. Figure 2 , the autonomous driving device 1200 is a vehicle, and the transceiver 1202 can be used to communicate with a server.

[0199] Optionally, the transceiver 1202 may include a receiver and a transmitter ( Fig.12 The receiver is used to implement a receiving function, and the transmitter is used to implement a sending function.

[0200] Optionally, the transceiver 1202 may be integrated with the processor 1201, or may exist independently and communicate with the processor 1201 through the input / output port ( Fig.12 ) is coupled to the processor 1201.

[0201] The above-mentioned memory 1203 can be used to store the software program for executing the solution of the present application, and the execution is controlled by the processor 1201. The specific implementation method can refer to the above-mentioned method embodiment, which will not be repeated here.

[0202] The memory 1203 may be a read-only memory (ROM) or other types of static storage communication devices that can store static information and instructions, a random access memory (RAM) or other types of dynamic storage communication devices that can store information and instructions, or an electrically erasable programmable read-only memory (EEPROM), a compact disc read-only memory (CD-ROM) or other optical disc storage, optical disc storage (including compressed optical disc, laser disc, optical disc, digital versatile disc, Blu-ray disc, etc.), a magnetic disk storage medium or other magnetic storage communication device, or any other medium that can be used to carry or store the desired program code in the form of instructions or data structures and can be accessed by a computer, but is not limited thereto. It should be noted that the memory 1203 may be integrated with the processor 1201, or may exist independently and be accessed through the input / output port ( Fig.12 ) is coupled to the processor 1201.

[0203] It should be noted that Fig.12 The structure of the autonomous driving device 1200 shown in the figure does not constitute a limitation on the implementation method of the autonomous driving device. The actual autonomous driving device may include more or fewer components than shown in the figure, or a combination of certain components, or a different arrangement of components.

[0204] An embodiment of the present application provides an autonomous driving device, comprising: a processor and a memory for storing processor executable instructions; wherein the processor is configured to implement the above method when executing the instructions.

[0205] An embodiment of the present application provides a terminal device, which can execute the above method.

[0206] An embodiment of the present application provides a non-volatile computer-readable storage medium on which computer program instructions are stored. When the computer program instructions are executed by a processor, the above method is implemented.

[0207] An embodiment of the present application provides a computer program product, including a computer-readable code, or a non-volatile computer-readable storage medium carrying the computer-readable code. When the computer-readable code runs in a processor of an electronic device, the processor in the electronic device executes the above method.

[0208] A computer-readable storage medium may be a tangible device that can hold and store instructions used by an instruction execution device. A computer-readable storage medium may be, for example, but not limited to, an electrical storage device, a magnetic storage device, an optical storage device, an electromagnetic storage device, a semiconductor storage device, or any suitable combination of the foregoing. More specific examples of computer-readable storage media (a non-exhaustive list) include: a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), a static random access memory (SRAM), a portable compact disc read-only memory (CD-ROM), a digital versatile disc (DVD), a memory stick, a floppy disk, a mechanical encoding device, such as a punch card or a raised structure in a groove on which instructions are stored, and any suitable combination of the foregoing.

[0209] The computer-readable program instructions or codes described herein can be downloaded from a computer-readable storage medium to each computing / processing device, or downloaded to an external computer or external storage device via a network, such as the Internet, a local area network, a wide area network, and / or a wireless network. The network can include copper transmission cables, optical fiber transmissions, wireless transmissions, routers, firewalls, switches, gateway computers, and / or edge servers. The network adapter card or network interface in each computing / processing device receives the computer-readable program instructions from the network and forwards the computer-readable program instructions for storage in the computer-readable storage medium in each computing / processing device.

[0210] The computer program instructions for performing the operation of the present application may be assembly instructions, instruction set architecture (ISA) instructions, machine instructions, machine-related instructions, microcode, firmware instructions, state setting data, or source code or object code written in any combination of one or more programming languages, including object-oriented programming languages, such as Smalltalk, C++, etc., and conventional procedural programming languages, such as "C" language or similar programming languages. Computer-readable program instructions may be executed completely on a user's computer, partially on a user's computer, as an independent software package, partially on a user's computer, partially on a remote computer, or completely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer via any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., using an Internet service provider to connect via the Internet). In some embodiments, by utilizing the state information of computer-readable program instructions to personalize an electronic circuit, such as a programmable logic circuit, a field programmable gate array (FPGA) or a programmable logic array (PLA), the electronic circuit can execute the computer-readable program instructions to implement various aspects of the present application.

[0211] Various aspects of the present application are described herein with reference to the flowcharts and / or block diagrams of the methods, devices (systems) and computer program products according to the embodiments of the present application. It should be understood that each box in the flowchart and / or block diagram and the combination of each box in the flowchart and / or block diagram can be implemented by computer-readable program instructions.

[0212] These computer-readable program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, thereby producing a machine, so that when these instructions are executed by the processor of the computer or other programmable data processing device, a device that implements the functions / actions specified in one or more boxes in the flowchart and / or block diagram is generated. These computer-readable program instructions can also be stored in a computer-readable storage medium, and these instructions cause the computer, programmable data processing device, and / or other equipment to work in a specific manner, so that the computer-readable medium storing the instructions includes a manufactured product, which includes instructions for implementing various aspects of the functions / actions specified in one or more boxes in the flowchart and / or block diagram.

[0213] Computer-readable program instructions may also be loaded onto a computer, other programmable data processing apparatus, or other device so that a series of operating steps are performed on the computer, other programmable data processing apparatus, or other device to produce a computer-implemented process, thereby causing the instructions executed on the computer, other programmable data processing apparatus, or other device to implement the functions / actions specified in one or more boxes in the flowchart and / or block diagram.

[0214] The flow chart and block diagram in the accompanying drawings show the possible architecture, function and operation of the device, system, method and computer program product according to multiple embodiments of the present application. In this regard, each square frame in the flow chart or block diagram can represent a part of a module, program segment or instruction, and a part of the module, program segment or instruction includes one or more executable instructions for realizing the logical function of the specification. In some alternative implementations, the functions marked in the square frame can also occur in a sequence different from that marked in the accompanying drawings. For example, two continuous square frames can actually be executed substantially in parallel, and they can also be executed in reverse order sometimes, depending on the functions involved.

[0215] It should also be noted that each box in the block diagram and / or flowchart, and the combination of boxes in the block diagram and / or flowchart, can be implemented by hardware (such as a circuit or ASIC (Application Specific Integrated Circuit)) that performs the corresponding function or action, or can be implemented by a combination of hardware and software, such as firmware.

[0216] Although the present invention is described herein in conjunction with various embodiments, in the process of implementing the claimed invention, those skilled in the art may understand and implement other variations of the disclosed embodiments by viewing the drawings, the disclosure, and the appended claims. In the claims, the word "comprising" does not exclude other components or steps, and "one" or "an" does not exclude multiple situations. A single processor or other unit may implement several functions listed in the claims. Certain measures are recorded in different dependent claims, but this does not mean that these measures cannot be combined to produce good results.

[0217] The embodiments of the present application have been described above, and the above description is exemplary, not exhaustive, and is not limited to the disclosed embodiments. Many modifications and changes are obvious to those of ordinary skill in the art without departing from the scope of the described embodiments. The selection of terms used herein is intended to best explain the principles of the embodiments, practical applications, or improvements to the technology in the market, or to enable other persons of ordinary skill in the art to understand the embodiments disclosed herein.

Claims

1. An automatic driving method, characterized in that: The method comprises: Acquire data collected by the sensor, the data including point cloud data in front of the vehicle and acceleration data of the vehicle in a direction perpendicular to the road surface; Determining a characteristic value according to the point cloud data, the characteristic value is used to indicate the degree of undulation of the road surface in front of the vehicle, and the characteristic value includes three characteristic values ​​indicating the degree of undulation of the local area in each lane, the degree of undulation of the road surface of each lane, and the degree of undulation of the road surface of all lanes respectively; The automatic driving strategy of the vehicle is determined at least based on the acceleration data and / or the characteristic value, and the acceleration data is used to correct the characteristic value.

2. The method according to claim 1, characterized in that The characteristic value is determined according to the coordinate value of the point cloud data in a direction perpendicular to the road surface.

3. The method according to claim 1, characterized in that Determining a characteristic value according to the point cloud data includes: Based on the point cloud data, at least one of a first eigenvalue, a second eigenvalue and a third eigenvalue is determined, the first eigenvalue being used to indicate the degree of undulation of the road surface in front of the vehicle and the local area in each lane, the second eigenvalue being used to indicate the degree of undulation of the road surface in front of the vehicle and the road surface in each lane, and the third eigenvalue being used to indicate the degree of undulation of the road surface in front of the vehicle and the road surface in all lanes.

4. The method according to claim 3, characterized in that: Determining an automatic driving strategy for the vehicle at least based on the acceleration data and / or the characteristic value includes: Determine, according to the second eigenvalue, a target lane corresponding to a minimum second eigenvalue; A strategy for switching the vehicle to the target lane is determined.

5. The method according to claim 3, characterized in that: Determining an automatic driving strategy for the vehicle at least according to the acceleration data and / or the characteristic value includes: According to the first eigenvalue, determining a target local area corresponding to the first eigenvalue exceeding a threshold; A strategy for the vehicle to avoid the target local area is determined.

6. The method according to any one of claims 3 to 5, characterized in that: Determining an automatic driving strategy for the vehicle at least based on the acceleration data and / or the characteristic value includes: Based on at least one of the first eigenvalue, the second eigenvalue, and the third eigenvalue, a strategy for limiting the vehicle's driving speed is determined, wherein an upper limit value of the vehicle's limited driving speed is negatively correlated with a maximum value of at least one of the first eigenvalue, the second eigenvalue, and the third eigenvalue.

7. The method according to any one of claims 3 to 5, characterized in that: Determining an automatic driving strategy for the vehicle at least based on the acceleration data and / or the characteristic value includes: When the characteristic value exceeds a threshold value, or the rate of change of the acceleration data exceeds a threshold value, a strategy for adjusting parameters of the active suspension of the vehicle is determined.

8. The method according to claim 1, characterized in that Determining a characteristic value according to the point cloud data includes: When the rate of change of the acceleration data exceeds a predetermined threshold, the determined characteristic value is adjusted to obtain an adjusted characteristic value, and the adjusted characteristic value is greater than the characteristic value before the adjustment.

9. The method according to any one of claims 1 to 5 and 8, characterized in that: Determining a characteristic value according to the point cloud data includes: Divide the region of interest in the road surface in front of the vehicle into a grid; Deleting the point cloud data corresponding to the obstacle in the point cloud data within the region of interest to obtain processed point cloud data; The characteristic value is determined based on the processed point cloud data in at least one of the grids.

10. The method according to claim 9, characterized in that Determining a characteristic value according to the point cloud data includes: Determine, according to the coordinate values ​​of the point cloud data in one or a group of grids in any lane in a direction perpendicular to the road surface, the characteristic value of the local area corresponding to the one or a group of grid data to obtain a first characteristic value; and / or Determine the eigenvalue corresponding to any lane according to the coordinate values ​​of the point cloud data in one or more columns of grids in any lane direction in a direction perpendicular to the road surface, to obtain a second eigenvalue; and / or The third eigenvalue is determined according to the coordinate values ​​of the point cloud data in all grids in a direction perpendicular to the road surface.

11. The method according to any one of claims 1 to 5 and 8, characterized in that: The characteristic value is determined based on one or more of the z value of the highest point, the z value of the lowest point, the z value difference between the highest point and the lowest point, the average z value, and the variance of the z value in the processed point cloud data, and the z value represents the coordinate value of the point cloud data in a direction perpendicular to the road surface.

12. The method according to any one of claims 1 to 5 and 8, characterized in that: The method further comprises: According to the strategy, prompt information on the undulation of the road surface in front of the vehicle and / or the automatic driving strategy of the vehicle is generated, and the prompt information includes at least one of text, image, audio, and video.

13. An automatic driving device, characterized in that: The device comprises: An acquisition module, used to acquire data collected by the sensor, the data including point cloud data in front of the vehicle and acceleration data of the vehicle in a direction perpendicular to the road surface; A first determination module is used to determine a feature value according to the point cloud data, wherein the feature value is used to indicate the degree of undulation of the road surface in front of the vehicle, and the feature value includes three feature values ​​indicating the degree of undulation of the local area in each lane, the degree of undulation of the road surface of each lane, and the degree of undulation of the road surface of all lanes respectively; The second determination module is used to determine the automatic driving strategy of the vehicle at least based on the acceleration data and / or the characteristic value, and the acceleration data is used to correct the characteristic value.

14. An automatic driving device, characterized in that: include: processor; a memory for storing processor-executable instructions; Wherein, the processor is configured to implement the method of any one of claims 1-12 when executing the instructions.

15. A non-volatile computer-readable storage medium having computer program instructions stored thereon, characterized in that: When the computer program instructions are executed by a processor, the method according to any one of claims 1 to 12 is implemented.

16. A computer program product, comprising a computer-readable code, or a non-volatile computer-readable storage medium carrying the computer-readable code, wherein when the computer-readable code is executed in an electronic device, a processor in the electronic device executes the method according to any one of claims 1 to 12.

Images