Travelable path boundary calculation method and device, storage medium and computer equipment

Abstract

The application relates to the technical field of automatic driving, in particular to a drivable path boundary calculation method and device, a storage medium and computer equipment. The method comprises the following steps: acquiring vehicle data, road data and obstacle data of a target vehicle; projecting the vehicle data and the obstacle data onto a same preset map; in the projected preset map, determining a target driving constraint object of the target vehicle from driving constraint objects contained in a target lane based on the vehicle data; taking the vehicle center line of the target vehicle located on the lane center line of the target lane as a reference, determining a target safety lateral offset distance between the rear axle center point of the target vehicle and the target driving constraint object; and correcting the target safety lateral offset distance, so as to determine the drivable path boundary of the target vehicle according to the corrected target safety lateral offset distance. The application significantly improves the driving safety of the automatic driving vehicle in a complex road environment.

Description

Technical Field

[0001] This application relates to the field of autonomous driving technology, and in particular to a method, apparatus, storage medium, and computer device for calculating the boundary of a drivable path. Background Technology

[0002] With the rapid development of autonomous driving technology, safety remains paramount. Path planning is a crucial component of autonomous driving technology, involving the selection and optimization of vehicle routes within a road network to achieve the best driving strategy. The goal of path planning is to find a path that meets multiple requirements, including safety, efficiency, and comfort, while also considering the vehicle's dynamic characteristics and environmental uncertainties. Therefore, the primary objective of path planning is to determine the boundaries of the vehicle's drivable paths.

[0003] In related technologies, planning path boundaries using only obstacle data can only ensure that the planned path boundaries do not collide with obstacles. However, it does not fully consider the collision risks between vehicles and different road boundaries, nor does it fully consider the constraints of curves, vehicle heading and road heading deviations on path boundary calculations. This results in the risk of the final planned driving path colliding with obstacles or road boundaries. Summary of the Invention

[0004] In view of this, this application provides a method, apparatus, storage medium, and computer device for calculating drivable path boundaries, which significantly improves the driving safety of autonomous vehicles in complex road environments.

[0005] According to one aspect of this application, a method for calculating the boundary of a drivable path is provided, comprising: Acquire vehicle data of the target vehicle, road data of the target lane where the target vehicle is located, and obstacle data of the target lane; The vehicle data and obstacle data are projected onto the same preset map; In the projected preset map, based on the vehicle data, the target driving constraint object of the target vehicle is determined from the driving constraint objects contained in the target lane. The driving constraint object is determined according to the road data and obstacle data. Based on the fact that the center line of the target vehicle is located on the center line of the target lane, the target safe lateral offset distance between the rear axle center point of the target vehicle and the target driving constraint object is determined, wherein the rear axle center point is located on the center line of the vehicle. Based on the vehicle data and the road data, the target safe lateral offset distance is corrected to determine the drivable path boundary of the target vehicle according to the corrected target safe lateral offset distance.

[0006] According to another aspect of this application, a drivable path boundary calculation device is provided, comprising: The acquisition module is used to acquire vehicle data of the target vehicle, road data of the target lane where the target vehicle is located, and obstacle data of the target lane; The projection module is used to project the vehicle data and obstacle data onto the same preset map; The calculation module is configured to, in the projected preset map, determine the target driving constraint object of the target vehicle among the driving constraint objects included in the target lane based on the vehicle data, wherein the driving constraint object is determined according to the road data and obstacle data; and, with the vehicle centerline of the target vehicle located on the lane centerline of the target lane as a reference, determine the target safe lateral offset distance between the rear axle center point of the target vehicle and the target driving constraint object, wherein the rear axle center point is located on the vehicle centerline; and, based on the vehicle data and the road data, correct the target safe lateral offset distance to determine the drivable path boundary of the target vehicle according to the corrected target safe lateral offset distance.

[0007] According to another aspect of this application, a readable storage medium is provided, on which a program or instructions are stored, which, when executed by a processor, implement the steps of the above-described method for calculating the drivable path boundary.

[0008] According to another aspect of this application, a computer device is provided, including a storage medium, a processor, and a computer program stored on the storage medium and executable on the processor, wherein the processor executes the program to implement the steps of the above-described method for calculating the drivable path boundary.

[0009] By employing the above technical solutions, this application provides a method, apparatus, storage medium, and computer device for calculating drivable path boundaries. By comprehensively considering the collision risks between autonomous vehicles and obstacles, different lane lines, and road boundaries, and integrating the geometric constraints of vehicle heading deviation and road curvature, it achieves accurate quantification and dynamic correction of drivable path boundaries, calculates more accurate and safer drivable path boundaries, and thus significantly improves the driving safety of autonomous vehicles in complex road environments.

[0010] The above description is only an overview of the technical solution of this application. In order to better understand the technical means of this application and to implement it in accordance with the contents of the specification, and to make the above and other objects, features and advantages of this application more obvious and understandable, the following are specific embodiments of this application. Attached Figure Description

[0011] The accompanying drawings, which are included to provide a further understanding of this application and form part of this application, illustrate exemplary embodiments and are used to explain this application, but do not constitute an undue limitation of this application. In the drawings: Figure 1 A flowchart illustrating the drivable path boundary calculation method provided in an embodiment of this application is shown. Figure 2 A flowchart illustrating a drivable path boundary calculation method provided in another embodiment of this application is shown; Figure 3 This application shows a projected target lane provided by another embodiment; Figure 4 This illustration shows a schematic diagram of a target lane that is a curve, according to another embodiment of this application: Figure 5 This illustration shows a schematic diagram of a target vehicle exhibiting a heading deviation, according to another embodiment of this application: Figure 6 This illustration shows a schematic diagram of a target lane that is a curve and the target vehicle has a heading deviation, according to another embodiment of this application: Figure 7 A structural block diagram of the drivable path boundary calculation device provided in an embodiment of this application is shown. Detailed Implementation

[0012] The present application will be described in detail below with reference to the accompanying drawings and embodiments. It should be noted that, unless otherwise specified, the embodiments and features described in the embodiments of the present application can be combined with each other.

[0013] The embodiments of this application are described in detail below. Examples of these embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and are only used to explain this application, and should not be construed as limiting this application.

[0014] Those skilled in the art will understand that, unless specifically stated otherwise, the singular forms “a,” “an,” “the,” and “the” used herein may also include the plural forms. It should be further understood that the term “comprising” as used in this application means the presence of the stated features, integers, steps, operations, elements, and / or components, but does not exclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and / or groups thereof. It should be understood that when we say an element is “connected” or “attached” to another element, it can be directly connected or attached to the other element, or there may be intermediate elements. Furthermore, “connected” or “attached” as used herein can include wireless connections or wireless interconnections. The term “and / or” as used herein includes all or any unit and all combinations of one or more associated listed items.

[0015] Exemplary embodiments according to this application will now be described in more detail with reference to the accompanying drawings. However, these exemplary embodiments may be implemented in many different forms and should not be construed as being limited to the embodiments set forth herein. It should be understood that these embodiments are provided so that the disclosure of this application is thorough and complete, and that the concept of these exemplary embodiments is fully conveyed to those skilled in the art.

[0016] This application provides a method for calculating the boundary of a drivable path, such as... Figure 1 As shown, the method includes: Step 101: Obtain vehicle data of the target vehicle, road data of the target lane where the target vehicle is located, and obstacle data of the target lane.

[0017] It should be noted that the execution subject in this embodiment is a terminal, server, or processor with computing capabilities. This is an example, not a limitation, illustrating the application of this method in an autonomous vehicle. When this method is applied to an autonomous vehicle, the execution subject is the Automated Vehicle Control Unit (AVCU), i.e., the central processing unit of the autonomous vehicle.

[0018] In this step, the target vehicle is the vehicle currently performing the autonomous driving task. Specifically, vehicle data of the target vehicle at the current moment of travel is acquired. This vehicle data includes, but is not limited to, dynamic and static data such as the target vehicle's current position, width, target length, speed, and heading. Here, the target length of the target vehicle refers to the distance from the rear axle to the front boundary of the target vehicle, that is, the straight-line distance from the center point of the rear axle to the foremost point of the target vehicle. The center point of the rear axle is the center point connecting the two rear wheels of the target vehicle, used to determine the vehicle's position and attitude. The target length is used to determine the position of the target vehicle's front end, so as to accurately determine whether the front end of the target vehicle will collide with lane lines or obstacles when the target vehicle turns or deviates from its heading.

[0019] Furthermore, based on the current location data of the target vehicle in the vehicle data, the location of the target vehicle is determined. Then, from the lane topology of the preset high-precision map, road data for the target lane where the target vehicle is located is obtained according to the target vehicle's location. This road data includes, but is not limited to, the lane width, radius of curvature, lane line type, and road boundaries. Here, lane line types include solid lines and dashed lines. Road boundaries include fences, curbs, etc.

[0020] It's important to note that the target lane is the smallest unit lane with complete lane boundaries currently occupied by the target vehicle, within which it intends to travel normally. For example, if the target vehicle is on a two-way road, such a road is typically divided into multiple lanes, possibly with lanes for vehicles traveling in the same direction and lanes for vehicles traveling in opposite directions. For instance, on a two-way four-lane road, each side has two lanes for vehicles traveling in the same direction. In this case, if the target vehicle is traveling in the right-hand lane on one side of the road, then that right-hand lane is the target lane for the target vehicle.

[0021] Furthermore, obstacle data in the target lane can be perceived through the autonomous vehicle control unit of the target vehicle. This obstacle data includes information such as the position, type, heading, speed, and acceleration of obstacles in the target lane.

[0022] Step 102: Project vehicle data and obstacle data onto the same preset map.

[0023] In this step, such as Figure 3 As shown, a unified UTM (Universal Transverse Mercator Grid System) coordinate system is used to project vehicle data and obstacle data onto a preset high-precision map, so that the target vehicle, target lane and obstacle are located in the same reference system, which facilitates subsequent unified calculation.

[0024] Step 103: In the projected preset map, based on the vehicle data, determine the target driving constraint object of the target vehicle from the driving constraint objects contained in the target lane.

[0025] The driving constraint objects are determined based on road data and obstacle data.

[0026] In this step, different types of lane lines, road boundaries, and obstacles from the road data are first used as driving constraints for the target vehicle. This allows for the setting of appropriate preset safety lateral thresholds based on the different safety risk levels of each driving constraint.

[0027] It should be noted that "lateral" refers to the direction perpendicular to the tangent of the centerline of the target lane. The preset safe lateral threshold is the minimum lateral buffer distance that the outermost boundary of the vehicle must maintain between it and the driving constraint object. Specifically, the preset safe lateral threshold can be set according to traffic rules and relevant laws and regulations to act as a preset safety buffer, ensuring that the target vehicle not only avoids physical collisions with its surroundings but also maintains a minimum distance that complies with traffic rules and safety margins.

[0028] Here, the lane centerline is the reference line for the target lane, located in the exact center of the target lane and running the entire length of the target lane.

[0029] Furthermore, based on the target vehicle's current position data in the vehicle data, candidate driving constraint objects within a preset range of the target vehicle's current position are determined in the target lane. It is understood that the front corner of the target vehicle is the most likely point of collision or lane departure during its movement. Therefore, the candidate driving constraint object with the closest straight-line distance to the front corner of the target vehicle is designated as the first target driving constraint object. The candidate driving constraint object with the closest straight-line distance to the other front corner of the target vehicle is designated as the second target driving constraint object.

[0030] Step 104: Using the center line of the target vehicle located at the center line of the target lane as a reference, determine the target safe lateral offset distance between the rear axle center point of the target vehicle and the target driving constraint object.

[0031] The center point of the rear axle is located on the center line of the vehicle.

[0032] In this step, the target vehicle's centerline is located on the centerline of the target lane as a reference. It is assumed that the target vehicle is traveling on a straight road and its heading is parallel to the target lane. That is, the radius of curvature of the target lane in the road data is 0 (i.e., the preset value), and the heading of the lane in the road data is the same as the heading of the vehicle in the vehicle data. The maximum safe lateral offset distance from the rear axle center point of the target vehicle to the centerline of the lane (i.e., the target safe lateral offset distance) is calculated.

[0033] The target safe lateral offset distance is the maximum safe distance that the center point of the target vehicle's rear axle is allowed to move towards the side of the target driving constraint in a direction perpendicular to the tangent of the lane centerline. Exceeding this distance, the target vehicle risks colliding with the lane line, road boundary, or obstacle on that side.

[0034] Here, the centerline of the target vehicle passes through the center point of the rear axle and is parallel to the longitudinal axis of the target vehicle, geometrically dividing the target vehicle into two symmetrical parts. In this embodiment, the target vehicle is assumed to be a rigid body, and the center point of the rear axle is taken as the center of rotation of the target vehicle.

[0035] Step 105: Based on vehicle data and road data, correct the target safe lateral offset distance to determine the drivable path boundary of the target vehicle according to the corrected target safe lateral offset distance.

[0036] In this step, considering situations where the target vehicle's actual heading is not parallel to the lane's heading, and where the target lane is a curve with a radius of curvature, the additional lateral offset of the outermost point of the target vehicle's front end relative to the rear axle center is calculated. This additional offset is the distance the target vehicle's rear axle center needs to move inward. This offset is used to correct the target's safe lateral offset distance, thereby narrowing the drivable path boundary. This ensures that when the target vehicle veers or travels on a curve, the front end does not exceed the target constraint object, thus obtaining the precise drivable path boundary for the target vehicle.

[0037] This embodiment comprehensively considers the collision risks of autonomous vehicles with obstacles, different lane lines and road boundaries, and integrates the geometric constraints of vehicle heading deviation and road curvature to achieve accurate quantification and dynamic correction of the drivable path boundary, and calculates a more accurate and safer drivable path boundary, thereby significantly improving the driving safety of autonomous vehicles in complex road environments.

[0038] Another embodiment of this application provides a method for calculating the boundary of a drivable path, such as... Figure 2 As shown, the method includes: Step 201: Obtain vehicle data of the target vehicle, road data of the target lane where the target vehicle is located, and obstacle data of the target lane.

[0039] It should be noted that the execution subject in this embodiment is a terminal, server, or processor with computing capabilities. This is an example, not a limitation, illustrating the application of this method in an autonomous vehicle. When this method is applied to an autonomous vehicle, the execution subject is the Automated Vehicle Control Unit (AVCU), i.e., the central processing unit of the autonomous vehicle.

[0040] In this step, the target vehicle is the vehicle currently performing the autonomous driving task. Specifically, vehicle data of the target vehicle at the current moment is acquired. This vehicle data includes, but is not limited to, dynamic and static data such as the target vehicle's current position, width, target length, speed, and heading. Here, the target length of the target vehicle refers to the distance from the rear axle to the front boundary of the target vehicle, that is, the straight-line distance from the center point of the rear axle to the foremost point of the vehicle. The center point of the rear axle is the center point connecting the two rear wheels of the target vehicle, used to determine the vehicle's position and attitude. The target length of the target vehicle is used to determine the position of the target vehicle's front end, so as to accurately determine whether the front end of the target vehicle will collide with lane lines or obstacles when the target vehicle turns or deviates from its heading.

[0041] Furthermore, based on the current location data of the target vehicle in the vehicle data, the location of the target vehicle is determined, and thus, from the lane topology structure of the preset high-precision map, the road data of the target lane where the target vehicle is located is obtained according to the location of the target vehicle. For example, Figure 3 As shown, road data includes, but is not limited to, lane width, radius of curvature, lane line type, and road boundaries of the target lane. Here, lane line types include solid lines and dashed lines. Road boundaries include fences, curbs, etc. For example, Figure 3 Thin solid lines represent solid lane lines, thin dashed lines represent dashed lane lines, and thick solid lines represent road boundaries. Figure 3 The target vehicle is abstracted as a rectangle, the longer side of which is determined by the target length of the target vehicle, and the wider side of which is determined by the width of the target vehicle.

[0042] It's important to note that the target lane is the smallest unit lane with complete lane boundaries currently occupied by the target vehicle, within which it intends to travel normally. For example, if the target vehicle is on a two-way road, such a road is typically divided into multiple lanes, possibly with lanes for vehicles traveling in the same direction and lanes for vehicles traveling in opposite directions. For instance, on a two-way four-lane road, each side has two lanes for vehicles traveling in the same direction. In this case, if the target vehicle is traveling in the right-hand lane on one side of the road, then that right-hand lane is the target lane for the target vehicle.

[0043] Furthermore, obstacle data in the target lane can be perceived through the autonomous vehicle control unit of the target vehicle. This obstacle data includes information such as the position, type, heading, speed, and acceleration of obstacles in the target lane.

[0044] Step 202: Project vehicle data and obstacle data onto the same preset map.

[0045] In this step, such as Figure 3 As shown, a unified UTM (universal transverse mercartorgrid system) coordinate system is used to project vehicle data and obstacle data onto a preset high-precision map, so that the target vehicle, target lane and obstacle are located in the same reference system, which facilitates subsequent unified calculation.

[0046] Step 203: In the projected preset map, based on the vehicle data, determine the target driving constraint object of the target vehicle from the driving constraint objects contained in the target lane.

[0047] The driving constraint objects are determined based on road data and obstacle data.

[0048] In this step, different types of lane lines, road boundaries, and obstacles from the road data are first used as driving constraints for the target vehicle. This allows for the setting of appropriate preset safety lateral thresholds based on the different safety risk levels of each driving constraint.

[0049] It should be noted that "lateral" refers to the direction perpendicular to the tangent of the centerline of the target lane. The preset safe lateral threshold is the minimum lateral buffer distance that the outermost boundary of the vehicle must maintain between it and the driving constraint object. Specifically, the preset safe lateral threshold can be set according to traffic rules and relevant laws and regulations to act as a preset safety buffer, ensuring that the target vehicle not only avoids physical collisions with its surroundings but also maintains a minimum distance that complies with traffic rules and safety margins.

[0050] Here, the lane centerline is the reference line for the target lane, located in the exact center of the target lane and running the entire length of the target lane.

[0051] Furthermore, based on the target vehicle's current position data in the vehicle data, candidate driving constraint objects within a preset range of the target vehicle's current position are determined in the target lane. It is understood that the front corner of the target vehicle is the most likely point of collision or lane departure during its movement. Therefore, the candidate driving constraint object with the closest straight-line distance to the front corner of the target vehicle is designated as the first target driving constraint object. The candidate driving constraint object with the closest straight-line distance to the other front corner of the target vehicle is designated as the second target driving constraint object. For example... Figure 4 As shown, the target vehicle is making a right turn within the target lane. The first target driving constraint is the solid lane line on the left that is closer to the target vehicle, and the second target driving constraint is the solid lane line on the right that is opposite to the solid lane line on the left.

[0052] Step 204: Using the center line of the target vehicle located at the center line of the target lane as a reference, determine the target safe lateral offset distance between the rear axle center point of the target vehicle and the target driving constraint object.

[0053] The center point of the rear axle is located on the center line of the vehicle.

[0054] In this step, the target vehicle's centerline is located on the centerline of the target lane as a reference. It is assumed that the target vehicle is traveling on a straight road and its heading is parallel to the target lane. That is, the radius of curvature of the target lane in the road data is 0 (i.e., the preset value), and the heading of the lane in the road data is the same as the heading of the vehicle in the vehicle data. The maximum safe lateral offset distance from the rear axle center point of the target vehicle to the centerline of the lane (i.e., the target safe lateral offset distance) is calculated.

[0055] The target safe lateral offset distance is the maximum safe distance that the center point of the target vehicle's rear axle is allowed to move towards the side of the target driving constraint in a direction perpendicular to the tangent of the lane centerline. Exceeding this distance, the target vehicle risks colliding with the lane line, road boundary, or obstacle on that side.

[0056] Here, we assume the target vehicle is a rigid body, with its centerline passing through the center point of the rear axle and parallel to its longitudinal axis, geometrically dividing the vehicle into two symmetrical parts. In this embodiment, the center point of the rear axle is taken as the center of rotation of the target vehicle.

[0057] Furthermore, as a refinement and extension of the specific implementation of the above embodiments, in order to fully explain the specific implementation process of this embodiment, determining the target safe lateral offset distance between the rear axle center point of the target vehicle and the target driving constraint object specifically includes: determining the target safe lateral offset distance between the rear axle center point of the target vehicle and the target driving constraint object based on the lane width of the target lane in the road data, the vehicle width in the vehicle data, and the preset safe lateral threshold corresponding to the target driving constraint object.

[0058] In this step, for example, such as Figure 3 As shown, the target safe lateral offset distance between the rear axle center point of the target vehicle and the target driving constraint object is determined according to the following formula: , in, The rear axle center point of the target vehicle and the target driving constraint object The target safety lateral offset distance between them Lane width, For vehicle width, For the target driving constraint object The corresponding preset horizontal safety threshold. =1,2; Based on the first target driving constraint object Corresponding preset horizontal safety threshold The calculated rear axle center point of the target vehicle and the first target driving constraint object The first target safety lateral offset distance between them Based on the second target driving constraint object Corresponding preset horizontal safety threshold The calculated safe lateral offset distance between the rear axle center point of the target vehicle and the second target driving constraint object.

[0059] Step 205: Based on the vehicle width and target length in the vehicle data and the lane width in the road data, determine the target lateral offset distance between the rear axle center point and the lane center line; based on the lane width, vehicle width and target lateral offset distance, determine the correction amount generated by the first target driving constraint object on the first target safe lateral offset distance; correct the first target safe lateral offset distance based on the correction amount.

[0060] In this step, based on the actual driving conditions of the target vehicle, and considering both the curved target lane and the heading difference between the target vehicle and the target lane, the maximum lateral offset distance (i.e., the target lateral offset distance) between the rear axle center point of the target vehicle and the lane centerline of the target lane is calculated, with the constraint that the front corner of the target vehicle cannot exceed the first target driving constraint object. Therefore, based on the target lateral offset distance, the amount by which the first target safe lateral offset distance needs to be reduced towards the rear axle center point of the target vehicle is calculated for both curved target lanes and heading differences between the target vehicle and the target lane. This reduction amount is used as the correction amount generated by the first target driving constraint object on the first target safe lateral offset distance. This correction amount is then used in subsequent steps to adjust the first target safe lateral offset distance, resulting in a more precise maximum safe lateral offset distance for the target vehicle on the side of the first target driving constraint object.

[0061] Here, for the case where the target lane is a curve, there exists a first target lateral offset distance between the rear axle center point of the target vehicle and the lane centerline of the target lane, and thus a first correction amount is generated by the first target driving constraint object to the first target safe lateral offset distance. For the case where there is a heading difference between the target vehicle and the target lane, there exists a second target lateral offset distance between the rear axle center point of the target vehicle and the lane centerline of the target lane, and thus a second correction amount is generated by the first target driving constraint object to the first target safe lateral offset distance.

[0062] Furthermore, as a refinement and extension of the specific implementation of the above embodiments, in order to fully illustrate the specific implementation process of this embodiment, based on the vehicle width and target length in the vehicle data and the lane width in the road data, the target lateral offset distance between the rear axle center point and the lane centerline is determined; based on the lane width, vehicle width, and target lateral offset distance, the correction amount generated by the first target driving constraint object on the first target safe lateral offset distance is determined, specifically including: if the radius of curvature of the target lane in the road data is not equal to a preset value, taking the vehicle heading of the target vehicle in the vehicle data and the lane heading of the target lane in the road data as being the same as the vehicle heading, based on the radius of curvature, target length, and vehicle width, the first target lateral offset distance between the rear axle center point and the lane centerline is determined when the target lane has a radius of curvature; based on the lane width, vehicle width, and first target lateral offset distance, the first correction amount generated by the first target driving constraint object on the first target safe lateral offset distance is determined when the target lane has a radius of curvature.

[0063] In this step, such as Figure 4As shown, for the case where the target vehicle is driving on a curve, i.e., the radius of curvature of the target lane in the road data is not equal to 0, a controlled variable method is used. It is assumed that the vehicle heading of the target vehicle is parallel to the target lane, that is, the velocity direction of the rear axle center point of the target vehicle is parallel to the tangent direction of its projection point on the lane centerline. This is manifested as the vehicle heading of the target vehicle in the vehicle data being the same as the lane heading of the target lane in the road data, avoiding the simultaneous handling of yaw and curve effects. Therefore, based on the critical situation where the front angle of the target vehicle is about to exceed the first target driving constraint object, the maximum lateral offset distance between the rear axle center point and the lane centerline (i.e., the first target lateral offset distance) is calculated when the target lane has a radius of curvature.

[0064] For example, the first target lateral offset distance between the rear axle center point and the lane centerline is determined according to the following formula: , in, The lateral offset distance of the first target. R Let be the radius of curvature. The target length.

[0065] Here, as Figure 4 As shown, a right triangle is formed by connecting the center of the target lane to the front angle of the target vehicle closest to the first target driving constraint object, and connecting the center of the lane to the rear angle of the target vehicle on the same side as the front angle. According to the Pythagorean theorem, the length D1 of the other leg of this right triangle (excluding the longer side of the target vehicle) is... Therefore, by subtracting half the radius of curvature and half the vehicle width from D1, we obtain the maximum lateral offset distance between the rear axle center point and the lane centerline when the target lane has a radius of curvature.

[0066] Furthermore, the first correction amount generated by the first target driving constraint object to the first target safe lateral offset distance is determined according to the following formula: , in, This is the first correction amount.

[0067] Here, the first correction amount represents the minimum safe distance that the rear of the vehicle must maintain from the first target driving constraint object due to the curvature of the curve. It can be understood that the first correction amount is also the minimum safe distance that the rear axle center point of the target vehicle must reserve when the target lane has a radius of curvature. Therefore, the first correction amount is used to correct the first target safe lateral offset distance corresponding to the first target driving constraint object, thereby tightening the boundary of the drivable path of the target vehicle on the side closest to the first target driving constraint object.

[0068] In this embodiment, the first correction amount ensures that when the vehicle is turning, the outermost point of the front of the vehicle cannot exceed the first target driving constraint object, that is, the outermost point of the front of the vehicle must be within the first target driving constraint object.

[0069] Furthermore, as a refinement and extension of the specific implementation of the above embodiments, in order to fully illustrate the specific implementation process of this embodiment, based on the vehicle width and target length in the vehicle data and the lane width in the road data, the target lateral offset distance between the rear axle center point and the lane centerline is determined; according to the lane width, vehicle width, and target lateral offset distance, the correction amount generated by the first target driving constraint object on the first target safe lateral offset distance is determined, specifically including: if the vehicle heading of the target vehicle in the vehicle data is not the same as the lane heading of the target lane in the road data, the front corner of the target vehicle closest to the first target driving constraint object is taken as the target point of the target vehicle; connecting the rear axle center point of the target vehicle and the target lane centerline... The system obtains the target line segment of the target vehicle; using the radius of curvature of the target lane in the road data as a preset value as a benchmark, it determines the length of the target line segment and the target angle between the target line segment and the vehicle centerline based on the vehicle width and target length; based on the difference between the vehicle heading and the lane heading, the length and target angle of the target line segment, and the lane width, it determines the second target lateral offset distance between the rear axle center point and the lane centerline when the vehicle heading and the lane heading are not the same; based on the lane width, vehicle width, and the second target lateral offset distance, it determines the second correction amount generated by the first target driving constraint object on the first target safe lateral offset distance when the vehicle heading and the lane heading are not the same.

[0070] In this step, such as Figure 5 As shown, for cases where there is a heading difference between the target vehicle and the target lane (i.e., the vehicle heading in the vehicle data differs from the lane heading in the road data), a controlled variable method is used. The target lane is assumed to be a straight road, meaning the radius of curvature of the target lane in the road data is 0, avoiding the simultaneous handling of yaw and curve effects. Therefore, based on the critical situation where the front angle of the target vehicle is about to exceed the first target driving constraint, the maximum lateral offset distance between the rear axle center point and the lane centerline (i.e., the second target lateral offset distance) is calculated when there is a heading difference between the target vehicle and the target lane.

[0071] Specifically, such as Figure 5As shown, if the vehicle heading of the target vehicle in the vehicle data is different from the lane heading of the target lane in the road data, it indicates that the target vehicle is at risk of veergence. In this case, the front corner of the target vehicle closest to the first target driving constraint object is taken as the target point of the target vehicle. The target point is the point where a collision is most likely to occur when the target vehicle has a heading deviation. Connecting the rear axle center point of the target vehicle with the target point forms the target line segment of the target vehicle. Based on the vehicle width and target length of the target vehicle in the vehicle data, the length of the target line segment and the target angle between the target line segment and the vehicle centerline are determined.

[0072] For example, based on the Pythagorean theorem, the length of the target line segment and the target angle between the target line segment and the vehicle's centerline are determined according to the following formula: , , in, From the perspective of the target, The length of the target line segment.

[0073] Furthermore, such as Figure 5 As shown, the target vehicle is rotated with its rear axle center as the rotation center, so that it is parallel to the target lane. A perpendicular line is drawn from the target point of the target vehicle to the centerline of the rotating vehicle. The foot of this perpendicular on the centerline of the rotating vehicle is taken as the reference point. A right triangle is formed by connecting the target point, the rear axle center point, and the reference point. Applying the Pythagorean theorem within this right triangle, the length D2 of the leg between the target point and the reference point is obtained. Based on D2, the maximum lateral offset distance between the rear axle center point and the lane centerline (i.e., the second target lateral offset distance) is obtained when there is a heading difference between the target vehicle and the target lane.

[0074] For example, the second target lateral offset distance between the rear axle center point and the lane centerline is determined according to the following formula: , in, This represents the lateral offset distance of the second target. For lane heading, For vehicle heading, It is D2.

[0075] Furthermore, the second correction amount generated by the first target driving constraint object relative to the first target's safe lateral offset distance is determined according to the following formula: , in, This is the second correction amount.

[0076] Here, the second correction amount represents the minimum safe distance that the rear of the vehicle must maintain from the first target driving constraint object due to vehicle yaw. It can be understood that the second correction amount is also the minimum safe distance that the rear axle center point of the target vehicle must reserve when the target vehicle is yawing. Therefore, the second correction amount is used to correct the first target safe lateral offset distance corresponding to the first target driving constraint object, in order to further tighten the boundary of the drivable path of the target vehicle on the side closer to the first target driving constraint object.

[0077] In this embodiment, the second correction amount ensures that when the vehicle yaws, the outermost point of the vehicle's front end cannot exceed the first target driving constraint object, that is, the outermost point of the vehicle's front end must be within the first target driving constraint object.

[0078] Step 206: Determine the longitudinal constraint length of the target vehicle based on the vehicle speed and preset duration in the vehicle data; when the target vehicle is traveling within the longitudinal constraint length range, correct the first target safe lateral offset distance based on the first correction amount and the second correction amount; when the target vehicle is traveling outside the longitudinal constraint length range, correct the first target safe lateral offset distance based on the first correction amount; form the drivable path boundary based on the corrected first target safe lateral offset distance and the second target lateral safe offset distance.

[0079] In this step, the longitudinal constraint length of the drivable path boundary for the target vehicle is calculated based on the product of the target vehicle's speed and the preset duration. Here, longitudinal refers to the direction of travel along the lane centerline.

[0080] It should be noted that the drivable path boundary includes the boundaries on both sides of the target vehicle.

[0081] like Figure 6 As shown, for the drivable path boundary of the target vehicle near the first target driving constraint object, when the target vehicle is within the longitudinal constraint length range, the constraints caused by heading deviation and road curvature radius are considered simultaneously. Therefore, the safe lateral offset distance of the first target is corrected according to the first correction amount and the second correction amount. For example, it is expressed as: , in, The corrected first target safety lateral offset distance.

[0082] It is worth mentioning that when the lane is a straight road, that is, when the lane radius R approaches infinity, then: tending to ; When the vehicle's heading is parallel to the lane's heading, then: ,Right now: ; This explains why, when the target lane is a straight road and the vehicle's heading is parallel to the lane's heading, but: .

[0083] Heading deviation correction is typically a short-term dynamic adjustment, while long-term path planning focuses more on road geometry. Therefore, for the drivable path boundary near the side of the target vehicle that is close to the first target driving constraint object, when the target vehicle travels outside the longitudinal constraint length range, the constraint caused by the road curvature radius is applied, without considering the heading deviation constraint. Thus, based on the first correction amount, the safe lateral offset distance of the first target is corrected. For example, this can be represented as: .

[0084] The heading deviation and road curvature radius cause the target vehicle to move closer to the first target constraint object. Therefore, for the drivable path boundary on the side of the target vehicle that is closer to the second target driving constraint object, the second target safe lateral offset distance corresponding to the second target driving constraint object is still used, and the impact on the drivable path boundary on the side of the target vehicle that is closer to the second target driving constraint object can be ignored.

[0085] Based on the corrected first target safety lateral offset distance and second target lateral safety offset distance, a drivable path boundary is formed in front of the target vehicle, extending longitudinally along the target lane, and located on both sides of the target vehicle.

[0086] In another embodiment of this application, such as Figure 6 As shown, the preset safe lateral threshold for solid line lane markings is set to 0.2, the preset safe lateral threshold for dashed line lane markings is set to 0.1, the preset safe lateral threshold for road boundaries is set to 0.3, the preset safe lateral threshold for obstacles is set to 0.3, and a preset duration is set. =3.0s.

[0087] like Figure 6 As shown, obtain the vehicle width. =2.0m, from the rear axle to the front boundary of the vehicle. =5.0m, vehicle heading =0.336rad, vehicle speed V =2.0m / s, lane width =3.8m, radius of curvature of the target lane R =30.0m, target lane heading =0.341 rad.

[0088] exist Figure 6In the scenario, the vehicle (i.e., the target vehicle) is on a right-turn lane. The first target driving constraint object of the vehicle is the solid lane line on the left side of the vehicle, and the second target driving constraint object is the solid lane line on the right side of the vehicle.

[0089] Calculate the first target safe lateral offset distance corresponding to the first target driving constraint object. .

[0090] Since the first and second target driving constraint objects are of the same type, both being solid lane lines, the second target driving constraint object's second target safe lateral offset distance... It is also 0.7m.

[0091] Next, calculate the first correction caused by the road curvature radius: .

[0092] Next, calculate the second correction caused by the deviation between the vehicle's heading and the road's heading: .

[0093] Next, calculate the longitudinal constraint length of the drivable path boundary for the vehicle: .

[0094] Therefore, when the longitudinal distance traveled by the vehicle is less than the longitudinal constraint length, the drivable path boundary located on the side of the vehicle closest to the first target driving constraint object is determined according to... The drivable path boundary on the side of the vehicle closest to the second target driving constraint is determined based on 0.7 meters. When the longitudinal distance traveled by the vehicle is greater than the longitudinal constraint length, the drivable path boundary on the side of the vehicle closest to the first target driving constraint is determined based on... The drivable path boundary located on the side of the vehicle closest to the second target driving constraint object is determined based on 0.7 meters.

[0095] It should be noted that the sequence number of each step in the above embodiments does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this application.

[0096] Furthermore, such as Figure 7 As shown, as a specific implementation of the above-mentioned drivable path boundary calculation method, this application embodiment provides a drivable path boundary calculation device 700, which includes: an acquisition module 701, a projection module 702, and a calculation module 703.

[0097] The acquisition module 701 is used to acquire vehicle data of the target vehicle, road data of the target lane where the target vehicle is located, and obstacle data of the target lane. Projection module 702 is used to project vehicle data and obstacle data onto the same preset map; The calculation module 703 is used to determine the target driving constraint object of the target vehicle in the preset map after projection, based on vehicle data, among the driving constraint objects contained in the target lane, the driving constraint object being determined according to road data and obstacle data; and to determine the target safe lateral offset distance between the rear axle center point of the target vehicle and the target driving constraint object, with the vehicle center line of the target vehicle located on the lane center line of the target lane as a reference, the rear axle center point being located on the vehicle center line; and to correct the target safe lateral offset distance based on vehicle data and road data, so as to determine the drivable path boundary of the target vehicle according to the corrected target safe lateral offset distance.

[0098] Optionally, the calculation module 703 is specifically used to determine the target safe lateral offset distance between the rear axle center point of the target vehicle and the target driving constraint object based on the lane width of the target lane in the road data, the vehicle width in the vehicle data, and the preset safe lateral threshold corresponding to the target driving constraint object in the road data or obstacle data.

[0099] Optionally, the calculation module 703 is specifically used to determine the target lateral offset distance between the rear axle center point and the lane center line based on the vehicle width and target length in the vehicle data and the lane width in the road data, wherein the target length is determined based on the rear axle center point and the front boundary of the target vehicle; determine the correction amount generated by the first target driving constraint object on the first target safe lateral offset distance based on the lane width, vehicle width and target lateral offset distance; and correct the first target safe lateral offset distance based on the correction amount.

[0100] Optionally, the calculation module 703 is specifically used to determine the first target lateral offset distance between the rear axle center point and the lane centerline when the curvature radius of the target lane in the road data is not equal to the preset value, based on the fact that the vehicle heading of the target vehicle in the vehicle data is the same as the lane heading of the target lane in the road data, according to the curvature radius, target length, and vehicle width.

[0101] Optionally, the calculation module 703 is specifically used to determine, based on the lane width, vehicle width and the first target lateral offset distance, the first correction amount generated by the first target driving constraint object on the first target safe lateral offset distance when the target lane has a radius of curvature.

[0102] Optionally, the calculation module 703 is specifically used to: if the vehicle heading of the target vehicle in the vehicle data is different from the lane heading of the target lane in the road data, take the front corner of the target vehicle closest to the first target driving constraint object as the target point of the target vehicle; connect the rear axle center point of the target vehicle with the target point to obtain the target line segment of the target vehicle; use the radius of curvature of the target lane in the road data as a preset value as a reference, and determine the length of the target line segment and the target angle between the target line segment and the vehicle centerline according to the vehicle width and the target length; and determine the second target lateral offset distance between the rear axle center point and the lane centerline when the vehicle heading and the lane heading are different, based on the difference between the vehicle heading and the lane heading, the length and target angle of the target line segment, and the lane width.

[0103] Optionally, the calculation module 703 is specifically used to determine the longitudinal constraint length of the target vehicle based on the vehicle speed and preset duration in the vehicle data; when the target vehicle is traveling within the longitudinal constraint length range, the first target safe lateral offset distance is corrected according to the first correction amount and the second correction amount; when the target vehicle is traveling outside the longitudinal constraint length range, the first target safe lateral offset distance is corrected according to the first correction amount; and the drivable path boundary of the target vehicle is determined according to the corrected target safe lateral offset distance, specifically including: forming the drivable path boundary according to the corrected first target safe lateral offset distance and the second target lateral safe offset distance.

[0104] Specific limitations regarding the drivable path boundary calculation device can be found in the limitations of the drivable path boundary calculation method described above, and will not be repeated here. Each module in the aforementioned drivable path boundary calculation device can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in or independent of the processor in a computer device in hardware form, or stored in the memory of a computer device in software form, so that the processor can call and execute the operations corresponding to each module.

[0105] Based on the above, Figures 1 to 2 Accordingly, embodiments of this application also provide a readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the above-described method. Figures 1 to 2 The method for calculating the drivable path boundary is shown.

[0106] Based on this understanding, the technical solution of this application can be embodied in the form of a software product. The software product can be stored in a non-volatile storage medium (such as a CD-ROM, USB flash drive, or portable hard drive), and includes several instructions to cause a computer device (such as a personal computer, server, or network device) to execute the methods described in the various implementation scenarios of this application.

[0107] Based on the above, Figures 1 to 2 The method shown, and Figure 7 To achieve the above objectives, the present application also provides a computer device, specifically a personal computer, server, network device, etc., as shown in the virtual device embodiment. This computer device includes a storage medium and a processor; the storage medium stores a computer program; the processor executes the computer program to achieve the above-described objectives. Figures 1 to 2 The method for calculating the drivable path boundary is shown.

[0108] Optionally, the computer device may also include a user interface, a network interface, a camera, radio frequency (RF) circuitry, sensors, audio circuitry, a Wi-Fi module, etc. The user interface may include a display screen, input units such as a keyboard, etc., and optional user interfaces may also include USB ports, card reader ports, etc. The network interface may optionally include standard wired interfaces, wireless interfaces (such as Bluetooth interfaces, Wi-Fi interfaces), etc.

[0109] Those skilled in the art will understand that the computer device structure provided in this embodiment does not constitute a limitation on the computer device, and may include more or fewer components, or combine certain components, or have different component arrangements.

[0110] The storage medium may also include an operating system and a network communication module. The operating system is a program that manages and stores the hardware and software resources of a computer device, supporting the operation of information processing programs and other software and / or programs. The network communication module is used to enable communication between the various components within the storage medium, as well as communication with other hardware and software within the physical device.

[0111] Through the above description of the embodiments, those skilled in the art can clearly understand that this application can be implemented by means of software plus necessary general-purpose hardware platform, or the embodiments of this application can be implemented by hardware.

[0112] Those skilled in the art will understand that the accompanying drawings are merely schematic diagrams of a preferred embodiment, and the modules or processes shown in the drawings are not necessarily essential for implementing this application. Those skilled in the art will understand that the modules in the apparatus of the embodiment can be distributed within the apparatus of the embodiment as described, or can be modified to be located in one or more apparatuses different from this embodiment. The modules of the above-described embodiment can be combined into one module, or further divided into multiple sub-modules.

[0113] The serial numbers in this application are for descriptive purposes only and do not represent the superiority or inferiority of any particular implementation scenario. The above disclosures are merely a few specific implementation scenarios of this application; however, this application is not limited thereto, and any variations conceived by those skilled in the art should fall within the protection scope of this application.

Claims

1. A method for calculating the boundary of a drivable path, characterized in that, The method includes: Acquire vehicle data of the target vehicle, road data of the target lane where the target vehicle is located, and obstacle data of the target lane; The vehicle data and obstacle data are projected onto the same preset map; In the projected preset map, based on the vehicle data, the target driving constraint object of the target vehicle is determined from the driving constraint objects contained in the target lane. The driving constraint object is determined according to the road data and obstacle data. Based on the fact that the center line of the target vehicle is located on the center line of the target lane, the target safe lateral offset distance between the rear axle center point of the target vehicle and the target driving constraint object is determined, wherein the rear axle center point is located on the center line of the vehicle. Based on the vehicle data and the road data, the target safe lateral offset distance is corrected, so as to determine the drivable path boundary of the target vehicle according to the corrected target safe lateral offset distance; The target driving constraint object includes a first target driving constraint object closer to the target vehicle, and the target safe lateral offset distance includes a first target safe lateral offset distance corresponding to the first target driving constraint object; The step of correcting the target safe lateral offset distance based on the vehicle data and the road data specifically includes: If the radius of curvature of the target lane in the road data is not equal to the preset value, based on the fact that the vehicle heading of the target vehicle in the vehicle data is the same as the lane heading of the target lane in the road data, the first target lateral offset distance between the rear axle center point and the lane centerline is determined according to the radius of curvature, target length, and vehicle width when the target lane has a radius of curvature. Based on the lane width, vehicle width and first target lateral offset distance, determine the first correction amount generated by the first target driving constraint object on the first target safe lateral offset distance when the target lane has a radius of curvature; If the vehicle heading of the target vehicle in the vehicle data is different from the lane heading of the target lane in the road data, the front corner of the target vehicle that is closest to the first target driving constraint object is taken as the target point of the target vehicle. Connect the center point of the rear axle of the target vehicle with the target point to obtain the target line segment of the target vehicle; Using the radius of curvature of the target lane in the road data as a preset value as a benchmark, the length of the target line segment and the target angle between the target line segment and the vehicle centerline are determined according to the vehicle width and target length. Based on the difference between the vehicle heading and the lane heading, the length and angle of the target line segment, and the lane width, determine the second target lateral offset distance between the rear axle center point and the lane centerline when the vehicle heading and the lane heading are not the same. Based on the lane width, vehicle width, and lateral offset distance of the second target, determine the second correction amount generated by the first target driving constraint object on the safe lateral offset distance of the first target when the vehicle heading and the lane heading are not the same; When the target vehicle is traveling within the longitudinal constraint length range, the first target safe lateral offset distance is corrected according to the first correction amount and the second correction amount; When the target vehicle travels outside the longitudinal constraint length range, the first target safe lateral offset distance is corrected according to the first correction amount.

2. The method for calculating the drivable path boundary according to claim 1, characterized in that, Determining the target safe lateral offset distance between the rear axle center point of the target vehicle and the target driving constraint object specifically includes: Based on the lane width of the target lane in the road data, the vehicle width in the vehicle data, and the preset safe lateral threshold corresponding to the target driving constraint object, the target safe lateral offset distance between the rear axle center point of the target vehicle and the target driving constraint object is determined.

3. The method for calculating the drivable path boundary according to claim 1, characterized in that, The target driving constraint object also includes a second target driving constraint object located on the other side of the target vehicle, and the target safe lateral offset distance also includes a second target safe lateral offset distance corresponding to the second target driving constraint object.

4. The method for calculating the drivable path boundary according to claim 3, characterized in that, The method further includes: Based on the target vehicle's speed and preset duration in the vehicle data, determine the longitudinal constraint length of the target vehicle; The drivable path boundary of the target vehicle is determined based on the corrected target safety lateral offset distance, specifically including: The drivable path boundary is formed based on the corrected first target safe lateral offset distance and the second target safe lateral offset distance.

5. An apparatus for implementing the drivable path boundary calculation method according to any one of claims 1-4, characterized in that, The device includes: The acquisition module is used to acquire vehicle data of the target vehicle, road data of the target lane where the target vehicle is located, and obstacle data of the target lane; The projection module is used to project the vehicle data and obstacle data onto the same preset map; The calculation module is configured to, in the projected preset map, determine the target driving constraint object of the target vehicle among the driving constraint objects included in the target lane based on the vehicle data, wherein the driving constraint object is determined according to the road data and obstacle data; and, with the vehicle centerline of the target vehicle located on the lane centerline of the target lane as a reference, determine the target safe lateral offset distance between the rear axle center point of the target vehicle and the target driving constraint object, wherein the rear axle center point is located on the vehicle centerline; and, based on the vehicle data and the road data, correct the target safe lateral offset distance to determine the drivable path boundary of the target vehicle according to the corrected target safe lateral offset distance.

6. A readable storage medium having a program or instructions stored thereon, characterized in that, When the program or instructions are executed by the processor, they implement the steps of the drivable path boundary calculation method as described in any one of claims 1 to 4.

7. A computer device, comprising a storage medium, a processor, and a computer program stored on the storage medium and executable on the processor, characterized in that, When the processor executes the program, it implements the drivable path boundary calculation method as described in any one of claims 1 to 4.

Images