Method and device for determining a drivable area

Abstract

Embodiments of the present invention disclose a method and apparatus for determining a drivable area. The method comprises: obtaining sensor parameters, a region of interest, and road boundary data of a driving vehicle, and determining an initial drivable area for the driving vehicle based on the sensor parameters, the region of interest, and the road boundary data; obtaining obstacle data of at least one obstacle sensed by the driving vehicle, and determining a target corner point based on the initial drivable area, the obstacle data, and a preset angular resolution; and determining a target drivable area for the driving vehicle based on the target corner point. The technical solution of the embodiments of the present invention can reduce computational time and improve area utilization.

Description

Technical Field

[0001] The embodiments of the present invention relate to the field of data processing technology, and in particular to a method and device for determining a drivable area. Background Art

[0002] The Free Space refers to an obstacle-free area where a vehicle can safely travel. By determining the Free Space, the driver's driving decision can be assisted, such as providing lane change guidance to prevent traffic accidents and collision prevention.

[0003] However, the existing methods for determining the drivable area are computationally time-consuming and have low area utilization, which needs to be solved. Summary of the Invention

[0004] The embodiments of the present invention provide a method and device for determining a drivable area, so as to reduce computation time and improve area utilization.

[0005] According to one aspect of the present invention, a method for determining a drivable area is provided, which may include:

[0006] Obtaining sensor parameters, regions of interest, and road boundary data of the driving vehicle, and determining an initial drivable area of ​​the driving vehicle based on the sensor parameters, regions of interest, and road boundary data;

[0007] Obtaining obstacle data of at least one obstacle that can be sensed by the driving vehicle, and determining a target corner point based on the initial drivable area, the obstacle data, and a preset angular resolution;

[0008] According to the target corner points, the target drivable area of ​​the driving vehicle is determined.

[0009] According to another aspect of the present invention, a device for determining a drivable area is provided, which may include:

[0010] An initial drivable area determination module is used to obtain sensor parameters, regions of interest, and road boundary data of the driving vehicle, and determine the initial drivable area of ​​the driving vehicle based on the sensor parameters, regions of interest, and road boundary data;

[0011] a target corner point determination module, configured to obtain obstacle data of at least one obstacle that can be sensed by the driving vehicle, and determine a target corner point based on the initial drivable area, the obstacle data, and a preset angular resolution;

[0012] The target drivable area determination module is used to determine the target drivable area of ​​the driving vehicle based on the target corner point.

[0013] The technical solution of the embodiment of the present invention obtains sensor parameters, regions of interest, and road boundary data of the driving vehicle, and determines the initial drivable area of ​​the driving vehicle based on the sensor parameters, regions of interest, and road boundary data; obtains obstacle data of at least one obstacle that can be sensed by the driving vehicle, and determines a target corner point based on the initial drivable area, the obstacle data, and a preset angular resolution; and determines the target drivable area of ​​the driving vehicle based on the target corner point. The technical solution of the embodiment of the present invention, through the sensor parameters, regions of interest, and road boundary data of the driving vehicle, can effectively reduce the calculation scope of the initial drivable area determined, and the initial drivable area is more targeted, thereby reducing calculation time through the reduced calculation scope and improving area utilization through the more targeted initial drivable area.

[0014] It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present invention, nor is it intended to limit the scope of the present invention. Other features of the present invention will become readily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] Figure 1 This is a flow chart of a method for determining a drivable area provided in the first embodiment of the present invention;

[0016] Figure 2 Schematic diagram of an initial drivable area in a drivable area determination method provided in Embodiment 1 of the present invention;

[0017] Figure 3 This is a schematic diagram of determining spike points in a method for determining a drivable area provided in the first embodiment of the present invention;

[0018] Figure 4 This is a schematic diagram of determining a second contour point that needs to be removed in a method for determining a drivable area provided in the first embodiment of the present invention;

[0019] Figure 5 This is a flow chart of a method for determining a drivable area provided in the second embodiment of the present invention;

[0020] Figure 6 This is a flowchart of a method for determining a drivable area provided in the third embodiment of the present invention;

[0021] Figure 7 Schematic diagram of an envelope cube in a method for determining a drivable area provided in the third embodiment of the present invention;

[0022] Figure 8 This is a flowchart of a method for determining a drivable area provided in a fourth embodiment of the present invention;

[0023] Figure 9 Schematic diagram of determining an obstacle sector in a method for determining a drivable area provided in a fourth embodiment of the present invention;

[0024] Figure 10 Schematic diagram of a fused obstacle sector in a method for determining a drivable area provided in a fourth embodiment of the present invention;

[0025] Figure 11 This is a schematic diagram of determining obstacle corner points in a method for determining a drivable area provided in a fourth embodiment of the present invention;

[0026] Figure 12 Schematic diagram of connecting obstacle corner points in a method for determining a drivable area provided in a fourth embodiment of the present invention;

[0027] Figure 13 This is a schematic diagram of determining the chord length of the nearest sector in a method for determining a drivable area provided in a fourth embodiment of the present invention;

[0028] Figure 14 1 is a schematic diagram of determining an obstacle-free corner point in a method for determining a drivable area provided in Embodiment 1 of the present invention;

[0029] Figure 15 This is a flowchart of an operation of reading a configuration file of a driving vehicle in an optional example of a method for determining a drivable area provided in a fourth embodiment of the present invention;

[0030] Figure 16 This is a flowchart of obtaining an initial drivable area in an optional example of a method for determining a drivable area provided in the fourth embodiment of the present invention;

[0031] Figure 17 This is a flowchart of obtaining at least one obstacle sector in an optional example of a method for determining a drivable area provided in Embodiment 4 of the present invention;

[0032] Figure 18 This is a flowchart of determining a target drivable area for a driving vehicle in an optional example of a drivable area determination method provided in Embodiment 4 of the present invention;

[0033] Figure 19 This is a flowchart of another optional example of a method for determining a drivable area provided in the fourth embodiment of the present invention;

[0034] Figure 20 This is a structural block diagram of the device for determining a drivable area provided in the fifth embodiment of the present invention. DETAILED DESCRIPTION

[0035] In order to enable those skilled in the art to better understand the solutions of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the embodiments described are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts should fall within the scope of protection of the present invention.

[0036] It should be noted that the terms "first", "second", etc. in the description and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. The situations of "target", "original", etc. are similar and will not be repeated here. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or that are inherent to these processes, methods, products or devices.

[0037] Example 1

[0038] Figure 1 This is a flowchart of a method for determining a drivable area provided in Embodiment 1 of the present invention. This embodiment is applicable to situations where a drivable area is determined. This method can be performed by a drivable area determination device provided in an embodiment of the present invention. This device can be implemented in software and / or hardware and can be integrated into an electronic device, such as various user terminals or servers.

[0039] See also Figure 1 The method of the embodiment of the present invention specifically includes the following steps:

[0040] S101: Acquire sensor parameters, regions of interest, and road boundary data of a driving vehicle, and determine an initial drivable area of ​​the driving vehicle based on the sensor parameters, regions of interest, and road boundary data.

[0041] The driving vehicle may be a vehicle driven by a driver, an autonomous driving vehicle, an assisted autonomous driving vehicle, and the like. The sensor parameters are parameters of the sensors on the driving vehicle, and the sensor parameters may be the sensor type, the field of view (FOV) of the sensor, the detection range and / or the maximum detectable distance, and the like. The sensor may be a lidar, a millimeter wave radar, a camera, an infrared sensor and / or an ultrasonic sensor, and the like. The region of interest may be a pre-set region of interest of the driving vehicle; the region of interest may be determined based on the vehicle parameters of the driving vehicle, for example, based on the body size of the driving vehicle and / or the steering angle of the driving vehicle, and the like; the region of interest may also be determined based on driving needs; in the embodiment of the present invention, there is no specific limitation on the method for determining the region of interest. Road boundary data is data related to the boundary of the road corresponding to the driving vehicle; the road boundary data can be expressed in the form of a road boundary equation, for example; the road boundary data can be data on the boundary of the road where the driving vehicle is located, or data on the boundary of the road within a preset range of the driving vehicle, etc.; the road boundary data can be sensed by sensor data on the driving vehicle, or generated by driving software such as autonomous driving software, or obtained based on relevant data of maps such as high-precision maps; the road boundary data can include the location of the road boundary line, the width of the road and / or the length of the road, etc.

[0042] It's important to note that if the vehicle has at least one sensor, the sensor parameters can be determined based on the parameters of at least one sensor. For example, the field of view angle (FOV) of a sensor can be derived by fusing the FOV angles of at least one sensor. This solution allows for unlimited angular range and 360° detection, regardless of the limitations of a single radar's FOV and other sensor parameters, allowing for efficient adjustments based on demand.

[0043] In an embodiment of the present invention, sensor parameters, area of ​​interest, and road boundary data of a driving vehicle can be obtained, and an initial drivable area of ​​the driving vehicle can be determined based on the sensor parameters, area of ​​interest, and road boundary data. The initial drivable area is an area in which the driving vehicle can be driven, which is determined based on the sensor parameters, area of ​​interest, and road boundary data. Determining the initial drivable area of ​​the driving vehicle can also be understood as determining the boundary line of the initial drivable area of ​​the driving vehicle.

[0044] For example, see Figure 2, the sensor parameters of the driving vehicle and the region of interest (ROI) can be obtained. The region of interest can be an area with a four-dimensional range; according to the position point of the driving vehicle and the maximum detectable distance in the sensor parameters, a circular area with the position point as the center and the maximum detectable distance as the radius is determined as the original drivable area; according to the field of view angle of the sensor in the sensor parameters, the FOV range, that is, the field of view angle range, is determined; the original drivable area, FOV range and ROI area are fused to obtain Figure 2 The fused four-dimensional range in the shaded area is used as the initial drivable area for the driving vehicle. A location point can be understood as a point that can represent the position of the driving vehicle. For example, the location point can be the center point of the driving vehicle, the center point of the front axle of the driving vehicle, the center point of the rear axle of the driving vehicle, and so on. In the embodiments of the present invention, there is no specific limitation on the location point. A location point can simply represent the position of the driving vehicle relative to at least one obstacle sensed by the driving vehicle or the road on which the driving vehicle is located. A location point can also be a point that can represent the position of the driving vehicle on a map or in a world coordinate system, and so on.

[0045] It should be noted that since the obstacle data obtained is for at least one obstacle that can be sensed by the drivable vehicle, not all obstacle data is required for subsequent steps. Therefore, after obtaining the obstacle data for at least one obstacle that can be sensed by the drivable vehicle, the obstacle data for the at least one obstacle can be filtered based on the initial drivable area, retaining only the obstacle data for obstacles within the initial drivable area, and updating the obstacle data for the at least one obstacle based on the filtering result. The obstacle data for the at least one obstacle can also be filtered based on a preset obstacle height threshold and / or size threshold, filtering out the obstacle data for smaller and / or shorter obstacles among the at least one obstacle, thereby filtering out obstacles such as plastic bags, waste paper, or small boxes that will not affect the driving process, and updating the obstacle data for the at least one obstacle based on the filtering result.

[0046] S102: Obtain obstacle data of at least one obstacle that can be sensed by the driving vehicle, and determine a target corner point based on the initial drivable area, the obstacle data, and a preset angular resolution.

[0047] An obstacle is any obstacle that can be sensed by the driving vehicle. Obstacles may include other vehicles besides the driving vehicle, humans, animals, trash cans, boxes, or plastic bags, among others. Obstacle data refers to data related to at least one obstacle; obstacle data may include information such as the obstacle's location, size, and / or outline. The preset angular resolution is a preset angular resolution; the preset angular resolution may be a preset fixed angular resolution, or may be determined based on the size of the initial drivable area, or based on the accuracy of the target drivable area determined based on requirements. In the embodiments of the present invention, the method for determining the preset angular resolution is not specifically limited.

[0048] In an embodiment of the present invention, the sensors on the driving vehicle can detect obstacles within the sensor detection range and perceive obstacle data of the obstacles, thereby obtaining obstacle data of at least one obstacle that can be sensed by the driving vehicle. The obstacle data of at least one obstacle can be, for example, in the form of an obstacle list. Based on the initial drivable area, obstacle data, and preset angular resolution, a target corner point is determined. The target corner point can be understood as a corner point that can determine the target drivable area. Specifically, the target corner point can be a point that can serve as the vertex of an angle on the target drivable area. The target drivable area can be understood as an area in which the driving vehicle can actually drivable. In an embodiment of the present invention, there is no specific limitation on the method of determining the target corner point based on the initial drivable area, obstacle data, and preset angular resolution.

[0049] S103: Determine a target drivable area for the vehicle based on the target corner point.

[0050] In an embodiment of the present invention, a target drivable area for a driving vehicle can be determined based on target corner points. For example, the target corner points can be connected in a certain order, and at least one closed boundary line is obtained based on the connecting lines between the target corner points. The area within the at least one boundary line is used as the target drivable area.

[0051] The technical solution of the embodiment of the present invention obtains sensor parameters, regions of interest, and road boundary data of the driving vehicle, and determines the initial drivable area of ​​the driving vehicle based on the sensor parameters, regions of interest, and road boundary data; obtains obstacle data of at least one obstacle that can be sensed by the driving vehicle, and determines a target corner point based on the initial drivable area, the obstacle data, and a preset angular resolution; and determines the target drivable area of ​​the driving vehicle based on the target corner point. The technical solution of the embodiment of the present invention, through the sensor parameters, regions of interest, and road boundary data of the driving vehicle, can effectively reduce the calculation scope of the initial drivable area determined, and the initial drivable area is more targeted, thereby reducing calculation time through the reduced calculation scope and improving area utilization through the more targeted initial drivable area.

[0052] An optional technical solution, after determining the target drivable area, also includes: for each first contour point on the area contour of the target drivable area, determining the first adjacent point of the first contour point from the area contour; based on the first adjacent point, the first contour point and the position point of the driving vehicle, judging whether the first contour point is a spike point on the area contour; if the first contour point is a spike point, removing the first contour point.

[0053] The area contour can be understood as the outer contour of the target drivable area, or as the contour of the boundary line of the target drivable area. A first contour point is a point on the area contour; a first contour point can correspond one-to-one with a target corner point. A first adjacent point can be understood as a point adjacent to a first contour point; a first adjacent point can include the contour point closest to the first contour point in different directions on the area contour; under normal circumstances, the number of first adjacent points for each first contour point is two. A spike point can be understood as a point on the area contour that is more prominent than other first contour points.

[0054] In an embodiment of the present invention, for each first contour point on the area contour of the target drivable area, the first adjacent point of the first contour point can be determined from the area contour; based on the first adjacent point, the first contour point, and the position point of the driving vehicle, it is determined whether the first contour point is a spike point on the area contour. In an embodiment of the present invention, there is no specific limitation on the method of determining whether the first contour point is a spike point on the area contour based on the first adjacent point, the first contour point, and the position point of the driving vehicle; if the first contour point is a spike point, the first contour point is removed; and the target drivable area is updated based on the removal result after removing the first contour point. The above technical solution, by removing the spike points, realizes smoothing of the target drivable area, can remove invalid drivable areas, and effectively ensure the feasibility of the target drivable area.

[0055] Based on the above scheme, another optional technical scheme is to determine the target adjacent points of the first contour point on the area contour, including: determining the first adjacent points of the first contour point on the area contour, wherein the first adjacent points include a first left adjacent point and a first right adjacent point; judging whether the first contour point is a spike point on the area contour based on the first adjacent points, the first contour point and the position point of the driving vehicle, including: when the distance between the first contour point and the position point of the driving vehicle is greater than the distance between the first left adjacent point and the position point, and greater than the distance between the first right adjacent point and the position point, determining the maximum distance between the first left adjacent point and the position point, and the distance between the first right adjacent point and the position point; calculating the adjacent chord length based on the maximum distance, the first left adjacent point and the first right adjacent point; judging whether the first contour point is a spike point on the area contour based on the adjacent chord length and a preset drivable width threshold.

[0056] Among them, the preset drivable width threshold is a preset minimum width threshold that the driving vehicle can travel. The preset drivable width threshold can be determined according to vehicle parameters of the driving vehicle, for example, it can be determined according to vehicle parameters such as the body size of the driving vehicle; the preset drivable width threshold can also be a preset fixed drivable width threshold; and so on.

[0057] It should be noted that the first left neighbor point can be understood as a contour point on the left side of the first contour point; the first right neighbor point can be understood as a contour point on the right side of the first contour point. Specifically, a coordinate system can be established with the position point as the origin and the front of the vehicle facing the positive direction of the longitudinal axis, and the first adjacent point located in the first quadrant or the third quadrant of the coordinate system is used as the first left neighbor point, and the first adjacent point located in the second quadrant or the fourth quadrant of the coordinate system is used as the first right neighbor point; or a coordinate system can be established with the position point as the origin and the north direction of the vehicle in the world coordinate system as the positive direction of the longitudinal axis, and the first adjacent point located in the first quadrant or the third quadrant of the coordinate system is used as the first left neighbor point, and the first adjacent point located in the second quadrant or the fourth quadrant of the coordinate system is used as the first right neighbor point. In an embodiment of the present invention, the first left neighbor point and the first right neighbor point are respectively two adjacent first adjacent points of the first contour point, and the specific positions of the first left neighbor point and the first right neighbor point relative to the first contour point are not specifically limited.

[0058] In the embodiment of the present invention, see Figure 3, the first left neighbor point and the first right neighbor point of the first contour point can be determined from the area contour; when the distance between the first contour point and the position point of the driving vehicle is greater than the distance between the first left neighbor point and the position point, and greater than the distance between the first right neighbor point and the position point, determine the maximum distance between the first left neighbor point and the position point, and the distance between the first right neighbor point and the position point; when the difference between the distance between the first contour point and the position point and the maximum distance exceeds a preset difference threshold, calculate the adjacent chord length based on the maximum distance, the first left neighbor point and the first right neighbor point, for example, the maximum distance can be used as the radius, the position point can be used as the center, and the line segment between the first left neighbor point and the position point can be located at the position of A smooth sector is established using a ray with the position point as an endpoint and a ray with the position point as an edge where the line segment between the first right neighbor point and the position point is located. The chord length of the smooth sector is determined as the adjacent chord length distance. The smooth sector is used to determine whether the first contour point is a spike point. The adjacent chord length distance is the chord length of the sector established with the maximum distance, the first left neighbor point, and the first right neighbor point. Based on the adjacent chord length distance and a preset drivable width threshold, it is determined whether the first contour point is a spike point on the area contour. For example, if the adjacent chord length distance is greater than the preset drivable width threshold, the first contour point can be determined to be a spike point on the area contour.

[0059] In an embodiment of the present invention, when the distance between the first contour point and the position point of the driving vehicle is greater than the distance between the first left neighbor point and the position point, and greater than the distance between the first right neighbor point and the position point, the maximum distance between the distance between the first left neighbor point and the position point and the distance between the first right neighbor point and the position point can be determined; based on the distance between the first contour point and the position point, the maximum distance and the preset difference threshold, it is judged whether the first contour point is a spike point on the area contour. For example, when the difference between the distance between the first contour point and the position point and the maximum distance exceeds the preset difference threshold, it is determined that the first contour point is a spike point on the area contour.

[0060] In an embodiment of the present invention, the first adjacent point of the first contour point can be determined from the area contour, wherein the first adjacent point includes a first left adjacent point and a first right adjacent point; when the distance between the first contour point and the position point of the driving vehicle is greater than the distance between the first left adjacent point and the position point, and greater than the distance between the first right adjacent point and the position point, the maximum distance between the first left adjacent point and the position point, and the distance between the first right adjacent point and the position point are determined; the adjacent chord length is calculated based on the maximum distance, the first left adjacent point, and the first right adjacent point; based on the adjacent chord length and a preset drivable width threshold, it is determined whether the first contour point is a spike point on the area contour. In an embodiment of the present invention, the accuracy of spike point determination can be improved to further remove invalid drivable areas, further effectively ensuring the feasibility of the target drivable area.

[0061] Another optional technical solution, after determining the target drivable area, also includes: when the number of second contour points on the area contour of the target drivable area is greater than a preset point number threshold, for each second contour point on the area contour, determining the second adjacent point of the second contour point from the area contour, wherein the second adjacent point includes a second left adjacent point and a second right adjacent point; determining the adjacent line between the second left adjacent point and the second right adjacent point, and determining the point-line distance between the second contour point and the adjacent line; when the point-line distance is less than the preset distance, removing the second contour point.

[0062] Among them, the second contour point is a point on the area contour; the second contour point can correspond one-to-one with the target corner point. The second adjacent point can be understood as a point adjacent to the second contour point; the second adjacent point can include the contour point closest to the second contour point in different directions on the second contour point on the area contour; under normal circumstances, the number of second adjacent points of each second contour point is two. The preset point count threshold is a preset maximum number threshold of contour points on the target drivable area, and the preset point count threshold can be determined according to the vehicle parameters of the driving vehicle; the preset point count threshold can also be a preset fixed drivable width threshold; the preset point count threshold can also be determined according to the accuracy of the target drivable area determined as required; and so on. The preset distance can be understood as a preset distance used to determine whether the second contour point needs to be removed.

[0063] It should be noted that the second left neighbor point can be understood as a contour point on the left side of the second contour point; the second right neighbor point can be understood as a contour point on the right side of the second contour point. Specifically, a coordinate system can be established with the position point as the origin and the front of the driving vehicle facing the positive direction of the longitudinal axis, and the second adjacent point located in the first quadrant or the third quadrant of the coordinate system is used as the second left neighbor point, and the second adjacent point located in the second quadrant or the fourth quadrant of the coordinate system is used as the second right neighbor point; or a coordinate system can be established with the position point as the origin and the north direction of the driving vehicle in the world coordinate system as the positive direction of the longitudinal axis, and the second adjacent point located in the first quadrant or the third quadrant of the coordinate system is used as the second left neighbor point, and the second adjacent point located in the second quadrant or the fourth quadrant of the coordinate system is used as the second right neighbor point. In an embodiment of the present invention, the second left neighbor point and the second right neighbor point are respectively two adjacent second adjacent points of the second contour point, and the specific positions of the second left neighbor point and the second right neighbor point relative to the second contour point are not specifically limited.

[0064] For example, see Figure 4 , when the number of second contour points on the area contour of the target drivable area is greater than a preset point number threshold, for each second contour point on the area contour, second adjacent points of the second contour point can be determined from the area contour, where the second adjacent points include a second left adjacent point and a second right adjacent point; adjacent connecting lines line1, line2, line3, and line4 between the second left adjacent point and the second right adjacent point of each second contour point are respectively determined, where the adjacent connecting lines are lines obtained by connecting the second left adjacent point and the second right adjacent point; and point-to-line distances dis1, dis2, dis3, and dis4 between each second contour point and the adjacent connecting lines are respectively determined, where the point-to-line distances are the distances between the second contour point and the adjacent connecting lines; for each second contour point on the area contour, if the point-to-line distance is less than a preset distance, the second contour point is removed; and the target drivable area is updated according to the removal result after removing the second contour point.

[0065] In an embodiment of the present invention, when the number of second contour points on the area contour of the target drivable area is greater than a preset point number threshold, for each second contour point on the area contour, second adjacent points of the second contour point can be determined from the area contour, where the second adjacent points include a second left adjacent point and a second right adjacent point; an adjacent connecting line between the second left adjacent point and the second right adjacent point can be determined, and a point-to-line distance between the second contour point and the adjacent connecting line can be determined; and when the point-to-line distance is less than a preset distance, the second contour point can be removed. In an embodiment of the present invention, by removing the second contour points, the number of contour points on the contour area can be controlled, thereby improving the processing efficiency when subsequently using the target drivable area without affecting the wheel shape of the target drivable area.

[0066] Example 2

[0067] Figure 5 This is a flowchart of another method for determining a drivable area provided in the second embodiment of the present invention. This embodiment is optimized based on the above-mentioned technical solutions. In this embodiment, optionally, based on the initial drivable area, obstacle data and preset angular resolution, the target corner point is determined, including: determining sector data corresponding to at least one obstacle based on the obstacle data; determining obstacle corner points based on the initial drivable area, preset angular resolution and sector data; determining obstacle-free corner points based on the initial drivable area, preset angular resolution and sector data; and using obstacle corner points and obstacle-free corner points as target corner points. The explanations of terms that are the same as or corresponding to the above-mentioned embodiments are not repeated here.

[0068] See also Figure 5 The method of this embodiment may specifically include the following steps:

[0069] S201: Acquire sensor parameters, regions of interest, and road boundary data of a driving vehicle, and determine an initial drivable area of ​​the driving vehicle based on the sensor parameters, regions of interest, and road boundary data.

[0070] S202: Obtain obstacle data of at least one obstacle that can be sensed by the driving vehicle.

[0071] S203: Determine sector data corresponding to at least one obstacle based on the obstacle data.

[0072] Sector data can be understood as data corresponding to an obstacle sector established based on obstacle data. Sector data can include data related to the obstacle sector's outline, obstacle numbers for obstacles within the obstacle sector, obstacle data for obstacles within the obstacle sector, data related to obstacle points on the obstacle within the obstacle sector, and / or obstacle point angle information corresponding to at least one obstacle point on the obstacle within the obstacle sector. An obstacle sector can be understood as a sector established within the initial drivable area based on sector data. An obstacle point can be understood as a point on the obstacle's outline.

[0073] It should be noted that in an embodiment of the present invention, a coordinate system can be established with the position point as the origin and the front of the driving vehicle facing the positive direction of the longitudinal axis; a coordinate system can also be established with the position point as the origin and the north direction of the driving vehicle in the world coordinate system facing the positive direction of the longitudinal axis; for each obstacle point among at least one obstacle point on the obstacle in the obstacle sector, the angle between the line connecting the obstacle point and the position point and the positive direction of the longitudinal axis of the coordinate system is determined; obstacle point angle information corresponding to the obstacle point is determined based on the angle, and the obstacle point angle information is information related to the angle between the line connecting the obstacle point and the position point and the positive direction of the longitudinal axis of the coordinate system.

[0074] In the embodiment of the present invention, there is no specific limitation on the method of determining the sector data corresponding to at least one obstacle based on the obstacle data.

[0075] S204: Determine obstacle corner points based on the initial drivable area, the preset angular resolution, and the sector data.

[0076] The obstacle corner point may be understood as a corner point on the obstacle that can determine the target drivable area.

[0077] In the embodiment of the present invention, there is no specific limitation on the method of determining the corner points of the obstacle based on the initial drivable area, the preset angular resolution, and the sector data.

[0078] S205: Determine obstacle-free corner points based on the initial drivable area, the preset angular resolution, and the sector data.

[0079] The obstacle-free corner point may be understood as a corner point in an area without obstacles that can determine the target drivable area.

[0080] In the embodiment of the present invention, there is no specific limitation on the method of determining the obstacle-free corner point based on the initial drivable area, the preset angular resolution, and the sector data.

[0081] S206: Taking the obstacle corner point and the obstacle-free corner point as the target corner point.

[0082] In the embodiment of the present invention, both obstacle corner points and unobstructed corner points may be used as target corner points.

[0083] S207: Determine a target drivable area for the vehicle based on the target corner point.

[0084] The technical solution of the embodiments of the present invention determines sector data corresponding to at least one obstacle based on obstacle data; determines obstacle corner points based on the initial drivable area, a preset angular resolution, and the sector data; and determines obstacle-free corner points based on the initial drivable area, the preset angular resolution, and the sector data; and uses the obstacle corner points and the obstacle-free corner points as target corner points. In this embodiment of the present invention, the obstacle corner points and the obstacle-free corner points can be determined and then used as target corner points, thereby increasing the accuracy of the determined target corner points and thereby improving the accuracy of the target drivable area determined for the driving vehicle.

[0085] Example 3

[0086] Figure 6This is a flowchart of another method for determining a drivable area provided in the third embodiment of the present invention. This embodiment is optimized based on the above-mentioned technical solutions. In this embodiment, optionally, based on the obstacle data, sector data corresponding to at least one obstacle is determined, including: establishing a coordinate system on the ground plane with the position point of the driving vehicle as the origin; for each obstacle in the at least one obstacle, determining the obstacle point angle information corresponding to at least one obstacle point on the obstacle based on the obstacle data and the coordinate system; determining the left point, right point, left point angle information and right point angle information of the obstacle based on the obstacle point angle information, wherein the left point angle information is the obstacle point angle information of the left point, and the right point angle information is the obstacle point angle information of the right point; determining the sector data corresponding to the obstacle based on the obstacle data, the left point, right point, left point angle information and right point angle information. The explanations of the terms that are the same or corresponding to the above-mentioned embodiments are not repeated here.

[0087] See also Figure 6 The method of this embodiment may specifically include the following steps:

[0088] S301: Acquire sensor parameters, regions of interest, and road boundary data of a driving vehicle, and determine an initial drivable area of ​​the driving vehicle based on the sensor parameters, regions of interest, and road boundary data.

[0089] S302: Obtain obstacle data of at least one obstacle that can be sensed by the driving vehicle.

[0090] S303: Establish a coordinate system on the ground plane with the position point of the driving vehicle as the origin.

[0091] In an embodiment of the present invention, a coordinate system can be established with the position point of the driving vehicle as the origin, the two-dimensional ground plane as the plane on which the coordinate system is located, and the direction of the front of the driving vehicle as the positive direction of the longitudinal axis; or a coordinate system can be established with the position point as the origin, the two-dimensional ground plane as the plane on which the coordinate system is located, the two-dimensional ground plane as the plane on which the coordinate system is located, and the direction of due north in the world coordinate system of the driving vehicle as the positive direction of the longitudinal axis.

[0092] S304: For each obstacle of the at least one obstacle, determine obstacle point angle information corresponding to at least one obstacle point on the obstacle according to the obstacle data and the coordinate system.

[0093] In an embodiment of the present invention, obstacle point angle information corresponding to at least one obstacle point on the obstacle can be determined for each of at least one obstacle based on obstacle data and a coordinate system. For example, for each of at least one obstacle point on an obstacle in an obstacle sector, the obstacle point can be projected into the coordinate system, and the angle between a line connecting the obstacle point projected into the coordinate system and the position point and the positive longitudinal axis, negative longitudinal axis, positive transverse axis, or negative transverse axis of the coordinate system can be determined. Obstacle point angle information corresponding to the obstacle point can be determined based on the angle.

[0094] In the embodiment of the present invention, for each obstacle in the at least one obstacle, the envelope cube of the obstacle can be calculated based on the obstacle data, for example, see Figure 7 Based on the obstacle data, the obstacle's enveloping cube Geo can be calculated. The cube corner points of the enveloping cube are projected onto the ground plane to obtain at least one projection point. The at least one projection point is used as an obstacle point of the obstacle. Then, for each obstacle in the at least one obstacle, the obstacle point angle information corresponding to the at least one obstacle point on the obstacle is determined based on the obstacle data and the coordinate system.

[0095] S305. Determine the left point, right point, left point angle information, and right point angle information of the obstacle based on the obstacle point angle information, where the left point angle information is the obstacle point angle information of the left point, and the right point angle information is the obstacle point angle information of the right point.

[0096] The left point can be understood as the obstacle point with the smallest horizontal coordinate in the coordinate system among at least one obstacle point on the obstacle, and the right point can be understood as the obstacle point with the largest horizontal coordinate in the coordinate system among at least one obstacle point on the obstacle.

[0097] In an embodiment of the present invention, the left point, right point, left point angle information, and right point angle information of an obstacle can be determined based on the obstacle point angle information. For example, based on the obstacle point angle information, the angles between the lines connecting at least one obstacle point on the obstacle and the origin of the coordinate system and the positive direction of the longitudinal axis of the coordinate system can be determined. The obstacle point corresponding to the maximum angle among the angles corresponding to the at least one obstacle point is used as the left point, and the obstacle point corresponding to the minimum angle among the angles corresponding to the at least one obstacle point is used as the right point. For another example, the obstacle point with the smallest horizontal coordinate in the coordinate system among the at least one obstacle point on the obstacle can be used as the left point, and the obstacle point with the largest horizontal coordinate in the coordinate system among the at least one obstacle point on the obstacle can be used as the right point. The obstacle point angle information of the left point is used as the left point angle information, and the angle information of the left and right obstacle points is used as the right point angle information.

[0098] S306: Determine sector data corresponding to the obstacle based on the obstacle data, the left point, the right point, the left point angle information, and the right point angle information.

[0099] In an embodiment of the present invention, relevant information of an obstacle in a sector can be determined based on the obstacle data, and sector data corresponding to the obstacle can be determined based on the relevant information of the obstacle in the sector, the left point, the right point, the left point angle information, the right point angle information, and the obstacle point angle information corresponding to at least one obstacle point on the obstacle.

[0100] S307: Determine obstacle corner points based on the initial drivable area, the preset angular resolution, and the sector data.

[0101] S308: Determine obstacle-free corner points based on the initial drivable area, the preset angular resolution, and the sector data.

[0102] S309: Taking the obstacle corner point and the obstacle-free corner point as the target corner point.

[0103] S310: Determine a target drivable area for the vehicle based on the target corner point.

[0104] The technical solution of an embodiment of the present invention establishes a coordinate system on the ground plane with the driving vehicle's position as the origin. For each of at least one obstacle, obstacle point angle information corresponding to at least one obstacle point on the obstacle is determined based on the obstacle data and the coordinate system. Based on the obstacle point angle information, the left point, right point, left point angle information, and right point angle information of the obstacle are determined, where the left point angle information is the obstacle point angle information of the left point, and the right point angle information is the obstacle point angle information of the right point. Sector data corresponding to the obstacle is determined based on the obstacle data, the left point, right point, left point angle information, and the right point angle information. In this embodiment of the present invention, the determination of the obstacle point angle information, the left point, right point, left point angle information, and the right point angle information can make the resulting sector data more accurate.

[0105] An optional technical solution determines obstacle point angle information corresponding to at least one obstacle point on the obstacle based on obstacle data and a coordinate system, including: for each of the at least one obstacle point on the obstacle, determining the obstacle point angle information between a point connection line and a coordinate axis of the coordinate system based on the obstacle data, wherein the point connection line is a line connecting the obstacle point and the origin of the coordinate system.

[0106] In an embodiment of the present invention, for each of at least one obstacle point on the obstacle, the angle between the line connecting the points and a coordinate axis of the coordinate system can be determined based on the obstacle data, and the angle can be used as the obstacle point angle information. For example, the angle between the line connecting the points and the positive direction of the ordinate axis of the coordinate system can be determined based on the obstacle data, and the angle can be used as the obstacle point angle information. The line connecting the points is the line connecting the obstacle point and the origin of the coordinate system. In an embodiment of the present invention, the above steps can be used to determine the obstacle point angle information corresponding to at least one obstacle point on the obstacle with high accuracy.

[0107] Example 4

[0108] Figure 8 It is a flow chart of another method for determining a drivable area provided in the fourth embodiment of the present invention. This embodiment is optimized based on the above-mentioned technical solutions. In this embodiment, optionally, based on the initial drivable area, the preset angular resolution and the sector data, the obstacle corner points are determined, including: based on the sector data, at least one obstacle sector is established in the initial drivable area; for each obstacle sector in at least one obstacle sector, based on the preset angular resolution and the sector data, the obstacle corner points are determined in the obstacle sector; and / or, based on the initial drivable area, the preset angular resolution and the sector data, the obstacle-free corner points are determined, including: based on at least one obstacle sector and the initial drivable area, at least one obstacle-free area is determined; for each obstacle-free area in at least one obstacle-free area, the obstacle-free corner points are determined in the obstacle-free area based on the preset angular resolution and the sector data. Among them, the explanations of the terms that are the same as or corresponding to the above-mentioned embodiments are not repeated here.

[0109] In this embodiment, taking the following scheme as an example, obstacle corner points are determined based on the initial drivable area, the preset angular resolution, and the sector data, including: establishing at least one obstacle sector in the initial drivable area based on the sector data; determining obstacle corner points in each obstacle sector based on the preset angular resolution and the sector data; and determining obstacle-free corner points based on the initial drivable area, the preset angular resolution, and the sector data, including: determining at least one obstacle-free area based on the at least one obstacle sector and the initial drivable area; determining obstacle-free corner points in each obstacle-free area in the at least one obstacle-free area based on the preset angular resolution and the sector data. Figure 8 The method of this embodiment may specifically include the following steps:

[0110] S401: Acquire sensor parameters, regions of interest, and road boundary data of a driving vehicle, and determine an initial drivable area of ​​the driving vehicle based on the sensor parameters, regions of interest, and road boundary data.

[0111] S402: Obtain obstacle data of at least one obstacle that can be sensed by the driving vehicle.

[0112] S403: Determine sector data corresponding to at least one obstacle based on the obstacle data.

[0113] S404: Establish at least one obstacle sector in the initial drivable area based on the sector data.

[0114] In the embodiment of the present invention, for each obstacle in the at least one obstacle, see Figure 9 The sector data may include a left point and a right point determined from at least one obstacle point on the obstacle; determining the left point distance between the left point and the position point according to the position point and the left point; determining the right point distance between the right point and the position point according to the position point and the right point; taking the largest distance between the left point distance and the right point distance as the radius, and taking the ray with the position point as the endpoint on which the line segment between the left point and the position point is located, and the ray with the position point as the endpoint on which the line segment between the right point and the position point is located as the edge, and taking the position point as the center of the circle, at least one obstacle sector is established in the initial drivable area.

[0115] In the embodiment of the present invention, see Figure 10 After establishing at least one obstacle sector in the initial drivable area, it is also possible to perform a fusion operation on the obstacle sectors with overlapping areas in the at least one obstacle sector based on the sector data corresponding to the at least one obstacle sector, and update the at least one obstacle sector based on the fusion result.

[0116] S405: For each obstacle sector in the at least one obstacle sector, determine an obstacle corner point in the obstacle sector based on a preset angular resolution and sector data.

[0117] In an embodiment of the present invention, the sector data may include contour data of the obstacle in the obstacle sector, where the contour data is data related to the contour of the obstacle. For each obstacle sector in at least one obstacle sector, an obstacle corner point may be determined in the obstacle sector based on a preset angular resolution and the contour data.

[0118] S406: Determine at least one obstacle-free area based on the at least one obstacle sector and the initial drivable area.

[0119] Among them, the barrier-free area can be understood as an area without obstacles.

[0120] In the embodiment of the present invention, other areas in the initial drivable area except for the at least one obstacle sector may be used as at least one obstacle-free area.

[0121] S407 . For each obstacle-free area in the at least one obstacle-free area, determine an obstacle-free corner point in the obstacle-free area based on a preset angular resolution and sector data.

[0122] In an embodiment of the present invention, the sector data may include corner points or obstacle points located on the boundary of at least one obstacle sector; for each obstacle-free area in at least one obstacle-free area, the obstacle-free corner points can be determined in the obstacle-free area based on a preset angular resolution and the corner points or obstacle points located on the boundary of at least one obstacle sector.

[0123] S408: Taking the obstacle corner point and the obstacle-free corner point as the target corner point.

[0124] S409: Determine a target drivable area for the vehicle based on the target corner point.

[0125] In an embodiment of the present invention, at least one obstacle sector is established within the initial drivable area based on sector data. For each of the at least one obstacle sector, an obstacle corner point is determined within the obstacle sector based on a preset angular resolution and the sector data. At least one obstacle-free area is determined based on the at least one obstacle sector and the initial drivable area. For each of the at least one obstacle-free area, an obstacle-free corner point is determined within the obstacle-free area based on a preset angular resolution and the sector data. In this embodiment of the present invention, obstacle corner points and / or obstacle-free corner points can be determined with higher accuracy.

[0126] An optional technical solution, based on a preset angular resolution and sector data, determines an obstacle corner point in an obstacle sector, including: determining at least one sector ray in the obstacle sector using a ray method with the position point of the driving vehicle as the endpoint according to the preset angular resolution; for each of the at least one sector ray, determining, based on the sector data, a first intersection point closest to the position point among all intersection points between a target obstacle in the obstacle sector and the sector ray, and using the first intersection point as the obstacle corner point, wherein the target obstacle is an obstacle located within the obstacle sector among the at least one obstacle.

[0127] The first intersection point is the intersection point closest to the position point among all intersection points between the target obstacle in the obstacle sector and the sector ray.

[0128] In an embodiment of the present invention, for each obstacle in at least one obstacle, an envelope cube of the obstacle may be calculated based on the obstacle data; the envelope cube may be projected onto a ground plane, the obstacle may be updated according to the projection result, and the obstacle data and contour data of the obstacle may be updated according to the updated obstacle.

[0129] In the embodiment of the present invention, see Figure 11At least one sector ray can be determined in the obstacle sector using a ray method with the position point of the driving vehicle as an endpoint according to a preset angular resolution. That is, a ray can be extended in the obstacle sector with the position point as an endpoint at intervals of the preset angular resolution with the position point as an endpoint. At least one sector ray can be determined in the obstacle sector. The sector ray is a ray obtained in the obstacle sector using the ray method. For each of the at least one sector ray, based on sector data, for example, based on obstacle contour data in the obstacle sector in the sector data, the first intersection point closest to the position point among all intersection points between the contour of the target obstacle in the obstacle sector and the sector ray is determined, and the first intersection point is used as the obstacle corner point. Figure 11 The white intersection points in the image are the intersection points that are not the corner points of obstacles. Figure 11 The black intersection point in is the first intersection point as the obstacle corner point; see Figure 12 After using the first intersection as the obstacle corner point, at least one obstacle corner point can be directly connected in a certain order to facilitate the subsequent determination of the target drivable area for the vehicle. The technical solution of the embodiment of the present invention adopts a purely geometric approach, eliminating the need for deep learning and the need for large amounts of data collection, high-quality annotation, and long-term deep learning model formation. This allows for fast calculation speeds, saves time, and can further obtain more accurate obstacle corner points.

[0130] Another optional technical solution is to determine the obstacle-free corner point in the obstacle-free area based on a preset angular resolution and sector data, including: judging whether the driving vehicle can pass through the obstacle-free area according to the sector data; if the driving vehicle can pass through the obstacle-free area, according to the preset angular resolution, with the position point of the driving vehicle as the endpoint, using the ray method to determine at least one area ray in the obstacle-free area; for each area ray in the at least one area ray, determining the second intersection point between the edge line of the obstacle-free area and the area ray, and using the second intersection point as the obstacle-free corner point.

[0131] In an embodiment of the present invention, it is possible to determine whether the vehicle can pass through the barrier-free area based on the sector data. Figure 13Based on the sector data, the nearest corner point on the boundary of the obstacle sector adjacent to the obstacle-free area can be determined. The nearest corner point is the obstacle corner point on the boundary of the obstacle sector adjacent to the obstacle-free area that is closest to the position point. The nearest corner point can also be understood as the obstacle point on the boundary of the obstacle sector adjacent to the obstacle-free area that is closest to the position point. A nearest sector is established in the obstacle-free area with the line between the nearest corner point and the driving vehicle as the radius and the position point as the center. The nearest sector is the sector established based on the nearest corner point. Based on the radius and the central angle of the nearest sector, a chord length threshold of the nearest sector is determined. The chord length threshold is compared with a preset drivable width threshold. Based on the comparison result, it is determined whether the driving vehicle can pass through the obstacle-free area. That is, if the chord length threshold is greater than or equal to the preset drivable width threshold, the driving vehicle can pass through the obstacle-free area. If the chord length threshold is less than the preset drivable width threshold, the driving vehicle cannot pass through the obstacle-free area.

[0132] In the embodiment of the present invention, see Figure 14 When the vehicle can pass through the obstacle-free area, a ray method is used to determine at least one area ray in the obstacle-free area using the vehicle's location as an endpoint, according to a preset angular resolution. The area ray is the ray determined in the obstacle-free area using the ray method. For each of the at least one area ray, a second intersection point between the boundary line of the obstacle-free area and the area ray is determined, and the second intersection point is used as the obstacle-free corner point. The second intersection point is the intersection point between the boundary line of the obstacle-free area and the area ray. The boundary line can be understood as the boundary line of the obstacle-free area. In this embodiment of the present invention, a more accurate obstacle-free corner point can be determined when the vehicle can pass through the obstacle-free area.

[0133] Based on the above scheme, another optional technical scheme is to determine the obstacle-free corner point in the obstacle-free area based on the preset angular resolution and sector data, and also includes: when the driving vehicle cannot pass through the obstacle-free area, based on the sector data, determining the nearest corner point on the boundary of the obstacle sector adjacent to the obstacle-free area, wherein the nearest corner point is the obstacle corner point on the boundary that is closest to the position point; establishing the nearest sector in the obstacle-free area with the line between the nearest corner point and the driving vehicle as the radius and the position point as the center of the circle; according to the preset angular resolution, with the position point as the endpoint, using the ray method to determine at least one nearest ray in the nearest sector; for each nearest ray in the at least one nearest ray, determining the third intersection point between the edge line of the nearest sector and the nearest ray, and using the third intersection point as the obstacle-free corner point.

[0134] In an embodiment of the present invention, if a driving vehicle cannot pass through an obstacle-free area, it means that the driving vehicle cannot directly reach a position on the edge of the obstacle-free area. Based on the sector data, the nearest corner point on the boundary of the obstacle sector adjacent to the obstacle-free area can be determined; a nearest sector is established in the obstacle-free area with the line between the nearest corner point and the driving vehicle as the radius and the position point as the center; according to a preset angular resolution, with the position point as the endpoint, a ray method is used to determine at least one nearest ray in the nearest sector. The ray in the area is the ray determined by the ray method in the nearest sector; for each of the at least one nearest ray, the third intersection point between the edge of the nearest sector and the nearest ray is determined. The third intersection point is the intersection point between the edge without the nearest sector and the nearest ray, and the third intersection point is used as the obstacle-free corner point. In an embodiment of the present invention, if a driving vehicle cannot pass through an obstacle-free area, a more accurate obstacle-free corner point is determined.

[0135] In order to better understand the technical solution of the above embodiment of the present invention, an optional example is provided here. Figure 15 , the configuration file operation of the driving vehicle can be read. The configuration file operation of the driving vehicle can specifically include obtaining sensor parameters, obtaining ROI range, obtaining road boundary range, obtaining preset angular resolution, obtaining preset drivable width threshold, obtaining preset difference threshold and preset point number threshold.

[0136] See also Figure 16 The original drivable area can be determined according to the maximum detectable distance in the sensor parameters. The original drivable area is a circular area with the position point as the center and the maximum detectable distance as the radius. The original drivable area is cropped according to the FOV range, ROI range and road boundary range in the sensor parameters to obtain the initial drivable area.

[0137] See also Figure 17 Obtain an obstacle list of at least one obstacle that can be sensed by the driving vehicle; filter the obstacle list based on the initial drivable area and preset obstacle height thresholds and size thresholds, and update the obstacle list according to the filtering result; calculate an envelope cube corresponding to each obstacle in the at least one obstacle based on the obstacle list; determine the left point, right point, left point angle information, and right point angle information of the obstacle based on the envelope cube; determine sector data corresponding to the obstacle based on the obstacle list, the left point, right point, left point angle information, and right point angle information; establish at least one obstacle sector in the initial drivable area based on the sector data; perform a fusion operation on obstacle sectors with overlapping areas in the at least one obstacle sector, and update the at least one obstacle sector based on the fusion result.

[0138] See also Figure 18 For each obstacle sector in at least one obstacle sector, an obstacle corner point is determined in the obstacle sector based on a preset angular resolution and sector data; at least one obstacle-free area is determined based on the at least one obstacle sector and the initial drivable area; for each obstacle-free area in the at least one obstacle-free area, an obstacle-free corner point is determined in the obstacle-free area based on the preset angular resolution and sector data; the obstacle corner point and the obstacle-free corner point are used as target corner points; and a target drivable area for the driving vehicle is determined based on the target corner point.

[0139] In order to better understand the technical solution of the above embodiment of the present invention, another optional example is provided here. Figure 19, obtaining sensor parameters and ROI range; determining an original drivable area according to the maximum detectable distance in the sensor parameters; cropping the original drivable area according to the FOV range and ROI range in the sensor parameters to obtain an initial drivable area, and determining the boundary of the initial drivable area; obtaining an obstacle list of at least one obstacle that can be sensed by the driving vehicle; filtering the obstacle list based on the initial drivable area and a preset obstacle height threshold and size threshold, and updating the obstacle list according to the filtering result; calculating an envelope cube corresponding to each obstacle in the at least one obstacle based on the obstacle list; determining the left point, right point, left point angle information, and right point angle information of the obstacle based on the envelope cube; determining sector data corresponding to the obstacle based on the obstacle list, the left point, right point, left point angle information, and right point angle information; establishing at least one obstacle sector in the initial drivable area based on the sector data; performing a fusion operation on obstacle sectors with overlapping areas in the at least one obstacle sector, and updating the at least one obstacle sector according to the fusion result; obtaining a preset angular resolution; For each obstacle sector, the obstacle corner point of the obstacle sector is determined based on the ray method and the preset angular resolution; at least one obstacle-free area is determined based on at least one obstacle sector and the initial drivable area; for each obstacle-free area in the at least one obstacle-free area, the chord length of the nearest sector in the obstacle-free area is determined based on the sector data; a preset drivable width threshold is obtained; it is determined whether the chord length of the nearest sector is greater than the preset drivable width threshold; if the chord length of the nearest sector is greater than the preset drivable width threshold, the boundary line of the obstacle-free area is determined based on the boundary line of the initial drivable area; based on the obstacle-free area The method includes sampling the edge of the nearest sector to obtain an obstacle-free corner point; sampling the edge of the nearest sector when the chord length of the nearest sector is less than or equal to the preset drivable width threshold to obtain an obstacle-free corner point; taking the obstacle corner point and the obstacle-free corner point as the target corner point; obtaining a preset difference threshold and a preset point count threshold; smoothing and simplifying the target corner point based on the preset difference threshold and the preset point count threshold; updating the target corner point according to the processing results of the smoothing and simplifying processing; obtaining the road boundary range; and determining the target drivable area of ​​the driving vehicle based on the target corner point and the road boundary range.

[0140] Example 5

[0141] Figure 20 This is a block diagram of the structure of the device for determining a drivable area provided in the fifth embodiment of the present invention. The device is used to execute the method for determining a drivable area provided in any of the above embodiments. The device and the method for determining a drivable area provided in the above embodiments belong to the same inventive concept. For details not fully described in the embodiment of the device for determining a drivable area, please refer to the embodiment of the method for determining a drivable area provided in the above embodiments. Figure 20The device may specifically include: an initial drivable area determination module 510, a target corner point determination module 520 and a target drivable area determination module 530.

[0142] The initial drivable area determination module 510 is configured to obtain sensor parameters, regions of interest, and road boundary data of the driving vehicle, and determine the initial drivable area of ​​the driving vehicle based on the sensor parameters, regions of interest, and road boundary data;

[0143] a target corner point determination module 520 for acquiring obstacle data of at least one obstacle that can be sensed by the driving vehicle and determining a target corner point based on the initial drivable area, the obstacle data, and a preset angular resolution;

[0144] The target drivable area determination module 530 is configured to determine a target drivable area for the vehicle according to the target corner point.

[0145] Optionally, the target corner point determination module 520 may include:

[0146] a sector data determining unit, configured to determine sector data corresponding to at least one obstacle based on the obstacle data;

[0147] An obstacle corner point determination unit, configured to determine the obstacle corner points based on the initial drivable area, a preset angular resolution, and sector data;

[0148] An obstacle-free corner point determination unit, configured to determine an obstacle-free corner point based on an initial drivable area, a preset angular resolution, and sector data;

[0149] The target corner point is used as a unit to take the obstacle corner point and the obstacle-free corner point as the target corner point.

[0150] Based on the above solution, optionally, the sector data determination unit may include:

[0151] A coordinate system establishment subunit is used to establish a coordinate system on the ground plane with the position point of the driving vehicle as the origin;

[0152] an obstacle point angle information determination subunit, configured to determine, for each obstacle among the at least one obstacle, obstacle point angle information corresponding to at least one obstacle point on the obstacle based on the obstacle data and the coordinate system;

[0153] a right point angle information determination subunit, configured to determine the left point, right point, left point angle information, and right point angle information of the obstacle based on the obstacle point angle information, wherein the left point angle information is the obstacle point angle information of the left point, and the right point angle information is the obstacle point angle information of the right point;

[0154] The sector data determination subunit is used to determine the sector data corresponding to the obstacle according to the obstacle data, the left point, the right point, the left point angle information and the right point angle information.

[0155] Based on the above solution, the obstacle point angle information determination subunit is optionally used to:

[0156] For each obstacle point of at least one obstacle point on the obstacle, determine, based on the obstacle data, information about an angle between a point connection line and a coordinate axis of the coordinate system, where the point connection line is a line between the obstacle point and the origin of the coordinate system.

[0157] Based on the above solution, optionally, the obstacle corner point determination unit may include:

[0158] an obstacle sector establishing subunit, configured to establish at least one obstacle sector in the initial drivable area based on the sector data;

[0159] an obstacle corner point determination subunit, configured to determine, for each obstacle sector in at least one obstacle sector, an obstacle corner point in the obstacle sector based on a preset angular resolution and sector data;

[0160] and / or,

[0161] The obstacle-free corner point determination unit may include:

[0162] an obstacle-free area determination subunit, configured to determine at least one obstacle-free area based on at least one obstacle sector and an initial drivable area;

[0163] The obstacle-free corner point determination subunit is configured to determine an obstacle-free corner point in each obstacle-free area of ​​the at least one obstacle-free area based on a preset angular resolution and sector data.

[0164] Based on the above solution, the optional obstacle corner point determination subunit can be used to:

[0165] According to the preset angular resolution, with the position of the driving vehicle as the endpoint, a ray method is used to determine at least one sector ray in the obstacle sector;

[0166] For each sector ray in the at least one sector ray, determine, based on the sector data, a first intersection point closest to the position point among all intersection points between the target obstacle in the obstacle sector and the sector ray, and use the first intersection point as the obstacle corner point, wherein the target obstacle is an obstacle in the at least one obstacle located within the obstacle sector.

[0167] Based on the above solution, the optional obstacle-free corner point determination subunit can be used to:

[0168] Based on sector data, determine whether the driving vehicle can pass through the obstacle-free area;

[0169] When the driving vehicle can pass through the obstacle-free area, at least one area ray is determined in the obstacle-free area using a ray method with the position of the driving vehicle as the endpoint according to a preset angular resolution;

[0170] For each area ray of the at least one area ray, a second intersection point between the edge line of the obstacle-free area and the area ray is determined, and the second intersection point is used as an obstacle-free corner point.

[0171] Based on the above solution, the optional obstacle-free corner point determination subunit can also be used to:

[0172] In the case where the driving vehicle cannot pass through the obstacle-free area, the nearest corner point located on the boundary of the obstacle sector adjacent to the obstacle-free area is determined based on the sector data, wherein the nearest corner point is the obstacle corner point on the boundary that is closest to the position point;

[0173] With the line between the nearest corner point and the driving vehicle as the radius and the position point as the center, a nearest sector is established in the obstacle-free area;

[0174] According to the preset angular resolution, with the position point as the endpoint, the ray method is used to determine at least one nearest ray in the nearest sector;

[0175] For each of the at least one closest ray, a third intersection point between the edge line of the closest sector and the closest ray is determined, and the third intersection point is used as an unobstructed corner point.

[0176] Optionally, the drivable area determining device may further include:

[0177] A first adjacent point determination module is configured to, after determining the target drivable area, determine, for each first contour point on the area contour of the target drivable area, a first adjacent point of the first contour point on the area contour;

[0178] a spike point determination module, configured to determine whether the first contour point is a spike point on the area contour based on the first adjacent point, the first contour point, and the position point of the driving vehicle;

[0179] The first contour point removal module is used to remove the first contour point if the first contour point is a thorn point.

[0180] Based on the above solution, optionally, the first adjacent point determination module may include:

[0181] A first adjacent point determining unit, configured to determine first adjacent points of a first contour point on the region contour, wherein the first adjacent points include a first left adjacent point and a first right adjacent point;

[0182] The spike point judgment module may include:

[0183] a maximum distance determining unit configured to determine a maximum distance between the first left neighboring point and the location point, and between the first right neighboring point and the location point, when the distance between the first contour point and the location point is greater than the distance between the first left neighboring point and the location point, and greater than the distance between the first right neighboring point and the location point;

[0184] an adjacent chord length calculation unit, configured to calculate the adjacent chord length according to the maximum distance, the first left neighbor point, and the first right neighbor point;

[0185] The spike point judgment unit is used to judge whether the first contour point is a spike point on the area contour according to the adjacent chord length and the preset drivable width threshold.

[0186] Optionally, the drivable area determining device may further include:

[0187] A second adjacent point determination module is configured to, after determining the target drivable area, determine, for each second contour point on the area contour, second adjacent points of the second contour point on the area contour if the number of second contour points on the area contour of the target drivable area is greater than a preset point number threshold, wherein the second adjacent points include a second left adjacent point and a second right adjacent point;

[0188] a point-line distance determination module, configured to determine an adjacent line between the second left neighbor point and the second right neighbor point, and determine a point-line distance between the second contour point and the adjacent line;

[0189] The second contour point removal module is used to remove the second contour point when the point-line distance is less than a preset distance.

[0190] The drivable area determination device provided in the fifth embodiment of the present invention obtains the sensor parameters, area of ​​interest, and road boundary data of the driving vehicle through the initial drivable area determination module, and determines the initial drivable area of ​​the driving vehicle based on the sensor parameters, area of ​​interest, and road boundary data; obtains obstacle data of at least one obstacle that can be sensed by the driving vehicle through the target corner point determination module, and determines the target drivable area of ​​the driving vehicle based on the target corner point through the target drivable area determination module. The above-mentioned device, through the sensor parameters, area of ​​interest, and road boundary data of the driving vehicle, can effectively reduce the calculation range of the initial drivable area determined, and the initial drivable area is more targeted, thereby reducing the calculation time through the reduced calculation range and improving the area utilization through the more targeted initial drivable area.

[0191] The drivable area determination device provided in the embodiment of the present invention can execute the drivable area determination method provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method.

[0192] It is worth noting that in the embodiment of the above-mentioned drivable area determination device, the various units and modules included are only divided according to functional logic, but are not limited to the above-mentioned division, as long as the corresponding functions can be achieved; in addition, the specific names of the functional units are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of the present invention.

Claims

1. A method for determining a drivable area, characterized in that: include: Acquiring sensor parameters, a region of interest, and road boundary data of a driving vehicle, and determining an initial drivable area of ​​the driving vehicle based on the sensor parameters, the region of interest, and the road boundary data; Obtaining obstacle data of at least one obstacle that can be sensed by the driving vehicle, and determining a target corner point based on the initial drivable area, the obstacle data, and a preset angular resolution; determining a target drivable area of ​​the driving vehicle according to the target corner point; The determining of a target corner point based on the initial drivable area, the obstacle data, and a preset angular resolution includes: Determining sector data corresponding to each of the at least one obstacle based on the obstacle data; Determining obstacle corners based on the initial drivable area, the preset angular resolution, and the sector data; Determining an obstacle-free corner point based on the initial drivable area, the preset angular resolution, and the sector data; The obstacle corner point and the obstacle-free corner point are used as target corner points.

2. The method according to claim 1, characterized in that The determining, based on the obstacle data, sector data corresponding to the at least one obstacle includes: Establishing a coordinate system on the ground plane with the position point of the driving vehicle as the origin; For each obstacle of the at least one obstacle, determining obstacle point angle information corresponding to at least one obstacle point on the obstacle according to the obstacle data and the coordinate system; Based on the obstacle point angle information, determine the left point, right point, left point angle information, and right point angle information of the obstacle, wherein the left point angle information is the obstacle point angle information of the left point, and the right point angle information is the obstacle point angle information of the right point; The sector data corresponding to the obstacle is determined according to the obstacle data, the left point, the right point, the left point angle information, and the right point angle information.

3. The method according to claim 2, characterized in that The determining, based on the obstacle data and the coordinate system, obstacle point angle information corresponding to at least one obstacle point on the obstacle includes: For each obstacle point of at least one obstacle point on the obstacle, determine, based on the obstacle data, information about an angle between a point connection line and a coordinate axis of the coordinate system, wherein the point connection line is a line between the obstacle point and the origin of the coordinate system.

4. The method according to claim 1, wherein The determining of the obstacle corner points based on the initial drivable area, the preset angular resolution, and the sector data includes: establishing at least one obstacle sector in the initial drivable area based on the sector data; For each obstacle sector of the at least one obstacle sector, determining an obstacle corner point in the obstacle sector based on a preset angular resolution and the sector data; and / or, The determining of an obstacle-free corner point based on the initial drivable area, the preset angular resolution, and the sector data includes: Determining at least one obstacle-free area based on the at least one obstacle sector and the initial drivable area; For each obstacle-free area in the at least one obstacle-free area, an obstacle-free corner point is determined in the obstacle-free area based on the preset angular resolution and the sector data.

5. The method according to claim 4, characterized in that The determining an obstacle corner point in the obstacle sector based on a preset angular resolution and the sector data includes: According to a preset angular resolution, with the position point of the driving vehicle as an endpoint, a ray method is used to determine at least one sector ray in the obstacle sector; For each sector ray of the at least one sector ray, determine, based on the sector data, a first intersection point closest to the position point among all intersection points between the target obstacle in the obstacle sector and the sector ray, and use the first intersection point as an obstacle corner point, wherein the target obstacle is an obstacle among the at least one obstacle located within the obstacle sector.

6. The method according to claim 4, characterized in that The determining, based on the preset angular resolution and the sector data, an obstacle-free corner point in the obstacle-free area includes: Determining whether the driving vehicle can pass through the barrier-free area according to the sector data; In a case where the driving vehicle can pass through the obstacle-free area, determining at least one area ray in the obstacle-free area using a ray method with the position point of the driving vehicle as an endpoint according to the preset angular resolution; For each area ray of the at least one area ray, a second intersection point between the edge line of the obstacle-free area and the area ray is determined, and the second intersection point is used as an obstacle-free corner point.

7. The method according to claim 6, characterized in that The determining, based on the preset angular resolution and the sector data, an obstacle-free corner point in the obstacle-free area further includes: In a case where the driving vehicle cannot pass through the obstacle-free area, determining, based on the sector data, a nearest corner point located on a boundary of an obstacle sector adjacent to the obstacle-free area, wherein the nearest corner point is an obstacle corner point on the boundary that is closest to the position point; Establishing a nearest sector in the obstacle-free area with a line between the nearest corner point and the driving vehicle as a radius and the position point as a center; According to the preset angular resolution, with the position point as an endpoint, a ray method is used to determine at least one nearest ray in the nearest sector; For each of the at least one closest ray, a third intersection point between the edge line of the closest sector and the closest ray is determined, and the third intersection point is used as an obstacle-free corner point.

8. The method according to claim 1, characterized in that After determining the target drivable area, the method further includes: For each first contour point on the area contour of the target drivable area, determining a first adjacent point of the first contour point on the area contour; determining, based on the first adjacent point, the first contour point, and the position point of the driving vehicle, whether the first contour point is a spike point on the area contour; In the case where the first contour point is the spike point, the first contour point is removed.

9. The method according to claim 8, characterized in that The step of determining target adjacent points of the first contour point from the area contour includes: Determining first adjacent points of the first contour point from the region contour, wherein the first adjacent points include a first left adjacent point and a first right adjacent point; The determining, based on the first adjacent point, the first contour point, and the position point of the driving vehicle, whether the first contour point is a spike point on the area contour includes: When the distance between the first contour point and the position point of the driving vehicle is greater than the distance between the first left neighboring point and the position point, and greater than the distance between the first right neighboring point and the position point, determining the maximum distance between the distance between the first left neighboring point and the position point and the distance between the first right neighboring point and the position point; Calculating an adjacent chord length according to the maximum distance, the first left neighbor point, and the first right neighbor point; According to the adjacent chord lengths and a preset drivable width threshold, it is determined whether the first contour point is a spike point on the area contour.

10. The method according to claim 1, characterized in that After determining the target drivable area, the method further includes: When the number of second contour points on the area contour of the target drivable area is greater than a preset point number threshold, determining, for each second contour point on the area contour, second adjacent points of the second contour point on the area contour, wherein the second adjacent points include a second left adjacent point and a second right adjacent point; Determine an adjacent line between the second left neighbor point and the second right neighbor point, and determine a point-to-line distance between the second contour point and the adjacent line; When the point-line distance is less than a preset distance, the second contour point is removed.

11. A device for determining a drivable area, characterized in that: include: an initial drivable area determination module, configured to obtain sensor parameters, an area of ​​interest, and road boundary data of a driving vehicle, and determine an initial drivable area of ​​the driving vehicle based on the sensor parameters, the area of ​​interest, and the road boundary data; a target corner point determination module, configured to obtain obstacle data of at least one obstacle that can be sensed by the driving vehicle, and determine a target corner point based on the initial drivable area, the obstacle data, and a preset angular resolution; a target drivable area determination module, configured to determine a target drivable area of ​​the driving vehicle based on the target corner point; The target corner point determination module includes: a sector data determining unit, configured to determine sector data corresponding to each of the at least one obstacle based on the obstacle data; an obstacle corner point determination unit, configured to determine an obstacle corner point based on the initial drivable area, a preset angular resolution, and the sector data; an obstacle-free corner point determining unit, configured to determine an obstacle-free corner point based on the initial drivable area, the preset angular resolution, and the sector data; The target corner point is used as a unit to take the obstacle corner point and the obstacle-free corner point as the target corner point.

Images