A drivable area detection method, device, vehicle and storage medium

Abstract

The application discloses a drivable area detection method and device, a vehicle and a computer readable storage medium, and relates to the technical field of auxiliary driving, and the method comprises the following steps: acquiring lane line information and obstacle information in front of a host vehicle; determining a lane center line according to the lane line information; determining a drivable area in front of the host vehicle according to the projection of each obstacle on the target vertical line in the obstacle information; and dividing the drivable area according to the minimum lateral drivable area of the host vehicle to obtain a longitudinal drivable area in front of the host vehicle; the application has a strong correlation between the division of the drivable area and the obstacle contour, can meet the flexibility of the division of the drivable area and take into account the algorithm operation efficiency, solves the problem of large calculation amount of the grid area operation, and adopts the mode of projecting the obstacle contour to the vertical line of the center line to divide the area with the center line of the lane as the reference line, so that the curved road and straight road scenes can be effectively met.

Description

Technical Field

[0001] This invention relates to the field of driver assistance technology, and in particular to a method, apparatus, vehicle, and computer-readable storage medium for detecting drivable areas. Background Technology

[0002] In Advanced Driving Assistance Systems (ADAS) of vehicles, to ensure safe assisted driving, it is necessary to detect information about the operating environment in front of the vehicle, such as the drivable area. The drivable area is typically represented in two ways: a collision-free space and a grid region. The collision-free space is usually represented by its boundary, which encloses the area between the main vehicle and one or more detected objects. The grid region divides the area in front of the vehicle into individual grid areas using a grid map, and then labels the grids containing obstacles.

[0003] In existing technologies, the selection of grid size is crucial for the grid region. A grid that is too large can lead to inaccurate identification of drivable areas, while a grid that is too small results in a large computational load and high demands on the processor (such as the CPU). Therefore, providing an accurate drivable area detection method that addresses the issue of high computational load in grid region operation while maintaining flexibility in drivable area detection is an urgent problem to be solved. Summary of the Invention

[0004] The purpose of this invention is to provide a method, apparatus, vehicle, and computer-readable storage medium for detecting drivable areas, in order to solve the problem of high computational load in grid area operation while taking into account the flexibility of drivable areas.

[0005] To solve the above-mentioned technical problems, the present invention provides a method for detecting a drivable area, comprising:

[0006] Acquire lane line information and obstacle information in front of the main vehicle; wherein, the lane line information includes lane line data of the current lane where the main vehicle is located and lane line data of the adjacent lanes of the current lane, and the obstacle information includes the lateral width and position information of each obstacle;

[0007] Determine the lane centerline based on the lane line information;

[0008] Based on the projection of each obstacle in the obstacle information onto the target vertical line, the drivable area in front of the main vehicle is determined; wherein, the target vertical line is the vertical line on the center line of the lane.

[0009] Based on the minimum lateral drivable area of ​​the main vehicle, the drivable area is divided to obtain the longitudinal drivable area in front of the main vehicle.

[0010] Optionally, determining the drivable area in front of the main vehicle based on the projections of each obstacle in the obstacle information onto the target vertical line includes:

[0011] The drivable area is determined based on the longitudinal position of each obstacle in the obstacle information, the projection of each obstacle in the obstacle information onto the target vertical line, and the lateral width of the drivable area corresponding to the lane line information; wherein, the position information includes the longitudinal position.

[0012] Optionally, determining the drivable area based on the longitudinal position of each obstacle in the obstacle information, the projection of each obstacle in the obstacle information onto the target vertical line, and the lateral width of the drivable area corresponding to the lane line information includes:

[0013] Based on the longitudinal position of each obstacle in the obstacle information, the obstacles are sorted in ascending order to obtain the queue corresponding to each obstacle.

[0014] According to the sorting order of the queues, obstacles are projected onto the target line segments on the target vertical line in sequence to determine the target unprojected line segments corresponding to each queue; wherein, the target line segment is the projected line segment corresponding to the lateral width of the drivable area on the target vertical line, and the target unprojected line segments corresponding to each queue do not overlap.

[0015] The drivable area is determined based on the unprojected line segment and longitudinal position of the target corresponding to each queue.

[0016] Optionally, determining the drivable area based on the unprojected line segment and longitudinal position of the target corresponding to each queue includes:

[0017] If the current queue is the first queue, then the drivable area between the main vehicle and the first queue is determined based on the lateral width of the drivable area and the longitudinal position corresponding to the first queue.

[0018] If the current queue is the i-th queue, then the drivable area between the (i-1)-th queue and the i-th queue is determined based on the unprojected line segment of the target corresponding to the (i-1)-th queue and the difference between the longitudinal position of the i-th queue and the longitudinal position of the (i-1)-th queue; where i is a positive integer greater than 1 and less than or equal to n, and n is the number of queues;

[0019] If the current queue is the nth queue, then the drivable area in front of the nth queue is determined based on the unprojected line segment and longitudinal position of the target corresponding to the nth queue.

[0020] Optionally, the step of sorting the obstacles in ascending order according to their longitudinal positions in the obstacle information to obtain the queue corresponding to each obstacle includes:

[0021] Based on the longitudinal position of each obstacle in the obstacle information, the obstacles are sorted in ascending order to obtain the obstacle sorting order;

[0022] Based on the obstacle sorting order and the queue longitudinal distance threshold, the queue corresponding to each obstacle is determined sequentially.

[0023] Optionally, the step of projecting obstacles onto target line segments on the target vertical line in the order of the queues to determine the unprojected target line segments corresponding to each queue includes:

[0024] Project the obstacles in the current queue onto the target vertical line to determine the unprojected line segment corresponding to the current queue on the target vertical line; wherein the projected line segment corresponding to the current queue is within the target line segment;

[0025] If there is an overlapping line segment between the unprojected line segment corresponding to the current queue and the current unprojected line segment in the target line segment, then the overlapping line segment is taken as the target unprojected line segment corresponding to the current queue, and the projected line segment corresponding to the current queue on the target vertical line is used to update the current unprojected line segment.

[0026] If there is no overlapping line segment between the unprojected line segment corresponding to the current queue and the current unprojected line segment in the target line segment, then the target unprojected line segment corresponding to the current queue is empty.

[0027] Optionally, the step of dividing the drivable area according to the minimum lateral drivable area of ​​the main vehicle to obtain the longitudinal drivable area in front of the main vehicle includes:

[0028] Based on the minimum lateral drivable area and the longitudinal speed of the obstacles in the obstacle information, the drivable area is divided to obtain the longitudinal drivable area in front of the main vehicle; wherein, the longitudinal drivable area is marked with its corresponding obstacle driving speed information.

[0029] The present invention also provides a device for detecting drivable areas, comprising:

[0030] The information acquisition module is used to acquire lane line information and obstacle information in front of the main vehicle; wherein, the lane line information includes lane line data of the current lane where the main vehicle is located and lane line data of the adjacent lanes of the current lane, and the obstacle information includes the lateral width and position information of each obstacle;

[0031] The lane determination module is used to determine the lane centerline based on the lane line information.

[0032] The area determination module is used to determine the drivable area in front of the main vehicle based on the projection of each obstacle in the obstacle information onto the target vertical line; wherein, the target vertical line is the vertical line on the center line of the lane;

[0033] The region division module is used to divide the drivable area according to the minimum lateral drivable area of ​​the main vehicle, and obtain the longitudinal drivable area in front of the main vehicle.

[0034] The present invention also provides a vehicle, comprising:

[0035] Memory, used to store computer programs;

[0036] A processor is used to implement the drivable area detection method as described above when executing the computer program.

[0037] Furthermore, the present invention also provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the steps of the drivable area detection method as described above.

[0038] The present invention provides a method for detecting a drivable area, comprising: acquiring lane line information and obstacle information in front of a main vehicle; wherein, the lane line information includes lane line data of the current lane where the main vehicle is located and lane line data of the adjacent lanes of the current lane, and the obstacle information includes the lateral width and position information of each obstacle; determining the lane centerline based on the lane line information; determining the drivable area in front of the main vehicle based on the projection of each obstacle on a target vertical line in the obstacle information; wherein, the target vertical line is a vertical line on the lane centerline; and dividing the drivable area according to the minimum lateral drivable area of ​​the main vehicle to obtain the longitudinal drivable area in front of the main vehicle.

[0039] As can be seen, this invention determines the drivable area in front of the main vehicle based on the lateral width of the drivable area and the projection of each obstacle onto the target perpendicular line from the obstacle information. It strongly correlates the division of the drivable area with the obstacle contours, satisfying both the flexibility of drivable area division and the efficiency of algorithm operation, thus solving the problem of high computational load in grid-based operations. Furthermore, using the lane centerline as a reference line and dividing the area by projecting the obstacle contours onto the perpendicular line of the centerline, it can effectively meet the needs of both curved and straight road scenarios, improving the applicability of drivable area detection. In addition, this invention also provides a drivable area detection device, a vehicle, and a computer-readable storage medium, which also have the above-mentioned beneficial effects. Attached Figure Description

[0040] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on the provided drawings without creative effort.

[0041] Figure 1 A flowchart illustrating a method for detecting a drivable area provided in an embodiment of the present invention;

[0042] Figure 2 A flowchart illustrating another method for detecting a drivable area provided in an embodiment of the present invention;

[0043] Figure 3 This is a schematic diagram of the drivable area division for another drivable area detection method provided in an embodiment of the present invention;

[0044] Figure 4 for Figure 3 The diagram shows the output of the longitudinal drivable area division.

[0045] Figure 5 This is a schematic diagram of the drivable area division for another drivable area detection method provided in an embodiment of the present invention;

[0046] Figure 6 for Figure 5 The diagram shows the output of the longitudinal drivable area division.

[0047] Figure 7 This is a schematic diagram of the drivable area division for another drivable area detection method provided in an embodiment of the present invention;

[0048] Figure 8 for Figure 7 The diagram shows the output of the longitudinal drivable area division.

[0049] Figure 9 This is a structural block diagram of a drivable area detection device provided in an embodiment of the present invention;

[0050] Figure 10 This is a schematic diagram of the structure of a vehicle provided in an embodiment of the present invention. Detailed Implementation

[0051] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0052] Please refer to Figure 1 , Figure 1 A flowchart illustrating a method for detecting a drivable area provided in an embodiment of the present invention. The method may include:

[0053] Step 101: Obtain lane line information and obstacle information in front of the main vehicle; wherein, the lane line information includes the lane line data of the current lane where the main vehicle is located and the lane line data of the adjacent lanes of the current lane, and the obstacle information includes the lateral width and position information of each obstacle.

[0054] It is understood that the main vehicle in this embodiment can be a vehicle performing drivable area detection. The lane line information in this embodiment can be information related to the lane lines in front of the main vehicle, such as lane line information collected by the sensing device installed on the main vehicle in the direction the main vehicle is traveling. The specific content of the lane line information in this embodiment can be set by the designer according to the practical scenario and user needs. For example, the lane line information may include lane line data of the currently occupied lane and lane line data of adjacent lanes to determine the maximum drivable range of the main vehicle.

[0055] Correspondingly, the obstacle information in this embodiment can be information related to obstacles (such as other vehicles) in front of the main vehicle, such as information about obstacles in front of the main vehicle's driving direction collected by the sensing device installed on the main vehicle. The specific content of the obstacle information in this embodiment can be set by the designer according to the practical scenario and user needs. For example, obstacle information may include the lateral width of each obstacle, i.e., the width of each obstacle in its respective lane; obstacle information may also include the position information of each obstacle, such as its longitudinal position relative to the main vehicle; obstacle information may also include obstacle speed information, such as the speed and acceleration of each obstacle. This embodiment does not impose any limitations on this.

[0056] Correspondingly, the main vehicle can be equipped with sensing devices, such as cameras, rangefinders, and / or speedometers, to collect lane line information and obstacle information in front of the main vehicle in the direction of travel.

[0057] It should be noted that the drivable area detection method provided in this embodiment can be applied to a main vehicle. For example, the processor of the main vehicle can execute the method provided in this embodiment, using lane line information and obstacle information collected by its own sensing devices to detect the longitudinal drivable area in front of the main vehicle. The drivable area detection method provided in this embodiment can also be applied to a server. For example, the processor of a cloud server connected to the main vehicle can execute the method provided in this embodiment, using lane line information and obstacle information collected by the main vehicle's sensing devices to detect the longitudinal drivable area in front of the main vehicle. This embodiment does not impose any limitations on this.

[0058] Specifically, the method by which the processor acquires lane line and obstacle information in front of the main vehicle in this embodiment can be set by the designer according to the practical scenario and user needs. For example, the processor of the main vehicle can adopt the same or similar method as the lane line and obstacle detection method in the prior art, using the sensing device installed on the main vehicle to acquire lane line and obstacle information in front of the main vehicle; or the processor of the cloud server can receive lane line and obstacle information in front of the main vehicle sent by the main vehicle. This embodiment does not impose any restrictions on this.

[0059] Step 102: Determine the lane center line based on the lane line information.

[0060] In this embodiment, the lane centerline can be the centerline of the lane in front of the main vehicle, such as the centerline of the current lane where the main vehicle is located.

[0061] It is understood that in this step, the processor can calculate the lane centerline based on the lane line information in front of the main vehicle. The specific method by which the processor determines the lane centerline based on the lane line information in this step can be set by the designer, such as using a method similar to or the same as existing lane centerline detection methods. This embodiment does not impose any restrictions on this.

[0062] Step 103: Determine the drivable area in front of the main vehicle based on the projection of each obstacle on the target vertical line in the obstacle information; wherein, the target vertical line is the vertical line on the center line of the lane.

[0063] It is understood that the target perpendicular line in this embodiment can be a perpendicular line on the lane centerline, such as the perpendicular line on the centerline of the lane where the main vehicle is currently located (i.e., the current lane); for example, the target perpendicular line can be the perpendicular line corresponding to each obstacle, or it can be a perpendicular line corresponding to any obstacle or the main vehicle. In this step, the processor can use the obstacle lateral width and position information of each obstacle in the obstacle information to obtain the projection of each obstacle on the target perpendicular line, determine the drivable area in front of the main vehicle, and use the lane centerline as a reference line to divide the drivable area by projecting the obstacle outline onto the perpendicular line of the lane centerline, thereby effectively satisfying both curved and straight road scenarios and ensuring the applicability of drivable area detection.

[0064] Specifically, the method by which the processor determines the drivable area in front of the main vehicle based on the projection of each obstacle in the obstacle information onto the target vertical line in this embodiment can be set by the designer. For example, the position information of each obstacle in the obstacle information can be the longitudinal position of each obstacle, that is, the distance of each obstacle relative to the main vehicle in the driving direction. The processor can determine the drivable area based on the lane line information, the longitudinal position of each obstacle in the obstacle information, and the projection of each obstacle in the obstacle information onto the target vertical line.

[0065] For example, the processor can determine the drivable area based on the longitudinal position of each obstacle in the obstacle information, the projection of each obstacle onto the target vertical line, and the lateral width of the drivable area corresponding to the lane line information. In other words, the processor can determine the sum of the widths of the lane centerline and each lane (i.e., the lateral width of the drivable area) based on the lane line information, and then project each obstacle onto the vertical line of the lane centerline (i.e., the target vertical line) to determine the drivable area within the range corresponding to the lateral width of the drivable area. For instance, the processor sorts the obstacles in ascending order based on their longitudinal positions in the obstacle information, obtaining the queue corresponding to each obstacle; according to the queue sorting order, it projects obstacles onto the target line segments on the target vertical line sequentially, determining the target unprojected line segments corresponding to each queue; and based on the target unprojected line segments and longitudinal positions corresponding to each queue, it determines the drivable area; where the target line segment is the projected line segment corresponding to the lateral width of the drivable area on the target vertical line, and the target unprojected line segments corresponding to each queue do not overlap.

[0066] Step 104: Divide the drivable area according to the minimum lateral drivable area of ​​the main vehicle to obtain the longitudinal drivable area in front of the main vehicle.

[0067] It is understood that the minimum lateral drivable area in this step can be the smallest lateral area (e.g., lateral distance) that the main vehicle can drive in, to ensure that each longitudinal drivable area can meet the minimum lateral drivable area requirement. In this embodiment, the longitudinal drivable area can be a quadrilateral area in the direction in which the main vehicle can drive (i.e., longitudinally), such as a rectangular area when the lane centerline is a straight line or an arc-shaped area when the lane centerline is an arc; in this embodiment, there are no obstacles behind each longitudinal drivable area.

[0068] Specifically, the method by which the processor divides the drivable area based on the minimum lateral drivable area of ​​the main vehicle to obtain the longitudinal drivable area in front of the main vehicle can be set by the designers according to the practical scenario and user needs. For example, the processor can divide the drivable area only based on the minimum lateral drivable area to ensure that each longitudinal drivable area can meet the minimum lateral drivable area requirement. Alternatively, the processor can divide the drivable area based on the minimum lateral drivable area and the longitudinal speed of the obstacles in the obstacle information. This ensures that each longitudinal drivable area meets the minimum lateral drivable area requirement, and adjusts the lateral width of the longitudinal drivable area according to the longitudinal speed of the obstacle corresponding to the longitudinal drivable area. For example, the higher the longitudinal speed of the obstacle in front of the longitudinal drivable area, the wider or narrower the lateral width of that longitudinal drivable area can be.

[0069] Furthermore, the longitudinal drivable areas in front of the main vehicle obtained in this step can also be marked with the driving speed information of the obstacles in front of each longitudinal drivable area, such as speed (e.g., longitudinal speed) and acceleration, so that the obtained longitudinal drivable areas can carry the status information of the obstacles in front, providing more sufficient information for subsequent driving decisions and planning.

[0070] In this embodiment, the present invention determines the drivable area in front of the main vehicle based on the lateral width of the drivable area and the projection of each obstacle on the target vertical line in the obstacle information. The division of the drivable area is strongly correlated with the obstacle outline, which satisfies the flexibility of the drivable area division while taking into account the algorithm's running efficiency, and solves the problem of large computational load in grid area operation. Furthermore, using the lane center line as a reference line, the area is divided by projecting the obstacle outline onto the vertical line of the center line, which can effectively meet the needs of curved and straight road scenarios and improve the applicability of drivable area detection.

[0071] Based on the above embodiments, the present invention also provides another method for detecting drivable areas. For details, please refer to... Figure 2 , Figure 2 A flowchart illustrating another method for detecting a drivable area provided by an embodiment of the present invention. The method may include:

[0072] Step 201: Obtain lane line information and obstacle information in front of the main vehicle; wherein, the lane line information includes the lane line data of the current lane where the main vehicle is located and the lane line data of the adjacent lanes of the current lane, and the obstacle information includes the lateral width and position information of each obstacle.

[0073] This step is similar to step 101, and will not be described again here.

[0074] Step 202: Determine the lane centerline and the lateral width of the drivable area based on the lane line information.

[0075] Specifically, in this step, the processor can calculate the centerline of the current lane (i.e., the lane centerline) based on the lane line data of the current lane obtained from the lane line information; based on the width of the current lane corresponding to the lane line data and the width of the adjacent lanes corresponding to the lane line data of the adjacent lanes, it can calculate the maximum lateral width of the drivable area in front of the main vehicle (i.e., the lateral width of the drivable area), such as the width of the current lane and the sum of the widths of each adjacent lane, such as... Figure 3 , 5 The lateral width of region 1 in section 7 is the sum of the widths of the current lane and the two adjacent lanes on the left and right.

[0076] Step 203: Based on the vertical position of each obstacle in the obstacle information, sort the obstacles in ascending order to obtain the queue corresponding to each obstacle.

[0077] Understandably, in this step, the processor can sort the obstacles in front of the main vehicle from near to far according to the longitudinal position (such as the vertical coordinate) of the obstacles (i.e., queue sorting), obtain the queue corresponding to each obstacle, and thus determine the obstacles corresponding to each queue after sorting.

[0078] Specifically, the method by which the processor sorts obstacles in ascending order based on their vertical positions in the obstacle information to obtain the corresponding queues for each obstacle in this step can be set by the designer. For example, each queue can correspond to only one obstacle, meaning that in this step, the processor can sort the obstacles in ascending order based on their vertical positions in the obstacle information to obtain a queue for each sorted obstacle. Alternatively, each queue can correspond to at least one obstacle to group obstacles with similar vertical positions into the same queue, thus classifying the obstacles. For example, in this step, the processor can sort the obstacles in ascending order based on their vertical positions in the obstacle information to obtain the obstacle sorting order. Based on the obstacle sorting order and the queue vertical distance threshold, the queue corresponding to each obstacle is determined sequentially. For example, the difference in vertical position between the obstacle with the largest vertical position and the obstacle with the smallest vertical position in the same queue is less than or equal to the queue vertical distance threshold.

[0079] Correspondingly, in this embodiment, the identifier of each queue (such as ID number) can be the longitudinal position of the obstacle in the queue, such as the longitudinal position of the obstacle with the smallest longitudinal position in the queue, such as the longitudinal coordinate of the obstacle, so as to facilitate the subsequent configuration of the target vertical line of each queue and / or the determination of the drivable area.

[0080] Step 204: According to the sorting order of the queues, project obstacles onto the target line segments on the target vertical line in sequence to determine the target unprojected line segments corresponding to each queue; wherein, the target line segment is the projected line segment corresponding to the horizontal width of the drivable area on the target vertical line, and the target unprojected line segments corresponding to each queue do not overlap.

[0081] It is understood that the target line segment in this step can be the projection line segment corresponding to the lateral width of the drivable area on the target vertical line, that is, the projection line segment of all lanes corresponding to the lane line information on the target vertical line along the lane center line, and the length of the target line segment is equal to the lateral width of the drivable area; if the lane center line is a straight line, the target line segment can be the orthographic projection of all lanes on the target vertical line.

[0082] Specifically, in this step, the unprojected target line segment corresponding to each queue can be the overlapping part between the line segment of the obstacle corresponding to the queue that has not been projected into the target line segment and the line segment of the target line segment that has not yet been projected. For example... Figure 7 The unprojected line segment corresponding to the queue containing obstacle 1 can be the projected line segment within the target line segment corresponding to the lateral width of region 2 and region 3, such as... Figure 5 The unprojected line segment corresponding to the queue containing obstacle 3 can be the projected line segment within the target line segment corresponding to the lateral width of region 3 and the lateral width of the region to the left of obstacle 1, such as... Figure 3 The unprojected line segment of the target corresponding to the queue where obstacle 3 is located can be the projected line segment within the target line segment corresponding to the horizontal width of region 3 and the horizontal width of the left side region of obstacle 1 and the right side region of obstacle 2.

[0083] Correspondingly, in this step, the processor projects obstacles onto the target line segments on the target vertical line in the order of the queues to determine the specific method for determining the target unprojected line segments corresponding to each queue. This method can be set by the designer. For example, the obstacles in the current queue can be projected onto the target vertical line to determine the unprojected line segments corresponding to the current queue on the target vertical line. If there is an overlapping line segment between the unprojected line segment corresponding to the current queue and the current unprojected line segment in the target line segment, the overlapping line segment is taken as the target unprojected line segment corresponding to the current queue, and the current unprojected line segment is updated using the projected line segment corresponding to the current queue on the target vertical line to remove the projected line segment corresponding to the current queue from the current unprojected line segment. If there is no overlapping line segment between the unprojected line segment corresponding to the current queue and the current unprojected line segment in the target line segment, the target unprojected line segment corresponding to the current queue is empty. Here, the projected line segment corresponding to the current queue is within the target line segment, and the current queue can be any queue.

[0084] Step 205: Determine the drivable area in front of the main vehicle based on the target unprojected line segment and longitudinal position corresponding to each queue.

[0085] Specifically, in this step, when the number of queues is 1, the processor can determine the drivable area (i.e., the drivable sub-area) between the main vehicle and the first queue based on the lateral width of the drivable area and the longitudinal position corresponding to the first queue. Figure 7 Region 1 in the diagram; based on the unprojected line segment and longitudinal position of the target corresponding to the first queue, determine the drivable area in front of the first queue, that is, the drivable area in front of the longitudinal position corresponding to the first queue, such as... Figure 7 Regions 2 and 3 in the text.

[0086] Correspondingly, when the number of queues in this step is greater than or equal to 2, if the current queue is the first queue, the processor can determine the drivable area between the main vehicle and the first queue based on the lateral width of the drivable area and the longitudinal position corresponding to the first queue; for example, a quadrilateral with the lateral width of the drivable area as its lateral width and the longitudinal position as its longitudinal length; such as... Figure 3 The queue containing obstacle 1 corresponds to region 1. If the current queue is the i-th queue, the processor can determine the drivable area between the (i-1)-th queue and the i-th queue based on the unprojected line segment of the target corresponding to the (i-1)-th queue and the difference between the longitudinal positions of the i-th queue and the (i-1)-th queue. For example, a quadrilateral with the unprojected line segment of the target corresponding to the (i-1)-th queue as the lateral width of each drivable area and the difference between the longitudinal positions as the longitudinal length of the drivable area; Figure 3 The queue containing obstacle 2 corresponds to region 2, and the corresponding region to the left of obstacle 1. If the current queue is the nth queue, then based on the unprojected line segment and longitudinal position of the target corresponding to the nth queue, the processor can determine the drivable area in front of the nth queue, such as... Figure 3 The region 3 is the queue containing obstacle 3, the corresponding region to the left of obstacle 1, and the corresponding region to the right of obstacle 2; where i is a positive integer greater than 1 and less than or equal to n, n is the number of queues, and n is a positive integer greater than or equal to 2.

[0087] Step 206: Based on the minimum lateral drivable area of ​​the main vehicle and the longitudinal speed of the obstacle in the obstacle information, the drivable area is divided to obtain the longitudinal drivable area in front of the main vehicle; wherein, the longitudinal drivable area is marked with the corresponding obstacle driving speed information.

[0088] It is understandable that in this step, the processor can comprehensively divide the longitudinal drivable area in front of the main vehicle in the longitudinal direction (i.e., the direction of travel) based on the different longitudinal speeds of obstacles and the minimum lateral drivable area of ​​the main vehicle.

[0089] Specifically, the method by which the processor divides the drivable area based on the minimum lateral drivable area of ​​the main vehicle and the longitudinal velocity of obstacles in the obstacle information to obtain the longitudinal drivable area in front of the main vehicle in this step can be set by the designer. For example, the processor can filter out drivable areas with a lateral width smaller than the minimum lateral drivable area from all drivable areas to obtain the target drivable area. Figure 3 and Figure 4The corresponding areas to the left of obstacle 1 and the corresponding areas to the right of obstacle 2 are filtered out. The lateral width of each target drivable area is adjusted according to the longitudinal speed of the obstacle in front of each target drivable area. The target drivable areas that are at the same projection position (i.e., lateral position) on the target vertical line are merged to obtain each longitudinal drivable area in front of the main vehicle, that is, the projections of each longitudinal drivable area on the target vertical line do not overlap.

[0090] Correspondingly, in this step, the longitudinal drivable area in front of the main vehicle can be marked with the speed information of each obstacle, such as the speed and acceleration of the obstacles in front, to provide more comprehensive information for subsequent driving decisions and planning.

[0091] In this embodiment, the present invention marks the corresponding obstacle speed information on the longitudinal drivable area in front of the main vehicle, thus strongly correlated the longitudinal drivable area with the obstacles, providing more sufficient information for subsequent driving decisions and planning; and using the lane center line as a reference line, the division of the drivable area is not restricted by the lane, which can meet the scenario of the vehicle driving on the line.

[0092] Corresponding to the above method embodiments, this invention also provides a drivable area detection device. The drivable area detection device described below and the drivable area detection method described above can be referred to in correspondence.

[0093] Please refer to Figure 9 , Figure 9 This is a structural block diagram of a drivable area detection device provided in an embodiment of the present invention. The device may include:

[0094] The information acquisition module 10 is used to acquire lane line information and obstacle information in front of the main vehicle; wherein, the lane line information includes lane line data of the current lane where the main vehicle is located and lane line data of the adjacent lanes of the current lane, and the obstacle information includes the lateral width and position information of each obstacle.

[0095] Lane determination module 20 is used to determine the lane centerline based on lane line information;

[0096] The area determination module 30 is used to determine the drivable area in front of the main vehicle based on the projection of each obstacle on the target vertical line in the obstacle information; wherein, the target vertical line is the vertical line on the center line of the lane.

[0097] The area division module 40 is used to divide the drivable area according to the minimum lateral drivable area of ​​the main vehicle, and obtain the longitudinal drivable area in front of the main vehicle.

[0098] Optionally, the area determination module 30 can be specifically used to determine the drivable area based on the longitudinal position of each obstacle in the obstacle information, the projection of each obstacle in the obstacle information onto the target vertical line, and the lateral width of the drivable area corresponding to the lane line information.

[0099] Optionally, the region determination module 30 may include:

[0100] The sorting submodule is used to sort the obstacles in ascending order based on their vertical positions in the obstacle information, and obtain the queue corresponding to each obstacle.

[0101] The projection submodule is used to project obstacles onto the target line segments on the target vertical line in the order of the queues, and to determine the target unprojected line segments corresponding to each queue. The target line segments are the projected line segments corresponding to the horizontal width of the drivable area on the target vertical line, and the target unprojected line segments corresponding to each queue do not overlap.

[0102] The region determination submodule is used to determine the drivable region based on the unprojected line segment and longitudinal position of the target corresponding to each queue.

[0103] Optionally, the region determination submodule can be specifically used for: if the current queue is the first queue, then determining the drivable area between the main vehicle and the first queue based on the lateral width of the drivable area and the longitudinal position corresponding to the first queue; if the current queue is the i-th queue, then determining the drivable area between the (i-1)-th queue and the i-th queue based on the unprojected line segment of the target corresponding to the (i-1)-th queue and the difference between the longitudinal position corresponding to the i-th queue and the longitudinal position corresponding to the (i-1)-th queue; where i is a positive integer greater than 1 and less than or equal to n, and n is the number of queues; if the current queue is the n-th queue, then determining the drivable area in front of the n-th queue based on the unprojected line segment of the target corresponding to the n-th queue and the longitudinal position.

[0104] Optionally, the sorting submodule may include:

[0105] The obstacle sorting unit is used to sort the obstacles in ascending order based on their longitudinal positions in the obstacle information, and to obtain the obstacle sorting order.

[0106] The queue classification unit is used to determine the queue corresponding to each obstacle in turn based on the obstacle sorting order and the queue longitudinal distance threshold.

[0107] Optionally, the projection submodule may include:

[0108] The projection unit is used to project the obstacles in the current queue onto the target vertical line, and determine the unprojected line segment corresponding to the current queue on the target vertical line; wherein, the projected line segment corresponding to the current queue is within the target line segment;

[0109] The update unit is determined so that if there is an overlapping line segment between the unprojected line segment corresponding to the current queue and the current unprojected line segment in the target line segment, the overlapping line segment is taken as the target unprojected line segment corresponding to the current queue, and the current unprojected line segment is updated using the projected line segment corresponding to the current queue on the target perpendicular line.

[0110] The filtering and determination unit is used to determine that if there is no overlapping line segment between the unprojected line segment corresponding to the current queue and the current unprojected line segment in the target line segment, then the target unprojected line segment corresponding to the current queue is empty.

[0111] Optionally, the area division module 40 can be specifically used to divide the drivable area according to the minimum lateral drivable area and the longitudinal speed of the obstacle in the obstacle information, and obtain the longitudinal drivable area in front of the main vehicle; wherein, the longitudinal drivable area is marked with its corresponding obstacle driving speed information.

[0112] In this embodiment, the region determination module 30 determines the drivable area in front of the main vehicle based on the lateral width of the drivable area and the projection of each obstacle on the target vertical line in the obstacle information. The division of the drivable area is strongly correlated with the obstacle outline, which satisfies the flexibility of the drivable area division while taking into account the algorithm's running efficiency, and solves the problem of large computational load in grid area operation. Furthermore, using the lane center line as a reference line, the region is divided by projecting the obstacle outline onto the vertical line of the center line, which can effectively meet the needs of curved and straight road scenarios and improve the applicability of drivable area detection.

[0113] Corresponding to the above method embodiments, this invention also provides a vehicle. The vehicle described below and the method for detecting a drivable area described above can be referred to in correspondence.

[0114] Please refer to Figure 10 , Figure 10 This is a schematic diagram of a vehicle provided in an embodiment of the present invention. The vehicle may include:

[0115] Memory D1 is used to store computer programs;

[0116] The processor D2 is used to implement the steps of the drivable area detection method provided in the above method embodiments when executing a computer program.

[0117] Specifically, the vehicle provided in this embodiment can be the main vehicle in the above embodiment; the vehicle provided in this embodiment may also include sensing devices to collect lane line information and obstacle information in front of the vehicle.

[0118] Corresponding to the above method embodiments, this invention also provides a computer-readable storage medium. The computer-readable storage medium described below and the method for detecting a drivable area described above can be referred to in correspondence.

[0119] This invention provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the steps of the drivable area detection method provided in the above-described method embodiments.

[0120] The computer-readable storage medium can specifically be a USB flash drive, a portable hard drive, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk, or any other readable storage medium capable of storing program code.

[0121] The various embodiments in this specification are described in a progressive manner, with each embodiment focusing on its differences from other embodiments. Similar or identical parts between embodiments can be referred to interchangeably. For the apparatus, vehicle, and computer-readable storage medium disclosed in the embodiments, since they correspond to the methods disclosed in the embodiments, the descriptions are relatively simple, and relevant details can be found in the method section.

[0122] The present invention has provided a detailed description of a method, apparatus, vehicle, and computer-readable storage medium for detecting a drivable area. Specific examples have been used to illustrate the principles and implementation methods of the invention. The descriptions of these embodiments are merely illustrative and are intended to aid in understanding the method and core concepts of the invention. It should be noted that those skilled in the art can make various improvements and modifications to the invention without departing from its principles, and these improvements and modifications also fall within the scope of protection of the claims.

Claims

1. A method for detecting a drivable area, characterized in that, include: Acquire lane line information and obstacle information in front of the main vehicle; wherein, the lane line information includes lane line data of the current lane where the main vehicle is located and lane line data of the adjacent lanes of the current lane, and the obstacle information includes the lateral width, position information and speed information of each obstacle, and the speed information of the obstacle includes the longitudinal speed of the obstacle. Determine the lane centerline based on the lane line information; Using the lateral width and position information of each obstacle in the obstacle information, the projection of each obstacle on the target vertical line is obtained; wherein, the target vertical line is the vertical line on the center line of the lane; Based on the longitudinal position of each obstacle in the obstacle information, the projection of each obstacle onto the target vertical line, and the lateral width of the drivable area corresponding to the lane line information, the drivable area in front of the main vehicle is determined; wherein, the position information includes the longitudinal position; Based on the minimum lateral drivable area of ​​the main vehicle and the longitudinal velocity of the obstacle in the obstacle information, the drivable area is divided to obtain the longitudinal drivable area in front of the main vehicle, including: Based on the minimum lateral drivable area of ​​the main vehicle, filter out all drivable areas in the drivable area whose lateral width is smaller than the minimum lateral drivable area, and obtain the target drivable area; Adjust the lateral width of each target drivable area according to the longitudinal speed of the obstacles in front of each target drivable area; The target drivable areas at the same projection position on the target vertical line are merged to obtain the longitudinal drivable areas in front of the main vehicle; wherein, the longitudinal drivable areas are marked with their respective obstacle driving speed information.

2. The method for detecting a drivable area according to claim 1, characterized in that, The step of determining the drivable area in front of the main vehicle based on the longitudinal position of each obstacle in the obstacle information, the projection of each obstacle onto the target vertical line, and the lateral width of the drivable area corresponding to the lane line information includes: Based on the longitudinal position of each obstacle in the obstacle information, the obstacles are sorted in ascending order to obtain the queue corresponding to each obstacle. According to the sorting order of the queues, obstacles are projected onto the target line segments on the target vertical line in sequence to determine the target unprojected line segments corresponding to each queue; wherein, the target line segment is the projected line segment corresponding to the lateral width of the drivable area on the target vertical line, and the target unprojected line segments corresponding to each queue do not overlap. The drivable area is determined based on the unprojected line segment and longitudinal position of the target corresponding to each queue.

3. The method for detecting a drivable area according to claim 2, characterized in that, The step of determining the drivable area based on the unprojected line segment and longitudinal position of the target corresponding to each queue includes: If the current queue is the first queue, then the drivable area between the main vehicle and the first queue is determined based on the lateral width of the drivable area and the longitudinal position corresponding to the first queue. If the current queue is the i-th queue, then the drivable area between the (i-1)-th queue and the i-th queue is determined based on the unprojected line segment of the target corresponding to the (i-1)-th queue and the difference between the longitudinal position of the i-th queue and the longitudinal position of the (i-1)-th queue; where i is a positive integer greater than 1 and less than or equal to n, and n is the number of queues; If the current queue is the nth queue, then the drivable area in front of the nth queue is determined based on the unprojected line segment and longitudinal position of the target corresponding to the nth queue.

4. The method for detecting a drivable area according to claim 2, characterized in that, The step of sorting the obstacles in ascending order based on their vertical positions in the obstacle information to obtain the queue corresponding to each obstacle includes: Based on the longitudinal position of each obstacle in the obstacle information, the obstacles are sorted in ascending order to obtain the obstacle sorting order; Based on the obstacle sorting order and the queue longitudinal distance threshold, the queue corresponding to each obstacle is determined sequentially.

5. The method for detecting a drivable area according to claim 4, characterized in that, The step of projecting obstacles onto target line segments on the target vertical line in the order of the queues, and determining the unprojected target line segments corresponding to each queue, includes: Project the obstacles in the current queue onto the target vertical line to determine the unprojected line segment corresponding to the current queue on the target vertical line; wherein the projected line segment corresponding to the current queue is within the target line segment; If there is an overlapping line segment between the unprojected line segment corresponding to the current queue and the current unprojected line segment in the target line segment, then the overlapping line segment is taken as the target unprojected line segment corresponding to the current queue, and the projected line segment corresponding to the current queue on the target vertical line is used to update the current unprojected line segment. If there is no overlapping line segment between the unprojected line segment corresponding to the current queue and the current unprojected line segment in the target line segment, then the target unprojected line segment corresponding to the current queue is empty.

6. A device for detecting drivable areas, characterized in that, include: The information acquisition module is used to acquire lane line information and obstacle information in front of the main vehicle; wherein, the lane line information includes lane line data of the current lane where the main vehicle is located and lane line data of the adjacent lanes of the current lane, and the obstacle information includes the lateral width, position information and driving speed information of each obstacle, and the driving speed information of the obstacle includes the longitudinal speed of the obstacle. The lane determination module is used to determine the lane centerline based on the lane line information. The region determination module is used to obtain the projection of each obstacle on the target vertical line using the lateral width and position information of each obstacle in the obstacle information; and to determine the drivable area in front of the main vehicle based on the longitudinal position of each obstacle in the obstacle information, the projection of each obstacle on the target vertical line, and the lateral width of the drivable area corresponding to the lane line information; wherein the target vertical line is a vertical line on the center line of the lane; and the position information includes the longitudinal position. The region division module is used to divide the drivable area according to the minimum lateral drivable area of ​​the main vehicle and the longitudinal speed of the obstacle in the obstacle information, and obtain the longitudinal drivable area in front of the main vehicle; wherein, the longitudinal drivable area is marked with its corresponding obstacle driving speed information. The region division module is specifically used to filter out all drivable regions whose lateral width is smaller than the minimum lateral drivable region based on the minimum lateral drivable region of the main vehicle, and obtain target drivable regions; adjust the lateral width of each target drivable region based on the longitudinal speed of the obstacles in front of each target drivable region; and merge the target drivable regions that are at the same projection position on the target vertical line to obtain each longitudinal drivable region in front of the main vehicle.

7. A vehicle, characterized in that, include: Memory, used to store computer programs; A processor for executing the computer program to implement the method for detecting drivable areas as described in any one of claims 1 to 5.

8. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that, when executed by a processor, implements the steps of the method for detecting a drivable area as described in any one of claims 1 to 5.

Images