Smoothing Optimization Method, Device and Electronic Equipment for Lane Center Line

Abstract

The present invention provides a method, apparatus and electronic device for smoothing and optimizing a lane center line. In the method for smoothing and optimizing the lane center line, a smoothed and optimized right-turn lane center line is formed by combining a Bézier curve and a right-turn lane center line. The curvature of the smoothed and optimized right-turn lane center line meets a first preset condition and the lateral distance from the inner lane inflection point meets a second preset condition, which can meet the requirement of the minimum turning radius of an autonomous driving vehicle, and can be used as a reference path for an autonomous driving planning algorithm. Moreover, the process of smoothing and optimization is simple and the computational amount is small, which alleviates the technical problems of large computational amount and complex calculation in the existing method for smoothing and optimizing the lane center line.

Description

Technical Field

[0001] The present invention relates to the technical field of autonomous driving, and in particular, to a method, device, and electronic device for smoothing and optimizing a lane center line. Background Art

[0002] Existing autonomous driving planning algorithms often use the lane center line as a reference path and perform path planning based on the SD coordinate system. These autonomous driving planning algorithms have strict requirements for the curvature of the lane center line (i.e., the reference path) (the curvature should be less than the reciprocal of the minimum turning radius of the vehicle). If the curvature of a certain point on the lane center line does not meet the minimum turning radius of the controlled vehicle, then these autonomous driving planning algorithms cannot be applied.

[0003] In outdoor road scenarios, the curvature of the lane center line at curves often meets the turning radius requirements of vehicles; while in the scenario of a narrow underground parking lot, if the lane center line is directly used as the reference path, the curvature at the turning point is extremely large and discontinuous, and the turning radius of a right turn is only 1.5 meters (as Figure 1 shown, Figure 1 two lanes are shown, where the dashed line and the solid line on its right represent the first lane, and the dashed line and the leftmost solid line represent the second lane. The solid line in the second lane is the lane center line), which is much smaller than the minimum turning radius of common vehicles. Therefore, the autonomous driving planning algorithm based on the SD reference coordinate system cannot be applied.

[0004] In order to make the curvature of the lane center line in the narrow underground parking lot scenario meet the minimum turning radius of the controlled vehicle, it is necessary to smooth and optimize the lane center line. Currently, the method of combining constraint terms with objective function optimization is often used to smooth and optimize the lane center line, which consumes a large amount of computing power and cannot even converge in some complex and large scenarios.

[0005] In summary, the existing methods for smoothing and optimizing the lane center line have the technical problems of large computational amount and complex calculation. Summary of the Invention

[0006] In view of this, the purpose of the present invention is to provide a method, device, and electronic device for smoothing and optimizing a lane center line to alleviate the technical problems of large computational amount and complex calculation in the existing methods for smoothing and optimizing the lane center line.

[0007] In a first aspect, an embodiment of the present invention provides a method for smoothing and optimizing a lane center line, including:

[0008] When determining that the target lane center line in the environmental map according to the target scenario is the right-turn lane center line, obtain preset vertices and construct a Bezier curve based on the vertices, where the number of the vertices is at least six, and among the vertices, at least two vertices coincide with one side of the right-turn lane center line, and at least two other vertices coincide with the other side of the right-turn lane center line;

[0009] Detect the curvature of the constructed Bezier curve and the lateral distance between the Bezier curve and the inner lane inflection point corresponding to the right-turn lane center line;

[0010] Judge whether the curvature meets the first preset condition and judge whether the lateral distance meets the second preset condition, where the first preset condition is related to the minimum turning radius of the autonomous vehicle;

[0011] If the curvature meets the first preset condition and the lateral distance meets the second preset condition, connect the Bezier curve with the right-turn lane center line at both ends of the Bezier curve, and then obtain the smoothly optimized right-turn lane center line;

[0012] If the curvature does not meet the first preset condition, and / or the lateral distance does not meet the second preset condition, adjust the vertices, construct a Bezier curve based on the adjusted vertices, and return to execute the steps of detecting the curvature of the constructed Bezier curve and the lateral distance between the Bezier curve and the inner lane inflection point corresponding to the right-turn lane center line until the curvature meets the first preset condition and the lateral distance meets the second preset condition.

[0013] Further, detecting the curvature of the constructed Bezier curve and the lateral distance between the Bezier curve and the inner lane inflection point corresponding to the right-turn lane center line includes:

[0014] Determine a plurality of target discrete points at preset intervals on the Bezier curve;

[0015] Detect the curvature of the Bezier curve at each of the target discrete points, and then obtain a plurality of the curvatures;

[0016] Determine the tangent line of the Bezier curve at each of the target discrete points, and detect the distance from the inner lane inflection point to each of the tangent lines, and then obtain a plurality of the lateral distances.

[0017] Further, the first preset condition is the condition that each of the curvatures is less than a first preset threshold, the second preset condition is the condition that each of the lateral distances is greater than a second preset threshold, the first preset threshold is the reciprocal of the minimum turning radius of the autonomous vehicle, and the second preset threshold is related to the width of the autonomous vehicle.

[0018] Further, when the number of the vertices is six, along the driving direction of the autonomous vehicle, a first vertex, a second vertex, a third vertex, a fourth vertex, a fifth vertex, and a sixth vertex are included in sequence, wherein the first vertex and the second vertex coincide with one side of the center line of the right-turn lane, the fifth vertex and the sixth vertex coincide with the other side of the center line of the right-turn lane, the third vertex is located above the left of the second vertex, the fourth vertex is located above the right of the third vertex, and the fourth vertex is located above the left of the fifth vertex.

[0019] Further, if the coordinates of the inflection point of the inner lane are (1.5, 4.5), the relative coordinates of the first vertex with respect to the inflection point of the inner lane are (-1.5, -8.5), the relative coordinates of the second vertex with respect to the inflection point of the inner lane are (-1.5, -4.5), the relative coordinates of the third vertex with respect to the inflection point of the inner lane are (-6, -0.5), the relative coordinates of the fourth vertex with respect to the inflection point of the inner lane are (0.5, 6), the relative coordinates of the fifth vertex with respect to the inflection point of the inner lane are (4.5, 1.5), and the relative coordinates of the sixth vertex with respect to the inflection point of the inner lane are (8.5, 1.5);

[0020] Adjusting the vertices includes:

[0021] If the curvature does not meet the first preset condition, the third vertex is adjusted to be close to the second vertex along the direction of the line segment formed by the third vertex and the second vertex, and the fourth vertex is adjusted to be close to the fifth vertex along the direction of the line segment formed by the fourth vertex and the fifth vertex;

[0022] If the lateral distance does not meet the second preset condition, the third vertex is adjusted to be away from the second vertex along the direction of the line segment formed by the second vertex and the third vertex, and the fourth vertex is adjusted to be away from the fifth vertex along the direction of the line segment formed by the fifth vertex and the fourth vertex.

[0023] Further, the method further includes:

[0024] Using the center line of the right-turn lane after smooth optimization as the reference path of the autonomous driving planning algorithm.

[0025] Further, the target scenario at least includes: an underground parking lot scenario where the width of a single lane is not greater than a third preset threshold.

[0026] In a second aspect, an embodiment of the present invention further provides a smooth optimization device for a lane center line, including:

[0027] An acquisition and construction unit, configured to, when determining that the target lane center line in the environmental map of the target scenario is a right-turn lane center line, acquire preset vertices and construct a Bezier curve according to the vertices, where the number of the vertices is at least six, and among the vertices, at least two vertices coincide with one side of the right-turn lane center line, and at least two other vertices coincide with the other side of the right-turn lane center line;

[0028] A detection unit, configured to detect the curvature of the constructed Bezier curve and the lateral distance between the Bezier curve and the inner lane inflection point corresponding to the right-turn lane center line;

[0029] A judgment unit, configured to judge whether the curvature meets a first preset condition and judge whether the lateral distance meets a second preset condition, where the first preset condition is related to the minimum turning radius of an autonomous vehicle;

[0030] A connection unit, configured to, if the curvature meets the first preset condition and the lateral distance meets the second preset condition, connect the Bezier curve with the right-turn lane center line located at both ends of the Bezier curve, so as to obtain a smoothly optimized right-turn lane center line;

[0031] An adjustment unit, configured to, if the curvature does not meet the first preset condition, or the lateral distance does not meet the second preset condition, adjust the vertices, construct a Bezier curve according to the adjusted vertices, and return to execute the step of detecting the curvature of the constructed Bezier curve and the lateral distance between the Bezier curve and the inner lane inflection point corresponding to the right-turn lane center line until the curvature meets the first preset condition and the lateral distance meets the second preset condition.

[0032] In a third aspect, an embodiment of the present invention further provides an electronic device, including a memory, a processor, and a computer program stored on the memory and executable on the processor, where when the processor executes the computer program, the steps of the method according to any one of the first aspects are implemented.

[0033] Fourthly, an embodiment of the present invention further provides a computer-readable storage medium storing machine-executable instructions, which, when called and executed by a processor, cause the processor to execute the method according to any one of the above first aspects.

[0034] In an embodiment of the present invention, a method for smoothing and optimizing a lane center line is provided, including: when determining that the target lane center line in the environmental map of the target scenario is a right-turn lane center line, obtaining preset vertices and constructing a Bezier curve according to the vertices, where the number of vertices is at least six, and among the vertices, at least two vertices coincide with one side of the right-turn lane center line, and at least two other vertices coincide with the other side of the right-turn lane center line; detecting the curvature of the constructed Bezier curve and the lateral distance between the Bezier curve and the inner lane inflection point corresponding to the right-turn lane center line; determining whether the curvature meets a first preset condition and whether the lateral distance meets a second preset condition, where the first preset condition is related to the minimum turning radius of the autonomous vehicle; if the curvature meets the first preset condition and the lateral distance meets the second preset condition, connecting the Bezier curve with the right-turn lane center line at both ends of the Bezier curve to obtain a smoothly optimized right-turn lane center line; if the curvature does not meet the first preset condition and / or the lateral distance does not meet the second preset condition, adjusting the vertices and constructing a Bezier curve according to the adjusted vertices, and returning to execute the steps of detecting the curvature of the constructed Bezier curve and the lateral distance between the Bezier curve and the inner lane inflection point corresponding to the right-turn lane center line until the curvature meets the first preset condition and the lateral distance meets the second preset condition. It can be seen from the above description that in the method for smoothing and optimizing the lane center line of the present invention, the smoothly optimized right-turn lane center line is formed by combining the Bezier curve and the right-turn lane center line. The curvature of the smoothly optimized right-turn lane center line meets the first preset condition and the lateral distance from the inner lane inflection point meets the second preset condition, which can meet the requirements of the minimum turning radius of the autonomous vehicle, and can be used as a reference path for the autonomous driving planning algorithm. Moreover, the above process of smoothing and optimizing is simple and has a small amount of calculation, alleviating the technical problems of large calculation amount and complex calculation in the existing method for smoothing and optimizing the lane center line. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] In order to more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the following will briefly introduce the drawings required for the description of the specific embodiments or the prior art. Obviously, the following drawings are some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0036] Figure 1 Schematic diagram of two lanes and the lane center line provided by an embodiment of the present invention;

[0037] Figure 2 Flowchart of a method for smoothing and optimizing a lane center line provided by an embodiment of the present invention;

[0038] Figure 3 Schematic diagram of preset vertices provided by an embodiment of the present invention;

[0039] Figure 4 Schematic diagram of a Bezier curve constructed based on preset vertices provided by an embodiment of the present invention;

[0040] Figure 5 Schematic diagram of the right - turn lane center line after smoothing and optimization provided by an embodiment of the present invention;

[0041] Figure 6 Flowchart of detecting the curvature of the constructed Bezier curve and the lateral distance between the Bezier curve and the inner - lane inflection point corresponding to the right - turn lane center line provided by an embodiment of the present invention;

[0042] Figure 7 Schematic diagram of a device for smoothing and optimizing a lane center line provided by an embodiment of the present invention;

[0043] Figure 8 Schematic diagram of an electronic device provided by an embodiment of the present invention. Detailed implementation manners

[0044] Next, the technical solutions of the present invention will be clearly and completely described in conjunction with the embodiments. Obviously, the described embodiments are part of the embodiments of the present invention, rather than all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0045] In the prior art, the method of combining constraint terms with objective - function optimization is often used for smoothing and optimizing the lane center line, which has a large amount of calculation and is computationally complex.

[0046] Based on this, in the method for smoothing and optimizing the lane center line of the present invention, the smoothed and optimized right - turn lane center line is formed by combining a Bezier curve and the right - turn lane center line. The curvature of the smoothed and optimized right - turn lane center line meets the first preset condition and the lateral distance from the inner - lane inflection point meets the second preset condition, which can meet the requirements of the minimum turning radius of an autonomous driving vehicle, and the above - mentioned smoothing and optimizing process is simple and has a small amount of calculation.

[0047] To facilitate the understanding of this embodiment, first, a smooth optimization method for a lane center line disclosed in the embodiments of the present invention will be introduced in detail.

[0048] Embodiment 1:

[0049] According to the embodiments of the present invention, an embodiment of a smooth optimization method for a lane center line is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions. And although the logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in a different order than here.

[0050] Figure 2 is a flowchart of a smooth optimization method for a lane center line according to the embodiments of the present invention. As Figure 2 shown, the method includes the following steps:

[0051] Step S202, when determining that the target lane center line in the environmental map of the target scenario is the right-turn lane center line, obtain preset vertices and construct a Bezier curve based on the vertices. Among them, the number of vertices is at least six, and among the vertices, at least two vertices coincide with one side of the right-turn lane center line, and at least two other vertices coincide with the other side of the right-turn lane center line;

[0052] In the embodiments of the present invention, the above target scenario at least includes: an underground parking lot scenario where the width of a single lane is not greater than a third preset threshold, that is, a narrow underground parking lot scenario. The above third preset threshold is generally 3 meters. The embodiments of the present invention do not specifically limit the above target scenario, and it can also be other narrow right-turn scenarios. The method of the present invention is a process of smoothly optimizing the right-turn lane center line included in the environmental map of the target scenario after constructing the environmental map of the target scenario. It is not executed on an autonomous vehicle, but is completed on other computing devices before the autonomous vehicle travels.

[0053] The above target lane center line is any lane center line in the environmental map of the target scenario. The present invention performs smooth optimization on the right-turn lane center line. The reason for performing smooth optimization on the right-turn lane center line is that an autonomous vehicle travels along the right side (as Figure 1 shown, the autonomous vehicle is traveling in the second lane, and only when turning right will the turning radius be less than the minimum turning radius of the vehicle. Therefore, the right-turn lane center line needs to be smoothly optimized). Only the curvature of the right-turn lane center line does not meet the turning radius requirements of the vehicle. When turning left, it is a large turn, and the curvature of the left-turn lane center line meets the turning radius requirements of the vehicle. Therefore, only the right-turn lane center line needs to be smoothly optimized.

[0054] The above preset vertices are preset by the inventor based on experience. They are the theoretical values of the vertices determined by the inventor after adjusting the vertex parameters multiple times in the environmental map of the target scenario, so as to ensure that the curvature of the Bezier curve constructed based on the vertices and the lateral distance from the inflection point of the inner lane corresponding to the center line of the right-turn lane meet their respective preset conditions.

[0055] Figure 3 The schematic diagram of the preset vertices is shown when the number of vertices is six. Figure 4 The schematic diagram of the Bezier curve constructed according to the preset vertices is shown.

[0056] Step S204: Detect the curvature of the constructed Bezier curve and the lateral distance between the Bezier curve and the inflection point of the inner lane corresponding to the center line of the right-turn lane.

[0057] Step S206: Judge whether the curvature meets the first preset condition and whether the lateral distance meets the second preset condition, where the first preset condition is related to the minimum turning radius of the autonomous vehicle.

[0058] Step S208: If the curvature meets the first preset condition and the lateral distance meets the second preset condition, then connect the Bezier curve with the center lines of the right-turn lane at both ends of the Bezier curve, and then obtain the center line of the right-turn lane after smooth optimization.

[0059] Figure 5 The schematic diagram of the center line of the right-turn lane after smooth optimization is shown.

[0060] Step S210: If the curvature does not meet the first preset condition and / or the lateral distance does not meet the second preset condition, then adjust the vertices, construct a Bezier curve according to the adjusted vertices, and return to execute the step of detecting the curvature of the constructed Bezier curve and the lateral distance between the Bezier curve and the inflection point of the inner lane corresponding to the center line of the right-turn lane until the curvature meets the first preset condition and the lateral distance meets the second preset condition.

[0061] In an embodiment of the present invention, a method for smoothing and optimizing a lane center line is provided, including: when determining that the target lane center line in the environmental map of the target scenario is a right-turn lane center line, obtaining preset vertices and constructing a Bezier curve based on the vertices, where the number of vertices is at least six, and among the vertices, at least two vertices coincide with one side of the right-turn lane center line, and at least two other vertices coincide with the other side of the right-turn lane center line; detecting the curvature of the constructed Bezier curve and the lateral distance between the Bezier curve and the inner lane inflection point corresponding to the right-turn lane center line; determining whether the curvature meets a first preset condition and determining whether the lateral distance meets a second preset condition, where the first preset condition is related to the minimum turning radius of the autonomous vehicle; if the curvature meets the first preset condition and the lateral distance meets the second preset condition, connecting the Bezier curve with the right-turn lane center line at both ends of the Bezier curve, thereby obtaining a smoothed and optimized right-turn lane center line; if the curvature does not meet the first preset condition, and / or the lateral distance does not meet the second preset condition, adjusting the vertices and constructing a Bezier curve based on the adjusted vertices, and returning to execute the step of detecting the curvature of the constructed Bezier curve and the lateral distance between the Bezier curve and the inner lane inflection point corresponding to the right-turn lane center line until the curvature meets the first preset condition and the lateral distance meets the second preset condition. Through the above description, it can be seen that in the method for smoothing and optimizing the lane center line of the present invention, the smoothed and optimized right-turn lane center line is formed by combining the Bezier curve and the right-turn lane center line. The curvature of the smoothed and optimized right-turn lane center line meets the first preset condition and the lateral distance from the inner lane inflection point meets the second preset condition, which can meet the requirements of the minimum turning radius of the autonomous vehicle, and can be used as a reference path for the autonomous driving planning algorithm. Moreover, the above smoothing and optimizing process is simple and has a small amount of calculation, alleviating the technical problems of large calculation amount and complex calculation in the existing method for smoothing and optimizing the lane center line.

[0062] The above content briefly introduces the method for smoothing and optimizing the lane center line of the present invention. The following describes the specific content involved in detail.

[0063] In an alternative embodiment of the present invention, referring to Figure 6 , the above step S204, detecting the curvature of the constructed Bezier curve and the lateral distance between the Bezier curve and the inner lane inflection point corresponding to the right-turn lane center line, specifically includes the following steps:

[0064] Step S601, determining a plurality of target discrete points at preset intervals on the Bezier curve;

[0065] Step S602, detecting the curvature of the Bezier curve at each target discrete point, thereby obtaining a plurality of curvatures;

[0066] Step S603: Determine the tangent of the Bezier curve at each target discrete point, and detect the distances from the inner lane inflection points to each tangent, so as to obtain multiple lateral distances.

[0067] In an optional embodiment of the present invention, the first preset condition is the condition that each curvature is less than the first preset threshold, the second preset condition is the condition that each lateral distance is greater than the second preset threshold, the first preset threshold is the reciprocal of the minimum turning radius of the autonomous vehicle, and the second preset threshold is related to the width of the autonomous vehicle.

[0068] Specifically, the second preset threshold is a value not less than half of the width of the autonomous vehicle.

[0069] It should be noted that: the minimum turning radius in the embodiment of the present invention is different from the value of the turning radius given by the manufacturer of the autonomous vehicle. The value of the turning radius given by the manufacturer is the distance between the left front wheel and the turning center, and the value of the turning radius in the present invention is the distance between the center of the rear axle of the vehicle and the turning center.

[0070] In an optional embodiment of the present invention, refer to Figure 3 When the number of vertices is six, it sequentially includes a first vertex, a second vertex, a third vertex, a fourth vertex, a fifth vertex, and a sixth vertex along the driving direction of the autonomous vehicle. Among them, the first vertex and the second vertex coincide with one side of the right-turn lane center line, the fifth vertex and the sixth vertex coincide with the other side of the right-turn lane center line, the third vertex is located above the left of the second vertex, the fourth vertex is located above the right of the third vertex, and the fourth vertex is located above the left of the fifth vertex.

[0071] Specifically, if the coordinates of the inner lane inflection point are (1.5, 4.5), the relative coordinates of the first vertex with respect to the inner lane inflection point are (-1.5, -8.5), the relative coordinates of the second vertex with respect to the inner lane inflection point are (-1.5, -4.5), the relative coordinates of the third vertex with respect to the inner lane inflection point are (-6, -0.5), the relative coordinates of the fourth vertex with respect to the inner lane inflection point are (0.5, 6), the relative coordinates of the fifth vertex with respect to the inner lane inflection point are (4.5, 1.5), and the relative coordinates of the sixth vertex with respect to the inner lane inflection point are (8.5, 1.5).

[0072] The above first vertex and second vertex, fifth vertex and sixth vertex are to ensure that the curvature is continuous when connecting to the center line of the right-turn lane; the third vertex and fourth vertex (the points controlling the curvature and lateral distance, i.e., controllable points) are to make the trajectory of the Bezier curve similar to the trajectory when a person drives. The relative coordinates of the above six vertices are preferred values obtained from a large number of experiments and are applicable to most right-turn scenarios in parking lots (that is, the curvature of the Bezier curve constructed with the above six vertices meets the first preset condition, and the lateral distance meets the second preset condition). Here, after constructing the Bezier curve with the above six vertices, it is to verify / check whether the constructed Bezier curve meets the current right-turn scenario in the parking lot (that is, whether the curvature of the Bezier curve meets the first preset condition and whether the lateral distance meets the second preset condition).

[0073] In an alternative embodiment of the present invention, adjusting the vertices includes:

[0074] If the curvature does not meet the first preset condition, then adjust the third vertex closer to the second vertex along the direction of the line segment formed by the third vertex and the second vertex, and adjust the fourth vertex closer to the fifth vertex along the direction of the line segment formed by the fourth vertex and the fifth vertex;

[0075] If the lateral distance does not meet the second preset condition, then adjust the third vertex away from the second vertex along the direction of the line segment formed by the second vertex and the third vertex, and adjust the fourth vertex away from the fifth vertex along the direction of the line segment formed by the fifth vertex and the fourth vertex.

[0076] In an alternative embodiment of the present invention, the method further includes: using the smoothed and optimized center line of the right-turn lane as a reference path for the autonomous driving planning algorithm.

[0077] Specifically, use the smoothed and optimized center line of the right-turn lane as a reference path for the autonomous driving planning algorithm based on the SD coordinate system for path planning.

[0078] The method for smoothing and optimizing the center line of the lane in the present invention is simple, has a low computing power occupancy rate, and is applicable to most curved scenarios in parking lots; the curvature of the generated smoothed and optimized center line of the right-turn lane not only meets the vehicle control requirements but is also continuous, and the control trajectory is smoother; when adjusting the curvature and lateral distance of the Bezier curve, only the positions of the third vertex and the fourth vertex need to be adjusted along a straight line, with strong controllability and a certain adaptability to different scenarios.

[0079] Embodiment 2:

[0080] An embodiment of the present invention also provides a device for smoothing and optimizing the center line of a lane. This device for smoothing and optimizing the center line of a lane is mainly used to execute the method for smoothing and optimizing the center line of a lane provided in the first embodiment of the present invention. The following is a specific introduction to the device for smoothing and optimizing the center line of a lane provided in the embodiment of the present invention.

[0081] Figure 7 It is a schematic diagram of a device for smoothing and optimizing the center line of a lane according to an embodiment of the present invention. As Figure 7 shown, the device mainly includes: an acquisition and construction unit 10, a detection unit 20, a judgment unit 30, a connection unit 40, and an adjustment unit 50, where:

[0082] The acquisition and construction unit is configured to, when determining that the target lane center line in the environmental map of the target scenario is a right-turn lane center line, acquire preset vertices and construct a Bezier curve according to the vertices. Among them, the number of vertices is at least six, and among the vertices, at least two vertices coincide with one side of the right-turn lane center line, and at least two other vertices coincide with the other side of the right-turn lane center line;

[0083] The detection unit is configured to detect the curvature of the constructed Bezier curve and the lateral distance between the Bezier curve and the inner lane inflection point corresponding to the right-turn lane center line;

[0084] The judgment unit is configured to judge whether the curvature meets a first preset condition and judge whether the lateral distance meets a second preset condition. Among them, the first preset condition is related to the minimum turning radius of the autonomous driving vehicle;

[0085] The connection unit is configured to, if the curvature meets the first preset condition and the lateral distance meets the second preset condition, connect the Bezier curve with the right-turn lane center line located at both ends of the Bezier curve, and then obtain the smoothed and optimized right-turn lane center line;

[0086] The adjustment unit is configured to, if the curvature does not meet the first preset condition or the lateral distance does not meet the second preset condition, adjust the vertices, construct a Bezier curve according to the adjusted vertices, and return to execute the steps of detecting the curvature of the constructed Bezier curve and the lateral distance between the Bezier curve and the inner lane inflection point corresponding to the right-turn lane center line until the curvature meets the first preset condition and the lateral distance meets the second preset condition.

[0087] In an embodiment of the present invention, a smooth optimization device for a lane center line is provided, including: when determining that the target lane center line in the environmental map of the target scenario is a right-turn lane center line, obtaining preset vertices and constructing a Bézier curve according to the vertices, where the number of vertices is at least six, and among the vertices, at least two vertices coincide with one side of the right-turn lane center line, and at least two other vertices coincide with the other side of the right-turn lane center line; detecting the curvature of the constructed Bézier curve and the lateral distance between the Bézier curve and the inner lane inflection point corresponding to the right-turn lane center line; determining whether the curvature meets the first preset condition and determining whether the lateral distance meets the second preset condition, where the first preset condition is related to the minimum turning radius of the autonomous vehicle; if the curvature meets the first preset condition and the lateral distance meets the second preset condition, connecting the Bézier curve with the right-turn lane center line at both ends of the Bézier curve, thereby obtaining the smoothly optimized right-turn lane center line; if the curvature does not meet the first preset condition, and / or, the lateral distance does not meet the second preset condition, adjusting the vertices and constructing a Bézier curve according to the adjusted vertices, and returning to execute the steps of detecting the curvature of the constructed Bézier curve and the lateral distance between the Bézier curve and the inner lane inflection point corresponding to the right-turn lane center line until the curvature meets the first preset condition and the lateral distance meets the second preset condition. Through the above description, it can be seen that in the smooth optimization device for the lane center line of the present invention, the smoothly optimized right-turn lane center line is formed by combining the Bézier curve and the right-turn lane center line. The curvature of the smoothly optimized right-turn lane center line meets the first preset condition and the lateral distance from the inner lane inflection point meets the second preset condition, which can meet the requirements of the minimum turning radius of the autonomous vehicle, and can be used as a reference path for the autonomous driving planning algorithm. Moreover, the above smooth optimization process is simple and has a small amount of calculation, alleviating the technical problems of large calculation amount and complex calculation in the existing smooth optimization method for the lane center line.

[0088] Optionally, the detection unit is further configured to: determine a plurality of target discrete points at preset intervals on the Bézier curve; detect the curvature of the Bézier curve at each target discrete point, thereby obtaining a plurality of curvatures; determine the tangent of the Bézier curve at each target discrete point, and detect the distance from the inner lane inflection point to each tangent, thereby obtaining a plurality of lateral distances.

[0089] Optionally, the first preset condition is the condition that each curvature is less than the first preset threshold, the second preset condition is the condition that each lateral distance is greater than the second preset threshold, the first preset threshold is the reciprocal of the minimum turning radius of the autonomous vehicle, and the second preset threshold is related to the width of the autonomous vehicle.

[0090] Optionally, when the number of vertices is six, it sequentially includes a first vertex, a second vertex, a third vertex, a fourth vertex, a fifth vertex, and a sixth vertex along the driving direction of the autonomous vehicle. Among them, the first vertex and the second vertex coincide with one side of the center line of the right-turn lane, the fifth vertex and the sixth vertex coincide with the other side of the center line of the right-turn lane, the third vertex is located above the left of the second vertex, the fourth vertex is located above the right of the third vertex, and the fourth vertex is located above the left of the fifth vertex.

[0091] Optionally, if the coordinates of the inflection point of the inner lane are (1.5, 4.5), the relative coordinates of the first vertex with respect to the inflection point of the inner lane are (-1.5, -8.5), the relative coordinates of the second vertex with respect to the inflection point of the inner lane are (-1.5, -4.5), the relative coordinates of the third vertex with respect to the inflection point of the inner lane are (-6, -0.5), the relative coordinates of the fourth vertex with respect to the inflection point of the inner lane are (0.5, 6), the relative coordinates of the fifth vertex with respect to the inflection point of the inner lane are (4.5, 1.5), and the relative coordinates of the sixth vertex with respect to the inflection point of the inner lane are (8.5, 1.5). Among them, the first vertex and the second vertex coincide with one side of the center line of the right-turn lane, and the fifth vertex and the sixth vertex coincide with the other side of the center line of the right-turn lane; the adjustment unit is further configured to: if the curvature does not meet the first preset condition, adjust the third vertex closer to the second vertex along the direction of the line segment formed by the third vertex and the second vertex, and adjust the fourth vertex closer to the fifth vertex along the direction of the line segment formed by the fourth vertex and the fifth vertex; if the lateral distance does not meet the second preset condition, adjust the third vertex away from the second vertex along the direction of the line segment formed by the second vertex and the third vertex, and adjust the fourth vertex away from the fifth vertex along the direction of the line segment formed by the fifth vertex and the fourth vertex.

[0092] Optionally, the device is further configured to: use the smoothed and optimized center line of the right-turn lane as the reference path for the autonomous driving planning algorithm.

[0093] Optionally, the target scenario at least includes: an underground parking lot scenario where the width of a single lane is not greater than a third preset threshold.

[0094] For the device provided by the embodiments of the present invention, its implementation principle and the technical effects produced are the same as those of the foregoing method embodiments. For the sake of brief description, for the parts not mentioned in the device embodiments, reference may be made to the corresponding content in the foregoing method embodiments.

[0095] As Figure 8As shown, an electronic device 600 provided by an embodiment of the present application includes: a processor 601, a memory 602, and a bus. The memory 602 stores machine-readable instructions executable by the processor 601. When the electronic device runs, the processor 601 communicates with the memory 602 through the bus. The processor 601 executes the machine-readable instructions to perform the steps of the lane centerline smoothing optimization determination method as described above.

[0096] Specifically, the above-mentioned memory 602 and processor 601 can be general-purpose memory and processor, and no specific limitation is made here. When the processor 601 runs the computer program stored in the memory 602, it can execute the above-mentioned lane centerline smoothing optimization determination method.

[0097] The processor 601 may be an integrated circuit chip with signal processing capabilities. In the implementation process, each step of the above method can be completed by the integrated logic circuit in the hardware of the processor 601 or instructions in software form. The above-mentioned processor 601 can be a general-purpose processor, including a central processing unit (CPU for short), a network processor (NP for short), etc.; it can also be a digital signal processor (DSP for short), an application specific integrated circuit (ASIC for short), a field-programmable gate array (FPGA for short), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components. It can implement or execute the various methods, steps, and logic block diagrams disclosed in the embodiments of the present application. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor, etc. The steps of the method disclosed in combination with the embodiments of the present application can be directly embodied as being executed and completed by a hardware decoding processor, or executed and completed by a combination of hardware and software modules in the decoding processor. The software module can be located in a mature storage medium in the art such as a random access memory, a flash memory, a read-only memory, a programmable read-only memory, or an electrically erasable programmable memory, a register, etc. This storage medium is located in the memory 602, and the processor 601 reads the information in the memory 602 and combines its hardware to complete the steps of the above method.

[0098] Corresponding to the above-mentioned method for determining the smoothing optimization of the lane center line, an embodiment of the present application further provides a computer-readable storage medium. The computer-readable storage medium stores machine-executable instructions. When the computer-executable instructions are called and run by a processor, the computer-executable instructions cause the processor to run the steps of the above-mentioned method for determining the smoothing optimization of the lane center line.

[0099] The device for determining the smoothing optimization of the lane center line provided by the embodiment of the present application can be specific hardware on the device or software or firmware installed on the device, etc. For the device provided by the embodiment of the present application, the implementation principle and the technical effects produced are the same as those of the foregoing method embodiment. For the sake of brief description, for the parts not mentioned in the device embodiment, reference can be made to the corresponding content in the foregoing method embodiment. Those skilled in the art can clearly understand that for the convenience and conciseness of description, the specific working processes of the foregoing-described systems, devices, and units can all refer to the corresponding processes in the above method embodiment, and will not be repeated here.

[0100] In the embodiments provided by the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. The device embodiments described above are only illustrative. For example, the division of the units is only a logical function division, and there may be other division methods in actual implementation. For another example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the displayed or discussed mutual coupling or direct coupling or communication connection may be through some communication interfaces, and the indirect coupling or communication connection of the devices or units may be in an electrical, mechanical, or other form.

[0101] For another example, the flowcharts and block diagrams in the accompanying drawings show the possible architectures, functions, and operations of devices, methods, and computer program products according to multiple embodiments of the present application. In this regard, each block in the flowchart or block diagram may represent a module, a program segment, or a part of code, and the module, program segment, or part of code contains one or more executable instructions for implementing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the blocks may occur in a different order than marked in the accompanying drawings. For example, two consecutive blocks may actually be executed substantially in parallel, and they may sometimes be executed in the reverse order, depending on the functions involved. It should also be noted that each block in the block diagram and / or flowchart, and the combination of blocks in the block diagram and / or flowchart, can be implemented by a dedicated hardware-based system for performing the specified functions or actions, or can be implemented by a combination of dedicated hardware and computer instructions.

[0102] The unit described as a separation component may or may not be physically separated. The component shown as a unit may or may not be a physical unit, that is, it may be located in one place or may be distributed across multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0103] In addition, each functional unit in the embodiments provided in this application may be integrated into a processing unit, may exist physically separately for each unit, or two or more units may be integrated into one unit.

[0104] If the described function is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on such an understanding, the technical solution of this application, in essence, or the part that contributes to the prior art or part of this technical solution can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for causing an electronic device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the vehicle marking method described in each embodiment of this application. The aforementioned storage medium includes: various media that can store program codes such as USB flash drives, mobile hard disks, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical discs.

[0105] It should be noted that: similar reference numerals and letters represent similar items in the following drawings. Therefore, once an item is defined in one drawing, it does not need to be further defined and explained in subsequent drawings. In addition, the terms "first", "second", "third", etc. are only used for descriptive distinction and cannot be understood as indicating or implying relative importance.

[0106] Finally, it should be noted that: the above-described embodiments are only specific implementation manners of this application, used to illustrate the technical solution of this application, rather than limiting it. The protection scope of this application is not limited thereto. Although this application has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that: any person skilled in the art within the technical scope disclosed in this application can still modify the technical solutions described in the foregoing embodiments or can easily think of changes, or perform equivalent replacements for some of the technical features; and these modifications, changes, or replacements do not make the essence of the corresponding technical solutions deviate from the scope of the technical solutions of the embodiments of this application. All should be covered within the protection scope of this application. Therefore, the protection scope of this application should be subject to the protection scope of the claims.

Claims

1. A method for smoothing and optimizing a lane center line, characterized in that, Including: When determining that the target lane center line in the environmental map according to the target scenario is a right-turn lane center line, obtaining preset vertices and constructing a Bezier curve based on the vertices, where the number of the vertices is at least six, and among the vertices, at least two vertices coincide with one side of the right-turn lane center line, and at least two other vertices coincide with the other side of the right-turn lane center line; Detecting the curvature of the constructed Bezier curve and the lateral distance between the Bezier curve and the inner lane inflection point corresponding to the right-turn lane center line; Judging whether the curvature meets a first preset condition and judging whether the lateral distance meets a second preset condition, where the first preset condition is related to the minimum turning radius of the autonomous vehicle; If the curvature meets the first preset condition and the lateral distance meets the second preset condition, connecting the Bezier curve with the right-turn lane center line at both ends of the Bezier curve, and then obtaining a smoothly optimized right-turn lane center line; If the curvature does not meet the first preset condition, and / or the lateral distance does not meet the second preset condition, adjusting the vertices and constructing a Bezier curve based on the adjusted vertices, and returning to execute the step of detecting the curvature of the constructed Bezier curve and the lateral distance between the Bezier curve and the inner lane inflection point corresponding to the right-turn lane center line until the curvature meets the first preset condition and the lateral distance meets the second preset condition; 2. The method according to claim 1, wherein Detecting the curvature of the constructed Bezier curve and the lateral distance between the Bezier curve and the inner lane inflection point corresponding to the right-turn lane center line includes: Determining a plurality of target discrete points at preset intervals on the Bezier curve; Detecting the curvature of the Bezier curve at each of the target discrete points, and then obtaining a plurality of the curvatures; Determining the tangent line of the Bezier curve at each of the target discrete points and detecting the distance from the inner lane inflection point to each of the tangent lines, and then obtaining a plurality of the lateral distances; 3. The method according to claim 2, wherein The first preset condition is the condition that each of the curvatures is less than a first preset threshold, the second preset condition is the condition that each of the lateral distances is greater than a second preset threshold, the first preset threshold is the reciprocal of the minimum turning radius of the autonomous vehicle, and the second preset threshold is related to the width of the autonomous vehicle; 4. The method according to claim 1, wherein When the number of the vertices is six, it sequentially includes a first vertex, a second vertex, a third vertex, a fourth vertex, a fifth vertex and a sixth vertex along the driving direction of the autonomous vehicle, where the first vertex and the second vertex coincide with one side of the right-turn lane center line, the fifth vertex and the sixth vertex coincide with the other side of the right-turn lane center line, the third vertex is located above the left of the second vertex, the fourth vertex is located above the right of the third vertex, and the fourth vertex is located above the left of the fifth vertex.

5. The method according to claim 4, wherein If the coordinates of the inner lane inflection point are (1.5, 4.5), the relative coordinates of the first vertex with respect to the inner lane inflection point are (-1.5, -8.5), the relative coordinates of the second vertex with respect to the inner lane inflection point are (-1.5, -4.5), the relative coordinates of the third vertex with respect to the inner lane inflection point are (-6, -0.5), the relative coordinates of the fourth vertex with respect to the inner lane inflection point are (0.5, 6), the relative coordinates of the fifth vertex with respect to the inner lane inflection point are (4.5, 1.5), and the relative coordinates of the sixth vertex with respect to the inner lane inflection point are (8.5, 1.5); Adjusting the vertices includes: If the curvature does not meet the first preset condition, the third vertex is adjusted closer to the second vertex along the direction of the line segment formed by the third vertex and the second vertex, and the fourth vertex is adjusted closer to the fifth vertex along the direction of the line segment formed by the fourth vertex and the fifth vertex; If the lateral distance does not meet the second preset condition, the third vertex is adjusted away from the second vertex along the direction of the line segment formed by the second vertex and the third vertex, and the fourth vertex is adjusted away from the fifth vertex along the direction of the line segment formed by the fifth vertex and the fourth vertex.

6. The method according to claim 1, wherein The method further includes: Using the smoothed and optimized right-turn lane centerline as the reference path for the autonomous driving planning algorithm.

7. The method according to claim 1, characterized in that, The target scenario at least includes: an underground parking lot scenario where the width of a single lane is not greater than a third preset threshold.

8. A smooth optimization device for a lane center line, characterized in that, It includes: An acquisition and construction unit, configured to obtain preset vertices and construct a Bézier curve according to the vertices when determining that the target lane centerline in the environmental map of the target scenario is the right-turn lane centerline, where the number of vertices is at least six, and among the vertices, at least two vertices coincide with one side of the right-turn lane centerline, and at least two other vertices coincide with the other side of the right-turn lane centerline; A detection unit, configured to detect the curvature of the constructed Bézier curve and the lateral distance between the Bézier curve and the inner lane inflection point corresponding to the right-turn lane centerline; A judgment unit, configured to judge whether the curvature meets the first preset condition and judge whether the lateral distance meets the second preset condition; A connection unit, configured to connect the Bézier curve with the right-turn lane centerline located at both ends of the Bézier curve to obtain a smoothed and optimized right-turn lane centerline if the curvature meets the first preset condition and the lateral distance meets the second preset condition; An adjustment unit, configured to adjust the vertex if the curvature does not meet the first preset condition, or the lateral distance does not meet the second preset condition, construct a Bézier curve based on the adjusted vertex, and return to the step of detecting and constructing the curvature of the Bézier curve and the lateral distance between the Bézier curve and the inner lane inflection point corresponding to the center line of the right-turn lane, until the curvature meets the first preset condition and the lateral distance meets the second preset condition.

9. An electronic device, comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 7 above.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores machine-executable instructions, and when the machine-executable instructions are called and run by the processor, the machine-executable instructions cause the processor to run the method according to any one of claims 1 to 7 above.

Images