A lateral control method, device, medium and electronic equipment of a road vehicle

Abstract

The application provides a lateral control method, device, medium and electronic equipment of a road vehicle. The application determines the road type of the road through the perception parameter value; obtains the key road parameter value of the road type based on the road type and the perception parameter value; determines the virtual guide lane line in the target continuous image of the road based on the key road parameter value of the road type; and determines how the ego vehicle travels according to the virtual guide lane line based on the ego vehicle speed parameter value. The instability of the special road type scene control is made up, and the continuity of the lane keeping function is improved.

Description

Technical Field

[0001] This application relates to the field of computer technology, and more specifically, to a method, apparatus, medium, and electronic device for lateral control of road vehicles. Background Technology

[0002] Vehicles equipped with driver assistance cameras can detect road information ahead in real time (number and changes of lane lines, lane line curvature, lane line width, lateral and longitudinal distance, lane stop lines, road attributes, etc.), enabling lane keeping function to keep the car in the center of the lane, and even pass through roads without lane lines.

[0003] However, during actual debugging or road testing, it was found that the system that implements the above functions, especially the low-cost pure driver assistance camera solution, may experience function failure or unstable control in some special scenarios, such as changes in road conditions (lane lines may be aligned or misaligned), changes in the number of lane lines (from one to two, or a break in the middle, lane lines may be aligned or misaligned), or gaps.

[0004] Therefore, this application provides a lateral control method for road vehicles to solve the above-mentioned technical problems. Summary of the Invention

[0005] The purpose of this application is to provide a lateral control method, device, medium, and electronic device for road vehicles, which can solve at least one of the aforementioned technical problems. The specific solution is as follows:

[0006] According to a specific embodiment of this application, in a first aspect, this application provides a lateral control method for road vehicles, comprising:

[0007] Acquire the perception parameter values ​​of the vehicle on the road, wherein the perception parameter values ​​include the vehicle speed parameter values;

[0008] The road type of the road is determined based on the perceived parameter values;

[0009] Based on the road type and the sensing parameter values, obtain the key road parameter values ​​for the road type;

[0010] Based on the key road parameter values ​​of the road type, determine the virtual guide lane lines in the target continuous image of the road;

[0011] The vehicle speed parameter value is used to determine how the vehicle should travel along the virtual guide lane.

[0012] Optionally, determining the road type based on the perception parameter value includes:

[0013] When the perception parameter values ​​include a clear indication of the presence of the intersection stop line, an unobstructed view ahead, and a clear indication of perception segmentation, and when the vertical distance between the first stop line of the 5-lane road and the second stop line opposite the intersection is less than or equal to a preset short intersection distance threshold, the road type is determined to be a short intersection type.

[0014] When the perception parameter values ​​include a clear indication of the presence of the intersection stop line, an unobstructed view ahead, and a clear indication of perception segmentation, and when the vertical distance between the first stop line of the 5-lane road and the second stop line opposite the intersection is greater than a preset short intersection distance threshold, the road type is determined to be a long intersection type.

[0015] Accordingly, determining the virtual guide lane lines in the target continuous image of the road based on the key road parameter values ​​of the road type includes:

[0016] When the road type is either the short intersection type or the long intersection type, when the absolute value of the lateral distance deviation parameter between the target lane line of lane 5 and the target lane line of any lane traveling in the same direction opposite the intersection is less than or equal to a preset lateral distance deviation threshold, and the first angle parameter value is within a preset first angle range, a virtual guide lane line is determined in the target continuous image of the road between lane 5 and any lane. The first angle parameter value refers to the angle between the line connecting the first intersection point of lane 5 to the second intersection point of any lane and the first stop line of lane 5. The first intersection point refers to the intersection of the target lane line of lane 5 and the first stop line of lane 5, and the second intersection point refers to the intersection of the target lane line of any lane and the stop line of any lane.

[0017] Optionally, determining the virtual guide lane lines in the target continuous image of the road based on the key road parameter values ​​of the road type includes:

[0018] When the road type is either the short intersection type or the long intersection type, when the absolute value of the lateral distance deviation parameter between the target lane line of the 5-lane road and the target lane line of each lane traveling in the same direction opposite the intersection is greater than a preset lateral distance deviation threshold, when the width parameter values ​​of any two adjacent lanes are within a preset lane width range, and the second angle parameter values ​​of any two adjacent lanes are within a preset second angle range, and the first radius of curvature parameter values ​​of any two adjacent lanes are greater than or equal to a preset radius of curvature threshold, the target lane is determined from the two adjacent lanes, wherein the second angle parameter... The value refers to the angle between the line connecting the first intersection point of the five lanes to the second intersection point of any lane and the first stop line of the five lanes. The first intersection point is the intersection of the target lane line of the five lanes and the first stop line of the five lanes. The second intersection point is the intersection of the target lane line of any lane and the stop line of any lane. The second angle parameter value of the target lane is less than or equal to the second angle parameter value of the other lane among the two adjacent lanes, and the first radius of curvature parameter value of the target lane is less than or equal to the first radius of curvature parameter value of the other lane among the two adjacent lanes.

[0019] In the target continuous image of the road, a virtual guide lane line is determined between the self-5 lane and the target lane.

[0020] Optionally, determining the road type based on the perception parameter value includes:

[0021] When the perceived parameter values ​​include a clear indication of the existence of the two lane lines of lane 5, and the curvature radius parameter value of the right lane line of lane 5 is greater than or equal to a preset straight curvature radius threshold, and the loss length parameter value of the lost right lane line of lane 5 and the loss length parameter value of the lost left lane line of lane 5 are both less than or equal to a preset loss length threshold, and the incremental width parameter value of the current detection cycle is greater than a preset incremental width threshold, and the current width parameter value of lane 5 is greater than the current width parameter value of the adjacent left lane, and the inner angle parameter value of the road edge of the adjacent left lane is within a preset first inner angle range, the road type is determined to be the first one-two type, wherein the inner angle parameter value of the road edge of the adjacent left lane refers to the inner angle value between the left lane line of lane 5 and the straight line of the road edge of the adjacent left lane;

[0022] When the perceived parameter values ​​include a clear indication of the presence of the right lane line from lane 5, and the curvature radius parameter value of the right lane line from lane 5 is greater than or equal to a preset straight curvature radius threshold, and the loss length parameter value of the lost right lane line from lane 5 and the loss length parameter value of the lost left lane line from lane 5 are both less than or equal to a preset loss length threshold, and the incremental width parameter value of the current detection cycle is greater than a preset incremental width threshold, and the current width parameter value of lane 5 is greater than the current width parameter value of the adjacent left lane, and the inner angle parameter value of the road edge of the adjacent left lane is within a preset second inner angle range, the road type is determined to be a second one-to-two type, wherein the maximum angle value of the preset second inner angle range is greater than the maximum angle value of the preset first inner angle range;

[0023] Accordingly, determining the virtual guide lane lines in the target continuous image of the road based on the key road parameter values ​​of the road type includes:

[0024] When the road type is either the first one-to-two type or the second one-to-two type, a virtual guide lane line is determined in the target continuous image of the road based on the right lane line of the five lanes.

[0025] Optionally, determining the road type based on the perception parameter value includes:

[0026] When the perceived parameter value includes non-intersection sign and lane line misalignment sign, the road type is determined to be a non-intersection lane line misalignment type.

[0027] Accordingly, determining the virtual guide lane lines in the target continuous image of the road based on the key road parameter values ​​of the road type includes:

[0028] When the road type is the non-intersection lane line staggered type, when the width parameter values ​​of any two adjacent lanes staggered from lane 5 are both within the preset lane width range, and the third angle parameter values ​​of any two adjacent lanes are both within the preset third angle range, and the second curvature radius parameter values ​​of any two adjacent lanes are both greater than or equal to the preset curvature radius threshold, a target lane is determined from the two adjacent lanes. Here, the third angle parameter value of any lane in any two adjacent lanes refers to the angle between the line connecting the end point of the target lane line from lane 5 and the start point of the target lane line of any lane and the target lane line from lane 5. The third angle parameter value of the target lane is less than or equal to the third angle parameter value of the other lane in the two adjacent lanes, and the second curvature radius parameter value of the target lane is less than or equal to the second curvature radius parameter value of the other lane in the two adjacent lanes.

[0029] In the target continuous image of the road, a virtual guide lane line is determined between the self-5 lane and the target lane.

[0030] Optionally, determining how the vehicle should travel according to the virtual guide lane based on the vehicle speed parameter value includes:

[0031] When the road type is a long intersection type, a first one-to-two type, or a second one-to-two type, the expected execution time and expected speed value are obtained based on the vehicle speed parameter value, and the vehicle is controlled to drive according to the virtual guide lane line based on the expected execution time and the expected speed value;

[0032] When the road type is a short intersection type or a non-intersection lane line staggered type, the vehicle is controlled to drive according to the virtual guide lane line based on the vehicle speed parameter value.

[0033] Optionally, determining how the vehicle should travel according to the virtual guide lane based on the vehicle speed parameter value includes:

[0034] The virtual forward range value and the virtual length value, absolute value of the virtual radius of curvature value, absolute value of the virtual lane width value, and pixel length value of the virtual guide lane line are obtained from the target continuous image of the road.

[0035] When the virtual forward range value is less than the preset virtual forward range threshold, the virtual length value is greater than the preset virtual length threshold, the absolute value of the virtual lane width value is less than the preset virtual lane width threshold, and the pixel length value is greater than the preset pixel length threshold, the virtual guide lane line shape type is determined.

[0036] When the morphology type is a lane change type, and the absolute value of the virtual radius of curvature is less than a preset first virtual radius of curvature threshold, the vehicle speed parameter value is used to determine how the vehicle should travel according to the virtual guide lane line.

[0037] When the morphology type is straight-line type, when the absolute value of the virtual radius of curvature is less than the preset second virtual radius of curvature threshold, the vehicle speed parameter value is used to determine how the vehicle should travel according to the virtual guide lane line, wherein the preset second virtual radius of curvature threshold is greater than the preset first virtual radius of curvature threshold.

[0038] According to a specific embodiment of this application, in a second aspect, this application provides a lateral control device for road vehicles, comprising:

[0039] The acquisition unit is used to acquire the perception parameter values ​​of the vehicle on the road, wherein the perception parameter values ​​include the vehicle speed parameter values;

[0040] A type determination unit is used to determine the road type of the road based on the perceived parameter values;

[0041] A parameter acquisition unit is used to obtain key road parameter values ​​for the road type based on the road type and the perception parameter values.

[0042] A guidance determination unit is used to determine virtual guide lane lines in a target continuous image of the road based on key road parameter values ​​of the road type;

[0043] An execution unit is used to determine how the vehicle should travel according to the virtual guide lane line based on the vehicle speed parameter value.

[0044] Optionally, determining the road type based on the perception parameter value includes:

[0045] When the perception parameter values ​​include a clear indication of the presence of the intersection stop line, an unobstructed view ahead, and a clear indication of perception segmentation, and when the vertical distance between the first stop line of the 5-lane road and the second stop line opposite the intersection is less than or equal to a preset short intersection distance threshold, the road type is determined to be a short intersection type.

[0046] When the perception parameter values ​​include a clear indication of the presence of the intersection stop line, an unobstructed view ahead, and a clear indication of perception segmentation, and when the vertical distance between the first stop line of the 5-lane road and the second stop line opposite the intersection is greater than a preset short intersection distance threshold, the road type is determined to be a long intersection type.

[0047] Accordingly, determining the virtual guide lane lines in the target continuous image of the road based on the key road parameter values ​​of the road type includes:

[0048] When the road type is either the short intersection type or the long intersection type, when the absolute value of the lateral distance deviation parameter between the target lane line of lane 5 and the target lane line of any lane traveling in the same direction opposite the intersection is less than or equal to a preset lateral distance deviation threshold, and the first angle parameter value is within a preset first angle range, a virtual guide lane line is determined in the target continuous image of the road between lane 5 and any lane. The first angle parameter value refers to the angle between the line connecting the first intersection point of lane 5 to the second intersection point of any lane and the first stop line of lane 5. The first intersection point refers to the intersection of the target lane line of lane 5 and the first stop line of lane 5, and the second intersection point refers to the intersection of the target lane line of any lane and the stop line of any lane.

[0049] Optionally, determining the virtual guide lane lines in the target continuous image of the road based on the key road parameter values ​​of the road type includes:

[0050] When the road type is either the short intersection type or the long intersection type, when the absolute value of the lateral distance deviation parameter between the target lane line of the 5-lane road and the target lane line of each lane traveling in the same direction opposite the intersection is greater than a preset lateral distance deviation threshold, when the width parameter values ​​of any two adjacent lanes are within a preset lane width range, and the second angle parameter values ​​of any two adjacent lanes are within a preset second angle range, and the first radius of curvature parameter values ​​of any two adjacent lanes are greater than or equal to a preset radius of curvature threshold, the target lane is determined from the two adjacent lanes, wherein the second angle parameter... The value refers to the angle between the line connecting the first intersection point of the five lanes to the second intersection point of any lane and the first stop line of the five lanes. The first intersection point is the intersection of the target lane line of the five lanes and the first stop line of the five lanes. The second intersection point is the intersection of the target lane line of any lane and the stop line of any lane. The second angle parameter value of the target lane is less than or equal to the second angle parameter value of the other lane among the two adjacent lanes, and the first radius of curvature parameter value of the target lane is less than or equal to the first radius of curvature parameter value of the other lane among the two adjacent lanes.

[0051] In the target continuous image of the road, a virtual guide lane line is determined between the self-5 lane and the target lane.

[0052] Optionally, determining the road type based on the perception parameter value includes:

[0053] When the perceived parameter values ​​include a clear indication of the existence of the two lane lines of lane 5, and the curvature radius parameter value of the right lane line of lane 5 is greater than or equal to a preset straight curvature radius threshold, and the loss length parameter value of the lost right lane line of lane 5 and the loss length parameter value of the lost left lane line of lane 5 are both less than or equal to a preset loss length threshold, and the incremental width parameter value of the current detection cycle is greater than a preset incremental width threshold, and the current width parameter value of lane 5 is greater than the current width parameter value of the adjacent left lane, and the inner angle parameter value of the road edge of the adjacent left lane is within a preset first inner angle range, the road type is determined to be the first one-two type, wherein the inner angle parameter value of the road edge of the adjacent left lane refers to the inner angle value between the left lane line of lane 5 and the straight line of the road edge of the adjacent left lane;

[0054] When the perceived parameter values ​​include a clear indication of the presence of the right lane line from lane 5, and the curvature radius parameter value of the right lane line from lane 5 is greater than or equal to a preset straight curvature radius threshold, and the loss length parameter value of the lost right lane line from lane 5 and the loss length parameter value of the lost left lane line from lane 5 are both less than or equal to a preset loss length threshold, and the incremental width parameter value of the current detection cycle is greater than a preset incremental width threshold, and the current width parameter value of lane 5 is greater than the current width parameter value of the adjacent left lane, and the inner angle parameter value of the road edge of the adjacent left lane is within a preset second inner angle range, the road type is determined to be a second one-to-two type, wherein the maximum angle value of the preset second inner angle range is greater than the maximum angle value of the preset first inner angle range;

[0055] Accordingly, determining the virtual guide lane lines in the target continuous image of the road based on the key road parameter values ​​of the road type includes:

[0056] When the road type is either the first one-to-two type or the second one-to-two type, a virtual guide lane line is determined in the target continuous image of the road based on the right lane line of the five lanes.

[0057] Optionally, determining the road type based on the perception parameter value includes:

[0058] When the perceived parameter value includes non-intersection sign and lane line misalignment sign, the road type is determined to be a non-intersection lane line misalignment type.

[0059] Accordingly, determining the virtual guide lane lines in the target continuous image of the road based on the key road parameter values ​​of the road type includes:

[0060] When the road type is the non-intersection lane line staggered type, when the width parameter values ​​of any two adjacent lanes staggered from lane 5 are both within the preset lane width range, and the third angle parameter values ​​of any two adjacent lanes are both within the preset third angle range, and the second curvature radius parameter values ​​of any two adjacent lanes are both greater than or equal to the preset curvature radius threshold, a target lane is determined from the two adjacent lanes. Here, the third angle parameter value of any lane in any two adjacent lanes refers to the angle between the line connecting the end point of the target lane line from lane 5 and the start point of the target lane line of any lane and the target lane line from lane 5. The third angle parameter value of the target lane is less than or equal to the third angle parameter value of the other lane in the two adjacent lanes, and the second curvature radius parameter value of the target lane is less than or equal to the second curvature radius parameter value of the other lane in the two adjacent lanes.

[0061] In the target continuous image of the road, a virtual guide lane line is determined between the self-5 lane and the target lane.

[0062] Optionally, determining how the vehicle should travel according to the virtual guide lane based on the vehicle speed parameter value includes:

[0063] When the road type is a long intersection type, a first one-to-two type, or a second one-to-two type, the expected execution time and expected speed value are obtained based on the vehicle speed parameter value, and the vehicle is controlled to drive according to the virtual guide lane line based on the expected execution time and the expected speed value;

[0064] When the road type is a short intersection type or a non-intersection lane line staggered type, the vehicle is controlled to drive according to the virtual guide lane line based on the vehicle speed parameter value.

[0065] Optionally, determining how the vehicle should travel according to the virtual guide lane based on the vehicle speed parameter value includes:

[0066] The virtual forward range value and the virtual length value, absolute value of the virtual radius of curvature value, absolute value of the virtual lane width value, and pixel length value of the virtual guide lane line are obtained from the target continuous image of the road.

[0067] When the virtual forward range value is less than the preset virtual forward range threshold, the virtual length value is greater than the preset virtual length threshold, the absolute value of the virtual lane width value is less than the preset virtual lane width threshold, and the pixel length value is greater than the preset pixel length threshold, the virtual guide lane line shape type is determined.

[0068] When the morphology type is a lane change type, and the absolute value of the virtual radius of curvature is less than a preset first virtual radius of curvature threshold, the vehicle speed parameter value is used to determine how the vehicle should travel according to the virtual guide lane line.

[0069] When the morphology type is straight-line type, when the absolute value of the virtual radius of curvature is less than the preset second virtual radius of curvature threshold, the vehicle speed parameter value is used to determine how the vehicle should travel according to the virtual guide lane line, wherein the preset second virtual radius of curvature threshold is greater than the preset first virtual radius of curvature threshold.

[0070] According to a specific embodiment of this application, in a third aspect, this application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the lateral control method for road vehicles as described in any of the preceding claims.

[0071] According to a specific embodiment of this application, in a fourth aspect, this application provides an electronic device, including: one or more processors; and a storage device for storing one or more programs, which, when executed by the one or more processors, cause the one or more processors to implement the lateral control method for road vehicles as described in any of the preceding claims.

[0072] Compared with the prior art, the above-described solutions of this application have at least the following beneficial effects:

[0073] This application provides a method, device, medium, and electronic device for lateral control of road vehicles. The application determines the road type using perceived parameter values; obtains key road parameter values ​​for the road type based on the road type and the perceived parameter values; determines virtual guide lane lines in a continuous target image of the road based on the key road parameter values; and determines how the vehicle should travel along the virtual guide lane lines based on the vehicle speed parameter values. This compensates for the instability of control in special road type scenarios and improves the continuity of lane keeping function usage. Attached Figure Description

[0074] Figure 1 A flowchart of a lateral control method for road vehicles according to an embodiment of this application is shown;

[0075] Figure 2 A schematic diagram of an intersection is shown, illustrating a lateral control method for road vehicles according to an embodiment of this application.

[0076] Figure 3 A schematic diagram of a road splitting method for lateral control of road vehicles according to an embodiment of this application is shown.

[0077] Figure 4 A schematic diagram of a non-intersection lane line staggered road is shown in the road lateral control method for road vehicles according to an embodiment of this application;

[0078] Figure 5 A schematic diagram of an unaligned intersection is shown, illustrating a lateral control method for road vehicles according to an embodiment of this application.

[0079] Figure 6 A unit block diagram of a lateral control device for a road vehicle according to an embodiment of this application is shown.

[0080] Explanation of reference numerals in the attached figures:

[0081] 1-Automobile, 2-Automobile 5-lane, 3-Virtual guide lane line, 4-Adjacent lane to the left;

[0082] 21 - Intersection, 22 - First stop line, 23 - Second stop line, 24 - First intersection point, 25 - Second intersection point;

[0083] 31 - Lost line in left lane; 32 - Lost line in right lane; 33 - Inner angle of curb.

[0084] 41 - Third angle. Detailed Implementation

[0085] To make the objectives, technical solutions, and advantages of this application clearer, the application will be further described in detail below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments in this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0086] The terminology used in the embodiments of this application is for the purpose of describing particular embodiments only and is not intended to limit the application. The singular forms “a,” “said,” and “the” used in the embodiments of this application and the appended claims are also intended to include the plural forms, and “multiple” generally includes at least two unless the context clearly indicates otherwise.

[0087] It should be understood that the term "and / or" used in this article is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, and B existing alone. Additionally, the character " / " in this article generally indicates that the preceding and following related objects have an "or" relationship.

[0088] It should be understood that although the terms first, second, third, etc., may be used in the embodiments of this application, these descriptions should not be limited to these terms. These terms are only used to distinguish the descriptions. For example, first may also be referred to as second without departing from the scope of the embodiments of this application, and similarly, second may also be referred to as first.

[0089] Depending on the context, the words “if” or “suppose” as used here can be interpreted as “when” or “in response to determination” or “in response to detection.” Similarly, depending on the context, the phrases “if determination” or “if detection (of the stated condition or event)” can be interpreted as “when determination” or “in response to determination” or “when detection (of the stated condition or event)” or “in response to detection (of the stated condition or event).”

[0090] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that an article or device that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such an article or device. Without further limitation, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the article or device that includes said element.

[0091] It should be noted that any symbols and / or numbers present in the specification that are not marked in the accompanying drawings are not reference numerals.

[0092] The optional embodiments of this application are described in detail below with reference to the accompanying drawings.

[0093] The embodiments provided in this application are embodiments of a lateral control method for road vehicles.

[0094] The following is combined Figure 1 The embodiments of this application will be described in detail.

[0095] Step S101: Obtain the perception parameter values ​​of vehicle 1 on the road.

[0096] Sensing parameter values ​​are the parameter values ​​of the road environment around the vehicle collected by sensors and cameras;

[0097] The sensing parameter values ​​include, but are not limited to, the vehicle speed parameter values.

[0098] Step S102: Determine the road type of the road based on the perceived parameter values.

[0099] This application embodiment identifies road types based on the perception parameter values ​​of the roads surrounding the vehicle. The purpose is to generate virtual guide lane lines 3 in a targeted manner according to different road types to assist vehicles in passing through special road sections safely and stably.

[0100] In some specific embodiments, such as Figure 2 As shown, determining the road type based on the perceived parameter values ​​includes:

[0101] Step S102a-1: When the perception parameter values ​​include a clear indication of the presence of the intersection stop line, an indication of no obstruction ahead, and a clear indication of perception segmentation, when the vertical distance between the first stop line 22 of lane 2 and the second stop line 23 opposite the intersection 21 is less than or equal to a preset short intersection distance threshold, the road type is determined to be a short intersection type.

[0102] Lane 2 is the lane in which vehicle 1 travels.

[0103] The preset short-intersection distance threshold is an empirical value obtained through experiments. For example, the preset short-intersection distance threshold is 10m.

[0104] Step S102a-2: When the perception parameter values ​​include a clear indication of the presence of the intersection stop line, an indication of no obstruction ahead, and a clear indication of perception segmentation, when the vertical distance between the first stop line 22 of lane 2 and the second stop line 23 opposite the intersection 21 is greater than a preset short intersection distance threshold, the road type is determined to be a long intersection type.

[0105] In some specific embodiments, such as Figure 3 As shown, determining the road type based on the perceived parameter values ​​includes:

[0106] Step S102b-1: When the perceived parameter values ​​include a clear indication of the existence of the two lane lines of lane 2, and the curvature radius parameter value of the right lane line of lane 2 is greater than or equal to a preset straight curvature radius threshold, and the loss length parameter values ​​of the right lane lost line 32 and the left lane lost line 31 of lane 2 are both less than or equal to a preset loss length threshold, and the incremental width parameter value of the current detection cycle is greater than a preset incremental width threshold, and the current width parameter value of lane 2 is greater than the current width parameter value of the adjacent left lane 4, and the inner angle parameter value of the road edge of the adjacent left lane is within a preset first inner angle range, the road type is determined to be the first one-two type.

[0107] The included angle parameter value of the adjacent left lane refers to the included angle value between the left lane line of lane 2 and the roadside line of the adjacent left lane.

[0108] For example, a preset straight line curvature radius threshold of 1000m indicates that the right lane line is a straight line.

[0109] The preset loss length threshold is an empirical value obtained through experimentation. For example, the preset loss length threshold is equal to 15m.

[0110] The incremental width parameter value refers to the difference between the lane width parameter value in the current detection cycle and the lane width parameter value in the preceding detection cycle. For example, the preset incremental width threshold is 1.5m.

[0111] The curb inner angle parameter value is the angle value of the curb inner angle 33. For example, the preset range of the first curb inner angle is [25°, 90°].

[0112] Step S102b-2: When the perceived parameter values ​​include a clear indication of the presence of the right lane line of lane 2, and the curvature radius parameter value of the right lane line of lane 2 is greater than or equal to a preset straight curvature radius threshold, and the loss length parameter values ​​of the right lane lost line 32 and the left lane lost line 31 of lane 2 are both less than or equal to a preset loss length threshold, and the incremental width parameter value of the current detection cycle is greater than a preset incremental width threshold, and the current width parameter value of lane 2 is greater than the current width parameter value of the adjacent left lane 4, and the inner angle parameter value of the curb of the adjacent left lane is within a preset second inner angle range, the road type is determined to be a second one-to-two type.

[0113] Wherein, the maximum included angle value of the preset second path inner included angle range is greater than the maximum included angle value of the preset first path inner included angle range. For example, the preset second path inner included angle range is [25°, 155°].

[0114] In some specific embodiments, such as Figure 4 As shown, determining the road type based on the perceived parameter values ​​includes:

[0115] Step S102c: When the perceived parameter value includes non-intersection sign and lane line misalignment sign, the road type is determined to be a non-intersection lane line misalignment type.

[0116] Step S103: Obtain the key road parameter values ​​of the road type based on the road type and the perception parameter values.

[0117] The key road parameter values ​​are calculated using the road type and the perception parameter values.

[0118] Step S104: Determine the virtual guide lane line 3 in the target continuous image of the road based on the key road parameter values ​​of the road type.

[0119] The continuous target image of the road can be a real-time video, with the virtual guide lane line 3 added to the real-time video to simulate real lane lines and assist vehicles in driving safely; the continuous target image can also be a dynamic image of the simulated road from a 3D electronic map, with the virtual guide lane line 3 added to the dynamic image of the simulated road from the 3D electronic map to become part of the 3D electronic map and used to guide vehicles in driving safely.

[0120] In some specific embodiments, such as Figure 2 As shown, determining the virtual guide lane line 3 in the target continuous image of the road based on the key road parameter values ​​of the road type includes:

[0121] Step S104a: When the road type is the short intersection type or the long intersection type, when the absolute value of the lateral distance deviation parameter value between the target lane line of the self lane 2 and the target lane line of any lane traveling in the same direction opposite the intersection 21 is less than or equal to a preset lateral distance deviation threshold, and the first angle parameter value is within a preset first angle range, a virtual guide lane line 3 between the self lane 2 and any lane is determined in the target continuous image of the road.

[0122] Wherein, the first angle parameter value refers to the angle value between the line connecting the first intersection point 24 of the lane 2 to the second intersection point 25 of any lane and the first stop line 22 of the lane 2, the first intersection point 24 refers to the intersection of the target lane line of the lane 2 and the first stop line 22 of the lane 2, and the second intersection point 25 refers to the intersection of the target lane line of any lane and the stop line of any lane.

[0123] The target lane line can be either the left lane line or the right lane line.

[0124] The preset lateral distance deviation threshold is an empirical value obtained through experimentation. For example, the preset lateral distance deviation threshold is equal to 0.3m.

[0125] The preset first angle range is an empirical range obtained through experimentation. For example, the preset first angle range is [88°, 92°].

[0126] In some specific embodiments, such as Figure 5 As shown, determining the virtual guide lane line 3 in the target continuous image of the road based on the key road parameter values ​​of the road type includes:

[0127] Step S104b-1: When the road type is the short intersection type or the long intersection type, when the absolute value of the lateral distance deviation parameter value between the target lane line of lane 2 and the target lane line of each lane traveling in the same direction opposite to the intersection 21 is greater than the preset lateral distance deviation threshold, when the width parameter value of any two adjacent lanes is within the preset lane width range, and the second angle parameter value of any two adjacent lanes is within the preset second angle range, and the first curvature radius parameter value of any two adjacent lanes is greater than or equal to the preset curvature radius threshold, the target lane is determined from the two adjacent lanes.

[0128] Wherein, the second angle parameter value refers to the angle value between the line connecting the first intersection point 24 of the lane 2 to the second intersection point 25 of any lane and the first stop line 22 of the lane 2, the first intersection point 24 refers to the intersection of the target lane line of the lane 2 and the first stop line 22 of the lane 2, and the second intersection point 25 refers to the intersection of the target lane line of any lane and the stop line of any lane; the second angle parameter value of the target lane is less than or equal to the second angle parameter value of the other lane among the two adjacent lanes, and the first radius of curvature parameter value of the target lane is less than or equal to the first radius of curvature parameter value of the other lane among the two adjacent lanes.

[0129] This specific embodiment is a road at an misaligned intersection.

[0130] The preset lane width range is an empirically determined range based on testing. For example, the preset lane width range is [2.4m, 5.5m]. This is to prevent the function from malfunctioning due to lane widths that are too large or too small.

[0131] The preset second angle range is an empirically determined range obtained through experimentation. For example, the preset second angle range is [30°, 150°]. This avoids the included angle of the virtual guide lane line 3 being too large or too small.

[0132] The preset radius of curvature threshold is an empirical value obtained through experimentation. For example, the preset radius of curvature threshold is equal to 600m. This ensures that the first radius of curvature parameter value is not too small, preventing unstable control and excessive steering wheel sway.

[0133] Step S104b-2: In the target continuous image of the road, determine the virtual guide lane line 3 between the self lane 2 and the target lane.

[0134] In some specific embodiments, such as Figure 3 As shown, determining the virtual guide lane line 3 in the target continuous image of the road based on the key road parameter values ​​of the road type includes:

[0135] Step S104c: When the road type is the first one-to-two type or the second one-to-two type, a virtual guide lane line 3 is determined in the target continuous image of the road based on the right lane line of the lane 2.

[0136] In some specific embodiments, determining the virtual guide lane line 3 in the target continuous image of the road based on the key road parameter values ​​of the road type includes:

[0137] Step S104d-1: When the road type is the non-intersection lane line staggered type, when the width parameter values ​​of any two adjacent lanes staggered in front of lane 2 are all within the preset lane width range, and the third angle parameter values ​​of any two adjacent lanes are all within the preset third angle range, and the second curvature radius parameter values ​​of any two adjacent lanes are all greater than or equal to the preset curvature radius threshold, the target lane is determined from the two adjacent lanes.

[0138] Wherein, the third angle parameter value of any lane in any two adjacent lanes refers to the angle between the line connecting the end point of the target lane line of lane 2 and the start point of the target lane line of any lane and the target lane line of lane 2. The third angle parameter value of the target lane is less than or equal to the third angle parameter value of the other lane in the two adjacent lanes, and the second radius of curvature parameter value of the target lane is less than or equal to the second radius of curvature parameter value of the other lane in the two adjacent lanes.

[0139] like Figure 4 As shown, the third angle parameter is the parameter value of the third angle 41.

[0140] The preset lane width range is an empirically determined range based on testing. For example, the preset lane width range is [2.4m, 5.5m]. This is to prevent the function from malfunctioning due to lane widths that are too large or too small.

[0141] The preset third angle range is an empirically determined range obtained through experimentation. For example, the preset third angle range is [150°, 250°]. This avoids the included angle of the virtual guide lane line 3 being too large or too small.

[0142] The preset radius of curvature threshold is an empirical value obtained through experimentation. For example, the preset radius of curvature threshold is equal to 600m. This ensures that the first radius of curvature parameter value is not too small, preventing unstable control and excessive steering wheel sway.

[0143] Step S104d-2: In the target continuous image of the road, determine the virtual guide lane line 3 between the self lane 2 and the target lane.

[0144] Step S105: Determine how the vehicle 1 should travel according to the virtual guide lane line 3 based on the vehicle speed parameter value.

[0145] In some specific embodiments, determining how the vehicle 1 should travel according to the virtual guide lane line 3 based on the vehicle speed parameter value includes:

[0146] Step S105a-1: When the road type is a long intersection type, a first one-to-two type, or a second one-to-two type, the expected execution time and expected speed value are obtained based on the vehicle speed parameter value, and the vehicle 1 is controlled to drive according to the virtual guide lane line 3 based on the expected execution time and the expected speed value.

[0147] By establishing the correspondence between the vehicle speed parameter value and the expected execution time and expected speed value, the expected execution time and expected speed value can be obtained by looking up the table using the vehicle speed parameter value.

[0148] Both the expected execution time and the expected speed are empirical values ​​obtained through experiments.

[0149] The system controls the vehicle 1 to travel along the virtual guide lane line 3 based on the expected execution duration and the expected speed value. That is, within the expected execution duration, the vehicle travels at the expected speed value and the virtual guide lane line 3; outside the expected execution duration, it can travel freely. This specific embodiment utilizes the expected execution duration and the expected speed value for lane keeping control.

[0150] Step S105a-2: When the road type is a short intersection type or a non-intersection 21 lane line staggered type, the vehicle 1 is controlled to drive according to the virtual guide lane line 3 based on the vehicle speed parameter value.

[0151] In some specific embodiments, determining how the vehicle 1 should travel according to the virtual guide lane line 3 based on the vehicle speed parameter value includes:

[0152] Step S105b-1: Obtain the virtual forward range value and the virtual length value, the absolute value of the virtual curvature radius value, the absolute value of the virtual lane width value, and the pixel length value of the virtual guide lane line 3 from the target continuous image of the road.

[0153] Step S105b-2: When the virtual forward range value is less than the preset virtual forward range threshold, the virtual length value is greater than the preset virtual length threshold, the absolute value of the virtual lane width value is less than the preset virtual lane width threshold, and the pixel length value is greater than the preset pixel length threshold, the virtual guide lane line 3 is determined to have a defined shape type.

[0154] The preset virtual forward range threshold, preset virtual length threshold, preset virtual lane width threshold, and preset pixel length threshold are all empirical values ​​obtained through experimentation. For example, the preset virtual forward range threshold is 20m, the preset virtual length threshold is 10m, the preset virtual lane width threshold is 6m, and the preset pixel length threshold is 150 pixels.

[0155] Step S105b-3: When the morphology type is a lane change type, when the absolute value of the virtual radius of curvature is less than the preset first virtual radius of curvature threshold, determine how the vehicle 1 should travel according to the virtual guide lane line 3 based on the vehicle speed parameter value.

[0156] The preset first virtual radius of curvature threshold is an empirical value obtained through experiments. For example, the preset first virtual radius of curvature threshold is equal to 3.3m.

[0157] Step S105b-4: When the morphology type is straight-line type, when the absolute value of the virtual radius of curvature is less than the preset second virtual radius of curvature threshold, determine how the vehicle 1 should travel according to the virtual guide lane line 3 based on the vehicle speed parameter value.

[0158] Wherein, the preset second virtual curvature radius threshold is greater than the preset first virtual curvature radius threshold.

[0159] The preset second virtual radius of curvature threshold is an empirical value obtained through experiments. For example, the preset second virtual radius of curvature threshold is equal to 10m.

[0160] In this specific embodiment, the virtual guide lane line 3 is checked before execution to avoid executing incorrect guidance.

[0161] This application embodiment determines the road type of the road by the perceived parameter values; obtains key road parameter values ​​for the road type based on the road type and the perceived parameter values; determines virtual guide lane lines 3 in the target continuous image of the road based on the key road parameter values; and determines how the vehicle 1 should drive according to the virtual guide lane lines 3 based on the vehicle speed parameter values. This compensates for the instability of control in special road type scenarios and improves the continuity of lane keeping function usage.

[0162] This application also provides an apparatus embodiment that follows the above embodiments, used to implement the method steps described in the above embodiments. The interpretation of the same names is the same as that in the above embodiments, and the same technical effects are achieved. Therefore, it will not be repeated here.

[0163] like Figure 6 As shown, this application provides a lateral control device 600 for road vehicles, comprising:

[0164] The acquisition unit 601 is used to acquire the perception parameter values ​​of the vehicle on the road, wherein the perception parameter values ​​include the vehicle speed parameter values;

[0165] Type determination unit 602 is used to determine the road type of the road based on the perception parameter value;

[0166] The parameter acquisition unit 603 is used to obtain key road parameter values ​​of the road type based on the road type and the sensing parameter values;

[0167] The guidance determination unit 604 is used to determine virtual guide lane lines in the target continuous image of the road based on the key road parameter values ​​of the road type;

[0168] The execution unit 605 is used to determine how the vehicle should travel according to the virtual guide lane line based on the vehicle speed parameter value.

[0169] Optionally, determining the road type based on the perception parameter value includes:

[0170] When the perception parameter values ​​include a clear indication of the presence of the intersection stop line, an unobstructed view ahead, and a clear indication of perception segmentation, and when the vertical distance between the first stop line of the 5-lane road and the second stop line opposite the intersection is less than or equal to a preset short intersection distance threshold, the road type is determined to be a short intersection type.

[0171] When the perception parameter values ​​include a clear indication of the presence of the intersection stop line, an unobstructed view ahead, and a clear indication of perception segmentation, and when the vertical distance between the first stop line of the 5-lane road and the second stop line opposite the intersection is greater than a preset short intersection distance threshold, the road type is determined to be a long intersection type.

[0172] Accordingly, determining the virtual guide lane lines in the target continuous image of the road based on the key road parameter values ​​of the road type includes:

[0173] When the road type is either the short intersection type or the long intersection type, when the absolute value of the lateral distance deviation parameter between the target lane line of lane 5 and the target lane line of any lane traveling in the same direction opposite the intersection is less than or equal to a preset lateral distance deviation threshold, and the first angle parameter value is within a preset first angle range, a virtual guide lane line is determined in the target continuous image of the road between lane 5 and any lane. The first angle parameter value refers to the angle between the line connecting the first intersection point of lane 5 to the second intersection point of any lane and the first stop line of lane 5. The first intersection point refers to the intersection of the target lane line of lane 5 and the first stop line of lane 5, and the second intersection point refers to the intersection of the target lane line of any lane and the stop line of any lane.

[0174] Optionally, determining the virtual guide lane lines in the target continuous image of the road based on the key road parameter values ​​of the road type includes:

[0175] When the road type is either the short intersection type or the long intersection type, when the absolute value of the lateral distance deviation parameter between the target lane line of the 5-lane road and the target lane line of each lane traveling in the same direction opposite the intersection is greater than a preset lateral distance deviation threshold, when the width parameter values ​​of any two adjacent lanes are within a preset lane width range, and the second angle parameter values ​​of any two adjacent lanes are within a preset second angle range, and the first radius of curvature parameter values ​​of any two adjacent lanes are greater than or equal to a preset radius of curvature threshold, the target lane is determined from the two adjacent lanes, wherein the second angle parameter... The value refers to the angle between the line connecting the first intersection point of the five lanes to the second intersection point of any lane and the first stop line of the five lanes. The first intersection point is the intersection of the target lane line of the five lanes and the first stop line of the five lanes. The second intersection point is the intersection of the target lane line of any lane and the stop line of any lane. The second angle parameter value of the target lane is less than or equal to the second angle parameter value of the other lane among the two adjacent lanes, and the first radius of curvature parameter value of the target lane is less than or equal to the first radius of curvature parameter value of the other lane among the two adjacent lanes.

[0176] In the target continuous image of the road, a virtual guide lane line is determined between the self-5 lane and the target lane.

[0177] Optionally, determining the road type based on the perception parameter value includes:

[0178] When the perceived parameter values ​​include a clear indication of the existence of the two lane lines of lane 5, and the curvature radius parameter value of the right lane line of lane 5 is greater than or equal to a preset straight curvature radius threshold, and the loss length parameter value of the lost right lane line of lane 5 and the loss length parameter value of the lost left lane line of lane 5 are both less than or equal to a preset loss length threshold, and the incremental width parameter value of the current detection cycle is greater than a preset incremental width threshold, and the current width parameter value of lane 5 is greater than the current width parameter value of the adjacent left lane, and the inner angle parameter value of the road edge of the adjacent left lane is within a preset first inner angle range, the road type is determined to be the first one-two type, wherein the inner angle parameter value of the road edge of the adjacent left lane refers to the inner angle value between the left lane line of lane 5 and the straight line of the road edge of the adjacent left lane;

[0179] When the perceived parameter values ​​include a clear indication of the presence of the right lane line from lane 5, and the curvature radius parameter value of the right lane line from lane 5 is greater than or equal to a preset straight curvature radius threshold, and the loss length parameter value of the lost right lane line from lane 5 and the loss length parameter value of the lost left lane line from lane 5 are both less than or equal to a preset loss length threshold, and the incremental width parameter value of the current detection cycle is greater than a preset incremental width threshold, and the current width parameter value of lane 5 is greater than the current width parameter value of the adjacent left lane, and the inner angle parameter value of the road edge of the adjacent left lane is within a preset second inner angle range, the road type is determined to be a second one-to-two type, wherein the maximum angle value of the preset second inner angle range is greater than the maximum angle value of the preset first inner angle range;

[0180] Accordingly, determining the virtual guide lane lines in the target continuous image of the road based on the key road parameter values ​​of the road type includes:

[0181] When the road type is either the first one-to-two type or the second one-to-two type, a virtual guide lane line is determined in the target continuous image of the road based on the right lane line of the five lanes.

[0182] Optionally, determining the road type based on the perception parameter value includes:

[0183] When the perceived parameter value includes non-intersection sign and lane line misalignment sign, the road type is determined to be a non-intersection lane line misalignment type.

[0184] Accordingly, determining the virtual guide lane lines in the target continuous image of the road based on the key road parameter values ​​of the road type includes:

[0185] When the road type is the non-intersection lane line staggered type, when the width parameter values ​​of any two adjacent lanes staggered from lane 5 are both within the preset lane width range, and the third angle parameter values ​​of any two adjacent lanes are both within the preset third angle range, and the second curvature radius parameter values ​​of any two adjacent lanes are both greater than or equal to the preset curvature radius threshold, a target lane is determined from the two adjacent lanes. Here, the third angle parameter value of any lane in any two adjacent lanes refers to the angle between the line connecting the end point of the target lane line from lane 5 and the start point of the target lane line of any lane and the target lane line from lane 5. The third angle parameter value of the target lane is less than or equal to the third angle parameter value of the other lane in the two adjacent lanes, and the second curvature radius parameter value of the target lane is less than or equal to the second curvature radius parameter value of the other lane in the two adjacent lanes.

[0186] In the target continuous image of the road, a virtual guide lane line is determined between the self-5 lane and the target lane.

[0187] Optionally, determining how the vehicle should travel according to the virtual guide lane based on the vehicle speed parameter value includes:

[0188] When the road type is a long intersection type, a first one-to-two type, or a second one-to-two type, the expected execution time and expected speed value are obtained based on the vehicle speed parameter value, and the vehicle is controlled to drive according to the virtual guide lane line based on the expected execution time and the expected speed value;

[0189] When the road type is a short intersection type or a non-intersection lane line staggered type, the vehicle is controlled to drive according to the virtual guide lane line based on the vehicle speed parameter value.

[0190] Optionally, determining how the vehicle should travel according to the virtual guide lane based on the vehicle speed parameter value includes:

[0191] The virtual forward range value and the virtual length value, absolute value of the virtual radius of curvature value, absolute value of the virtual lane width value, and pixel length value of the virtual guide lane line are obtained from the target continuous image of the road.

[0192] When the virtual forward range value is less than the preset virtual forward range threshold, the virtual length value is greater than the preset virtual length threshold, the absolute value of the virtual lane width value is less than the preset virtual lane width threshold, and the pixel length value is greater than the preset pixel length threshold, the virtual guide lane line shape type is determined.

[0193] When the morphology type is a lane change type, and the absolute value of the virtual radius of curvature is less than a preset first virtual radius of curvature threshold, the vehicle speed parameter value is used to determine how the vehicle should travel according to the virtual guide lane line.

[0194] When the morphology type is straight-line type, when the absolute value of the virtual radius of curvature is less than the preset second virtual radius of curvature threshold, the vehicle speed parameter value is used to determine how the vehicle should travel according to the virtual guide lane line, wherein the preset second virtual radius of curvature threshold is greater than the preset first virtual radius of curvature threshold.

[0195] This application embodiment determines the road type of the road by the perceived parameter values; obtains key road parameter values ​​for the road type based on the road type and the perceived parameter values; determines virtual guide lane lines in the target continuous image of the road based on the key road parameter values; and determines how the vehicle should drive according to the virtual guide lane lines based on the vehicle speed parameter values. This compensates for the instability of control in special road type scenarios and improves the continuity of lane keeping function usage.

[0196] Example 3

[0197] This embodiment provides an electronic device, comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, the instructions being executed by the at least one processor to enable the at least one processor to perform the method steps described in the above embodiment.

[0198] Example 4

[0199] This application provides a non-volatile computer storage medium storing computer-executable instructions that can perform the steps described in the above embodiments.

[0200] Finally, it should be noted that the various embodiments in this specification are described in a progressive manner, with each embodiment focusing on its differences from other embodiments. Similar or identical parts between embodiments can be referred to interchangeably. For the systems or apparatus disclosed in the embodiments, since they correspond to the methods disclosed in the embodiments, the descriptions are relatively simple, and relevant parts can be referred to the method section.

[0201] The above embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application.

Claims

1. A method for lateral control of road vehicles, characterized in that, include: Obtain the perception parameter values ​​of the vehicle (1) on the road, wherein the perception parameter values ​​include the vehicle speed parameter values; The road type of the road is determined based on the perceived parameter values; Based on the road type and the sensing parameter values, obtain the key road parameter values ​​for the road type; Based on the key road parameter values ​​of the road type, determine the virtual guide lane line in the target continuous image of the road (3); Based on the vehicle speed parameter value, determine how the vehicle (1) travels according to the virtual guide lane line (3); in, When the road type is a short intersection or a long intersection, the key road parameter values ​​are the lateral distance deviation parameter value between the target lane line of the self-lane and the target lane line of any lane traveling in the same direction opposite the intersection, and the first angle parameter value. The first angle parameter value refers to the angle between the line connecting the first intersection point of the self-lane to the second intersection point of the any lane and the first stop line of the self-lane. The first intersection point refers to the intersection point of the target lane line of the self-lane and the first stop line of the self-lane, and the second intersection point refers to the intersection point of the target lane line of the any lane and the stop line of the any lane. When the road type is either the first one-to-two type or the second one-to-two type, the key road parameter value is the right lane line of the self-lane in the target continuous image of the road; When the road type is a non-intersection lane line staggered type, the key road parameter values ​​are the width parameter values ​​of each of the two adjacent lanes staggered in front of the self lane, the third angle parameter values ​​of each of the two adjacent lanes, and the second radius of curvature parameter values ​​of each of the two adjacent lanes. The third angle parameter value of any lane in the two adjacent lanes refers to the angle between the line connecting the end point of the target lane line of the self lane and the start point of the target lane line of the other lane and the target lane line of the self lane. The third angle parameter value of the target lane is less than or equal to the third angle parameter value of the other lane in the two adjacent lanes, and the second radius of curvature parameter value of the target lane is less than or equal to the second radius of curvature parameter value of the other lane in the two adjacent lanes.

2. The method according to claim 1, characterized in that, Determining the road type based on the perceived parameter values ​​includes: When the perception parameter values ​​include a clear indication of the presence of the intersection stop line, an unobstructed sign ahead, and a clear indication of perception segmentation, when the vertical distance between the first stop line (22) of the lane (2) and the second stop line (23) opposite the intersection (21) is less than or equal to a preset short intersection distance threshold, the road type is determined to be a short intersection type. When the perception parameter values ​​include a clear indication of the presence of the intersection stop line, an unobstructed sign ahead, and a clear indication of perception segmentation, when the vertical distance between the first stop line (22) of the lane (2) and the second stop line (23) opposite the intersection (21) is greater than a preset short intersection distance threshold, the road type is determined to be a long intersection type. Accordingly, determining the virtual guide lane line (3) in the target continuous image of the road based on the key road parameter values ​​of the road type includes: When the road type is the short intersection type or the long intersection type, when the absolute value of the lateral distance deviation parameter value between the target lane line of the self lane (2) and the target lane line of any lane traveling in the same direction opposite the intersection (21) is less than or equal to the preset lateral distance deviation threshold, and the first angle parameter value is within the preset first angle range, a virtual guide lane line (3) between the self lane (2) and any lane is determined in the target continuous image of the road.

3. The method according to claim 2, characterized in that, The determination of the virtual guide lane line (3) in the target continuous image of the road based on the key road parameter values ​​of the road type includes: When the road type is the short intersection type or the long intersection type, when the absolute value of the lateral distance deviation parameter value between the target lane line of the lane (2) and the target lane line of each lane traveling in the same direction opposite the intersection (21) is greater than the preset lateral distance deviation threshold, when the width parameter value of each of any two adjacent lanes is within the preset lane width range, and the second angle parameter value of each of any two adjacent lanes is within the preset second angle range, and the first curvature radius parameter value of each of any two adjacent lanes is greater than or equal to the preset curvature radius threshold, the target lane is determined from the two adjacent lanes, wherein the second angle parameter value refers to the first curvature radius parameter value of the lane (2). The angle value between the line connecting the first intersection point (24) to the second intersection point (25) of any lane and the first stop line (22) of the lane (2), wherein the first intersection point (24) is the intersection of the target lane line of the lane (2) and the first stop line (22) of the lane (2), and the second intersection point (25) is the intersection of the target lane line of any lane and the stop line of any lane; the second angle parameter value of the target lane is less than or equal to the second angle parameter value of the other lane among the two adjacent lanes, and the first radius of curvature parameter value of the target lane is less than or equal to the first radius of curvature parameter value of the other lane among the two adjacent lanes; In the target continuous image of the road, a virtual guide lane line (3) is determined between the self lane (2) and the target lane.

4. The method according to claim 1, characterized in that, Determining the road type based on the perceived parameter values ​​includes: When the perceived parameter values ​​include a clear indication of the existence of the two lane lines of the self lane (2), and the curvature radius parameter value of the right lane line of the self lane (2) is greater than or equal to a preset straight curvature radius threshold, and the loss length parameter value of the right lane loss line (32) of the self lane (2) and the loss length parameter value of the left lane loss line (31) of the self lane (2) are both less than or equal to a preset loss length threshold, and the incremental width parameter value of the current detection cycle is greater than a preset incremental width threshold, and the current width parameter value of the self lane (2) is greater than the current width parameter value of the left adjacent lane (4), and the inner angle parameter value of the road edge of the adjacent left lane is within the preset first inner angle range, the road type is determined to be the first one-two type, wherein the inner angle parameter value of the road edge of the adjacent left lane refers to the inner angle value between the left lane line of the self lane (2) and the road edge straight line of the adjacent left lane; When the perceived parameter value includes a clear presence of the right lane line of the lane (2), and the curvature radius parameter value of the right lane line of the lane (2) is greater than or equal to a preset straight curvature radius threshold, and the loss length parameter value of the right lane lost line (32) of the lane (2) and the loss length parameter value of the left lane lost line (31) of the lane (2) are both less than or equal to a preset loss length threshold, and the incremental width parameter value of the current detection cycle is greater than a preset incremental width threshold, and the current width parameter value of the lane (2) is greater than the current width parameter value of the adjacent left lane (4), and the inner angle parameter value of the road edge of the adjacent left lane is within a preset second inner angle range, the road type is determined to be the second one-to-two type, wherein the maximum angle value of the preset second inner angle range is greater than the maximum angle value of the preset first inner angle range; Accordingly, determining the virtual guide lane line (3) in the target continuous image of the road based on the key road parameter values ​​of the road type includes: When the road type is the first one-to-two type or the second one-to-two type, a virtual guide lane line (3) is determined in the target continuous image of the road based on the right lane line of the self lane (2).

5. The method according to claim 1, characterized in that, Determining the road type based on the perceived parameter values ​​includes: When the perceived parameter value includes non-intersection sign and lane line misalignment sign, the road type is determined to be a non-intersection lane line misalignment type. Accordingly, determining the virtual guide lane line (3) in the target continuous image of the road based on the key road parameter values ​​of the road type includes: When the road type is the non-intersection lane line staggered type, when the width parameter value of each of the two adjacent lanes staggered in front of lane (2) is within the preset lane width range, and the third angle parameter value of each of the two adjacent lanes is within the preset third angle range, and the second curvature radius parameter value of each of the two adjacent lanes is greater than or equal to the preset curvature radius threshold, the target lane is determined from the two adjacent lanes. In the target continuous image of the road, a virtual guide lane line (3) is determined between the self lane (2) and the target lane.

6. The method according to claim 1, characterized in that, The process of determining how the vehicle (1) should travel according to the virtual guide lane line (3) based on the vehicle speed parameter value includes: When the road type is a long intersection type, a first one-to-two type, or a second one-to-two type, the expected execution time and expected speed value are obtained based on the vehicle speed parameter value, and the vehicle (1) is controlled to drive according to the virtual guide lane line (3) based on the expected execution time and the expected speed value; When the road type is a short intersection type or a non-intersection lane line staggered type, the vehicle (1) is controlled to drive according to the virtual guide lane line (3) based on the vehicle speed parameter value.

7. The method according to claim 1, characterized in that, The process of determining how the vehicle (1) should travel according to the virtual guide lane line (3) based on the vehicle speed parameter value includes: The virtual forward range value and the virtual length value, the absolute value of the virtual radius of curvature value, the absolute value of the virtual lane width value and the pixel length value of the virtual guide lane line (3) are obtained from the target continuous image of the road. When the virtual forward range value is less than the preset virtual forward range threshold, the virtual length value is greater than the preset virtual length threshold, the absolute value of the virtual lane width value is less than the preset virtual lane width threshold, and the pixel length value is greater than the preset pixel length threshold, the virtual guide lane line is determined (3) to determine the shape type; When the morphology type is a lane change type, when the absolute value of the virtual radius of curvature is less than the preset first virtual radius of curvature threshold, the vehicle (1) is determined to drive according to the virtual guide lane line (3) based on the vehicle speed parameter value. When the morphology type is straight, when the absolute value of the virtual curvature radius value is less than the preset second virtual curvature radius threshold, the vehicle (1) is determined to drive according to the virtual guide lane line (3) based on the vehicle speed parameter value, wherein the preset second virtual curvature radius threshold is greater than the preset first virtual curvature radius threshold.

8. A lateral control device for road vehicles, characterized in that, include: The acquisition unit is used to acquire the perception parameter values ​​of the vehicle on the road, wherein the perception parameter values ​​include the vehicle speed parameter values; A type determination unit is used to determine the road type of the road based on the perceived parameter values; A parameter acquisition unit is used to obtain key road parameter values ​​for the road type based on the road type and the perception parameter values. A guidance determination unit is used to determine virtual guide lane lines in a target continuous image of the road based on key road parameter values ​​of the road type; An execution unit is configured to determine how the vehicle should travel along the virtual guide lane lines based on the vehicle speed parameter value. in, When the road type is a short intersection or a long intersection, the key road parameter values ​​are the lateral distance deviation parameter value between the target lane line of the self-lane and the target lane line of any lane traveling in the same direction opposite the intersection, and the first angle parameter value. The first angle parameter value refers to the angle between the line connecting the first intersection point of the self-lane to the second intersection point of the any lane and the first stop line of the self-lane. The first intersection point refers to the intersection point of the target lane line of the self-lane and the first stop line of the self-lane, and the second intersection point refers to the intersection point of the target lane line of the any lane and the stop line of the any lane. When the road type is either the first one-to-two type or the second one-to-two type, the key road parameter value is the right lane line of the self-lane in the target continuous image of the road; When the road type is a non-intersection lane line staggered type, the key road parameter values ​​are the width parameter values ​​of each of the two adjacent lanes staggered in front of the self lane, the third angle parameter values ​​of each of the two adjacent lanes, and the second radius of curvature parameter values ​​of each of the two adjacent lanes. The third angle parameter value of any lane in the two adjacent lanes refers to the angle between the line connecting the end point of the target lane line of the self lane and the start point of the target lane line of the other lane and the target lane line of the self lane. The third angle parameter value of the target lane is less than or equal to the third angle parameter value of the other lane in the two adjacent lanes, and the second radius of curvature parameter value of the target lane is less than or equal to the second radius of curvature parameter value of the other lane in the two adjacent lanes.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the program is executed by the processor, it implements the method as described in any one of claims 1 to 7.

10. An electronic device, characterized in that, include: One or more processors; Storage device for storing one or more programs. Wherein, when the one or more programs are executed by the one or more processors, the one or more processors implement the method as described in any one of claims 1 to 7.

Images