A method, apparatus, device, and storage medium for determining collision risk.

Abstract

This invention discloses a collision risk determination method, apparatus, device, and storage medium, belonging to the field of autonomous driving technology. The method includes: acquiring vehicle-related data of a target vehicle and vertex position information of the rectangular envelope of an obstacle corresponding to a target obstacle; wherein, the vehicle-related data includes the vehicle's planned trajectory and driving range; detecting whether the vertices of the obstacle's rectangular envelope fall within the vehicle's driving range based on the vertex position information; determining the number of intruding vertices within the vehicle's driving range if the vertices of the obstacle's rectangular envelope are detected to fall within the vehicle's driving range; determining the actual obstacle envelope corresponding to the target obstacle based on the number of intruding vertices and the obstacle's rectangular envelope; and determining whether there is a collision risk between the target vehicle and the target obstacle based on the actual obstacle envelope and the vehicle's planned trajectory. This invention improves the accuracy of collision risk determination and ensures driving safety.

Description

Technical Field

[0001] This invention relates to the field of autonomous driving technology, and in particular to a method, apparatus, device, and storage medium for determining collision risk. Background Technology

[0002] Path planning is one of the key technologies in intelligent driving. In path planning, it is necessary to calculate the collision risk of the planned path (i.e., the planned trajectory).

[0003] Existing collision risk assessment techniques involve setting sampling points along the planned trajectory, with each sampling point using a rectangular envelope. Obstacles are also represented by rectangular envelopes. Interference between the two envelopes is then detected; if interference is detected, a collision risk is considered present. However, this collision risk assessment technique involves significant computational load, and the data obtained from the vehicle's environmental perception module contains inherent errors, making it impossible to guarantee the accuracy of collision risk assessment. Summary of the Invention

[0004] This invention provides a method, apparatus, device, and storage medium for determining collision risk, thereby improving the accuracy of collision risk determination and ensuring driving safety.

[0005] According to one aspect of the present invention, a collision risk determination method is provided, the method comprising:

[0006] Acquire vehicle-related data of the target vehicle and vertex position information of the rectangular envelope of the obstacle corresponding to the target obstacle; among which, vehicle-related data includes the vehicle's planned trajectory and the vehicle's driving range;

[0007] Based on the vertex position information, detect whether the vertices of the obstacle rectangle envelope fall within the vehicle's driving range;

[0008] If the vertices of the obstacle rectangular envelope are detected to fall within the vehicle's driving range, determine the number of intruding vertices that fall within the vehicle's driving range.

[0009] Based on the number of intrusion vertices and the rectangular envelope of the obstacles, determine the actual obstacle envelope corresponding to the target obstacle;

[0010] Based on the actual obstacle envelope and the vehicle's planned trajectory, determine whether the target vehicle is at risk of colliding with the target obstacle.

[0011] According to another aspect of the present invention, a collision risk determination device is provided, the device comprising:

[0012] The data acquisition module is used to acquire vehicle-related data of the target vehicle and vertex position information of the rectangular envelope of the obstacle corresponding to the target obstacle; among which, the vehicle-related data includes the vehicle's planned trajectory and the vehicle's driving range;

[0013] The vertex detection module is used to detect whether the vertices of the rectangular envelope of the obstacle fall within the vehicle's driving range based on the vertex position information.

[0014] The intrusion vertex number determination module is used to determine the number of intrusion vertices that fall within the vehicle's driving range when the vertices of the obstacle's rectangular envelope are detected to fall within the vehicle's driving range.

[0015] The actual obstacle envelope determination module is used to determine the actual obstacle envelope corresponding to the target obstacle based on the number of intrusion vertices and the rectangular envelope of the obstacle.

[0016] The first collision risk determination module is used to determine whether the target vehicle is at risk of colliding with the target obstacle based on the actual obstacle envelope and the vehicle's planned trajectory.

[0017] According to another aspect of the present invention, an electronic device is provided, the electronic device comprising:

[0018] At least one processor; and

[0019] A memory that is communicatively connected to at least one processor; wherein,

[0020] The memory stores a computer program that can be executed by at least one processor, such that the at least one processor is able to perform the collision risk determination method according to any embodiment of the present invention.

[0021] According to another aspect of the present invention, a computer-readable storage medium is provided, the computer-readable storage medium storing computer instructions for causing a processor to execute and implement the collision risk determination method of any embodiment of the present invention.

[0022] According to another aspect of the present invention, a computer program product is provided, comprising a computer program that, when executed by a processor, implements the collision risk determination method of any embodiment of the present invention.

[0023] The technical solution of this invention acquires vehicle-related data of the target vehicle and vertex position information of the rectangular envelope of the obstacle corresponding to the target obstacle. The vehicle-related data includes the vehicle's planned trajectory and driving range. Based on the vertex position information, it detects whether the vertices of the obstacle rectangular envelope fall within the vehicle's driving range. If the vertices of the obstacle rectangular envelope are detected to fall within the vehicle's driving range, it determines the number of intruding vertices within the vehicle's driving range. Based on the number of intruding vertices and the obstacle rectangular envelope, it determines the actual obstacle envelope corresponding to the target obstacle. Based on the actual obstacle envelope and the vehicle's planned trajectory, it determines whether there is a collision risk between the target vehicle and the target obstacle. This technical solution, when detecting that the vertices of the obstacle rectangular envelope fall within the vehicle's driving range, determines the actual obstacle envelope corresponding to the target obstacle based on the number of intruding vertices within the obstacle rectangular envelope falling within the vehicle's driving range. This takes into account the possibility of errors in the data acquired by the target vehicle's environmental perception module. By expanding the obstacle envelope of the obstacle, it mitigates the risk caused by inaccurate data, thereby improving the accuracy of collision risk determination and enabling the target vehicle to avoid the target obstacle in a timely manner, ensuring driving safety.

[0024] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of the present invention, nor is it intended to limit the scope of the invention. Other features of the invention will become readily apparent from the following description. Attached Figure Description

[0025] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0026] Figure 1A This is a flowchart of a collision risk determination method provided in Embodiment 1 of the present invention;

[0027] Figure 1B This is a schematic diagram of determining the extended vertex corresponding to the intrusion vertex according to Embodiment 1 of the present invention;

[0028] Figure 1C This is a schematic diagram of determining the actual obstacle envelope according to Embodiment 1 of the present invention;

[0029] Figure 1D This is a schematic diagram of determining the actual obstacle envelope according to Embodiment 1 of the present invention;

[0030] Figure 1EThis is a schematic diagram of determining the actual obstacle envelope according to Embodiment 1 of the present invention;

[0031] Figure 2 This is a flowchart of a collision risk determination method provided in Embodiment 2 of the present invention;

[0032] Figure 3 This is a schematic diagram of a collision risk determination device according to Embodiment 3 of the present invention;

[0033] Figure 4 This is a schematic diagram of the structure of an electronic device that implements the collision risk determination method of the present invention. Detailed Implementation

[0034] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0035] It should be noted that the terms "target," "candidate," "first," and "second," etc., used in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0036] Furthermore, it should be noted that the collection, storage, use, processing, transmission, provision, and disclosure of vehicle-related data, vertex position information of obstacle rectangular envelope, preset extension length, extension vertex extension position information, first threshold, second threshold, and distance threshold involved in the technical solution of the present invention all comply with the provisions of relevant laws and regulations and do not violate public order and good morals.

[0037] Example 1

[0038] Figure 1AThis is a flowchart of a collision risk determination method provided in Embodiment 1 of the present invention. This embodiment is applicable to determining whether there is a collision risk in the planned trajectory of an unmanned vehicle or an autonomous vehicle. This method can be executed by a collision risk determination device, which can be implemented in hardware and / or software and can be configured in an electronic device. Figure 1A As shown, the method includes:

[0039] S101. Obtain vehicle-related data of the target vehicle and vertex position information of the rectangular envelope of the obstacle corresponding to the target obstacle; wherein, the vehicle-related data includes the vehicle's planned trajectory and the vehicle's driving range.

[0040] In this context, the target vehicle refers to an unmanned or autonomous vehicle whose planned trajectory poses a collision risk. The target obstacle refers to an obstacle located near the target vehicle's planned trajectory. The obstacle rectangular envelope is a calculated minimum rectangle on a two-dimensional plane that completely contains the target obstacle's projection; this envelope represents the space occupied by the target obstacle on the two-dimensional plane. It should be noted that the obstacle rectangular envelope includes four vertices. The planned vehicle trajectory refers to the pre-planned vehicle path. The vehicle travel range refers to the range of the target vehicle on the road. It should be noted that the vehicle travel range is determined by the nearest left and right lane lines, i.e., the area between the nearest left and right lane lines is defined as the vehicle travel range. It should be noted that vertex position information refers to the coordinate position information of the vertices of the obstacle rectangular envelope in the vehicle coordinate system.

[0041] Specifically, the vehicle's planned trajectory can be obtained through the trajectory planning module on the target vehicle. At the same time, the nearest left lane line and the nearest right lane line of the target vehicle, as well as the vertex position information of the rectangular envelope of the obstacle corresponding to the target obstacle, can be obtained through the environmental perception module on the target vehicle. Then, the range between the nearest left lane line and the nearest right lane line is determined as the vehicle's driving range.

[0042] S102. Based on the vertex position information, detect whether the vertices of the obstacle rectangular envelope fall within the vehicle's driving range.

[0043] Specifically, in the vehicle coordinate system, based on the vertex position information of the four vertices of the obstacle rectangular envelope, it is detected whether the vertices of the obstacle rectangular envelope fall within the vehicle's driving range.

[0044] S103. If the vertex of the rectangular envelope of the obstacle is detected to fall within the vehicle's driving range, determine the number of intruding vertices that fall within the vehicle's driving range.

[0045] The number of intruding vertices refers to the total number of vertices that fall within the vehicle's driving range from the four vertices of the obstacle's rectangular envelope.

[0046] Specifically, when it is detected that the vertices of the obstacle rectangular envelope fall within the vehicle's driving range, that is, when it is detected that the vertices of the obstacle rectangular envelope are between the nearest left lane line and the nearest right lane line, the number of vertices of the obstacle rectangular envelope falling within the vehicle's driving range is counted by a counter, and the final count is taken as the number of intruding vertices falling within the vehicle's driving range.

[0047] S104. Determine the actual obstacle envelope corresponding to the target obstacle based on the number of intrusion vertices and the obstacle rectangular envelope.

[0048] Among them, the actual obstacle envelope is used to characterize the actual space occupied by the target obstacle in the vehicle coordinate system.

[0049] Specifically, if the number of intruding vertices is greater than two, the obstacle rectangular envelope is taken as the actual obstacle envelope corresponding to the target obstacle; if the number of intruding vertices is less than or equal to two, the envelope edge where the intruding vertex is located is expanded according to the preset expansion length to obtain the expanded vertex corresponding to the intruding vertex; the target lane line is determined according to the y-axis coordinate value of the intruding vertex; the actual obstacle envelope corresponding to the target obstacle is determined according to the intersection information of the obstacle rectangular envelope, the envelope edge where the intruding vertex is located and the target lane line, and the expansion position information of the expanded vertex.

[0050] The preset extension length can be pre-set based on the experience of those skilled in the art; for example, the preset extension length can be 0.15 meters, and this embodiment of the invention does not specifically limit it. The intrusion vertex refers to the vertex among the four vertices of the obstacle's rectangular envelope that falls within the vehicle's driving range. The extension vertex refers to the vertex determined based on the intrusion vertex and the preset extension length. The target lane line refers to the lane line required to determine the actual obstacle envelope. The intersection point location information refers to the coordinate position information of the intersection point of the envelope edge where the intrusion vertex is located and the target lane line in the vehicle coordinate system. The extension position information refers to the coordinate position information of the extension vertex in the vehicle coordinate system.

[0051] If the number of invading vertices is less than or equal to two, then the envelope edges containing the invading vertices are expanded according to a preset expansion length to obtain the expanded vertices corresponding to the invading vertices. This can be done by referring to: Figure 1B If the number of intruded vertices is one, for example, the number of intruded vertices is... Figure 1B In the rectangular envelope of the obstacle, vertex p1 is taken as the starting point, and the path is taken along the envelope edge containing the intruding vertex p1 (i.e., ...). Figure 1BThe edges p1 and p2 of the rectangular envelope of the obstacle are extended outward by a preset extension length to obtain the extended vertex p corresponding to the intruding vertex p1. 1 If there are two intruding vertices, then according to the preset expansion length, the first envelope edge containing the first intruding vertex and the second envelope edge containing the second intruding vertex are expanded respectively, resulting in the first expanded vertex corresponding to the first intruding vertex and the second expanded vertex corresponding to the second intruding vertex. For example, see Figure 1B The first intrusion vertex is Figure 1B Vertex p1 in the rectangular envelope of the obstacle is the second intruding vertex. Figure 1B Vertex p4 in the rectangular envelope of the obstacle is then extended outward by a predetermined length along the first envelope edge p1p2 where the first intrusion vertex p1 is located, starting from the first intrusion vertex p1. This results in the first extended vertex p corresponding to the first intrusion vertex p1. 1 Starting from the second intrusion vertex p4, extend outwards by a predetermined extension length along the second envelope edge p3p4 where the second intrusion vertex p4 is located, thereby obtaining the second extended vertex p corresponding to the second intrusion vertex p4. 4 For example, see also Figure 1B The first intrusion vertex is Figure 1B Vertex p1 in the rectangular envelope of the obstacle is the second intruding vertex. Figure 1B Vertex p2 in the rectangular envelope of the obstacle is then extended outward by a predetermined length along the first envelope edge p1p2 where the first intrusion vertex p1 is located, starting from the first intrusion vertex p1. This results in the first extended vertex p corresponding to the first intrusion vertex p1. 1 Starting from the second intrusion vertex p2, extend outwards by a predetermined extension length along the second envelope edge p1p2 where the second intrusion vertex p2 is located, thereby obtaining the second extended vertex p corresponding to the second intrusion vertex p2. 2 .

[0052] Specifically, determining the target lane line based on the y-axis coordinate value of the intrusion vertex can be done as follows: if the y-axis coordinate value of the intrusion vertex is less than zero, then the nearest left lane line of the target vehicle is determined as the target lane line; if the y-axis coordinate value of the intrusion vertex is greater than zero, then the nearest right lane line of the target vehicle is determined as the target lane line.

[0053] Specifically, the actual obstacle envelope corresponding to the target obstacle is determined based on the obstacle's rectangular envelope, the intersection point information of the envelope edge where the intruding vertex is located and the target lane line, and the extended position information of the extended vertices. This can be achieved by: if the number of intruding vertices is one, see [reference needed]. Figure 1C For example, the intrusion vertex is Figure 1C In the context of p1, the extended vertex corresponding to the intruding vertex is p. 1Let Q1 be the intersection of the envelope edge p1p2 containing the intruding vertex p1 and the target lane line, and Q2 be the intersection of the envelope edge p1p4 containing the intruding vertex p1 and the target lane line. Then, based on the circle-based solution algorithm, according to the coordinate positions of Q1, Q2, and p... 1 Determine the coordinate position. Figure 1C The reference circle is used; then, the overlapping area between the obstacle rectangular envelope and the reference circle is determined; the area formed by the remaining envelope of the obstacle rectangular envelope excluding the overlapping area and the arcs of the reference circle excluding the overlapping area is determined as the actual obstacle envelope corresponding to the target obstacle, i.e. Figure 1C The area in the middle is composed of red lines.

[0054] Optionally, if there are two intrusion vertices, a first reference circle is determined based on the first intersection point information of the envelope edge of the first intrusion vertex and the target lane line, the first extended position information of the first extended vertex, and the second extended position information of the second extended vertex; a second reference circle is determined based on the second intersection point information of the envelope edge of the second intrusion vertex and the target lane line, the second extended position information, and the third intersection point information of the first reference circle and the target lane line; and the actual obstacle envelope corresponding to the target obstacle is determined based on the obstacle rectangular envelope, the first reference circle, and the second reference circle.

[0055] For example, see Figure 1D The first intrusion vertex is Figure 1D Vertex p1 in the rectangular envelope of the obstacle is the second intruding vertex. Figure 1D In the rectangular envelope of the obstacle, vertex p4, and the first extended vertex corresponding to the first intruding vertex p1 are p4 and p1, respectively. 1 The second extended vertex p corresponding to the second invading vertex 4 Let Q1 be the first intersection point of the envelope edge p1p2 containing the first intruding vertex p1 and the target lane line, and Q2 be the second intersection point of the envelope edge p3p4 containing the second intruding vertex p4 and the target lane line. Then, based on the circle-based solution algorithm, according to the coordinate position of Q1, p... 1 coordinates and p 4 The coordinates of the first reference circle are determined. Figure 1D The larger circle; the third intersection of the first reference circle and the target lane line is Figure 1D In Q3, a circle-based solution algorithm is used, based on the coordinate position of Q2 and p. 4 The coordinates of Q1 and Q2 are used to determine the second reference circle, i.e. Figure 1D The smaller circle; then, the largest region (i.e., the area defined by the combination of the obstacle rectangle envelope, the first reference circle, and the second reference circle) will be determined. Figure 1D The area (composed of three fill colors) serves as the actual obstacle envelope corresponding to the target obstacle.

[0056] For example, see Figure 1E The first intrusion vertex is Figure 1E Vertex p1 in the rectangular envelope of the obstacle is the second intruding vertex. Figure 1E In the rectangular envelope of the obstacle, vertex p2, the first extended vertex corresponding to the first intruding vertex p1 is p. 1 The second extended vertex p corresponding to the second invading vertex 2 Let Q1 be the first intersection point of the envelope edge p1p4 containing the first intruding vertex p1 and the target lane line, and Q2 be the second intersection point of the envelope edge p2p3 containing the second intruding vertex p2 and the target lane line. Then, based on the circle-based solution algorithm, according to the coordinate position of Q1, p... 1 coordinates and p 2 The coordinates of the first reference circle are determined. Figure 1E The larger circle; the third intersection of the first reference circle and the target lane line is Figure 1E In Q3, a circle-based solution algorithm is used, based on the coordinate position of Q2 and p. 2 The coordinates of Q1 and Q2 are used to determine the second reference circle, i.e. Figure 1E The smaller circle; then, the largest region (i.e., the area defined by the combination of the obstacle rectangle envelope, the first reference circle, and the second reference circle) will be determined. Figure 1E The area (composed of three fill colors) serves as the actual obstacle envelope corresponding to the target obstacle.

[0057] S105. Based on the actual obstacle envelope and the vehicle's planned trajectory, determine whether the target vehicle is at risk of colliding with the target obstacle.

[0058] Specifically, it detects whether the actual obstacle envelope overlaps with the vehicle's planned trajectory. If so, it determines that there is a risk of collision between the target vehicle and the target obstacle; otherwise, it determines that there is no risk of collision between the target vehicle and the target obstacle.

[0059] The technical solution of this invention involves acquiring vehicle-related data of the target vehicle and vertex position information of the rectangular envelope of the obstacle corresponding to the target obstacle. The vehicle-related data includes the vehicle's planned trajectory and driving range. Based on the vertex position information, it detects whether the vertices of the obstacle's rectangular envelope fall within the vehicle's driving range. If the vertices of the obstacle's rectangular envelope are detected to fall within the vehicle's driving range, it determines the number of intruding vertices within the vehicle's driving range. Based on the number of intruding vertices and the obstacle's rectangular envelope, it determines the actual obstacle envelope corresponding to the target obstacle. Based on the actual obstacle envelope and the vehicle's planned trajectory, it determines whether there is a collision risk between the target vehicle and the target obstacle. This technical solution, when detecting that the vertices of the obstacle's rectangular envelope fall within the vehicle's driving range, determines the actual obstacle envelope corresponding to the target obstacle based on the number of intruding vertices within the obstacle's rectangular envelope falling within the vehicle's driving range. This takes into account the possibility of errors in the data acquired by the target vehicle's environmental perception module. By expanding the obstacle envelope of the obstacle, it mitigates the risk caused by inaccurate data, thereby improving the accuracy of collision risk determination and enabling the target vehicle to avoid the target obstacle in a timely manner, ensuring driving safety.

[0060] Example 2

[0061] Figure 2 This is a flowchart of a collision risk determination method provided in Embodiment 2 of the present invention. This embodiment provides an optional implementation scheme based on the above embodiments. It should be noted that for parts not described in detail in the embodiments of the present invention, please refer to the relevant descriptions in other embodiments. Figure 2 As shown, the method includes:

[0062] S201. Obtain vehicle-related data of the target vehicle and vertex position information of the rectangular envelope of the obstacle corresponding to the target obstacle; wherein, the vehicle-related data includes the vehicle's planned trajectory and the vehicle's driving range.

[0063] S202. Based on the vertex position information, detect whether the vertices of the obstacle rectangular envelope fall within the vehicle's driving range.

[0064] S203. If the vertex of the obstacle rectangular envelope is not detected to fall within the vehicle's driving range, determine the target lane line and the set of candidate points on the target lane line based on the vertex position information of the vertices in the obstacle rectangular envelope, the first threshold, and the second threshold.

[0065] The vertex position information includes the x-axis coordinate value and the y-axis coordinate value.

[0066] Specifically, when it is detected that the vertices of the obstacle rectangular envelope do not fall within the vehicle's driving range, that is, when it is detected that the vertices of the obstacle rectangular envelope are not between the nearest left lane line and the nearest right lane line, in order to more accurately determine the shortest distance from each vertex in the obstacle rectangular envelope to the target lane line, the target lane line can be determined based on the y-axis coordinate values ​​of the vertices in the obstacle rectangular envelope; and the set of candidate points on the target lane line can be determined based on the x-axis coordinate values ​​of the vertices, the first threshold, and the second threshold.

[0067] The first threshold refers to the numerical value required to determine the range of the candidate point set on the target lane line. Optionally, the first threshold can be preset based on the experience of those skilled in the art or experimental experience. For example, the first threshold can be 5 meters, and this embodiment of the invention does not specifically limit it. The second threshold refers to the numerical value required to determine the candidate points in the candidate point set. Optionally, the second threshold can be preset based on the experience of those skilled in the art or experimental experience. For example, the second threshold can be 0.5 meters, and this embodiment of the invention does not specifically limit it. The candidate point set refers to a set composed of multiple candidate points; where a candidate point refers to a selected point on the target lane line.

[0068] More specifically, when the vertex of the obstacle rectangular envelope is detected not to fall within the vehicle's driving range (i.e., when the vertex of the obstacle rectangular envelope is not between the nearest left and right lane lines), for the first vertex (x1, y1) in the obstacle rectangular envelope, if the y-axis coordinate y1 of the first vertex (x1, y1) is less than zero, the target lane line is determined to be the nearest left lane line; if the y-axis coordinate y1 of the first vertex (x1, y1) is greater than zero, the target lane line is determined to be the rightmost lane line. [x1-α, x1+α] is used as the selection range for the x-axis coordinate values ​​of candidate points on the target lane line; where α represents the first threshold. Based on the second threshold, multiple candidate x-axis coordinate values ​​are determined from [x1-α, x1+α]. Each candidate x-axis coordinate value is substituted into the lane line equation of the target lane line to obtain multiple candidate points on the target lane line, resulting in a candidate point set composed of these multiple candidate points. Where β represents the second threshold; n is a positive integer representing the total number of candidate points. Similarly, we can obtain the target lane line determined by the vertex position information of the second vertex (x2, y2) in the obstacle rectangular envelope, the first threshold, and the second threshold, as well as the set of candidate points on the target lane line. We can obtain the target lane line determined by the vertex position information of the third vertex (x3, y3) in the rectangular envelope of the obstacle, the first threshold, and the second threshold, as well as the set of candidate points on the target lane line. We can obtain the target lane line determined by the vertex position information of the fourth vertex (x4, y4) in the rectangular envelope of the obstacle, the first threshold, and the second threshold, as well as the set of candidate points on the target lane line.

[0069] S204. Based on the Euclidean distance between each candidate point in the candidate point set and the vertex, determine the shortest distance between the vertex and the target lane line.

[0070] Specifically, for the first vertex (x1, y1) in the rectangular envelope of the obstacle, the first vertex and the candidate point set are calculated sequentially. The Euclidean distance of each candidate point is calculated, thus obtaining {Dist1, Dist2, ..., Dist n}; where n is a positive integer representing the total number of candidate points; then, {Dist1,Dist2,…,Dist n The minimum value in} is taken as the shortest distance between the first vertex (x1, y1) in the obstacle rectangular envelope and the target lane line, denoted as . Similarly, the shortest distance between the second vertex (x2, y2) in the rectangular envelope of the obstacle and the target lane line can be obtained, denoted as . The shortest distance between the third vertex (x3, y3) in the rectangular envelope of the obstacle and the target lane line is denoted as... The shortest distance between the fourth vertex (x4, y4) in the rectangular envelope of the obstacle and the target lane line is denoted as...

[0071] Understandably, determining the shortest distance between each vertex in the obstacle rectangular envelope and the target lane line, rather than using any point on the target lane line as a reference, unifies the standard for determining the shortest distance between each vertex in the obstacle rectangular envelope and the target lane line, making the subsequently determined shortest vertex more accurate.

[0072] S205. Based on the nearest distance between each vertex in the rectangular envelope of the obstacle and the target lane line, determine the nearest vertex closest to the target lane line, and the target distance between the nearest vertex and the target lane line.

[0073] Specifically, calculation and The minimum value in the range is used, and the vertex corresponding to this minimum value is taken as the nearest vertex. The shortest distance between the nearest vertex and the target lane line is taken as the target distance. For example, if and The minimum value in is Then, the first vertex (x1, y1) in the rectangular envelope of the obstacle is taken as the nearest vertex, and the shortest distance between the first vertex (x1, y1) and the target lane line is calculated. As the target distance.

[0074] Understandably, by determining the shortest distance (i.e., the target distance) between the rectangular envelope of the obstacle and the target lane line, the intelligent driving system on the target vehicle can determine whether the obstacle is about to or has already encroached on the lane where the target vehicle is located, thus facilitating the timely determination of collision risk.

[0075] S206. Based on the vehicle's planned trajectory, target distance, and distance threshold, determine whether the target vehicle is at risk of colliding with the target obstacle.

[0076] The distance threshold can be preset based on the experience of those skilled in the art or on experimental experience. For example, the distance threshold can be 0.15 meters. This embodiment of the invention does not make a specific setting for it.

[0077] Specifically, if the target distance is greater than the distance threshold, it is determined that there is no risk of collision between the target vehicle and the target obstacle; if the target distance is less than or equal to the distance threshold, the envelope length of the obstacle's rectangular envelope is obtained; a reference line segment is determined based on the position information of the nearest vertex and the envelope length; if the reference line segment overlaps with the vehicle's planned trajectory, it is determined that there is a risk of collision between the target vehicle and the target obstacle; otherwise, it is determined that there is no risk of collision between the target vehicle and the target obstacle.

[0078] Specifically, determining the reference line segment based on the position information of the nearest vertex and the envelope length can be done as follows: If the coordinate position of the nearest vertex is denoted as (x0, y0) and the envelope length is denoted as L, then the coordinate position of the reference point (x0-L, y0) is determined based on the coordinate position of the nearest vertex (x0, y0) and the envelope length L; and the reference line segment is determined based on the coordinate position of the nearest vertex (x0, y0) and the coordinate position of the reference point (x0-L, y0).

[0079] The technical solution of this invention involves acquiring vehicle-related data of the target vehicle and vertex position information of the rectangular envelope of the obstacle corresponding to the target obstacle. The vehicle-related data includes the vehicle's planned trajectory and driving range. Based on the vertex position information, it detects whether the vertices of the rectangular envelope of the obstacle fall within the vehicle's driving range. If the vertices of the rectangular envelope of the obstacle do not fall within the vehicle's driving range, it determines the target lane line and a set of candidate points on the target lane line based on the vertex position information of the vertices in the rectangular envelope of the obstacle, a first threshold, and a second threshold. Based on the Euclidean distance between each candidate point in the candidate point set and the vertex, it determines the closest distance between the vertex and the target lane line. Based on the closest distance between each vertex in the rectangular envelope of the obstacle and the target lane line, it determines the nearest vertex closest to the target lane line and the target distance between the nearest vertex and the target lane line. Based on the vehicle's planned trajectory, the target distance, and the distance threshold, it determines whether there is a collision risk between the target vehicle and the target obstacle. The above technical solution determines whether there is a collision risk between the target vehicle and the target obstacle when the vertex of the obstacle rectangular envelope does not fall within the vehicle's driving range. This is based on the shortest distance between the obstacle rectangular envelope and the target lane line (i.e., the target distance) and the distance threshold. It eliminates the need to sequentially calculate whether each vertex in the obstacle rectangular envelope poses a collision risk to the target vehicle, reducing computational load, saving computing power, and accelerating the collision risk determination process, thereby ensuring the real-time nature of the collision risk determination.

[0080] Based on the above embodiments, as an optional embodiment of the present invention, after determining that there is a risk of collision between the target vehicle and the target obstacle, the trajectory planning module on the target vehicle can be used to replan the vehicle's trajectory to avoid the target obstacle and ensure the driving safety of the target vehicle.

[0081] Example 3

[0082] Figure 3 This is a schematic diagram of a collision risk determination device provided in Embodiment 3 of the present invention. This embodiment is applicable to determining whether there is a collision risk in the planned trajectory of an unmanned vehicle or an autonomous vehicle. The device can be implemented in hardware and / or software and can be configured in an electronic device. Figure 3 As shown, the device includes:

[0083] The data acquisition module 301 is used to acquire vehicle-related data of the target vehicle and vertex position information of the rectangular envelope of the obstacle corresponding to the target obstacle; wherein, the vehicle-related data includes the vehicle's planned trajectory and the vehicle's driving range;

[0084] Vertex detection module 302 is used to detect whether the vertices of the rectangular envelope of the obstacle fall within the vehicle's driving range based on the vertex position information;

[0085] The intrusion vertex number determination module 303 is used to determine the number of intrusion vertices that fall within the vehicle's driving range when the vertex of the obstacle rectangular envelope is detected to fall within the vehicle's driving range.

[0086] The actual obstacle envelope determination module 304 is used to determine the actual obstacle envelope corresponding to the target obstacle based on the number of intrusion vertices and the rectangular envelope of the obstacle.

[0087] The first collision risk determination module 305 is used to determine whether the target vehicle is at risk of colliding with the target obstacle based on the actual obstacle envelope and the vehicle's planned trajectory.

[0088] The technical solution of this invention involves acquiring vehicle-related data of the target vehicle and vertex position information of the rectangular envelope of the obstacle corresponding to the target obstacle. The vehicle-related data includes the vehicle's planned trajectory and driving range. Based on the vertex position information, it detects whether the vertices of the obstacle's rectangular envelope fall within the vehicle's driving range. If the vertices of the obstacle's rectangular envelope are detected to fall within the vehicle's driving range, it determines the number of intruding vertices within the vehicle's driving range. Based on the number of intruding vertices and the obstacle's rectangular envelope, it determines the actual obstacle envelope corresponding to the target obstacle. Based on the actual obstacle envelope and the vehicle's planned trajectory, it determines whether there is a collision risk between the target vehicle and the target obstacle. This technical solution, when detecting that the vertices of the obstacle's rectangular envelope fall within the vehicle's driving range, determines the actual obstacle envelope corresponding to the target obstacle based on the number of intruding vertices within the obstacle's rectangular envelope falling within the vehicle's driving range. This takes into account the possibility of errors in the data acquired by the target vehicle's environmental perception module. By expanding the obstacle envelope of the obstacle, it mitigates the risk caused by inaccurate data, thereby improving the accuracy of collision risk determination and enabling the target vehicle to avoid the target obstacle in a timely manner, ensuring driving safety.

[0089] Optionally, the actual obstacle envelope determination module 304 includes:

[0090] An extended vertex determination unit is used to extend the envelope edge where the invading vertex is located according to a preset extension length if the number of invading vertices is less than or equal to two, so as to obtain the extended vertex corresponding to the invading vertex.

[0091] The target lane line determination unit is used to determine the target lane line based on the y-axis coordinate value of the intrusion vertex;

[0092] The actual obstacle envelope determination unit is used to determine the actual obstacle envelope corresponding to the target obstacle based on the obstacle rectangular envelope, the intersection point information of the envelope edge where the intrusion vertex is located and the target lane line, and the extended position information of the extended vertex.

[0093] Optionally, the vertex determination unit is extended, specifically for:

[0094] If there are two invading vertices, then according to the preset extension length, the first envelope edge where the first invading vertex is located and the second envelope edge where the second invading vertex is located are extended respectively to obtain the first extended vertex corresponding to the first invading vertex and the second extended vertex corresponding to the second invading vertex.

[0095] Optionally, the actual obstacle envelope determination unit is specifically used for:

[0096] If there are two intrusion vertices, the first reference circle is determined based on the first intersection point information of the envelope edge where the first intrusion vertex is located and the target lane line, the first extended position information of the first extended vertex, and the second extended position information of the second extended vertex.

[0097] The second reference circle is determined based on the second intersection point information of the envelope edge where the second intrusion vertex is located and the target lane line, the second extended position information, and the third intersection point information of the first reference circle and the target lane line.

[0098] The actual obstacle envelope corresponding to the target obstacle is determined based on the obstacle rectangular envelope, the first reference circle, and the second reference circle.

[0099] Optionally, the device may also include:

[0100] The candidate point set determination module is used to determine the target lane line and the candidate point set on the target lane line based on the vertex position information of the vertices in the obstacle rectangular envelope, a first threshold and a second threshold when the vertex of the obstacle rectangular envelope does not fall within the vehicle's driving range.

[0101] The nearest distance determination module is used to determine the nearest distance between the vertex and the target lane line based on the Euclidean distance between each candidate point in the candidate point set and the vertex.

[0102] The target distance determination module is used to determine the nearest vertex closest to the target lane line and the target distance between the nearest vertex and the target lane line based on the nearest distance between each vertex in the rectangular envelope of the obstacle and the target lane line.

[0103] The second collision risk determination module is used to determine whether there is a collision risk between the target vehicle and the target obstacle based on the vehicle's planned trajectory, target distance, and distance threshold.

[0104] Optionally, the vertex position information includes x-axis coordinates and y-axis coordinates; the candidate point set determination module is specifically used for:

[0105] The target lane line is determined based on the y-axis coordinates of the vertices in the rectangular envelope of the obstacle.

[0106] Based on the x-axis coordinates of the vertices, the first threshold, and the second threshold, a set of candidate points on the target lane line is determined.

[0107] Optional, the second collision risk determination module is specifically used for:

[0108] If the target distance is greater than the distance threshold, it is determined that there is no risk of collision between the target vehicle and the target obstacle;

[0109] If the target distance is less than or equal to the distance threshold, then obtain the envelope length of the obstacle rectangle envelope;

[0110] Determine the reference line segment based on the position information of the nearest vertex and the envelope length;

[0111] If the reference line segment overlaps with the vehicle's planned trajectory, it is determined that there is a risk of collision between the target vehicle and the target obstacle.

[0112] Otherwise, it is determined that there is no risk of collision between the target vehicle and the target obstacle.

[0113] The collision risk determination device provided in the embodiments of the present invention can execute the collision risk determination method provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects for executing each collision risk determination method.

[0114] According to embodiments of the present invention, the present invention also provides an electronic device, a readable storage medium, and a computer program product.

[0115] Example 4

[0116] Figure 4 A schematic diagram of an electronic device 10 that can be used to implement embodiments of the present invention is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices (e.g., helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the invention described and / or claimed herein.

[0117] like Figure 4As shown, the electronic device 10 includes at least one processor 11 and a memory, such as a read-only memory (ROM) 12 or a random access memory (RAM) 13, communicatively connected to the at least one processor 11. The memory stores computer programs executable by the at least one processor. The processor 11 can perform various appropriate actions and processes based on the computer program stored in the ROM 12 or loaded from storage unit 18 into the RAM 13. The RAM 13 can also store various programs and data required for the operation of the electronic device 10. The processor 11, ROM 12, and RAM 13 are interconnected via a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0118] Multiple components in electronic device 10 are connected to I / O interface 15, including: input unit 16, such as keyboard, mouse, etc.; output unit 17, such as various types of displays, speakers, etc.; storage unit 18, such as disk, optical disk, etc.; and communication unit 19, such as network card, modem, wireless transceiver, etc. Communication unit 19 allows electronic device 10 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0119] Processor 11 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. Processor 11 performs the various methods and processes described above, such as collision risk determination methods.

[0120] In some embodiments, the collision risk determination method may be implemented as a computer program tangibly contained in a computer-readable storage medium, such as storage unit 18. In some embodiments, part or all of the computer program may be loaded and / or installed on electronic device 10 via ROM 12 and / or communication unit 19. When the computer program is loaded into RAM 13 and executed by processor 11, one or more steps of the collision risk determination method described above may be performed. Alternatively, in other embodiments, processor 11 may be configured to perform the collision risk determination method by any other suitable means (e.g., by means of firmware).

[0121] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), payload-programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0122] Computer programs used to implement the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when executed by the processor, the computer programs cause the functions / operations specified in the flowcharts and / or block diagrams to be performed. The computer programs may be executed entirely on a machine, partially on a machine, or as a standalone software package, partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0123] In the context of this invention, a computer-readable storage medium can be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, apparatus, or device. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination thereof. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0124] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the electronic device. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0125] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or computing systems that include middleware components (e.g., application servers), or computing systems that include frontend components (e.g., user computers with graphical user interfaces or web browsers through which users can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., communication networks). Examples of communication networks include local area networks (LANs), wide area networks (WANs), blockchain networks, and the Internet.

[0126] A computing system can include clients and servers. Clients and servers are generally located far apart and typically interact through communication networks. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or cloud host, which is a hosting product within the cloud computing service system to address the shortcomings of traditional physical hosts and VPS services, such as high management difficulty and weak business scalability.

[0127] It should be understood that the various forms of processes shown above can be used, with steps reordered, added, or deleted. For example, the steps described in this invention can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution of this invention can be achieved, and this is not limited herein.

[0128] The specific embodiments described above do not constitute a limitation on the scope of protection of this invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this invention should be included within the scope of protection of this invention.

Claims

1. A method for determining collision risk, characterized in that, include: Acquire vehicle-related data of the target vehicle and vertex position information of the rectangular envelope of the obstacle corresponding to the target obstacle; wherein, the vehicle-related data includes the vehicle's planned trajectory and the vehicle's driving range; Based on the vertex position information, it is detected whether the vertices of the obstacle rectangular envelope fall within the vehicle's driving range; If the vertex of the rectangular envelope of the obstacle is detected to fall within the driving range of the vehicle, the number of intruding vertices falling within the driving range of the vehicle is determined. Based on the number of intrusion vertices and the rectangular envelope of the obstacle, the actual obstacle envelope corresponding to the target obstacle is determined; Based on the actual obstacle envelope and the vehicle's planned trajectory, it is determined whether the target vehicle is at risk of colliding with the target obstacle.

2. The method according to claim 1, characterized in that, The step of determining the actual obstacle envelope corresponding to the target obstacle based on the number of intrusion vertices and the obstacle rectangular envelope includes: If the number of invading vertices is less than or equal to two, then the envelope edge where the invading vertex is located is expanded according to the preset expansion length to obtain the expanded vertex corresponding to the invading vertex; The target lane line is determined based on the y-axis coordinate value of the intrusion vertex; The actual obstacle envelope corresponding to the target obstacle is determined based on the obstacle rectangular envelope, the intersection point information of the envelope edge where the intrusion vertex is located and the target lane line, and the expansion position information of the expansion vertex.

3. The method according to claim 2, characterized in that, If the number of invading vertices is less than or equal to two, then according to a preset expansion length, the envelope edge containing the invading vertex is expanded to obtain the expanded vertex corresponding to the invading vertex, including: If there are two intrusion vertices, then according to the preset extension length, the first envelope edge where the first intrusion vertex is located and the second envelope edge where the second intrusion vertex is located are extended respectively to obtain the first extended vertex corresponding to the first intrusion vertex and the second extended vertex corresponding to the second intrusion vertex.

4. The method according to claim 3, characterized in that, The step of determining the actual obstacle envelope corresponding to the target obstacle based on the obstacle rectangular envelope, the intersection point information of the envelope edge where the intrusion vertex is located and the target lane line, and the expansion position information of the expansion vertex, includes: If the number of intrusion vertices is two, a first reference circle is determined based on the first intersection point information of the envelope edge where the first intrusion vertex is located and the target lane line, the first extended position information of the first extended vertex, and the second extended position information of the second extended vertex. The second reference circle is determined based on the second intersection point information of the envelope edge where the second intrusion vertex is located and the target lane line, the second extended position information, and the third intersection point information of the first reference circle and the target lane line; The actual obstacle envelope corresponding to the target obstacle is determined based on the obstacle rectangular envelope, the first reference circle, and the second reference circle.

5. The method according to claim 1, characterized in that, The method further includes: If it is detected that the vertices of the rectangular envelope of the obstacle do not fall within the driving range of the vehicle, the target lane line and the set of candidate points on the target lane line are determined based on the vertex position information of the vertices in the rectangular envelope of the obstacle, the first threshold and the second threshold. The shortest distance between the vertex and the target lane line is determined based on the Euclidean distance between each candidate point in the candidate point set and the vertex. Based on the nearest distance between each vertex in the rectangular envelope of the obstacle and the target lane line, determine the nearest vertex to the target lane line, and the target distance between the nearest vertex and the target lane line; Based on the vehicle's planned trajectory, the target distance, and the distance threshold, it is determined whether the target vehicle is at risk of colliding with the target obstacle.

6. The method according to claim 5, characterized in that, The vertex position information includes x-axis coordinates and y-axis coordinates; Based on the vertex position information of the vertices in the rectangular envelope of the obstacle, a first threshold, and a second threshold, a target lane line and a set of candidate points on the target lane line are determined, including: The target lane line is determined based on the y-axis coordinates of the vertices in the rectangular envelope of the obstacle. Based on the x-axis coordinates of the vertex, a first threshold, and a second threshold, a set of candidate points on the target lane line is determined.

7. The method according to claim 5, characterized in that, The step of determining whether the target vehicle is at risk of colliding with the target obstacle based on the vehicle's planned trajectory, the target distance, and a distance threshold includes: If the target distance is greater than a distance threshold, it is determined that there is no risk of collision between the target vehicle and the target obstacle. If the target distance is less than or equal to the distance threshold, then the envelope length of the obstacle rectangular envelope is obtained; The reference line segment is determined based on the position information of the nearest vertex and the envelope length; If the reference line segment overlaps with the planned trajectory of the vehicle, it is determined that there is a risk of collision between the target vehicle and the target obstacle. Otherwise, it is determined that there is no risk of collision between the target vehicle and the target obstacle.

8. A collision risk determination device, characterized in that, include: The data acquisition module is used to acquire vehicle-related data of the target vehicle and vertex position information of the rectangular envelope of the obstacle corresponding to the target obstacle; wherein, the vehicle-related data includes the vehicle's planned trajectory and the vehicle's driving range; The vertex detection module is used to detect whether the vertices of the rectangular envelope of the obstacle fall within the driving range of the vehicle based on the vertex position information. The intrusion vertex number determination module is used to determine the number of intrusion vertices that fall within the vehicle's driving range when the vertex of the obstacle's rectangular envelope is detected to fall within the vehicle's driving range. The actual obstacle envelope determination module is used to determine the actual obstacle envelope corresponding to the target obstacle based on the number of intrusion vertices and the obstacle rectangular envelope; The first collision risk determination module is used to determine whether the target vehicle has a collision risk with the target obstacle based on the actual obstacle envelope and the vehicle's planned trajectory.

9. An electronic device, characterized in that, The electronic device includes: At least one processor; and A memory communicatively connected to the at least one processor; wherein, The memory stores a computer program that can be executed by the at least one processor to enable the at least one processor to perform the collision risk determination method according to any one of claims 1-7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions that cause a processor to execute the collision risk determination method according to any one of claims 1-7.

11. A computer program product comprising a computer program that, when executed by a processor, implements the collision risk determination method according to any one of claims 1-7.

Images