Method, apparatus, computer-readable storage medium, and processor for determining a collision point

Abstract

The present application provides a method, an apparatus, a computer-readable storage medium and a processor for determining a collision point. The method includes: obtaining a target driving trajectory of a target vehicle; selecting a plurality of position points from a plurality of position points as target position points, and representing each target position point by a primary rectangular frame; obtaining position information of an obstacle within a future predetermined time period; abstracting a plurality of adjacent primary rectangular frames into a first intermediate-level rectangular frame, and repeating the process of abstracting a plurality of the M-th intermediate-level rectangular frames into an (M + 1)-th intermediate-level rectangular frame, where M starts from 1 and increases sequentially until a plurality of adjacent largest intermediate-level rectangular frames are abstracted into a final-level rectangular frame; determining whether there is a collision point between the target vehicle and the obstacle within the future predetermined time period at least based on whether there is an intersection between the final-level rectangular frame and the position information of the obstacle. This solution can accurately determine the collision point, and has simple calculation and less computational complexity.

Description

Technical Field

[0001] The present application relates to the field of autonomous driving, and in particular, to a method, device, computer-readable storage medium, processor, and vehicle for determining a collision point. Background Art

[0002] Collision calculation is a very important part in the field of autonomous driving. By giving the target driving trajectory of an autonomous driving vehicle (ADV) and the position information of an obstacle (such as an obstacle vehicle), the exact collision position of the ADV with the obstacle vehicle in the future is calculated to prevent accidents. The collision point calculation methods in the prior art have deficiencies such as large computational complexity and low accuracy. Summary of the Invention

[0003] The main objective of the present application is to provide a method, device, computer-readable storage medium, processor, and vehicle for determining a collision point to solve the problem of low accuracy of the collision point calculation method in the prior art.

[0004] To achieve the above objective, according to one aspect of the present application, a method for determining a collision point is provided, including: obtaining a target driving trajectory of a target vehicle, where the target driving trajectory refers to the driving trajectory of the target vehicle within a future predetermined time period, and the target driving trajectory includes a plurality of position points arranged in chronological order; selecting a plurality of position points from the plurality of position points as target position points, and representing each of the target position points by a primary rectangular frame; obtaining the position information of an obstacle within the future predetermined time period; abstracting a plurality of adjacent primary rectangular frames into a first intermediate-level rectangular frame, and repeating the process of abstracting a plurality of Mth intermediate-level rectangular frames into an (M + 1)th intermediate-level rectangular frame, where M starts from 1 and increases sequentially until a plurality of adjacent largest intermediate-level rectangular frames are abstracted into a final-level rectangular frame; determining whether there is a collision point between the target vehicle and the obstacle within the future predetermined time period at least based on whether there is an intersection between the final-level rectangular frame and the position information of the obstacle.

[0005] Optionally, determining whether there is a collision point between the target vehicle and the obstacle within the future predetermined time period at least based on whether there is an intersection between the final-level rectangular frame and the position information of the obstacle includes: determining that there is no collision point between the target vehicle and the obstacle within the future predetermined time period when there is no intersection between the plurality of final-level rectangular frames and the position information of the obstacle.

[0006] Optionally, determining whether there is a collision point between the target vehicle and the obstacle within the future predetermined time period is based at least on whether the final-level rectangular box has an intersection with the position information of the obstacle, including: selecting a target final-level rectangular box that intersects with the position information of the obstacle when at least one of the multiple final-level rectangular boxes has an intersection with the position information of the obstacle; determining a target intermediate-level rectangular box that intersects with the position information of the obstacle among the multiple upper-level intermediate-level rectangular boxes of the target final-level rectangular box; and querying the target intermediate-level rectangular boxes step by step upward until the primary rectangular box that intersects with the position information of the obstacle is determined.

[0007] Optionally, selecting multiple position points from the multiple position points as target position points includes: dividing the target driving trajectory into multiple trajectory segments; determining the proportion of the number of the target position points selected from the trajectory segment to the total number of the position points in the trajectory segment based on the type of the trajectory segment, the type of the trajectory segment including a straight trajectory segment, a left-turn trajectory segment and a right-turn trajectory segment; and selecting multiple target position points from the multiple position points in each trajectory segment based on the proportion.

[0008] Optionally, the ratio corresponding to the straight trajectory segment is a first ratio, the ratio corresponding to the left-turn trajectory segment is a second ratio, and the ratio corresponding to the right-turn trajectory segment is a third ratio, the second ratio is greater than the first ratio, and the third ratio is greater than the first ratio.

[0009] Optionally, the types of the trajectory segments further include dense trajectory segments and sparse trajectory segments, the number of position points in the dense trajectory segments of the same distance is greater than the number of position points in the sparse trajectory segments, the ratio corresponding to the dense trajectory segments is the fourth ratio, the ratio corresponding to the sparse trajectory segments is the fifth ratio, and the fourth ratio is greater than the fifth ratio.

[0010] Optionally, multiple adjacent primary rectangular frames are abstracted into a first intermediate-level rectangular frame, and multiple M-th intermediate-level rectangular frames are repeatedly abstracted into the M+1-th intermediate-level rectangular frame, where M increases sequentially starting from 1, until multiple adjacent largest intermediate-level rectangular frames are abstracted into a final-level rectangular frame, including: abstracting two adjacent primary rectangular frames into an intermediate-level rectangular frame, and abstracting two adjacent intermediate-level rectangular frames into the final-level rectangular frame.

[0011] Optionally, the method further includes: generating multiple current-level rectangular frames capable of surrounding multiple previous-level rectangular frames; and determining the current-level rectangular frame with the smallest area among the multiple current-level rectangular frames as the final current-level rectangular frame.

[0012] Optionally, the number of upper-level rectangular frames in different current-level rectangular frames is equal or unequal.

[0013] Optionally, the target vehicle is an autonomous vehicle, and the obstacle includes a social vehicle.

[0014] Optionally, the future predetermined time period is at least one of the following: 10s, 20s, 30s, 1min, 2min.

[0015] According to another aspect of the present application, there is provided an apparatus for determining a collision point, including: a first acquisition unit, configured to acquire a target driving trajectory of a target vehicle, where the target driving trajectory refers to a driving trajectory of the target vehicle within a future predetermined time period, and the target driving trajectory includes a plurality of position points arranged in chronological order; a selection unit, configured to select a plurality of position points from the plurality of position points as target position points, and represent each of the target position points by a primary rectangular frame; a second acquisition unit, configured to acquire position information of an obstacle within the future predetermined time period; a processing unit, configured to abstract a plurality of adjacent primary rectangular frames into a first intermediate-level rectangular frame, and repeat abstracting a plurality of Mth intermediate-level rectangular frames into an (M + 1)th intermediate-level rectangular frame, where M starts from 1 and increases sequentially until a plurality of adjacent largest intermediate-level rectangular frames are abstracted into a final-level rectangular frame; a first determination unit, configured to determine whether there is a collision point between the target vehicle and the obstacle within the future predetermined time period at least according to whether there is an intersection between the final-level rectangular frame and the position information of the obstacle.

[0016] According to another aspect of the present application, there is provided a computer-readable storage medium, where the computer-readable storage medium includes a stored program, and when the program runs, it controls a device where the computer-readable storage medium is located to execute any one of the methods.

[0017] According to yet another aspect of the present application, there is provided a processor, where the processor is used to run a program, and when the program runs, it executes any one of the methods.

[0018] According to still another aspect of the present application, there is provided a vehicle, including: one or more processors, and one or more programs, where the one or more programs are stored in a memory and are configured to be executed by the one or more processors, and the one or more programs include instructions for executing any one of the methods.

[0019] Applying the technical solution of the present application, by obtaining the target driving trajectory of the target vehicle, where the target driving trajectory refers to the driving trajectory of the target vehicle within a future predetermined time period, multiple position points are selected from the multiple position points as target position points, and each of the target position points is represented by a primary rectangular frame. The position information of obstacles within the future predetermined time period is obtained, and multiple adjacent primary rectangular frames are abstracted into a first intermediate-level rectangular frame. The process of repeatedly abstracting multiple Mth intermediate-level rectangular frames into an (M + 1)th intermediate-level rectangular frame is carried out, where M starts from 1 and increases sequentially until multiple adjacent largest intermediate-level rectangular frames are abstracted into a final-level rectangular frame. At least based on whether there is an intersection between the position information of the final-level rectangular frame and the obstacles, it is determined whether there is a collision point between the target vehicle and the obstacles within the future predetermined time period. By using rectangular frames to represent position points, abstracting adjacent rectangular frames into larger rectangular frames, and based on whether there is an intersection between the position information of the final-level rectangular frame and the obstacles, the determination of the collision point is realized, and the calculation amount is small. Brief Description of the Drawings

[0020] The specification drawings forming a part of the present application are used to provide a further understanding of the present application. The schematic embodiments and descriptions thereof of the present application are used to explain the present application and do not constitute an improper limitation to the present application. In the drawings:

[0021] Figure 1 The flowchart of the method for determining a collision point according to an embodiment of the present application is shown;

[0022] Figure 2 The schematic diagram of the principle for determining a collision point according to an embodiment of the present application is shown;

[0023] Figure 3 The structural diagram of a segment tree according to an embodiment of the present application is shown;

[0024] Figure 4 The schematic diagram of the device for determining a collision point according to an embodiment of the present application is shown. Detailed Embodiments

[0025] It should be noted that, without conflict, the embodiments in the present application and the features in the embodiments can be combined with each other. The present application will be described in detail below with reference to the drawings and in combination with the embodiments.

[0026] In order to enable those skilled in the art to better understand the solution of the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without making creative efforts shall fall within the protection scope of the present application.

[0027] It should be noted that the terms "first", "second", etc. in the description, claims and above-mentioned drawings of this application are used to distinguish similar objects, and do not necessarily describe a specific order or sequence. It should be understood that the data used in this way can be interchanged under appropriate circumstances, so as to implement the embodiments of the present application described herein. In addition, the terms "comprising" and "having" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product or device comprising a series of steps or units does not necessarily limit to those steps or units clearly listed, but may include other steps or units not clearly listed or inherent to these processes, methods, products or devices.

[0028] It should be understood that when an element (such as a layer, film, region, or substrate) is described as being "on" another element, the element can be directly on the other element, or there may also be intermediate elements. Moreover, in the description and claims, when an element is described as "connected" to another element, the element can be "directly connected" to the other element, or "connected" to the other element through a third element.

[0029] According to an embodiment of the present application, a method for determining a collision point is provided.

[0030] Figure 1 is a flowchart of the method for determining a collision point according to an embodiment of the present application. As Figure 1 shown, the method includes the following steps:

[0031] Step S101, obtain the target driving trajectory of the target vehicle. The above target driving trajectory refers to the driving trajectory of the target vehicle within a future predetermined time period. The above target driving trajectory includes a plurality of position points arranged in chronological order;

[0032] Specifically, the above future predetermined time period is at least one of the following: 10s, 20s, 30s, 1min, 2min. That is, obtain the driving trajectory of the target vehicle within a short future time to accurately predict whether the target vehicle will collide with an obstacle.

[0033] Specifically, the position of the target vehicle within a future predetermined time period can be determined according to the current position, driving speed and driving acceleration of the target vehicle, and a plurality of positions form a driving trajectory.

[0034] Step S102, select a plurality of position points from the above-mentioned plurality of position points as target position points, and use a primary rectangular frame to represent each of the above-mentioned target position points;

[0035] Specifically, there are many position points on the target driving trajectory, and a part of them are selected as the target position points from the multiple position points. For example, 10 position points are selected from 100 position points as the target position points, and then the target position points are represented by primary rectangular frames. Since the rectangular frame is closest to the shape of the target vehicle itself, it can represent the target vehicle.

[0036] Step S103: Obtain the position information of the obstacles within the above-mentioned future predetermined time period.

[0037] Specifically, the obstacles include fixed obstacles and movable obstacles. The positions of the fixed obstacles within the future predetermined time period are the same as their current positions. The positions of the movable obstacles (such as social vehicles) within the future predetermined time period can be determined based on their current positions, driving speeds, and driving accelerations.

[0038] Step S104: Abstract multiple adjacent primary rectangular frames into a first intermediate-level rectangular frame, and repeat the process of abstracting multiple Mth intermediate-level rectangular frames into an (M + 1)th intermediate-level rectangular frame, where M starts from 1 and increases sequentially until multiple adjacent largest intermediate-level rectangular frames are abstracted into a final-level rectangular frame.

[0039] In the above step S104, by abstracting the primary rectangular frame into the first intermediate-level rectangular frame, the first intermediate-level rectangular frame into the second intermediate-level rectangular frame, the second intermediate-level rectangular frame into the third intermediate-level rectangular frame, and so on, finally the largest intermediate-level rectangular frame is abstracted into a final-level rectangular frame.

[0040] Step S105: Determine whether there is a collision point between the target vehicle and the obstacles within the above-mentioned future predetermined time period based at least on whether there is an intersection between the position information of the final-level rectangular frame and the obstacles.

[0041] In the above step S105, in the case where there is an intersection between the position information of the final-level rectangular frame and the obstacles, it can be determined that the collision point is at least included within the area enclosed by the final-level rectangular frame.

[0042] Specifically, the above-mentioned target vehicle is an autonomous vehicle, and the obstacles include social vehicles, pedestrians, animals, unknown objects (such as garbage bags on the road), cyclists, traffic barriers, etc.

[0043] In the above solution, by obtaining the target driving trajectory of the target vehicle, where the target driving trajectory refers to the driving trajectory of the target vehicle within a future predetermined time period, multiple position points are selected from the multiple above-mentioned position points as target position points, and each of the above-mentioned target position points is represented by a primary rectangular frame. The position information of the obstacle within the above-mentioned future predetermined time period is obtained, and multiple adjacent above-mentioned primary rectangular frames are abstracted into a first intermediate-level rectangular frame. The process of repeatedly abstracting multiple level-M intermediate-level rectangular frames into a level-(M + 1) intermediate-level rectangular frame is carried out, where M starts from 1 and increases sequentially until multiple adjacent largest intermediate-level rectangular frames are abstracted into a final-level rectangular frame. At least based on whether there is an intersection between the position information of the above-mentioned final-level rectangular frame and the above-mentioned obstacle, it is determined whether there is a collision point between the above-mentioned target vehicle and the above-mentioned obstacle within the above-mentioned future predetermined time period. By using rectangular frames to represent position points, abstracting adjacent rectangular frames into larger rectangular frames, and based on whether there is an intersection between the position information of the above-mentioned final-level rectangular frame and the above-mentioned obstacle, the determination of the collision point is realized, and the computational complexity is small.

[0044] It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions. And although the logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in a different order than here.

[0045] In an embodiment of the present application, at least based on whether there is an intersection between the position information of the above-mentioned final-level rectangular frame and the above-mentioned obstacle, determining whether there is a collision point between the above-mentioned target vehicle and the above-mentioned obstacle within the above-mentioned future predetermined time period includes: in the case where there is no intersection between the position information of multiple above-mentioned final-level rectangular frames and the above-mentioned obstacle, it is determined that there is no collision point between the above-mentioned target vehicle and the above-mentioned obstacle within the above-mentioned future predetermined time period. Since all of the above-mentioned final-level rectangular frames include all of the target position points in the target driving trajectory of the target vehicle, and the target position points are representatives of all position points, in the case where there is no intersection between the position information of multiple above-mentioned final-level rectangular frames and the above-mentioned obstacle, it can be determined that there is no collision point between the above-mentioned target vehicle and the above-mentioned obstacle within the above-mentioned future predetermined time period.

[0046] In an embodiment of the present application, it is determined whether there is a collision point between the target vehicle and the obstacle within the future predetermined time period at least according to whether there is an intersection between the position information of the last-level rectangular box and the obstacle, including: when there is an intersection between the position information of at least one of the multiple last-level rectangular boxes and the obstacle, selecting a target last-level rectangular box whose position information has an intersection with the obstacle; determining a target intermediate rectangular box whose position information has an intersection with the obstacle among the multiple upper-level intermediate rectangular boxes of the target last-level rectangular box; querying step by step upward from the target intermediate rectangular box until the primary rectangular box whose position information has an intersection with the obstacle is determined. That is, first find the last-level rectangular box whose position information has an intersection with the obstacle, and then query step by step upward until the smallest-level rectangular box whose position information has an intersection with the obstacle, that is, the primary rectangular box, so as to accurately determine the collision point.

[0047] As Figure 2 and Figure 3 In the embodiment shown, ADV0, ADV1, ADV2, ADV3 represent primary rectangular boxes, BOX0~1, BOX2~3 represent the first intermediate rectangular boxes, BOX0~3 represent the second intermediate rectangular boxes, and so on until the last-level rectangular box. When it is determined that there is an intersection between the position information of BOX0~3 and the obstacle, query the upper-level rectangular boxes BOX0~1 and BOX2~3 of BOX0~3. When it is determined that there is an intersection between the position information of BOX0~1 and the obstacle, continue to determine whether there is an intersection between the position information of BOX0 and the obstacle or between the position information of BOX1 and the obstacle. When it is determined that there is an intersection between the position information of BOX2~3 and the obstacle, continue to determine whether there is an intersection between the position information of BOX2 and the obstacle or between the position information of BOX3 and the obstacle. Query from top to bottom using the structure of a segment tree until the leaf nodes of the segment tree to accurately determine the collision point. When the sampling points of the ADV (autonomous driving vehicle) trajectory are dense enough, the collision point will be accurate enough. Since only one segment tree needs to be constructed to perform collision calculations for all obstacles, the calculation speed will also be very fast. This solution can improve the accuracy of collision calculation by increasing the sampling density of the ADV trajectory by combining the segment tree and the bounding box (the rectangular box in this article) algorithm, while the existing method abstracts the ADV into an ellipse with a large error; when the number of obstacle vehicles is very large, since the segment tree is used to accelerate the query of the collision point, the present invention can still calculate the collision point at a very fast speed, while the existing method will be very slow in calculation because it samples the ADV and the obstacle vehicles simultaneously. In addition, this solution has good scalability. In addition to calculating the real collision point, it can also calculate information such as how far away from the collision point, while it is difficult to expand the existing method because it abstracts the ADV into an ellipse.

[0048] In one embodiment of the present application, selecting a plurality of position points from the above-mentioned plurality of position points as target position points includes: dividing the above-mentioned target driving trajectory into a plurality of trajectory segments; determining, according to the type of the above-mentioned trajectory segment, the proportion of the number of the above-mentioned target position points selected from the above-mentioned trajectory segment to the total number of the above-mentioned position points in the above-mentioned trajectory segment, where the type of the above-mentioned trajectory segment includes a straight trajectory segment, a left-turn trajectory segment, and a right-turn trajectory segment; and selecting a plurality of the above-mentioned target position points from the plurality of the above-mentioned position points in each of the above-mentioned trajectory segments based on the above-mentioned proportion. In this solution, selecting the number of target position points according to the type of the trajectory segment helps to accurately determine the collision point.

[0049] In one embodiment of the present application, the proportion corresponding to the above-mentioned straight trajectory segment is the first proportion, the proportion corresponding to the above-mentioned left-turn trajectory segment is the second proportion, the proportion corresponding to the above-mentioned right-turn trajectory segment is the third proportion, the second proportion is greater than the first proportion, and the third proportion is greater than the first proportion. Since left turns and right turns are relatively more complex than straight driving, setting the second proportion to be greater than the first proportion and the third proportion to be greater than the first proportion helps to accurately determine the collision point.

[0050] In one embodiment of the present application, the type of the above-mentioned trajectory segment further includes a dense trajectory segment and a sparse trajectory segment. The number of the above-mentioned position points in the above-mentioned dense trajectory segment of the same distance is greater than the number of the above-mentioned position points in the above-mentioned sparse trajectory segment. The proportion corresponding to the above-mentioned dense trajectory segment is the fourth proportion, and the proportion corresponding to the above-mentioned sparse trajectory segment is the fifth proportion. The fourth proportion is greater than the fifth proportion. That is, more target position points are collected for relatively crowded sections, and fewer target position points are collected for uncrowded sections, which helps to accurately determine the collision point.

[0051] In one embodiment of the present application, abstracting a plurality of adjacent above-mentioned primary rectangular frames into a first intermediate-level rectangular frame, and repeatedly abstracting a plurality of the above-mentioned M-th intermediate-level rectangular frames into a above-mentioned (M + 1)-th intermediate-level rectangular frame, where M starts from 1 and increases sequentially until a plurality of adjacent largest intermediate-level rectangular frames are abstracted into a final-level rectangular frame, includes: abstracting two adjacent above-mentioned primary rectangular frames into an intermediate-level rectangular frame, and abstracting two adjacent above-mentioned intermediate-level rectangular frames into a above-mentioned final-level rectangular frame.

[0052] In one embodiment of the present application, the above-mentioned method further includes: generating a plurality of current-level rectangular frames that can enclose a plurality of upper-level rectangular frames; and determining the current-level rectangular frame with the smallest area among the plurality of the above-mentioned current-level rectangular frames as the final current-level rectangular frame. Determining the current-level rectangular frame with the smallest area as the final current-level rectangular frame, as Figure 2As shown, BOX2 to BOX3 are the smallest rectangular frames that can enclose BOX2 and BOX3, and BOX0 to BOX1 are the smallest rectangular frames that can enclose BOX0 and BOX1. It can be ensured that the intermediate-level rectangular frames and the final-level rectangular frames have the smallest area on the premise of including the target position point, so as to reduce the calculation amount and speed up the calculation speed.

[0053] In an embodiment of the present application, the number of upper-level rectangular frames in different current-level rectangular frames is equal or not equal. Adaptively adjusting the number of upper-level rectangular frames helps to accurately determine the collision point.

[0054] The embodiment of the present application also provides a device for determining a collision point. It should be noted that the device for determining a collision point in the embodiment of the present application can be used to execute the method for determining a collision point provided in the embodiment of the present application. The following introduces the device for determining a collision point provided in the embodiment of the present application.

[0055] Figure 4 is a schematic diagram of the device for determining a collision point according to the embodiment of the present application. As Figure 4 shown, the device includes:

[0056] The first acquisition unit 10 is configured to acquire the target driving trajectory of the target vehicle. The target driving trajectory refers to the driving trajectory of the target vehicle within a future predetermined time period. The target driving trajectory includes a plurality of position points arranged in chronological order;

[0057] Specifically, the future predetermined time period is at least one of the following: 10s, 20s, 30s, 1min, 2min. That is, the driving trajectory of the target vehicle within a short future time is acquired to accurately predict whether the target vehicle will collide with an obstacle.

[0058] Specifically, the position of the target vehicle within the future predetermined time period can be determined according to the current position, driving speed and driving acceleration of the target vehicle, and a plurality of positions constitute the driving trajectory.

[0059] The selection unit 20 is configured to select a plurality of position points from the plurality of position points as target position points, and represent each of the target position points by using a primary rectangular frame;

[0060] Specifically, there are many position points on the target driving trajectory, and a part of the position points are selected from the plurality of position points as the target position points. For example, 10 position points are selected from 100 position points as the target position points, and then the primary rectangular frame is used to represent the target position points. Since the rectangular frame is closest to the shape of the target vehicle itself, it can represent the target vehicle.

[0061] The second acquisition unit 30 is configured to acquire the position information of the obstacle within the future predetermined time period;

[0062] Specifically, the obstacles include fixed obstacles and movable obstacles. The positions of the fixed obstacles are the same in a future predetermined time period and the current positions. The positions of the movable obstacles (such as social vehicles) in the future predetermined time period can be determined based on their current positions, traveling speeds, and traveling accelerations.

[0063] The processing unit 40 is configured to abstract a plurality of adjacent primary rectangular frames into a first intermediate-level rectangular frame, and repeatedly abstract a plurality of M-th intermediate-level rectangular frames into an M+1-th intermediate-level rectangular frame, where M starts from 1 and increases sequentially until a plurality of adjacent largest intermediate-level rectangular frames are abstracted into a final-level rectangular frame.

[0064] The first determination unit 50 is configured to determine whether there is a collision point between the target vehicle and the obstacle in the future predetermined time period at least based on whether there is an intersection between the position information of the final-level rectangular frame and the obstacle.

[0065] Specifically, the target vehicle is an autonomous vehicle, and the obstacles include social vehicles.

[0066] In the above solution, the first acquisition unit acquires the target driving trajectory of the target vehicle, where the target driving trajectory refers to the driving trajectory of the target vehicle in a future predetermined time period. The selection unit selects a plurality of position points from the plurality of position points as target position points, and represents each of the target position points by a primary rectangular frame. The second acquisition unit acquires the position information of the obstacle in the future predetermined time period. The processing unit abstracts a plurality of adjacent primary rectangular frames into a first intermediate-level rectangular frame, and repeatedly abstracts a plurality of M-th intermediate-level rectangular frames into an M+1-th intermediate-level rectangular frame, where M starts from 1 and increases sequentially until a plurality of adjacent largest intermediate-level rectangular frames are abstracted into a final-level rectangular frame. The first determination unit determines whether there is a collision point between the target vehicle and the obstacle in the future predetermined time period at least based on whether there is an intersection between the position information of the final-level rectangular frame and the obstacle. By representing the position points with rectangular frames, abstracting adjacent rectangular frames into larger rectangular frames, and determining whether there is an intersection between the position information of the final-level rectangular frame and the obstacle, the determination of the collision point is realized with a small amount of calculation.

[0067] In an embodiment of the present application, the first determination unit is further configured to determine that there is no collision point between the target vehicle and the obstacle within the future predetermined time period when there is no intersection between the position information of the plurality of the above-mentioned last-level rectangular frames and the obstacle. Since all of the above-mentioned last-level rectangular frames include all the target position points in the target driving trajectory of the target vehicle, and the target position points are representatives of all the position points, it can be determined that there is no collision point between the target vehicle and the obstacle within the future predetermined time period when there is no intersection between the position information of the plurality of the above-mentioned last-level rectangular frames and the obstacle.

[0068] In an embodiment of the present application, the first determination unit includes a first selection module, a first determination module, and a second determination module. The first selection module is configured to select a target last-level rectangular frame having an intersection with the position information of the obstacle when there is an intersection between the position information of at least one of the plurality of the above-mentioned last-level rectangular frames and the obstacle; the first determination module is configured to determine a target intermediate-level rectangular frame having an intersection with the position information of the obstacle among the multiple upper-level intermediate-level rectangular frames of the target last-level rectangular frame; the second determination module is configured to query upward step by step for the target intermediate-level rectangular frame until the primary rectangular frame having an intersection with the position information of the obstacle is determined. That is, first find the last-level rectangular frame having an intersection with the position information of the obstacle, and then query upward step by step until the smallest-level rectangular frame having an intersection with the position information of the obstacle, that is, the primary rectangular frame, is found, thereby realizing the accurate determination of the collision point.

[0069] In an embodiment of the present application, the selection unit includes a division module, a third determination module, and a second selection module. The division module is configured to divide the target driving trajectory into multiple trajectory segments; the third determination module is configured to determine the proportion of the number of the selected target position points in each trajectory segment to the total number of the position points in the trajectory segment according to the type of the trajectory segment, and the types of the trajectory segments include straight trajectory segments, left-turn trajectory segments, and right-turn trajectory segments; the second selection module is configured to select multiple target position points from the multiple position points of each trajectory segment based on the proportion. In this solution, selecting the number of target position points according to the type of the trajectory segment helps to achieve the accurate determination of the collision point.

[0070] In a specific embodiment, the proportion corresponding to the straight trajectory segment is the first proportion, the proportion corresponding to the left-turn trajectory segment is the second proportion, the proportion corresponding to the right-turn trajectory segment is the third proportion, the second proportion is greater than the first proportion, and the third proportion is greater than the first proportion. Since left-turn and right-turn are relatively complex compared to straight driving, setting the second proportion to be greater than the first proportion and the third proportion to be greater than the first proportion helps to achieve the accurate determination of the collision point.

[0071] In a specific embodiment, the types of the above trajectory segments further include dense trajectory segments and sparse trajectory segments. The number of the above position points in the above dense trajectory segments at the same distance is greater than that in the above sparse trajectory segments. The ratio corresponding to the above dense trajectory segments is the fourth ratio, and the ratio corresponding to the above sparse trajectory segments is the fifth ratio. The above fourth ratio is greater than the above fifth ratio. That is, more target position points are collected for relatively crowded road sections, and fewer target position points are collected for uncrowded road sections, which helps to accurately determine the collision point.

[0072] In an embodiment of the present application, the processing unit is further configured to abstract two adjacent above primary rectangular frames into one intermediate-level rectangular frame, and abstract two adjacent above intermediate-level rectangular frames into one above final-level rectangular frame.

[0073] In an embodiment of the present application, the above device further includes a generating unit and a second determining unit. The generating unit is configured to generate a plurality of current-level rectangular frames that can enclose a plurality of upper-level rectangular frames; the second determining unit is configured to determine the current-level rectangular frame with the smallest area among the above plurality of current-level rectangular frames as the final current-level rectangular frame. As Figure 2 shown, BOX2~3 is the smallest rectangular frame that can enclose BOX2 and BOX3, and BOX0~1 is the smallest rectangular frame that can enclose BOX0 and BOX1. Determining the current-level rectangular frame with the smallest area as the final current-level rectangular frame can ensure that the intermediate-level rectangular frame and the final-level rectangular frame have the smallest area on the premise of including the target position points, so as to reduce the calculation amount and speed up the calculation speed.

[0074] In a specific embodiment, the number of upper-level rectangular frames in different current-level rectangular frames may be equal or unequal. Adaptively adjusting the number of upper-level rectangular frames helps to accurately determine the collision point.

[0075] The device for determining the collision point includes a processor and a memory. The above first acquisition unit, selection unit, second acquisition unit, processing unit, first determination unit, etc. are all stored in the memory as program units, and the processor executes the above program units stored in the memory to implement corresponding functions.

[0076] The processor includes a kernel, and the kernel retrieves the corresponding program units from the memory. One or more kernels can be set, and the collision point can be accurately determined by adjusting the kernel parameters.

[0077] The memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of, for example, read-only memory (ROM) or flash memory (flash RAM). The memory includes at least one storage chip.

[0078] An embodiment of the present invention provides a computer-readable storage medium, where the computer-readable storage medium includes a stored program, and when the program runs, it controls the device where the computer-readable storage medium is located to execute the method for determining a collision point.

[0079] An embodiment of the present invention provides a processor for running a program, where when the program runs, it executes the method for determining a collision point.

[0080] An embodiment of the present invention provides a vehicle, including: one or more processors, and one or more programs, where the above one or more programs are stored in the above memory and are configured to be executed by the above one or more processors, and the above one or more programs include those for executing any one of the above methods.

[0081] An embodiment of the present invention provides a device, which includes a processor, a memory, and a program stored on the memory and executable on the processor. When the processor executes the program, it implements at least the following steps:

[0082] Step S101: Obtain the target driving trajectory of the target vehicle. The above target driving trajectory refers to the driving trajectory of the above target vehicle within a future predetermined time period, and the above target driving trajectory includes a plurality of position points arranged in chronological order.

[0083] Step S102: Select a plurality of position points from the above plurality of position points as target position points, and use a primary rectangular frame to represent each of the above target position points.

[0084] Step S103: Obtain the position information of the obstacle within the above future predetermined time period.

[0085] Step S104: Abstract adjacent multiple above primary rectangular frames into a first intermediate-level rectangular frame, and repeat abstracting multiple M-level intermediate rectangular frames into an M + 1-level intermediate rectangular frame, where M starts from 1 and increases sequentially until adjacent multiple largest intermediate rectangular frames are abstracted into a final-level rectangular frame.

[0086] Step S105: Determine whether there is a collision point between the above target vehicle and the above obstacle within the above future predetermined time period at least according to whether there is an intersection between the above final-level rectangular frame and the position information of the above obstacle.

[0087] The device in this article can be a server, a PC, a PAD, a mobile phone, etc.

[0088] The present application also provides a computer program product, which when executed on a data processing device, is adapted to execute a program initialized with at least the following method steps:

[0089] Step S101: Obtain the target driving trajectory of the target vehicle. The above-mentioned target driving trajectory refers to the driving trajectory of the above-mentioned target vehicle within a future predetermined time period, and the above-mentioned target driving trajectory includes multiple position points arranged in chronological order.

[0090] Step S102: Select multiple position points from the multiple above-mentioned position points as target position points, and use primary rectangular frames to represent each of the above-mentioned target position points.

[0091] Step S103: Obtain the position information of obstacles within the above-mentioned future predetermined time period.

[0092] Step S104: Abstract multiple adjacent above-mentioned primary rectangular frames into a first intermediate-level rectangular frame, and repeat the process of abstracting multiple Mth intermediate-level rectangular frames into an (M + 1)th intermediate-level rectangular frame, where M starts from 1 and increases sequentially until multiple adjacent largest intermediate-level rectangular frames are abstracted into a final-level rectangular frame.

[0093] Step S105: Determine whether there is a collision point between the above-mentioned target vehicle and the above-mentioned obstacle within the above-mentioned future predetermined time period based at least on whether there is an intersection between the above-mentioned final-level rectangular frame and the position information of the above-mentioned obstacle.

[0094] Those skilled in the art should understand that the embodiments of the present application can be provided as methods, systems, or computer program products. Therefore, the present application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present application can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0095] The present application is described with reference to the flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or block in the flowcharts and / or block diagrams, and the combination of processes and / or blocks in the flowcharts and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing devices to generate a machine, such that the instructions executed by the processor of the computer or other programmable data processing devices generate means for implementing the functions specified in one process Figure 1 one process or multiple processes and / or blocks Figure 1 one block or multiple blocks.

[0096] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to operate in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including an instruction means that implements the functions specified in one Figure 1 process or processes and / or blocks Figure 1 specified in one block or blocks.

[0097] These computer program instructions can also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer-implemented process, so that the instructions executed on the computer or other programmable apparatus provide steps for implementing the functions specified in one Figure 1 process or processes and / or blocks Figure 1 specified in one block or blocks.

[0098] In a typical configuration, a computing device includes one or more processors (CPUs), an input / output interface, a network interface, and memory.

[0099] The memory may include non-permanent memory in the form of computer-readable media, random access memory (RAM) and / or non-volatile memory such as read-only memory (ROM) or flash memory (flash RAM). The memory is an example of computer-readable media.

[0100] Computer-readable media includes both permanent and non-permanent, removable and non-removable media implemented by any method or technology for storage of information such as computer-readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, compact disc read-only memory (CD-ROM), digital versatile discs (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer-readable media does not include transitory media such as modulated data signals and carrier waves.

[0101] It should also be noted that the term "comprising", "including" or any other variant thereof is intended to cover non-exclusive inclusion, such that a process, method, commodity or device comprising a series of elements not only includes those elements but also other elements not expressly listed, or elements inherent to such process, method, commodity or device. Without further limitation, an element defined by the statement "comprising an..." does not exclude the presence of additional identical elements in the process, method, commodity or device comprising the element.

[0102] From the above description, it can be seen that the above embodiments of the present application achieve the following technical effects:

[0103] 1), The method for determining the collision point of the present application, by obtaining the target driving trajectory of the target vehicle, where the target driving trajectory refers to the driving trajectory of the target vehicle within a future predetermined time period, selecting multiple position points from multiple said position points as target position points, and using a primary rectangular frame to represent each said target position point, obtaining the position information of the obstacle within the future predetermined time period, abstracting multiple adjacent said primary rectangular frames into a first intermediate rectangular frame, repeating the abstraction of multiple Mth intermediate rectangular frames into an (M + 1)th intermediate rectangular frame, where M starts from 1 and increases sequentially until multiple adjacent largest intermediate rectangular frames are abstracted into a final rectangular frame, and determining whether there is a collision point between the target vehicle and the obstacle within the future predetermined time period at least according to whether there is an intersection between the position information of the final rectangular frame and the obstacle. By using a rectangular frame to represent the position point, abstracting adjacent rectangular frames into a larger rectangular frame, and determining whether there is an intersection between the position information of the final rectangular frame and the obstacle, the determination of the collision point is achieved with a small amount of calculation.

[0104] 2) The device for determining the collision point in the present application. The first acquisition unit acquires the target driving trajectory of the target vehicle, where the target driving trajectory refers to the driving trajectory of the target vehicle within a future predetermined time period. The selection unit selects multiple position points from multiple such position points as target position points, and uses a primary rectangular frame to represent each of the target position points. The second acquisition unit acquires the position information of the obstacle within the future predetermined time period. The processing unit abstracts multiple adjacent primary rectangular frames into a first intermediate-level rectangular frame, and repeats abstracting multiple Mth intermediate-level rectangular frames into an M + 1th intermediate-level rectangular frame, where M starts from 1 and increases sequentially until multiple adjacent largest intermediate-level rectangular frames are abstracted into a final-level rectangular frame. The first determination unit determines whether there is a collision point between the target vehicle and the obstacle within the future predetermined time period at least based on whether there is an intersection between the final-level rectangular frame and the position information of the obstacle. By using a rectangular frame to represent the position point, abstracting adjacent rectangular frames into a larger rectangular frame, and determining whether there is an intersection between the final-level rectangular frame and the position information of the obstacle, the determination of the collision point is realized, and the calculation amount is small.

[0105] The foregoing are only the preferred embodiments of the present application and are not used to limit the present application. For those skilled in the art, the present application may have various changes and modifications. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application shall be included in the protection scope of the present application.

Claims

1. A method for determining a collision point, characterized in that include: Obtaining a target driving trajectory of a target vehicle, wherein the target driving trajectory refers to a driving trajectory of the target vehicle within a predetermined time period in the future, and the target driving trajectory includes a plurality of position points arranged in chronological order; Selecting multiple position points from the multiple position points as target position points, and using a primary rectangular frame to represent each of the target position points; Obtaining location information of obstacles within the predetermined future time period; Abstracting a plurality of adjacent primary rectangular frames into a first intermediate rectangular frame, and repeatedly abstracting a plurality of Mth intermediate rectangular frames into an M+1th intermediate rectangular frame, where M increases sequentially from 1, until a plurality of adjacent largest intermediate rectangular frames are abstracted into a final rectangular frame; At least according to whether the final rectangular frame and the position information of the obstacle have an intersection, it is determined whether there is a collision point between the target vehicle and the obstacle within the future predetermined time period.

2. The method according to claim 1, characterized in that Determining whether there is a collision point between the target vehicle and the obstacle within the future predetermined time period based at least on whether the final rectangular frame and the position information of the obstacle intersect includes: In a case where the position information of the plurality of final-level rectangular frames and the obstacle has no intersection, it is determined that there is no collision point between the target vehicle and the obstacle within the future predetermined time period.

3. The method according to claim 1, wherein Determining whether there is a collision point between the target vehicle and the obstacle within the future predetermined time period based at least on whether the final rectangular frame and the position information of the obstacle intersect includes: In the case where at least one of the plurality of final-level rectangular frames intersects with the position information of the obstacle, selecting a target final-level rectangular frame that intersects with the position information of the obstacle; Determine a target intermediate-level rectangular frame that intersects with the position information of the obstacle among the multiple upper-level intermediate-level rectangular frames of the target final-level rectangular frame; The target intermediate-level rectangular frame is queried upwards level by level until the primary rectangular frame having an intersection with the position information of the obstacle is determined.

4. The method according to any one of claims 1 to 3, characterized in that, Selecting multiple location points from the multiple location points as target location points includes: Dividing the target driving trajectory into a plurality of trajectory segments; determining, according to a type of the trajectory segment, a ratio of the number of the target position points selected from the trajectory segment to the total number of the position points in the trajectory segment, wherein the types of the trajectory segment include a straight trajectory segment, a left-turn trajectory segment, and a right-turn trajectory segment; A plurality of target position points are selected from the plurality of position points of each of the trajectory segments based on the ratio.

5. The method according to claim 4, wherein The ratio corresponding to the straight trajectory segment is a first ratio, the ratio corresponding to the left-turn trajectory segment is a second ratio, and the ratio corresponding to the right-turn trajectory segment is a third ratio. The second ratio is greater than the first ratio, and the third ratio is greater than the first ratio.

6. The method according to claim 4, wherein The types of the trajectory segments further include dense trajectory segments and sparse trajectory segments. The number of position points in the dense trajectory segments of the same distance is greater than the number of position points in the sparse trajectory segments. The ratio corresponding to the dense trajectory segments is a fourth ratio, and the ratio corresponding to the sparse trajectory segments is a fifth ratio. The fourth ratio is greater than the fifth ratio.

7. The method according to any one of claims 1 to 3, characterized in that, Abstract adjacent multiple primary rectangular frames into a first intermediate-level rectangular frame, and repeatedly abstract multiple M-th intermediate-level rectangular frames into an M+1-th intermediate-level rectangular frame, where M starts from 1 and increases sequentially until adjacent multiple largest intermediate-level rectangular frames are abstracted into a final-level rectangular frame, including: Abstract two adjacent primary rectangular frames into an intermediate-level rectangular frame, and abstract two adjacent intermediate-level rectangular frames into a final-level rectangular frame.

8. The method according to any one of claims 1 to 3, characterized in that The method further includes: Generate multiple current-level rectangular frames that can enclose multiple upper-level rectangular frames; Determine the current-level rectangular frame with the smallest area among the multiple current-level rectangular frames as the final current-level rectangular frame.

9. The method according to claim 8, wherein The number of upper-level rectangular frames in different current-level rectangular frames may be equal or unequal.

10. The method according to any one of claims 1 to 3, characterized in that, The future predetermined time period is at least one of the following: 10s, 20s, 30s, 1min, 2min.

11. A device for determining a collision point, characterized in that Including: A first acquisition unit, configured to acquire a target driving trajectory of a target vehicle, where the target driving trajectory refers to the driving trajectory of the target vehicle within a future predetermined time period, and the target driving trajectory includes multiple position points arranged in chronological order; A selection unit, configured to select multiple position points from the multiple position points as target position points, and represent each of the target position points by a primary rectangular frame; A second acquisition unit, configured to acquire position information of an obstacle within the future predetermined time period; A processing unit, configured to abstract adjacent multiple primary rectangular frames into a first intermediate-level rectangular frame, and repeatedly abstract multiple M-th intermediate-level rectangular frames into an M+1-th intermediate-level rectangular frame, where M starts from 1 and increases sequentially until adjacent multiple largest intermediate-level rectangular frames are abstracted into a final-level rectangular frame; A first determination unit, configured to determine whether there is a collision point between the target vehicle and the obstacle within the future predetermined time period at least according to whether there is an intersection between the final-level rectangular frame and the position information of the obstacle.

12. A vehicle, characterized in that, Including: One or more processors, and one or more programs, where the one or more programs are stored in a memory and are configured to be executed by the one or more processors, and the one or more programs include methods for executing any one of claims 1 to 10.

Images