Determination method and apparatus for vehicle driving on narrow road, storage medium, and vehicle

Abstract

A determination method and apparatus for a vehicle driving on a narrow road, a storage medium, and a vehicle. The method comprises: acquiring obstacle information in front of a vehicle; adjusting the orientation of the vehicle, and obtaining narrow road detection areas of the vehicle in various orientations; performing grid processing on each narrow road detection area, and obtaining multiple grids divided in each narrow road detection area, and position information of each grid; on the basis of the obstacle information and the position information of each grid, determining a target obstacle and position information of the target obstacle; and, on the basis of the position information of the target obstacle in each grid in each narrow road detection area, obtaining a final narrow road width. Thus, the narrow road width is obtained by means of processing the narrow road detection areas obtained for different vehicle orientations, and the narrow road width can be accurately determined without limiting the vehicle to being located in the road and parallel to a road boundary; in this way an accurate basis can be provided for subsequently determining whether the vehicle can pass through the narrow road.

Description

Method and device for determining narrow lane, storage medium and vehicle

[0001] The present application claims priority to the Chinese patent application No. 202410473690.6, filed on April 19, 2024, and titled "Method and device for determining narrow lane, storage medium and vehicle", the content of which is incorporated herein by reference in its entirety. TECHNICAL FIELD

[0002] The present application relates to the field of vehicle driving assistance, in particular to a method and device for determining narrow lane, storage medium and vehicle. BACKGROUND

[0003] Obstacles on the road, such as illegally parked vehicles, etc., narrow the local width of the road, forming a narrow area, i.e., a narrow lane. For inexperienced drivers, it is difficult to accurately predict the width of the narrow lane, which may lead to the driver driving the vehicle into a narrow lane that the vehicle cannot pass through, resulting in a traffic accident with the obstacle.

[0004] To solve the above problem, narrow lane width determination technology has emerged. Currently, the principle of existing narrow lane width determination technology is to collect road data in front of the vehicle when the vehicle is located in the road and the vehicle head is parallel to the road boundary, and then determine the narrow lane width in front of the vehicle by processing the road data. By comparing the narrow lane width with the vehicle body width, it can be determined whether the vehicle can pass through the narrow lane.

[0005] However, the existing narrow lane width determination technology is only applicable to the case where the vehicle is located in the road and the vehicle head is parallel to the road boundary. When the vehicle head is not parallel to the road boundary, the obtained narrow lane width is inaccurate.

[0006] SUMMARY

[0007] Therefore, the embodiments of the present application provide a method and device for determining narrow lane, storage medium and vehicle to solve the problem that the existing narrow lane width determination technology is only applicable to the case where the vehicle is located in the road and the vehicle head is parallel to the road boundary, and the obtained narrow lane width is inaccurate when the vehicle head is not parallel to the road boundary.

[0008] In a first aspect, the embodiments of the present application provide a method for determining narrow lane of a vehicle, the method comprising:

[0009] obtaining obstacle information in front of the vehicle;

[0010] adjusting the posture of the vehicle to obtain a narrow lane detection area of the vehicle in each posture;

[0011] griding each of the narrow passage detection area to obtain a plurality of grids divided in each of the narrow passage detection area and position information of each of the grids;

[0012] determining a target obstacle and position information of the target obstacle based on the obstacle information and the position information of each of the grids, wherein the target obstacle is an obstacle falling into each of the grids of each of the narrow passage detection area;

[0013] obtaining a final narrow passage width based on the position information of the target obstacle in each of the grids of each of the narrow passage detection area.

[0014] In a possible implementation, the adjusting the attitude of the vehicle to obtain the narrow passage detection area of the vehicle in each attitude comprises:

[0015] obtaining a range of a steering angle of the vehicle head;

[0016] steering the vehicle head by a preset angle step in the range of the steering angle of the vehicle head;

[0017] determining a front area of the vehicle head after each steering as a corresponding narrow passage detection area.

[0018] In a possible implementation, the griding each of the narrow passage detection area to obtain a plurality of grids divided in each of the narrow passage detection area and position information of each of the grids comprises:

[0019] constructing a corresponding ego-vehicle coordinate system in each of the narrow passage detection area, wherein a first coordinate axis direction of the ego-vehicle coordinate system is a direction of the vehicle head, and the first coordinate axis coincides with a center line of the vehicle head, and a second coordinate axis direction of the ego-vehicle coordinate system is a direction pointing to a left side of the first coordinate axis and perpendicular to the first coordinate axis;

[0020] dividing grids along the first coordinate axis direction of the ego-vehicle coordinate system in the corresponding narrow passage detection area, wherein lengths of the grids gradually increase along the first coordinate axis direction of the ego-vehicle coordinate system, and widths of the grids are all the same;

[0021] determining coordinate information of each vertex of each of the grids based on the ego-vehicle coordinate system to obtain the position information of each of the grids.

[0022] In a possible implementation, the determining a target obstacle and position information of the target obstacle based on the obstacle information and the position information of each of the grids comprises:

[0023] calculating coordinate information of each of the obstacles in each of the ego-vehicle coordinate systems based on each of the obstacle information.

[0024] The coordinate information of each of the obstacles in each of the self-vehicle coordinate systems is compared with the coordinate information of each grid of the corresponding lane detection region, and the obstacles located in each grid range are determined as target obstacles, and the coordinate information of the obstacles located in each grid is determined as position information of the target obstacles.

[0025] In a possible implementation, the final lane width is obtained based on the position information of the target obstacles in each grid of each of the lane detection regions, and the method comprises:

[0026] The initial lane width of each grid of each of the lane detection regions is determined based on the coordinate information of the target obstacles in each grid of each of the lane detection regions.

[0027] The initial lane widths of the grids in each of the lane detection regions are compared to determine the smallest initial lane width as the lane width of the corresponding lane detection region.

[0028] The lane widths of each of the lane detection regions are compared to determine the largest lane width as the final lane width.

[0029] In a possible implementation, the coordinate information of the target obstacles comprises a first coordinate value and a second coordinate value of the target obstacles, and the initial lane width of each grid of each of the lane detection regions is determined based on the coordinate information of the target obstacles in each grid of each of the lane detection regions, and the method comprises:

[0030] The second coordinate values of the target obstacles in the first grid of each of the lane detection regions and the second coordinate values of the target obstacles in the grids adjacent to the first grid are sorted to obtain a corresponding second coordinate value sequence, and the first grid is any grid of the lane detection region.

[0031] The difference between the second coordinate values of two adjacent second coordinate values in the second coordinate value sequence and the corresponding median value are calculated.

[0032] The initial lane width of the first grid is determined according to all the differences and the median values.

[0033] Any grid in the remaining grids of the lane detection region is determined as a new first grid, and the above steps are repeated until there is no remaining grid in the lane detection region.

[0034] In a possible implementation, the initial lane width of the first grid is determined according to all the differences and the median values, and the method comprises:

[0035] determining whether each of the difference values is greater than the width of the vehicle, and if so, determining that a passable narrow lane exists, and determining the number of difference values that are greater than the width of the vehicle as the number of the passable narrow lanes; and if not, determining the maximum difference value as the initial narrow lane width of the first grid;

[0036] determining whether the number of the passable narrow lanes is greater than 1, and if so, calculating the distance between the median corresponding to the difference value greater than the width of the vehicle and the first coordinate axis, and determining the difference value corresponding to the median with the smallest distance as the initial narrow lane width of the first grid; and if not, determining the difference value as the initial narrow lane width of the first grid.

[0037] In a possible implementation, after obtaining the final narrow lane width based on the position information of the target obstacle in each grid of each narrow lane detection area, the method further includes:

[0038] comparing the final narrow lane width with the width of the vehicle to determine a narrow lane state.

[0039] In a possible implementation, after comparing the final narrow lane width with the width of the vehicle to determine the narrow lane state, the method further includes:

[0040] if the difference between the final narrow lane width and the width of the vehicle is less than a first preset value, determining that the narrow lane state is an impassable state;

[0041] if the difference between the final narrow lane width and the width of the vehicle is greater than the first preset value and less than a second preset value, determining that the narrow lane state is a narrow passable state;

[0042] if the difference between the final narrow lane width and the width of the vehicle is greater than the second preset value, determining that the narrow lane state is a passable state.

[0043] In a possible implementation, after comparing the final narrow lane width with the width of the vehicle to determine the narrow lane state, the method further includes:

[0044] if the narrow lane state is the impassable state, sending an impassable prompt message;

[0045] if the narrow lane state is the narrow passable state, sending a narrow passable prompt message;

[0046] if the narrow lane state is the passable state, not sending a prompt message.

[0047] In a second aspect, an embodiment of the present application provides a vehicle driving narrow lane determination device, including:

[0048] obstacle information in front of the vehicle is acquired;

[0049] a posture adjustment module is configured to adjust a posture of the vehicle to obtain a narrow road detection area of the vehicle in each posture;

[0050] a gridding module is configured to perform gridding processing on each of the narrow road detection areas to obtain a plurality of grids divided in each of the narrow road detection areas and position information of each of the grids;

[0051] a target obstacle determination module is configured to determine a target obstacle and position information of the target obstacle based on the obstacle information and the position information of each of the grids, wherein the target obstacle is an obstacle falling into each of the grids of each of the narrow road detection areas;

[0052] a narrow road width determination module is configured to obtain a final narrow road width based on the position information of the target obstacle in each of the grids of each of the narrow road detection areas.

[0053] In a third aspect, an embodiment of the present application provides a vehicle, which comprises the vehicle narrow road determination device described above.

[0054] In a fourth aspect, an embodiment of the present application provides a storage medium, which stores at least one executable instruction, and the executable instruction causes a processor to perform operations corresponding to the vehicle narrow road determination method described above.

[0055] According to the vehicle narrow road determination method, device, storage medium and vehicle provided in the embodiments of the present application, the obstacle information in front of the vehicle is acquired, the posture of the vehicle is adjusted to obtain the narrow road detection area of the vehicle in each posture, the gridding processing is performed on each of the narrow road detection areas to obtain the plurality of grids divided in each of the narrow road detection areas and the position information of each of the grids, the target obstacle and the position information of the target obstacle are determined based on the obstacle information and the position information of each of the grids, and the final narrow road width is obtained based on the position information of the target obstacle in each of the grids of each of the narrow road detection areas. Thus, the narrow road width obtained by processing the narrow road detection areas in different postures of the vehicle can be accurately determined without limiting the vehicle to be located in the road and parallel to the road boundary, thereby providing an accurate basis for subsequent determination of whether the vehicle can pass through the narrow road. BRIEF DESCRIPTION OF DRAWINGS

[0056] The following drawings of the present application are hereby incorporated as a part of the embodiments of the present application for understanding the present application. The embodiments of the present application and the description thereof shown in the drawings are used to explain the principles of the present application.

[0057] In the drawings:

[0058] FIG. 1 is a flow chart of a method for determining a narrow lane for a vehicle to travel, according to an example embodiment of the present application;

[0059] FIG. 2 is a flow chart of step S102 in FIG. 1;

[0060] FIG. 3 is a flow chart of step S103 in FIG. 1;

[0061] FIG. 4 is a flow chart of step S104 in FIG. 1;

[0062] FIG. 5 is a scenario diagram of griding a narrow lane detection area, according to an example embodiment of the present application;

[0063] FIG. 6 is a flow chart of step S105 in FIG. 1;

[0064] FIG. 7 is a flow chart of step S501 in FIG. 6;

[0065] FIG. 8 is a flow chart of step S603 in FIG. 7;

[0066] FIG. 9 is a structural schematic diagram of a device for determining a narrow lane for a vehicle to travel, according to an example embodiment of the present application. DETAILED DESCRIPTION

[0067] In the following description, numerous specific details are given to provide a thorough understanding of the application. However, it will be apparent that the application can be practiced without one or more of the specific details. In other instances, well-known features are not described in detail in order to avoid obscuring the application. Accordingly, the specific

[0068] It should be noted that the terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of example embodiments in accordance with the present application. As used herein, the singular forms "a", "an" and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. It will be further understood that the terms "comprises" and / or "comprising," when used in this specification, specify the presence of stated features, integers, steps, operations, elements, and / or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and / or groups thereof.

[0069] In accordance with the present application, example embodiments will now be described in detail with reference to the accompanying drawings. However, these example embodiments can be implemented in various different forms, and should not be construed as being limited to the embodiments set forth herein. It should be understood that the embodiments are provided so as to make the present disclosure thorough and complete, and to fully convey the concept of the example embodiments to those skilled in the art.

[0070] In a first aspect, as shown in FIG. 1, the embodiments of the present application provide a method for determining a narrow lane for a vehicle, comprising:

[0071] In step S101, obstacle information in front of the vehicle is obtained.

[0072] In the embodiments of the present application, the vehicle includes but is not limited to passenger cars and commercial vehicles. Common models of passenger cars include but are not limited to sedans, sport utility vehicles, multi-person business cars, etc. Common models of commercial vehicles include but are not limited to pickup trucks, microvans, self-loading vehicles, cargo trucks, tractors, trailers, and mining vehicles, etc.

[0073] The obstacle is an object that affects the driving of the vehicle, for example, a vehicle parked on the road, a wall, etc. The obstacle information includes but is not limited to the position information of the obstacle in a specific coordinate system, which can be a world coordinate system, an image coordinate system of a detection result image, etc. The obstacle information in front of the vehicle can be obtained by an obstacle detection sensor arranged in front. The obstacle detection sensor can use a laser radar. In a specific application, the detection result of the laser radar can be converted into a unified form, for example, the obstacle detected by the laser radar is converted into an obstacle point. Specifically, in one implementation, four sides of the laser radar output are uniformly sampled, and the sampling points are taken as the obstacle points. In another implementation, the scattered points of the laser radar output are taken as the obstacle points. In yet another implementation, the obstacle contour points are taken as the obstacle points.

[0074] In step S102, the attitude of the vehicle is adjusted to obtain a narrow lane detection area of the vehicle in each attitude.

[0075] The attitude of the vehicle is adjusted so that the vehicle head can form different angles with the boundary of the road, that is, there can be an attitude in which the vehicle head is parallel to the boundary of the road, and there can also be an attitude in which the vehicle head is not parallel to the boundary of the road.

[0076] The narrow lane detection area is an area located in front of the vehicle head under the corresponding vehicle attitude. Since the attitude of the vehicle is different, the narrow lane detection area under each attitude is also different.

[0077] In step S103, each narrow lane detection area is rasterized to obtain a plurality of grids divided in each narrow lane detection area and the position information of each grid.

[0078] In step S104, based on the obstacle information and the position information of each grid, a target obstacle and the position information of the target obstacle are determined, wherein the target obstacle is an obstacle falling into each grid of each narrow lane detection area.

[0079] The accuracy of the target obstacle determination is improved by comparing the obstacle information and the position information of each grid, thereby improving the accuracy of the narrow passage width calculation.

[0080] Step S105: obtaining the final narrow passage width based on the position information of the target obstacle in each grid of each narrow passage detection region.

[0081] In the embodiment, the narrow passage width is obtained by processing the narrow passage detection regions obtained in different vehicle postures, so that the narrow passage width can be accurately determined without limiting the vehicle to be located in the road and parallel to the road boundary, thereby providing an accurate basis for subsequent determination of whether the vehicle can pass through the narrow passage.

[0082] Specifically, in the above embodiment, as shown in FIG. 2, step S102 includes:

[0083] Step S201: obtaining a range of a head turning angle of the vehicle.

[0084] The range of the head turning angle can be set according to actual conditions. In a specific application, the range of the head turning angle is obtained by increasing or decreasing a range based on an angle between the head orientation and the x-axis of the geographic coordinate system. For example, when the angle between the head orientation and the x-axis of the geographic coordinate system is 0°, the range of the head turning angle is [-30°, 30°], i.e., the range of the head turning angle is between 30° and -30°.

[0085] Step S202: turning the head by a preset angle step within the range of the head turning angle.

[0086] The preset angle step can be set by the staff, and the embodiment is not strictly limited.

[0087] In one implementation, the preset angle step is 5°, and assuming that the range of the head turning angle is [-30°, 30°], the head needs to be turned 12 times so that the head orientation is respectively 30°, 25°, 20°, 15°, 10°, 5°, 0°, -5°, -10°, -15°, -20°, -25°, and -30° with respect to the x-axis of the geographic coordinate system.

[0088] Step S203: determining a front region of the head after each turning as a corresponding narrow passage detection region.

[0089] The front region of the head after each turning is determined as a corresponding narrow passage detection region, so that the narrow passage detection regions of the head at multiple angles can be obtained, thereby improving the accuracy of the final narrow passage width obtained subsequently.

[0090] Specifically, in the above embodiment, as shown in FIG. 3, step S103 comprises:

[0091] Step S301: constructing a corresponding ego-vehicle coordinate system in each lane detection region, wherein the first coordinate axis direction of the ego-vehicle coordinate system is the vehicle head direction, and the first coordinate axis coincides with the centerline of the vehicle head, and the second coordinate axis direction of the ego-vehicle coordinate system is the direction to the left of the first coordinate axis and perpendicular to the first coordinate axis.

[0092] As shown in FIG. 5, the ego-vehicle coordinate system is with the current direction of the vehicle head as the direction of the first coordinate axis (i.e. x-axis), and the direction of the second coordinate axis (i.e. y-axis) is the direction to the left of the first coordinate axis and perpendicular to the first coordinate axis.

[0093] It can be understood that, since the vehicle head direction corresponding to each lane detection region is different, the direction of the ego-vehicle coordinate system of each lane detection region is also different.

[0094] Step S302: dividing the corresponding lane detection region along the first coordinate axis direction of the ego-vehicle coordinate system, wherein the length L of the grid gradually increases along the first coordinate axis direction of the ego-vehicle coordinate system, and the width W of the grid is the same.

[0095] In a specific application, the region close to the vehicle head is not divided into grids, for example, the grid is divided within the range of 4m from the front end of the vehicle head, which can reduce the number of grid divisions, thereby reducing the data processing amount and improving the data processing efficiency.

[0096] The length L of the divided grid gradually increases along the direction of the first coordinate axis of the ego-vehicle coordinate system, that is, the farther the grid is from the vehicle head, the longer the length L is; the closer the grid is to the vehicle head, the shorter the length L is, and such division of the grid can improve the accuracy of the determination of the lane width.

[0097] In order to facilitate the calculation of the initial lane width of each grid in the subsequent steps, the centerline of each grid coincides with the first coordinate axis.

[0098] Step S303: determining the coordinate information of each vertex of each grid based on the ego-vehicle coordinate system to obtain the position information of each grid.

[0099] The units of the first coordinate axis and the second coordinate axis of the ego-vehicle coordinate system are the same as the unit of the vehicle width, thereby facilitating the comparison between the lane width and the vehicle width in the subsequent steps. Generally, the first coordinate axis, the second coordinate axis and the vehicle width all adopt meters as the unit.

[0100] By determining the coordinate information of each vertex of each grid, it is convenient to compare with the position of the obstacle in the subsequent steps, so as to more quickly determine the obstacle (i.e. target obstacle) in each grid and the position thereof, and also improve the accuracy of the determination of the target obstacle.

[0101] Specifically, in the above embodiment, as shown in FIG. 4, step S104 comprises:

[0102] Step S401: based on each obstacle information, the coordinate information of each obstacle in each ego-vehicle coordinate system is calculated.

[0103] The obstacle information obtained in step S101 includes the position information of each obstacle in a specific coordinate system, which can be a world coordinate system, an image coordinate system of a detection result image, etc. Thus, through the position information of each obstacle in the specific coordinate system, i.e., the coordinate information in the specific coordinate system, and the conversion matrix of the specific coordinate system and each ego-vehicle coordinate system, the coordinate information of each obstacle in each ego-vehicle coordinate system can be obtained.

[0104] In this step, the coordinate information of each obstacle in each ego-vehicle coordinate system is calculated, so that the coordinates of each obstacle and the coordinates of each vertex of each grid are unified in the ego-vehicle coordinate system, so as to facilitate the comparison between the coordinates of each obstacle and the coordinates of each vertex of each grid in the subsequent step, and the obstacles located in each grid can be quickly and accurately determined.

[0105] Step S402: comparing the coordinate information of each obstacle in each ego-vehicle coordinate system with the coordinate information of each grid of the corresponding narrow lane detection area, determining the obstacles located in each grid range as target obstacles, and determining the coordinate information of the obstacles located in each grid as the position information of the target obstacles.

[0106] For example, taking the grid a1 of the narrow lane detection area shown in FIG. 5 as an example, assuming that the coordinates of each vertex of the grid a1 in the ego-vehicle coordinate system of the detection area are (5, 2), (5, -2), (4, 2), (4, -2), and if the coordinates of a certain obstacle in the ego-vehicle coordinate system of the detection area are (5.5, 0), the first coordinate value (i.e., the x-axis of the ego-vehicle coordinate system) 5.5 exceeds the range of the grid a1, it is determined that the obstacle is not in the grid a1, and the coordinates of each vertex of the grid a2 are (5, 2.2), (5, -2.2), (6, 2.2), (6, -2.2), the first coordinate value and the second coordinate value of the obstacle fall within the range of the grid a2, it is determined that the obstacle is a target obstacle falling within the grid a2, and the position information of the target obstacle is the coordinates of the obstacle in the ego-vehicle coordinate system, i.e., (5.5, 0).

[0107] Specifically, in the above embodiment, as shown in FIG. 6, step S105 comprises:

[0108] Step S501: determining the initial lane width of each grid of each lane detection region based on the coordinate information of the target obstacle in the grid.

[0109] Step S502: comparing the initial lane width of each grid in each lane detection region to determine the minimum initial lane width as the lane width of the corresponding lane detection region.

[0110] The minimum initial lane width in each lane detection region is determined as the lane width of the lane detection region, that is, the narrowest region width in each lane detection region is determined as the lane width of the detection region, thereby improving the accuracy of the lane width determined by each lane detection region.

[0111] Step S503: comparing the lane width of each lane detection region to determine the maximum lane width as the final lane width.

[0112] For example, assuming that the lane width of each lane detection region is 2m, 1.8m, 0.5m, 3m, 0.8m, 0.3m, 1.2m, 1.1m, 1.6m, 2.1m, 0.6m, 0.1m, 1.9m, the final lane width is 2m.

[0113] The lane widths of each lane detection region are compared, and then the maximum lane width is selected as the final lane width, thereby ensuring that if the vehicle cannot pass through the finally determined lane, there is no other lane that can allow the vehicle to pass through, thereby improving the accuracy of subsequent vehicle passing determination.

[0114] Further, in the above embodiment, as shown in FIG. 7, step S501 includes:

[0115] Step S601: sorting the second coordinate values of the target obstacle in the first grid of each lane detection region and the second coordinate values of the target obstacle in the grid adjacent to the first grid to obtain the corresponding second coordinate value sequence.

[0116] Wherein, the first grid is any grid of the lane detection region. The coordinate information of the target obstacle includes the first coordinate value and the second coordinate value of the target obstacle, that is, the x-axis coordinate value and the y-axis coordinate value of the target obstacle in the ego coordinate system of the lane detection region where the first grid is located.

[0117] The grid adjacent to the first grid refers to the grid adjacent to the first grid. For example, if grid a1 is the first grid, then grid a2 is the adjacent grid of grid a1. If grid a2 is the first grid, then grid a1 and grid a3 are adjacent to grid a2.

[0118] The second coordinate values of the target obstacles in the first grid and the second coordinate values of the target obstacles in the grids adjacent to the first grid can be arranged in descending order or in ascending order.

[0119] Taking grid a1 as the first grid, assuming that there are two target obstacles in grid a1, target obstacle b1 with coordinate information (4.5, 1.8) and target obstacle b2 with coordinate information (4.3, 0.2), and three target obstacles in grid a2, target obstacle b3 with coordinate information (5.2, 0.5), target obstacle b4 with coordinate information (5.6, -1.3), and target obstacle b5 with coordinate information (5.5, -2), the second coordinate values are arranged in descending order of the second coordinate values of the target obstacles, and the sequence of the second coordinate values is (1.8, 0.5, 0.2, -1.3, -2).

[0120] Step S602: Calculate the difference between the second coordinate values of two adjacent second coordinate values in the sequence of the second coordinate values and the corresponding median.

[0121] Taking the sequence of the second coordinate values in the above step as an example, the sequence of the second coordinate values is (1.8, 0.5, 0.2, -1.3, -2), the difference between the second coordinate values of two adjacent second coordinate values is 1.3, 0.3, 1.5, 0.7, and the median of the two adjacent second coordinate values is 1.15, 0.35, -0.75, -1.65.

[0122] Step S603: Determine the initial lane width of the first grid according to all the differences and the medians.

[0123] Step S604: Determine any grid in the remaining grids of the lane detection area as a new first grid, and repeat the above steps until there is no remaining grid in the lane detection area.

[0124] Each grid of each lane detection area is processed according to steps S601-S603, so as to obtain the initial lane width of each grid of each lane detection area.

[0125] In the embodiment, by sorting the second coordinate values of the target obstacles in the first grid of each lane detection area and the second coordinate values of the target obstacles in the grids adjacent to the first grid, and processing the sequence of the second coordinate values obtained by sorting, the initial lane width can be accurately determined when the obstacles on both sides of the road are misaligned, and the accuracy of the finally determined lane width is higher.

[0126] Specifically, in the above embodiment, as shown in FIG. 8, step S603 includes:

[0127] Step S701: Determine whether each difference is greater than the width of the vehicle, if yes, execute step S702; if no, execute step S703.

[0128] Step S702: Determine that there is a passable narrow lane, and determine the number of differences greater than the width of the vehicle as the number of passable narrow lanes.

[0129] For example, assuming that the second coordinate sequence is (1.8, 0.5, 0.2, -1.3, -2), then the difference between the second coordinate values of adjacent two is 1.3, 0.3, 1.5, 0.7; the width of the vehicle is 1.2m, then the differences 1.3 and 1.5 are both greater than the width of the vehicle, so it is determined that there is a passable narrow lane, and the number of passable narrow lanes is two.

[0130] In another example, for example, assuming that the second coordinate sequence is (1, 0.5, 0.2, -1.3, -2), then the difference between the second coordinate values of adjacent two is 0.5, 0.3, 1.5, 0.7, and the width of the vehicle is 1.2m, then only 1.5m is greater than the width of the vehicle, so it is determined that there is a passable narrow lane, and the number of passable narrow lanes is one.

[0131] Step S703: Determine the maximum difference as the initial narrow lane width of the first grid.

[0132] For example, assuming that the second coordinate sequence is (1.8, 1, 0.1, -1.1, -2), the difference between the second coordinate values of adjacent two is 0.8, 0.9, 1, 0.9; the width of the vehicle is 1.2m, then all the differences are less than the width of the vehicle, so 1m is taken as the initial narrow lane width of the first grid.

[0133] Step S704: Determine whether the number of passable narrow lanes is greater than 1, if yes, execute step S705; if no, execute step S706.

[0134] Step S705: Calculate the distance between the median corresponding to the difference greater than the width of the vehicle and the first coordinate axis, and determine the difference corresponding to the median with the smallest distance as the initial narrow lane width of the first grid.

[0135] Continuing with the example in step S702, if the second coordinate sequence is (1.8, 0.5, 0.2, -1.3, -2), then the difference between the second coordinate values of two adjacent ones is 1.3, 0.3, 1.5, 0.7; the median of two adjacent second coordinate values is 1.15, 0.35, -0.75, -1.65; wherein the difference 1.3 corresponds to the median 1.15; the difference 1.5 corresponds to the median -0.75, thus the difference 1.5 is closest to the first coordinate axis (i.e. the x-axis of the ego vehicle coordinate system), and 1.5 m is determined as the initial lane of the first grid.

[0136] In this step, in the case where there are two or more passable lanes, the passable lane closest to the first coordinate axis (i.e. the x-axis of the ego vehicle coordinate system) is determined as the initial lane of the first grid.

[0137] Step S706: The difference is determined as the initial lane width of the first grid.

[0138] Continuing with the example in step S702, if the second coordinate sequence is (1.8, 0.5, 0.2, -1.3, -2), then the difference between the second coordinate values of two adjacent ones is 1.3, 0.3, 1.5, 0.7; the median of two adjacent second coordinate values is 1.15, 0.35, -0.75, -1.65; wherein the difference 1.3 corresponds to the median 1.15; the difference 1.5 corresponds to the median -0.75, thus the difference 1.5 is closest to the first coordinate axis (i.e. the x-axis of the ego vehicle coordinate system), and 1.5 m is determined as the initial lane of the first grid.

[0139] In this step, in the case where there is only one passable lane, the passable lane is determined as the initial lane of the first grid.

[0140] Further, in the above embodiment, step S105 is followed by:

[0141] Step S801: comparing the final lane width with the width of the vehicle to determine the lane state.

[0142] According to the comparison of the final lane width and the width of the vehicle, it is determined whether the lane is suitable for the vehicle to pass, so that the driver can accurately master whether the vehicle can pass through the lane and how to pass through the lane according to the lane state.

[0143] Specifically, step S801 includes:

[0144] Step S901: if the difference between the final lane width and the width of the vehicle is less than a first preset value, the lane state is determined as an impassable state.

[0145] The first preset value can be set by the staff according to the actual situation, and the present embodiment is not strictly limited. In one implementation, the first preset value is 0.5 m.

[0146] For example, if the final narrow passage width is 1.5 m, the width of the vehicle is 1.2 m, and the first preset value is 0.5 m, the difference between the final narrow passage width and the width of the vehicle is 0.3 m, which is less than 0.5 m, and thus the narrow passage state is determined as the impassable state.

[0147] In this step, the narrow passage which is greater than the width of the vehicle and the difference between the final narrow passage width and the width of the vehicle is less than the first preset value is determined as the impassable narrow passage, so that the driver knows that the vehicle cannot pass through the narrow passage, thereby effectively avoiding the situation that the driver drives the vehicle into the narrow passage and collides with the obstacle, and thus the safety of passing is improved.

[0148] Step S902: If the difference between the final narrow passage and the width of the vehicle is greater than the first preset value and less than the second preset value, the narrow passage state is determined as the narrow passable state.

[0149] The second preset value can be set by the staff according to the actual situation, and the embodiment is not strictly limited. In one implementation, the second preset value is 1.5 m.

[0150] For example, if the final narrow passage width is 2 m, the width of the vehicle is 1.2 m, the first preset value is 0.5 m, and the second preset value is 1.5 m, the difference between the final narrow passage width and the width of the vehicle is 0.8 m, which is greater than 0.5 m and less than 1.5 m, and thus the narrow passage state is determined as the narrow passable state.

[0151] In this step, the narrow passage which is greater than the width of the vehicle and the difference between the final narrow passage width and the width of the vehicle is greater than the first preset value and less than the second preset value is determined as the narrow passable narrow passage, so that the driver can reduce the vehicle speed and improve the attention when passing the narrow passage, thereby effectively avoiding the collision with the obstacle of the narrow passage when passing, and thus the safety of passing is improved.

[0152] Step S903: If the difference between the final narrow passage and the width of the vehicle is greater than the second preset value, the narrow passage state is determined as the passable state.

[0153] For example, if the final narrow passage width is 3 m, the width of the vehicle is 1.2 m, and the second preset value is 1.5 m, the difference between the final narrow passage width and the width of the vehicle is 1.8 m, which is greater than 1.5 m, and thus the narrow passage state is determined as the passable state.

[0154] In this step, the narrow passage which is greater than the width of the vehicle and the difference between the final narrow passage width and the width of the vehicle is greater than the second preset value is determined as the passable narrow passage, so that the driver can drive the vehicle normally to pass through the narrow passage smoothly, and thus the narrow passage passing speed is improved.

[0155] Further, in the above embodiment, step S801 is followed by:

[0156] Step S1001: If the narrow passage state is the impassable state, sending an impassable prompt information.

[0157] The prompt information includes but is not limited to text information and voice broadcast, etc.

[0158] When the narrow passage state is the impassable state, by sending the impassable prompt information, the driver is reminded not to drive into the narrow passage, thereby effectively avoiding the situation that the driver drives the vehicle into the narrow passage and collides with the obstacle, and the safety of passing is improved.

[0159] Step S1002: If the narrow passage state is the narrow passable state, sending a narrow passable prompt information.

[0160] When the narrow passage state is the narrow passable state, by sending the narrow passable prompt information, the driver is reminded to reduce the vehicle speed and improve the attention when driving through the narrow passage, thereby reducing the probability of collision with the obstacle.

[0161] Step S1003: If the narrow passage state is the passable state, no prompt information is sent.

[0162] When the narrow passage state is the passable state, no prompt information needs to be sent, that is, for the narrow passage in the passable state, the driver can smoothly pass through by normal driving.

[0163] It should be understood that the size of the serial number of each step in the above embodiment does not mean the order of execution, and the execution order of each process should be determined according to its function and inherent logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0164] In a second aspect, as shown in FIG. 9, the embodiments of the present application provide a determination device for vehicle driving in a narrow passage, comprising:

[0165] The acquisition module 1101 is configured to acquire obstacle information in front of the vehicle.

[0166] The posture adjustment module 1102 is configured to adjust the posture of the vehicle to obtain a narrow passage detection area of the vehicle in each posture.

[0167] The gridding module 1103 is configured to perform gridding processing on each narrow passage detection area to obtain a plurality of grids divided in each narrow passage detection area and position information of each grid.

[0168] The target obstacle determination module 1104 is configured to determine a target obstacle and position information of the target obstacle based on the obstacle information and the position information of each grid, wherein the target obstacle is an obstacle falling into each grid of each narrow passage detection region.

[0169] The narrow passage width determination module 1105 is configured to obtain a final narrow passage width based on the position information of the target obstacle in each grid of each narrow passage detection region.

[0170] According to the vehicle narrow passage determination device provided in the embodiments of the present application, the narrow passage width is obtained by processing the narrow passage detection regions obtained in different vehicle postures, so that the narrow passage width can be accurately determined without limiting the vehicle to be located in the road and parallel to the road boundary, thereby providing an accurate basis for subsequent determination of whether the vehicle can pass through the narrow passage.

[0171] In a third aspect, the embodiments of the present application provide a vehicle, which comprises the vehicle narrow passage determination device described above.

[0172] In a fourth aspect, the embodiments of the present application provide a storage medium, which stores at least one executable instruction. The executable instruction causes a processor to perform operations corresponding to the vehicle narrow passage determination method described above.

[0173] The present application has been described by the above embodiments, but it should be understood that the above embodiments are only for the purpose of example and illustration, and are not intended to limit the present application to the described embodiments. In addition, those skilled in the art can understand that the present application is not limited to the above embodiments, and more variations and modifications can be made according to the teachings of the present application, which all fall within the scope of the present application. The scope of protection of the present application is defined by the appended claims and their equivalent scope.

Claims

1. A method of determining a travelable lane of a vehicle, wherein, The method comprises: obtaining obstacle information in front of a vehicle; adjusting the posture of the vehicle to obtain a narrow lane detection area of the vehicle in each posture; performing grid processing on each narrow lane detection area to obtain a plurality of grids divided in each narrow lane detection area and position information of each grid; determining a target obstacle and position information of the target obstacle based on the obstacle information and the position information of each grid, wherein the target obstacle is an obstacle falling into each grid of each narrow lane detection area; obtaining a final narrow lane width based on the position information of the target obstacle in each grid of each narrow lane detection area.

2. The method of claim 1, wherein, The adjusting of the posture of the vehicle to obtain a narrow lane detection area of the vehicle in each posture comprises: obtaining a range of a steering angle of a vehicle head; rotating the vehicle head by a preset angle step within the range of the steering angle of the vehicle head; determining a front area of the vehicle head after each rotation as a corresponding narrow lane detection area.

3. The method of claim 2, wherein, The grid processing on each narrow lane detection area to obtain a plurality of grids divided in each narrow lane detection area and position information of each grid comprises: constructing a corresponding ego-vehicle coordinate system in each narrow lane detection area, wherein a first coordinate axis direction of the ego-vehicle coordinate system is a direction in which the vehicle head faces, and the first coordinate axis coincides with a center line of the vehicle head, and a second coordinate axis direction of the ego-vehicle coordinate system is a direction perpendicular to the first coordinate axis and pointing to a left side of the first coordinate axis; dividing grids along the first coordinate axis direction of the ego-vehicle coordinate system for the corresponding narrow lane detection area, wherein a length of the grid gradually increases along the first coordinate axis direction of the ego-vehicle coordinate system, and a width of the grid is the same; determining coordinate information of each vertex of each grid based on the ego-vehicle coordinate system to obtain position information of each grid.

4. The method of claim 3, wherein, The determination of a target obstacle and position information of the target obstacle based on the obstacle information and the position information of each grid comprises: calculating coordinate information of each obstacle in each ego-vehicle coordinate system based on each obstacle information; comparing the coordinate information of each obstacle in each ego-vehicle coordinate system with coordinate information of each grid of the corresponding narrow lane detection area, determining an obstacle located in each grid as a target obstacle, and determining coordinate information of the obstacle located in each grid as position information of the target obstacle.

5. The method of claim 4, wherein, The obtaining of a final narrow lane width based on the position information of the target obstacle in each grid of each narrow lane detection area comprises: determining an initial narrow lane width of each grid of each narrow lane detection area based on coordinate information of the target obstacle in each grid of each narrow lane detection area; comparing the initial narrow lane widths of each grid in each narrow lane detection area to determine a smallest initial narrow lane width as a narrow lane width of the corresponding narrow lane detection area; comparing the narrow lane widths of each narrow lane detection area to determine a largest narrow lane width as a final narrow lane width.

6. The method of claim 5, wherein, The coordinate information of the target obstacle includes a first coordinate value and a second coordinate value of the target obstacle; determining the initial narrow lane width of each grid of each narrow lane detection area based on the coordinate information of the target obstacle in each grid of each narrow lane detection area includes: The second coordinate values of the target obstacle in each first grid of each narrow lane detection area and the second coordinate values of the target obstacle in the grids adjacent to the first grid are sorted to obtain a corresponding second coordinate value sequence; wherein the first grid is any grid of the narrow lane detection area; The difference between the second coordinate values of two adjacent second coordinate values in the second coordinate value sequence and the corresponding median value are calculated; The initial narrow lane width of the first grid is determined according to all the differences and median values; Any grid in the remaining grids of the narrow lane detection area is determined as a new first grid, and the above steps are repeated until there is no remaining grid in the narrow lane detection area.

7. The method of claim 6, wherein, The initial narrow lane width of the first grid is determined according to all the differences and median values, including: It is judged whether each difference is greater than the width of the vehicle, if yes, it is determined that there is a passable narrow lane, and the number of differences greater than the width of the vehicle is determined as the number of passable narrow lanes; if not, the maximum difference is determined as the initial narrow lane width of the first grid; It is judged whether the number of passable narrow lanes is greater than 1, if yes, the distance between the median value corresponding to the difference greater than the width of the vehicle and the first coordinate axis is calculated, and the difference corresponding to the median value with the smallest distance is determined as the initial narrow lane width of the first grid; if not, the difference is determined as the initial narrow lane width of the first grid.

8. The method of claim 1, wherein, After obtaining the final narrow lane width based on the position information of the target obstacle in each grid of each narrow lane detection area, including: The final narrow lane width is compared with the width of the vehicle to determine the narrow lane state.

9. The method of claim 8, wherein, The final narrow lane width is compared with the width of the vehicle to determine the narrow lane state, including: If the difference between the final narrow lane width and the width of the vehicle is less than a first preset value, it is determined that the narrow lane state is an impassable state; If the difference between the final narrow lane and the width of the vehicle is greater than the first preset value and less than a second preset value, it is determined that the narrow lane state is a narrow passable state; If the difference between the final narrow lane and the width of the vehicle is greater than the second preset value, it is determined that the narrow lane state is a passable state.

10. The method of claim 9, wherein, After comparing the final narrow lane width with the width of the vehicle to determine the narrow lane state, it further includes: If the narrow lane state is an impassable state, an impassable prompt information is sent; If the narrow lane state is a narrow passable state, a narrow passable prompt information is sent; If the narrow lane state is a passable state, no prompt information is sent.

11. A device for determining a lane of travel of a vehicle, wherein Including: An acquisition module is configured to acquire obstacle information in front of a vehicle; An attitude adjustment module is configured to adjust an attitude of the vehicle to obtain a narrow lane detection area of the vehicle in each attitude. a gridding module configured to perform gridding processing on each of the lane detection areas to obtain a plurality of grids divided in each of the lane detection areas and position information of each of the grids; a target obstacle determination module configured to determine a target obstacle and position information of the target obstacle based on the obstacle information and the position information of each of the grids, wherein the target obstacle is an obstacle falling into each of the grids in each of the lane detection areas; a lane width determination module configured to obtain a final lane width based on the position information of the target obstacle in each of the grids in each of the lane detection areas.

12. A vehicle, wherein, The determination device of the lane for vehicle driving according to claim 11.

13. A storage medium, wherein, The storage medium has at least one executable instruction stored therein, and the executable instruction causes the processor to perform operations corresponding to the determination method of the lane for vehicle driving according to any one of claims 1-10.

Images