Collision detection method, device and electronic device for vehicle automatic driving system

Abstract

The present invention relates to the field of autonomous driving, and in particular to a collision detection method, device, electronic device and storage medium for a vehicle autonomous driving system. The method comprises: obtaining a first target position frame diagram corresponding to a target vehicle in a target coordinate system; obtaining a second target position corresponding to each vertex in a target obstacle in the target coordinate system; detecting whether a line between any two adjacent second target positions intersects with the first target position frame diagram; when a line between any two adjacent second target positions intersects with the first target position frame diagram, determining that a collision occurs between the target vehicle and the target obstacle. The above method does not simplify the shape and size of the target obstacle, thereby ensuring the accuracy of the shape and size of the target obstacle determined according to the second target position corresponding to each vertex in the target obstacle. In addition, the accuracy of the result of the collision between the target vehicle and the target obstacle can be ensured.

Description

Technical Field

[0001] The present invention relates to the field of autonomous driving, and in particular to a collision detection method, device, and electronic equipment for a vehicle autonomous driving system. Background Art

[0002] The transformation of the passenger car industry is centered around the "four new trends in automobiles", namely electrification, networking, intelligence, and sharing. Among them, "electrification" is the foundation, "networking" is the channel for data collection and analysis, and "intelligence and sharing" are the goals, which will ultimately realize autonomous driving and smart travel.

[0003] In recent years, the "New Four Modernizations" that started in the passenger car field are accelerating their penetration into the traditional engineering machinery industry. In the autonomous driving system, the environmental perception unit collects data on obstacles in the surrounding environment (such as people, cars, bicycles, etc.), and can output obstacle information with clear and distinct boundary contours. The perception module can input the obstacle's outline size, boundary coordinates, speed and other information to the downstream decision-making and planning unit. The decision-making and planning unit determines whether a collision will occur between the vehicle and the obstacle based on the obstacle's outline size, boundary coordinates, speed and other information combined with trajectory planning information detection, and generates vehicle motion control information based on the detection results.

[0004] In the prior art, the environment perception unit usually simplifies the outline of the obstacle when processing the collected environment data and outputs a contour frame diagram. However, the shapes of obstacles in real scenes vary, and the simplified contour frame diagram cannot truly reflect the size feature information of the obstacle, which may lead to inaccurate results in detecting whether a collision will occur between the vehicle and the obstacle. Summary of the invention

[0005] In view of this, an embodiment of the present invention provides a collision detection method, device, electronic device and storage medium for a vehicle automatic driving system, aiming to solve the problem of inaccurate results in detecting whether a collision will occur between a vehicle and an obstacle.

[0006] According to a first aspect, an embodiment of the present invention provides a collision detection method for a vehicle automatic driving system, the method comprising:

[0007] Obtain a first target position block diagram corresponding to the target vehicle in the target coordinate system;

[0008] Obtain the second target position corresponding to each vertex in the target obstacle in the target coordinate system;

[0009] Detect whether a line between any two adjacent second target positions intersects with a first target position frame diagram;

[0010] When the line between any two adjacent second target positions intersects with the first target position frame diagram, it is determined that a collision occurs between the target vehicle and the target obstacle.

[0011] The collision detection method for a vehicle automatic driving system provided by an embodiment of the present invention obtains a first target position frame diagram corresponding to a target vehicle in a target coordinate system, thereby ensuring the accuracy of the position information of the target vehicle obtained and the accuracy of the shape and size information of the target vehicle. Then, the second target position corresponding to each vertex in the target obstacle in the target coordinate system is obtained, instead of directly obtaining the contour frame diagram of the target obstacle in the target coordinate system, so that the accuracy of the second target position corresponding to each vertex in the target obstacle obtained can be ensured, and the shape and size of the target obstacle are not simplified, thereby ensuring the accuracy of the shape and size of the target obstacle determined according to the second target position corresponding to each vertex in the target obstacle. Detecting whether the line between any two adjacent second target positions intersects with the first target position frame diagram ensures the accuracy of the detection result. When the line between any two adjacent second target positions intersects with the first target position frame diagram, it is determined that a collision occurs between the target vehicle and the target obstacle, thereby ensuring the accuracy of the determined collision result between the target vehicle and the target obstacle.

[0012] In combination with the first aspect, in a second implementation of the first aspect, detecting whether a line between any two adjacent second target positions intersects with a first target position frame diagram includes:

[0013] Obtain a first horizontal coordinate range corresponding to the first target position frame diagram;

[0014] Connect any two adjacent second target positions to generate a target line segment, and determine a second horizontal coordinate range corresponding to the target line segment;

[0015] When the first horizontal coordinate range has no intersection with the second horizontal coordinate range, it is determined that the target line segment does not intersect with the first target position frame.

[0016] The collision detection method for a vehicle automatic driving system provided by an embodiment of the present invention obtains the first horizontal coordinate range corresponding to the first target position frame diagram, connects any two adjacent second target positions, and generates a target line segment, thereby ensuring that the generated target line segment can accurately represent the contour corresponding to the target obstacle. Then, the second horizontal coordinate range corresponding to the target line segment is determined, thereby ensuring the accuracy of the second horizontal coordinate range corresponding to the determined target line segment. When the first horizontal coordinate range and the second horizontal coordinate range have no intersection, it is determined that the target line segment does not intersect with the first target position frame diagram, thereby ensuring the accuracy of the result of determining that the target line segment does not intersect with the first target position frame diagram.

[0017] In combination with the first embodiment of the first aspect, in the second embodiment of the first aspect, the method further includes:

[0018] When the first horizontal coordinate range and the second horizontal coordinate range have an intersection, determining a third horizontal coordinate range where the first horizontal coordinate range and the second horizontal coordinate range intersect;

[0019] Determine a first ordinate range corresponding to the first target position frame diagram corresponding to the third abscissa range;

[0020] Determine a second ordinate range corresponding to the target line segment corresponding to the third abscissa range;

[0021] When the first ordinate range and the second ordinate range have an intersection, determining that the target line segment intersects with the first target position frame diagram;

[0022] When there is no intersection between the first ordinate range and the second ordinate range, it is determined that the target line segment does not intersect with the first target position frame.

[0023] In the collision detection method for a vehicle automatic driving system provided by an embodiment of the present invention, when the first horizontal coordinate range and the second horizontal coordinate range have an intersection, a third horizontal coordinate range where the first horizontal coordinate range and the second horizontal coordinate range intersect is determined, thereby ensuring the accuracy of the determined third horizontal coordinate range. Then, the first vertical coordinate range corresponding to the first target position frame diagram corresponding to the third horizontal coordinate range is determined, thereby ensuring the accuracy of the determined first vertical coordinate range. Then, the second vertical coordinate range corresponding to the target line segment corresponding to the third horizontal coordinate range is determined, and when the first vertical coordinate range and the second vertical coordinate range have an intersection, it is determined that the target line segment and the first target position frame diagram intersect, thereby determining that a collision occurs between the target vehicle and the target obstacle, thereby ensuring the accuracy of the result of the collision between the target vehicle and the target obstacle. When the first vertical coordinate range and the second vertical coordinate range do not have an intersection, it is determined that the target line segment and the first target position frame diagram do not intersect, thereby determining that the target vehicle and the target obstacle do not collide, thereby ensuring the accuracy of the result of the collision between the target vehicle and the target obstacle. The above method can not only accurately detect whether a collision occurs between a target vehicle and a target obstacle, but is also simple and convenient, has a small amount of calculation, and occupies less computing resources.

[0024] In combination with the first aspect, in a third implementation of the first aspect, obtaining a first target position block diagram corresponding to the target vehicle in the target coordinate system includes:

[0025] Obtain the positioning point of the target vehicle, take the positioning point as the origin of the target coordinate system, take the target vehicle's driving direction as the longitudinal axis, and take the axis perpendicular to the target vehicle's driving direction as the transverse axis to establish the target coordinate system;

[0026] Obtain the real position of each edge of the target vehicle in the target coordinate system;

[0027] A first target position frame diagram is generated according to the actual positions corresponding to the edges.

[0028] The collision detection method for the vehicle automatic driving system provided by the embodiment of the present invention obtains the positioning point of the target vehicle, and then establishes the target coordinate system with the positioning point as the origin of the target coordinate system, the target vehicle driving direction as the longitudinal axis, and the horizontal axis perpendicular to the target vehicle driving direction, ensuring that the established target coordinate system can be suitable for the driving of the target vehicle, thereby ensuring the accuracy of the established target coordinate system. Then, the real position of each edge in the target vehicle in the target coordinate system is obtained, ensuring the accuracy of the real position of each edge in the target vehicle in the target coordinate system, and generating a first target position block diagram according to the real position corresponding to each edge, ensuring that the generated first target position block diagram matches the position, size and shape of the target vehicle, thereby ensuring the accuracy of the result of whether a collision occurs between the target vehicle and the target obstacle.

[0029] In combination with the third implementation manner of the first aspect, in the fourth implementation manner of the first aspect, generating a first target position block diagram according to the real positions corresponding to the edges includes:

[0030] Get the safety distance corresponding to the target vehicle;

[0031] According to the real position corresponding to each edge, each edge is moved outward by a safe distance to generate the target position corresponding to each edge in the target vehicle;

[0032] The target positions corresponding to the edges are connected to generate a first target position block diagram.

[0033] The collision detection method for a vehicle automatic driving system provided by an embodiment of the present invention obtains the safety distance corresponding to the target vehicle, and ensures the accuracy of the safety distance corresponding to the target vehicle. According to the real position corresponding to each edge, each edge is moved outward by a safety distance to generate the target position corresponding to each edge in the target vehicle, which not only ensures that the generated target position matches the position, size and shape of the target vehicle, but also ensures the safe driving of the target vehicle. Then, the target positions corresponding to each edge are connected to generate a first target position block diagram, which ensures that the generated first target position block diagram matches the position, size and shape of the target vehicle, and can ensure the safe driving of the target vehicle, thereby making the result of determining whether a collision occurs between the target vehicle and the target obstacle more accurate.

[0034] In combination with the third implementation of the first aspect, in the fifth implementation of the first aspect, obtaining the second target position corresponding to each vertex in the target obstacle in the target coordinate system includes:

[0035] Obtaining first original position information of the positioning point of the target vehicle in the original geodetic coordinate system;

[0036] Obtain the second original position of each vertex in the target obstacle in the original earth coordinate system;

[0037] According to the relationship between the first original position information and the second original position, the second original position corresponding to each vertex is converted into a second target position corresponding to each vertex.

[0038] The collision detection method for a vehicle automatic driving system provided by an embodiment of the present invention obtains the first original position information of the positioning point of the target vehicle in the original geodetic coordinate system, and then obtains the second original position of each vertex in the target obstacle in the original geodetic coordinate system; according to the relationship between the first original position information and the second original position, the second original position corresponding to each vertex is converted into the second target position corresponding to each vertex. The accuracy of converting the second original position corresponding to each vertex into the second target position corresponding to each vertex is guaranteed.

[0039] In combination with the fifth implementation of the first aspect, in the sixth implementation of the first aspect, according to the relationship between the first original position information and the second original position, converting the second original position corresponding to each vertex into the second target position corresponding to each vertex includes:

[0040] Obtain the deflection angle of the target vehicle's positioning point relative to the original geodetic coordinate system;

[0041] According to the relationship between the deflection angle, the original earth coordinate system and the target coordinate system, a rotation matrix from the original earth coordinate system to the target coordinate system is generated;

[0042] The second target positions are obtained by using the relationship between the rotation matrix, the second original position and the first original position information.

[0043] The collision detection method for the vehicle automatic driving system provided by the embodiment of the present invention obtains the deflection angle of the positioning point of the target vehicle relative to the original geodetic coordinate system, and then generates a rotation matrix from the original geodetic coordinate system to the target coordinate system based on the relationship between the deflection angle and the original geodetic coordinate system and the target coordinate system, thereby ensuring the accuracy of the generated rotation matrix. The relationship between the rotation matrix, the second original position and the first original position information is used to obtain each second target position, thereby ensuring the accuracy of obtaining each second target position.

[0044] According to a second aspect, an embodiment of the present invention provides a collision detection device for a vehicle automatic driving system, the device comprising:

[0045] A first acquisition module is used to acquire a first target position block diagram corresponding to the target vehicle in the target coordinate system;

[0046] A second acquisition module is used to acquire a second target position corresponding to each vertex in the target obstacle in the target coordinate system;

[0047] A detection module, used for detecting whether a line between any two adjacent second target positions intersects with a first target position frame diagram;

[0048] The determination module is used to determine that a collision occurs between the target vehicle and the target obstacle when a line connecting any two adjacent second target positions intersects with a first target position frame diagram.

[0049] The collision detection device for the vehicle automatic driving system provided by the embodiment of the present invention obtains the first target position frame diagram corresponding to the target vehicle in the target coordinate system, thereby ensuring the accuracy of the position information of the target vehicle and the accuracy of the shape and size information of the target vehicle. Then, the second target position corresponding to each vertex in the target obstacle in the target coordinate system is obtained, instead of directly obtaining the contour frame diagram of the target obstacle in the target coordinate system, so that the accuracy of the second target position corresponding to each vertex in the target obstacle obtained can be ensured, and the shape and size of the target obstacle are not simplified, thereby ensuring the accuracy of the shape and size of the target obstacle determined according to the second target position corresponding to each vertex in the target obstacle. Detecting whether the line between any two adjacent second target positions intersects with the first target position frame diagram ensures the accuracy of the detection result. When the line between any two adjacent second target positions intersects with the first target position frame diagram, it is determined that the target vehicle and the target obstacle collide, thereby ensuring the accuracy of the determined collision result between the target vehicle and the target obstacle.

[0050] According to the third aspect, an embodiment of the present invention provides an electronic device, including a memory and a processor, the memory and the processor are communicatively connected to each other, computer instructions are stored in the memory, and the processor executes the collision detection method for a vehicle automatic driving system in the first aspect or any one of the embodiments of the first aspect by executing the computer instructions.

[0051] According to the fourth aspect, an embodiment of the present invention provides a computer-readable storage medium, which stores computer instructions, and the computer instructions are used to enable a computer to execute the collision detection method for a vehicle automatic driving system in the first aspect or any one of the embodiments of the first aspect. BRIEF DESCRIPTION OF THE DRAWINGS

[0052] In order to more clearly illustrate the specific implementation methods of the present invention or the technical solutions in the prior art, the drawings required for use in the specific implementation methods or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some implementation methods of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0053] Figure 1 It is a schematic diagram of simplifying obstacles in the prior art provided by the embodiment of the present invention;

[0054] Figure 2 is a schematic diagram of AABB simplification of obstacles in the prior art provided by another embodiment of the present invention;

[0055] Figure 3 It is a schematic diagram of applying OBB simplification of obstacles in the prior art provided by another embodiment of the present invention;

[0056] Figure 4 is a schematic diagram of applying the separating axis theorem in the prior art provided by another embodiment of the present invention;

[0057] Figure 5 is a flow chart of a collision detection method for a vehicle automatic driving system provided by another embodiment of the present invention;

[0058] Figure 6 is a flow chart of a collision detection method for a vehicle automatic driving system provided by another embodiment of the present invention;

[0059] Figure 7 is a flow chart of a collision detection method for a vehicle automatic driving system provided by another embodiment of the present invention;

[0060] Figure 8 is a schematic diagram of an original geodetic coordinate system and a target coordinate system provided by another embodiment of the present invention;

[0061] Fig. 9 is a flow chart of a collision detection method for a vehicle automatic driving system provided by another embodiment of the present invention;

[0062] Fig.10 is a functional module diagram of a collision detection device for a vehicle automatic driving system provided by an embodiment of the present invention;

[0063] Fig.11 It is a schematic diagram of the hardware structure of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0064] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present invention.

[0065] In the planning part of unmanned vehicles, the trajectory collision detection module is a necessary condition to ensure the safety and effectiveness of the planned trajectory. Trajectory collision detection requires a collision detection of all trajectory points on the planned local trajectory and all detected obstacles, so the detection algorithm must be fast.

[0066] In the autonomous driving system, the environmental perception unit collects data on obstacles in the surrounding environment (such as people, cars, bicycles, etc.) and can output obstacle information with clear boundary contours. The perception module can input the obstacle's outline size, boundary coordinates, speed and other information to the downstream decision-making and planning unit. The decision-making and planning unit detects and determines whether a collision will occur between the vehicle and the obstacle based on the obstacle's outline size, boundary coordinates, speed and other information combined with the trajectory planning information, and generates vehicle motion control information based on the detection results.

[0067] In the prior art, the environment perception unit usually simplifies the outline of the obstacle when processing the collected environment data and outputs a contour frame diagram. However, the shapes of obstacles in real scenes vary, and the simplified contour frame diagram cannot truly reflect the size feature information of the obstacle, which may lead to inaccurate results in detecting whether a collision will occur between the vehicle and the obstacle.

[0068] For example, in the prior art, autonomous driving is a planning problem on a two-dimensional plane. There are three commonly used methods for simplifying obstacles on a two-dimensional plane: Figure 1 As shown, they are a sphere, an AABB, i.e., a bounding box along an axis, and an OBB, i.e., the smallest square that encloses an object. Specifically:

[0069] 1) Sphere

[0070] It is very convenient to use spheres / circles to detect the overlap of two polygons by equating all objects to circumscribed circles / circles: just compare the distance between the center of the circle and the sum of the radius. The advantages and disadvantages of this method are so obvious. The advantage is fast calculation speed, and the disadvantage is low accuracy. This sphere detection method is not widely used in autonomous driving. First, the accuracy of this method is too low, and cars in adjacent lanes will detect collisions. Second, most of the obstacles given by perception are square, and there is no need to convert them into circles.

[0071] 2)Axis Aligned Bounding Box(AABB)

[0072] The name roughly explains what it means: the bounding box along the axis. That is, the object is surrounded by a square box, and the four sides of the square box are parallel to the coordinate axis.

[0073] This method requires less computation to determine whether there is overlap: the maximum and minimum values ​​of the x / y axis of each bounding box are extracted separately, and converted into line segment overlap detection on the one-dimensional axis. If the x-axis or y-axis does not intersect, the two do not overlap.

[0074] Compared with the circle collision detection, this method has much higher accuracy. It is especially suitable for objects (vehicles) with a square shape and a small amount of traffic. There is no time-consuming calculation such as trigonometric functions. However, the collision detection accuracy of AABB is limited. For example, in Figure 2 The following is the case: It is obvious that the bounding box of the AABB is too large compared to the actual size and the accuracy is very limited.

[0075] 3) Oriented Bounding Box (OBB)

[0076] The definition of OBB is very simple, which is to find the smallest square that encloses the object. For example, Figure 3 As shown. The collision detection principle of OBB is the separating axis theorem, as Figure 4 As shown below:

[0077] To determine whether two OBBs overlap, the separating axis theorem can be used. Since the separating axis should be orthogonal to the surfaces of A and B, p, q, s, and t can be selected as the separating axis, and then the OBBs are projected onto these axes. If the projections of the two OBBs on all these axes overlap, the two intersect, otherwise they do not intersect.

[0078] Therefore, in order to know whether two OBBs overlap, we only need to find an axis that makes the projections of A and B not overlap. It can be seen by the naked eye that the q axis is the only axis that can separate the two projections. However, this method still assumes that the obstacle must be rectangular, which is not necessarily applicable to non-vehicle obstacles.

[0079] In actual vehicle trajectory collision detection scenarios, it is reasonable to simplify the vehicle into a rectangle, but the obstacle is not necessarily a rectangle, and the outline frame diagram cannot truly reflect the size information of the obstacle, which may lead to inaccurate results in detecting whether a collision will occur between the vehicle and the obstacle. Therefore, the embodiment of the present application provides a collision detection method for a vehicle automatic driving system, which is used to solve the problem of inaccurate results in detecting whether a collision will occur between a vehicle and an obstacle in the prior art.

[0080] In an implementable scenario of an embodiment of the present application, the collision detection method for a vehicle automatic driving system can be used to detect the feasibility of an initial planned path obtained by path planning. Specifically, the electronic device obtains a first target position block diagram corresponding to any position of the target vehicle in the initial planned path in the target coordinate system, and then obtains a second target position corresponding to each vertex in each target obstacle in the initial planned path in the target coordinate system; detects whether the line between any two adjacent second target positions intersects with the first target position block diagram. When the line between any two adjacent second target positions intersects with the first target position block diagram, it is determined that a collision occurs between the target vehicle and the target obstacle, and the initial planned path is determined to be impassable.

[0081] In an implementable scenario of an embodiment of the present application, the collision detection method for a vehicle automatic driving system can be used to determine whether the target vehicle will collide with a target obstacle during the driving process of the target vehicle of the automatic driving. Specifically, the target vehicle can obtain the first target position frame diagram corresponding to the target vehicle after a preset sampling distance in the target coordinate system according to the current position information of the target vehicle; then, obtain the second target position corresponding to each vertex in the target obstacle corresponding to the preset sampling distance in the target coordinate system. Detect whether the line between any two adjacent second target positions intersects with the first target position frame diagram; when the line between any two adjacent second target positions intersects with the first target position frame diagram, it is determined that a collision occurs between the target vehicle and the target obstacle, thereby determining that the road ahead is impassable.

[0082] It should be noted that the method for collision detection provided in the embodiment of the present application may be executed by a collision detection device, which may be implemented as part or all of an electronic device through software, hardware, or a combination of software and hardware. The electronic device may be a control device in an intelligent driving vehicle, or a terminal device or server device connected to the intelligent driving vehicle but independent of the intelligent driving vehicle. The server in the embodiment of the present application may be a single server or a server cluster composed of multiple servers. The terminal in the embodiment of the present application may be a smart phone, a personal computer, a tablet computer, a wearable device, an intelligent robot, or other intelligent hardware devices. In the following method embodiments, the execution subject is an electronic device as an example for explanation.

[0083] In one embodiment of the present application, Figure 5 As shown, a collision detection method for a vehicle automatic driving system is provided, and the method is applied to an electronic device as an example for explanation, and includes the following steps:

[0084] S11. Obtain a first target position diagram corresponding to the target vehicle in the target coordinate system.

[0085] In an optional embodiment, the electronic device can use the positioning system to obtain the current position information of the target vehicle in the target coordinate system, and then determine the position information corresponding to the target position of the target vehicle in the target coordinate system after a preset sampling distance based on the current position information in the target coordinate system, and obtain the shape and size information of the target vehicle, and then generate a first target position block diagram corresponding to the target vehicle in the target coordinate system based on the position information corresponding to the target position of the target vehicle in the target coordinate system and the shape and size information of the target vehicle.

[0086] In another optional implementation, the electronic device may receive a first target position diagram corresponding to the target position of the target vehicle after a preset sampling distance in a target coordinate system sent by the target vehicle or other electronic device based on continuity with the target vehicle or other electronic device.

[0087] In another optional implementation, the electronic device may obtain an initial planning trajectory corresponding to the target vehicle, and determine a first target position diagram corresponding to the target vehicle in the target position in the target coordinate system from the initial planning trajectory. The target position corresponding to the target vehicle may be any position in the initial trajectory planning.

[0088] The embodiment of the present application does not specifically limit the manner in which the electronic device obtains the first target position block diagram corresponding to the target vehicle in the target coordinate system.

[0089] This step will be described in detail below.

[0090] S12. Obtain a second target position corresponding to each vertex in the target obstacle in the target coordinate system.

[0091] In an optional implementation of the present application, the electronic device can detect the second target position corresponding to each vertex in the target obstacle in the target coordinate system based on the radar device or other device. The electronic device can also receive the second target position corresponding to each vertex in the target obstacle in the target coordinate system sent by other devices.

[0092] In an optional implementation of the present application, the electronic device may obtain an initial planned trajectory corresponding to the target vehicle and obstacle information included in the initial planned trajectory, and determine a second target position corresponding to each vertex in the target obstacle in the target coordinate system according to the obstacle information.

[0093] The embodiment of the present application does not specifically limit the manner in which the electronic device obtains the first target position block diagram corresponding to the target vehicle in the target coordinate system.

[0094] It should be noted that the target coordinate system can be a geodetic coordinate system, a vehicle coordinate system, or other coordinate systems. What is important is that the target vehicle and the target obstacle are in the same target coordinate system.

[0095] This step will be described in detail below.

[0096] S13, detecting whether a line between any two adjacent second target positions intersects with a first target position frame diagram.

[0097] In an optional implementation of the present application, the electronic device can establish a target coordinate system, and obtain the first target position frame diagram corresponding to the target position of the target vehicle and the second target position corresponding to each vertex of the target obstacle in the target coordinate system, and then connect the second target positions corresponding to each vertex of the target obstacle to each other, and generate an arbitrary polygon that can completely surround the target obstacle and completely matches the shape of the target obstacle. The electronic device compares the first target position frame diagram corresponding to the target vehicle in the target coordinate system with the arbitrary polygon corresponding to the target obstacle, and detects whether the line between any two adjacent second target positions intersects with the first target position frame diagram based on the result of comparing the first target position frame diagram corresponding to the target vehicle in the target coordinate system with the arbitrary polygon corresponding to the target obstacle.

[0098] This step will be described in detail below.

[0099] S14. When a line connecting any two adjacent second target positions intersects with a line connecting the first target position frames, it is determined that a collision occurs between the target vehicle and the target obstacle.

[0100] Specifically, if any edge of any polygon corresponding to the target obstacle, that is, a line connecting any two adjacent second target positions, intersects with the first target position frame diagram, it is determined that a collision occurs between the target vehicle and the target obstacle.

[0101] If any edge of any polygon corresponding to the target obstacle, that is, the line between any two adjacent second target positions, does not intersect with the first target position frame diagram, it is determined that no collision occurs between the target vehicle and the target obstacle.

[0102] The collision detection method for a vehicle automatic driving system provided by an embodiment of the present invention obtains a first target position frame diagram corresponding to a target vehicle in a target coordinate system, thereby ensuring the accuracy of the position information of the target vehicle obtained and the accuracy of the shape and size information of the target vehicle. Then, the second target position corresponding to each vertex in the target obstacle in the target coordinate system is obtained, instead of directly obtaining the contour frame diagram of the target obstacle in the target coordinate system, so that the accuracy of the second target position corresponding to each vertex in the target obstacle obtained can be ensured, and the shape and size of the target obstacle are not simplified, thereby ensuring the accuracy of the shape and size of the target obstacle determined according to the second target position corresponding to each vertex in the target obstacle. Detecting whether the line between any two adjacent second target positions intersects with the first target position frame diagram ensures the accuracy of the detection result. When the line between any two adjacent second target positions intersects with the first target position frame diagram, it is determined that a collision occurs between the target vehicle and the target obstacle, thereby ensuring the accuracy of the determined collision result between the target vehicle and the target obstacle.

[0103] In one embodiment of the present application, Figure 6 As shown, a collision detection method for a vehicle automatic driving system is provided, and the method is applied to an electronic device as an example for explanation, and includes the following steps:

[0104] S21. Obtain a first target position diagram corresponding to the target vehicle in the target coordinate system.

[0105] For more information about this step, see Figure 5 The introduction of S11 will not be elaborated here.

[0106] S22. Obtain a second target position corresponding to each vertex in the target obstacle in the target coordinate system.

[0107] For more information about this step, see Figure 5 The introduction of S12 will not be elaborated here.

[0108] S23, detecting whether a line between any two adjacent second target positions intersects with a first target position frame diagram.

[0109] In an optional implementation manner of the present application, the above S23 "detecting whether a line between any two adjacent second target positions intersects with the first target position frame diagram" may include the following steps:

[0110] S231, obtaining a first horizontal coordinate range corresponding to the first target position frame diagram.

[0111] Specifically, the electronic device may determine the first horizontal coordinate range corresponding to the first target position frame diagram according to the position information of the first target position frame diagram in the target coordinate system.

[0112] Exemplarily, assuming that the first target position frame diagram is composed of four lines: x=x_max; x=x_min; y=y_max; y=y_min, therefore, the first horizontal coordinate range corresponding to the first target position frame diagram is [x_min, x_max].

[0113] S232. Connect any two adjacent second target positions to generate a target line segment, and determine a second horizontal coordinate range corresponding to the target line segment.

[0114] Specifically, the electronic device connects any two adjacent second target positions to generate a target line segment. Then, the electronic device solves the function for the target line segment according to the position information corresponding to any two adjacent second target positions to determine the functional relationship corresponding to the target line segment. The functional relationship may be a linear functional relationship, a quadratic functional relationship, or other functional relationships, and the embodiment of the present application does not specifically limit the functional relationship.

[0115] Then, the electronic device determines a second horizontal coordinate range corresponding to the target line segment according to the functional relationship corresponding to the target line segment.

[0116] Exemplarily, assuming that the functional relationship is the first functional relationship, the electronic device can use y=ax+b to represent the functional relationship, and then bring any two adjacent second target positions into the function, and then calculate the value of a and the value of b, so as to obtain the functional relationship corresponding to the target line segment. Then, the electronic device determines that the second horizontal coordinate range corresponding to the target line segment is [x1, x2] according to the determined functional relationship corresponding to the target line segment.

[0117] It should be noted that the above target line segment refers to the connection between any two adjacent second target positions.

[0118] S233: When the first horizontal coordinate range and the second horizontal coordinate range have no intersection, determine that the target line segment does not intersect with the first target position frame.

[0119] Specifically, after the electronic device determines the first horizontal coordinate range and the second horizontal coordinate range, the electronic device can compare the first horizontal coordinate range with the second horizontal coordinate range. When the first horizontal coordinate range and the second horizontal coordinate range have no intersection, it is determined that the target line segment does not intersect with the first target position frame diagram, that is, the line between any two adjacent second target positions does not intersect with the first target position frame diagram.

[0120] S234. When the first horizontal coordinate range and the second horizontal coordinate range have an intersection, determine a third horizontal coordinate range where the first horizontal coordinate range and the second horizontal coordinate range intersect.

[0121] Specifically, when the first horizontal coordinate range and the second horizontal coordinate range have an intersection, a third horizontal coordinate range where the first horizontal coordinate range and the second horizontal coordinate range intersect is determined.

[0122] Exemplarily, when [x_min, x_max] intersects with [x1, x2], a third horizontal coordinate range where the first horizontal coordinate range intersects with the second horizontal coordinate range is recorded as [x_low, x_high].

[0123] S235 , determining a first ordinate range corresponding to the first target position frame diagram corresponding to the third abscissa range.

[0124] Specifically, the electronic device may determine the first ordinate range corresponding to the first target position frame diagram corresponding to the third abscissa range according to the position information of the first target position frame diagram in the target coordinate system.

[0125] Exemplarily, assuming that the first target position frame diagram is composed of four lines: x=x_max; x=x_min; y=y_max; y=y_min, therefore, the vertical coordinate range corresponding to the first target position frame diagram is [y_min, y_max]. Then, according to the third horizontal coordinate range [x_low, x_high], determine the first vertical coordinate range corresponding to the first target position frame diagram corresponding to the third horizontal coordinate range.

[0126] S236. Determine a second ordinate range corresponding to the target line segment corresponding to the third abscissa range.

[0127] Specifically, the electronic device can determine the functional relationship corresponding to the target line segment. After determining the functional relationship corresponding to the target line segment, the electronic device can bring the minimum value and the maximum value in the third horizontal coordinate range into the functional relationship, determine the intersecting minimum vertical coordinate and the maximum vertical coordinate, and determine the second vertical coordinate range corresponding to the target line segment corresponding to the third horizontal coordinate range based on the minimum vertical coordinate and the maximum vertical coordinate.

[0128] Exemplarily, assuming that the functional relationship between any two adjacent second target positions is y=ax+b, the electronic device calculates the value of y at x_low and x_high, respectively, which are recorded as y_low and y_high, respectively.

[0129] S237. When the first ordinate range and the second ordinate range intersect, determine that the target line segment intersects with the first target position frame.

[0130] Specifically, after obtaining the first vertical coordinate range and the second vertical coordinate range, the electronic device can compare the first vertical coordinate range with the second vertical coordinate range. When the first vertical coordinate range and the second vertical coordinate range have an intersection, it determines that the target line segment intersects with the first target position frame diagram, that is, it determines that the line between any two adjacent second target positions intersects with the first target position frame diagram.

[0131] S238. When there is no intersection between the first ordinate range and the second ordinate range, determine that the target line segment does not intersect with the first target position frame.

[0132] Specifically, when the first ordinate range does not have an intersection with the second ordinate range, it is determined that the target line segment does not intersect with the first target position frame diagram, that is, it is determined that the line between any two adjacent second target positions does not intersect with the first target position frame diagram.

[0133] S24. When a line connecting any two adjacent second target positions intersects with a line connecting the first target position frames, it is determined that a collision occurs between the target vehicle and the target obstacle.

[0134] For more information about this step, see Figure 5 The introduction of S14 will not be elaborated here.

[0135] The collision detection method for a vehicle automatic driving system provided by an embodiment of the present invention obtains a first horizontal coordinate range corresponding to a first target position frame diagram. Any two adjacent second target positions are connected to generate a target line segment, thereby ensuring that the generated target line segment can accurately characterize the contour corresponding to the target obstacle. Then, the second horizontal coordinate range corresponding to the target line segment is determined, thereby ensuring the accuracy of the second horizontal coordinate range corresponding to the determined target line segment. When the first horizontal coordinate range and the second horizontal coordinate range have no intersection, it is determined that the target line segment does not intersect with the first target position frame diagram, thereby ensuring the accuracy of the result of determining that the target line segment does not intersect with the first target position frame diagram.

[0136] When the first horizontal coordinate range and the second horizontal coordinate range have an intersection, the third horizontal coordinate range where the first horizontal coordinate range and the second horizontal coordinate range intersect is determined, so as to ensure the accuracy of the determined third horizontal coordinate range. Then, the first ordinate range corresponding to the first target position frame diagram corresponding to the third horizontal coordinate range is determined, so as to ensure the accuracy of the determined first ordinate range. Then, the second ordinate range corresponding to the target line segment corresponding to the third horizontal coordinate range is determined, and when the first ordinate range and the second ordinate range have an intersection, it is determined that the target line segment and the first target position frame diagram intersect, so as to determine that the target vehicle and the target obstacle collide, so as to ensure the accuracy of the result of the determined target vehicle and the target obstacle collide. When the first ordinate range and the second ordinate range do not have an intersection, it is determined that the target line segment and the first target position frame diagram do not intersect, so as to determine that the target vehicle and the target obstacle do not collide, so as to ensure the accuracy of the result of the determined target vehicle and the target obstacle do not collide. The above method can not only accurately detect whether the target vehicle and the target obstacle collide, but also is simple and convenient, has a small amount of calculation, and occupies less computing resources.

[0137] In one embodiment of the present application, Figure 7 As shown, a collision detection method for a vehicle automatic driving system is provided, and the method is applied to an electronic device as an example for explanation, and includes the following steps:

[0138] S31. Obtain a first target position diagram corresponding to the target vehicle in the target coordinate system.

[0139] In an optional implementation manner of the present application, the above S31 "obtaining a first target position block diagram corresponding to the target vehicle in the target coordinate system" may include the following steps:

[0140] S311. Acquire the positioning point of the target vehicle, establish a target coordinate system with the positioning point as the origin of the target coordinate system, the target vehicle driving direction as the longitudinal axis, and the axis perpendicular to the target vehicle driving direction as the transverse axis.

[0141] In an optional implementation of the present application, the electronic device can locate the target vehicle through a positioning system, and then determine the position information of the target vehicle at the target position based on the positioning information after locating the target vehicle. Then, determine the positioning point of the target vehicle. After determining the positioning point of the target vehicle, the electronic device can establish a target coordinate system with the positioning point of the target vehicle as the origin of the target coordinate system, the target vehicle driving direction as the longitudinal axis, and the horizontal axis perpendicular to the target vehicle driving direction as the transverse axis.

[0142] The positioning point may be a mass point of the target vehicle or a center point of the rear axle of the target vehicle.

[0143] S312: Obtain the real position of each edge of the target vehicle in the target coordinate system.

[0144] Specifically, after establishing a target coordinate system with the positioning point of the target vehicle as the origin, the electronic device can determine the real position of each edge in the target vehicle in the target coordinate system.

[0145] S313: Generate a first target position frame diagram according to the actual positions corresponding to the edges.

[0146] In an optional implementation of the present application, after the electronic device determines the real positions of each edge in the target vehicle in the target coordinate system, the electronic device may connect the real positions corresponding to each edge to generate a first target position block diagram of the target vehicle in the target coordinate system.

[0147] In an optional implementation manner of the present application, the above S313 “generating a first target position block diagram according to the real positions corresponding to the edges” may include the following steps:

[0148] (1) Obtain the safety distance corresponding to the target vehicle.

[0149] (2) According to the actual position corresponding to each edge, each edge is moved outward by a safe distance to generate the target position corresponding to each edge in the target vehicle;

[0150] (3) Connect the target positions corresponding to the edges to generate a first target position block diagram.

[0151] Specifically, after determining the real position of each edge of the target vehicle in the target coordinate system, in order to ensure the safe driving of the target vehicle, the electronic device can also obtain the safety distance corresponding to the target vehicle. Optionally, the electronic device can receive the safety distance corresponding to the target vehicle input by the user, or can receive the safety distance corresponding to the target vehicle sent by other devices. The embodiment of the present application does not specifically limit the way in which the electronic device obtains the safety distance corresponding to the target vehicle.

[0152] After obtaining the safety distance corresponding to the target vehicle, the electronic device can move each edge outward by the safety distance according to the real position corresponding to each edge, and generate the target position corresponding to each edge in the target vehicle.

[0153] Exemplarily, it is assumed that the real positions of the left and right edges of the target vehicle are respectively at the positions of 1 meter and -1 meter on the horizontal coordinates in the target coordinate system, and the real positions of the front and rear edges of the target vehicle are respectively at the positions of 2 meters and -2 meters on the vertical coordinates. Assuming that the safety distance corresponding to the target vehicle is 1 meter, the electronic device moves the real positions corresponding to each edge outward by a safety distance of 1 meter, that is to say, the target positions of the left and right edges of the target vehicle are respectively at the positions of 2 meters and -2 meters on the horizontal coordinates, and the target positions of the front and rear edges of the target vehicle are respectively at the positions of 3 meters and -3 meters on the vertical coordinates. The target positions corresponding to each edge are connected, and a first target position block diagram corresponding to the target vehicle with a center at the origin, a length of 6 meters, and a width of 4 meters is generated in the target coordinate system.

[0154] Therefore, the first target position diagram can be represented by the four lines below, which are x=-2; x=2; y=-3; y=3.

[0155] S32: Obtain a second target position corresponding to each vertex in the target obstacle in the target coordinate system.

[0156] For more information about this step, see Figure 6 The introduction of S22 will not be elaborated here.

[0157] S33, detecting whether a line between any two adjacent second target positions intersects with a first target position frame diagram.

[0158] For more information about this step, see Figure 6 The introduction of S23 will not be elaborated here.

[0159] S34. When a line connecting any two adjacent second target positions intersects with a line connecting the first target position frames, it is determined that a collision occurs between the target vehicle and the target obstacle.

[0160] For more information about this step, see Figure 6 The introduction of S24 will not be elaborated here.

[0161] The collision detection method for a vehicle automatic driving system provided by an embodiment of the present invention obtains the positioning point of the target vehicle, then takes the positioning point as the origin of the target coordinate system, takes the target vehicle driving direction as the longitudinal axis, and takes the target vehicle driving direction as the transverse axis, and establishes the target coordinate system, ensuring that the established target coordinate system can be suitable for the driving of the target vehicle, thereby ensuring the accuracy of the established target coordinate system. Then, the real position of each edge in the target vehicle in the target coordinate system is obtained, ensuring the accuracy of the real position of each edge in the target vehicle in the target coordinate system. The safety distance corresponding to the target vehicle is obtained, ensuring the accuracy of the safety distance corresponding to the target vehicle. According to the real position corresponding to each edge, each edge is moved outward by a safety distance to generate the target position corresponding to each edge in the target vehicle, which not only ensures that the generated target position matches the position, size and shape of the target vehicle, but also ensures the safe driving of the target vehicle. Then, the target positions corresponding to each edge are connected to generate a first target position block diagram, ensuring that the generated first target position block diagram matches the position, size and shape of the target vehicle, and can ensure the safe driving of the target vehicle, thereby making the result of determining whether a collision occurs between the target vehicle and the target obstacle more accurate.

[0162] In one embodiment of the present application, Figure 8 As shown, a collision detection method for a vehicle automatic driving system is provided, and the method is applied to an electronic device as an example for explanation, and includes the following steps:

[0163] S41. Obtain a first target position diagram corresponding to the target vehicle in the target coordinate system.

[0164] For more information about this step, see Figure 7 The introduction of S31 will not be elaborated here.

[0165] S42: Obtain a second target position corresponding to each vertex in the target obstacle in the target coordinate system.

[0166] In an optional implementation manner of the present application, the above S42 “obtaining the second target position corresponding to each vertex in the target obstacle in the target coordinate system” may include the following steps:

[0167] S421. Obtain first original position information of the positioning point of the target vehicle in the original geodetic coordinate system.

[0168] Specifically, the electronic device can use the positioning system to obtain the current position information of the target vehicle in the original geodetic coordinate system, and determine the first original position information of the positioning point of the target vehicle in the original geodetic coordinate system based on the position information of the target vehicle in the original geodetic coordinate system.

[0169] In another optional implementation, the electronic device may receive the first original position information of the positioning point of the target vehicle at the current moment in the original geodetic coordinate system sent by the target vehicle or other electronic device based on the continuity with the target vehicle or other electronic device.

[0170] In another optional implementation, the electronic device may obtain an initial planning trajectory corresponding to the target vehicle, and determine the first original position information of the positioning point of the target vehicle in the original geodetic coordinate system from the initial planning trajectory.

[0171] The embodiment of the present application does not specifically limit the manner in which the electronic device obtains the first original position information of the positioning point of the target vehicle in the original geodetic coordinate system.

[0172] In an optional implementation of the present application, the original geodetic coordinate system may be the geodetic coordinate system corresponding to the target vehicle at the current position at the current moment.

[0173] In an optional implementation of the present application, the original geodetic coordinate system may be a geodetic coordinate system corresponding to a preset time before the target vehicle performs collision detection.

[0174] S422: Obtain the second original position of each vertex in the target obstacle in the original earth coordinate system.

[0175] Specifically, the electronic device detects the second original position corresponding to each vertex in the target obstacle in the original geodetic coordinate system based on the radar device or other devices.

[0176] S423. According to the relationship between the first original position information and the second original position, convert the second original position corresponding to each vertex into a second target position corresponding to each vertex.

[0177] In an optional embodiment of the present application, the electronic device can obtain the first original position information of the positioning point of the target vehicle in the original geodetic coordinate system and the first target position information of the positioning point of the target vehicle in the target coordinate system, and then determine the relationship between the first original position information and the first target position information, and determine the relationship between the first original position information and the second original position based on the relationship between the first original position information and the first target position information, and then convert the second original position corresponding to each vertex into the second target position corresponding to each vertex based on the relationship between the first original position information and the second original position.

[0178] In an optional implementation of the present application, S423 “converting the second original position corresponding to each vertex into a second target position corresponding to each vertex according to the relationship between the first original position information and the second original position” may include the following steps:

[0179] (1) Obtain the deflection angle of the target vehicle's positioning point relative to the original geodetic coordinate system;

[0180] (2) Generate a rotation matrix from the original geodetic coordinate system to the target coordinate system based on the relationship between the deflection angle and the original geodetic coordinate system and the target coordinate system;

[0181] (3) Using the relationship between the rotation matrix, the second original position and the first original position information, each second target position is obtained.

[0182] In an optional implementation, after obtaining the first original position information of the positioning point of the target vehicle in the original geodetic coordinate system, the electronic device can obtain the heading angle corresponding to the target vehicle. Then, according to the heading angle corresponding to the target vehicle, the deflection angle of the positioning point of the target vehicle relative to the original geodetic coordinate system is determined.

[0183] In another optional implementation, the electronic device may also receive a deflection angle of a positioning point of a target vehicle relative to an original geodetic coordinate system input by the target vehicle or other devices.

[0184] After obtaining the deflection angle of the positioning point of the target vehicle relative to the original geodetic coordinate system, the electronic device may generate a rotation matrix from the original geodetic coordinate system to the target coordinate system according to the relationship between the deflection angle, the original geodetic coordinate system and the target coordinate system;

[0185] For example, the rotation matrix from the original earth coordinate system to the target coordinate system can be expressed as:

[0186]

[0187] Among them, θ is the deviation angle of the target vehicle's positioning point relative to the original geodetic coordinate system.

[0188] After generating a rotation matrix from the original earth coordinate system to the target coordinate system, the electronic device obtains each second target position by using the relationship between the rotation matrix, the second original position and the first original position information.

[0189] Specifically, the electronic device may use the rotation matrix to multiply the difference between each second original position and the first original position information to obtain each second target position.

[0190] For example, Fig. 9 As shown, the XY coordinate system is the original geodetic coordinate system, the X1Y1 coordinate system is the target coordinate system, and O1 is the origin in the target coordinate system. The coordinate of the target vehicle O1 point in the XY coordinate system (i.e., the first original position information of the positioning point of the target vehicle in the original geodetic coordinate system) is P o1 =(x o1 ,y o1,0), the second original position corresponding to any vertex on the target obstacle is recorded as P vertex =(x,y,0), then the second target position P of the vertex in the target coordinates vertex_ It can be obtained by the following formula:

[0191] P vertex_ =R*(P vertex -P o1 )

[0192] Where R is the rotation matrix.

[0193] S43: Detect whether a line between any two adjacent second target positions intersects with a first target position frame diagram.

[0194] For more information about this step, see Figure 7 The introduction of S33 will not be elaborated in detail here.

[0195] S44: When a line connecting any two adjacent second target positions intersects with a line connecting the first target position frames, it is determined that a collision occurs between the target vehicle and the target obstacle.

[0196] For more information about this step, see Figure 7 The introduction of S34 will not be elaborated in detail here.

[0197] The collision detection method for a vehicle automatic driving system provided by an embodiment of the present invention obtains the first original position information of the positioning point of the target vehicle in the original geodetic coordinate system, and then obtains the second original position of each vertex in the target obstacle in the original geodetic coordinate system. The deflection angle of the positioning point of the target vehicle relative to the original geodetic coordinate system is obtained, and then, based on the relationship between the deflection angle and the original geodetic coordinate system and the target coordinate system, a rotation matrix from the original geodetic coordinate system to the target coordinate system is generated, thereby ensuring the accuracy of the generated rotation matrix. The rotation matrix is ​​multiplied by the difference between each second original position and the first original position information to obtain each second target position, thereby ensuring the accuracy of each second target position.

[0198] It should be understood that although Figure 5-8 The steps in the flowchart are shown in sequence as indicated by the arrows, but these steps are not necessarily executed in the order indicated by the arrows. Unless otherwise specified in this document, there is no strict order restriction for the execution of these steps, and these steps can be executed in other orders. Moreover, Figure 5-8At least part of the steps may include multiple steps or multiple stages. These steps or stages are not necessarily performed at the same time, but can be performed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed in turn or alternately with other steps or at least part of the steps or stages in other steps.

[0199] like Fig.10 As shown, this embodiment provides a collision detection device for a vehicle automatic driving system, comprising:

[0200] A first acquisition module 51 is used to acquire a first target position diagram corresponding to the target vehicle in the target coordinate system;

[0201] A second acquisition module 52 is used to acquire a second target position corresponding to each vertex in the target obstacle in the target coordinate system;

[0202] A detection module 53, used for detecting whether a line between any two adjacent second target positions intersects with a first target position frame diagram;

[0203] The determination module 54 is used to determine that a collision occurs between the target vehicle and the target obstacle when a line connecting any two adjacent second target positions intersects with a line connecting the first target positions.

[0204] In one embodiment of the present application, the above-mentioned detection module 53 is specifically used to obtain a first horizontal coordinate range corresponding to the first target position frame diagram; connect any two adjacent second target positions to generate a target line segment, and determine the second horizontal coordinate range corresponding to the target line segment; when the first horizontal coordinate range and the second horizontal coordinate range have no intersection, determine that the target line segment does not intersect with the first target position frame diagram.

[0205] In one embodiment of the present application, the above-mentioned detection module 53 is specifically used to determine a third horizontal coordinate range where the first horizontal coordinate range intersects with the second horizontal coordinate range when the first horizontal coordinate range and the second horizontal coordinate range have an intersection; determine a first vertical coordinate range corresponding to the first target position frame diagram corresponding to the third horizontal coordinate range; determine a second vertical coordinate range corresponding to the target line segment corresponding to the third horizontal coordinate range; when the first vertical coordinate range and the second vertical coordinate range have an intersection, determine that the target line segment intersects with the first target position frame diagram; when the first vertical coordinate range and the second vertical coordinate range do not have an intersection, determine that the target line segment does not intersect with the first target position frame diagram.

[0206] In one embodiment of the present application, the above-mentioned first acquisition module 51 is specifically used to obtain the positioning point of the target vehicle, establish a target coordinate system with the positioning point as the origin of the target coordinate system, the driving direction of the target vehicle as the longitudinal axis, and the axis perpendicular to the driving direction of the target vehicle as the horizontal axis; obtain the real position of each edge in the target vehicle in the target coordinate system; and generate a first target position block diagram based on the real position corresponding to each edge.

[0207] In one embodiment of the present application, the above-mentioned first acquisition module 51 is specifically used to obtain the safety distance corresponding to the target vehicle; according to the actual position corresponding to each edge, each edge is moved outward by a safety distance to generate the target position corresponding to each edge in the target vehicle; the target positions corresponding to each edge are connected to generate a first target position block diagram.

[0208] In one embodiment of the present application, the above-mentioned second acquisition module 52 is specifically used to obtain the first original position information of the positioning point of the target vehicle in the original geodetic coordinate system; obtain the second original position of each vertex in the target obstacle in the original geodetic coordinate system; and according to the relationship between the first original position information and the second original position, convert the second original position corresponding to each vertex into the second target position corresponding to each vertex.

[0209] In one embodiment of the present application, the above-mentioned second acquisition module 52 is specifically used to obtain the deviation angle of the positioning point of the target vehicle relative to the original geodetic coordinate system; based on the relationship between the deviation angle and the original geodetic coordinate system and the target coordinate system, generate a rotation matrix from the original geodetic coordinate system to the target coordinate system; and use the relationship between the rotation matrix, the second original position and the first original position information to obtain each second target position.

[0210] For the specific limitations and beneficial effects of the collision detection device for the vehicle automatic driving system, please refer to the limitations of the collision detection method for the vehicle automatic driving system above, which will not be repeated here. The various modules in the above-mentioned collision detection device for the vehicle automatic driving system can be implemented in whole or in part by software, hardware and a combination thereof. The above-mentioned modules can be embedded in or independent of the processor in the electronic device in the form of hardware, or can be stored in the memory of the electronic device in the form of software, so that the processor can call and execute the operations corresponding to the above modules.

[0211] The embodiment of the present invention further provides an electronic device, which may be an instantiation of an electronic device. A vehicle automatic driving controller, a vehicle computing platform, or a cloud server connected to a vehicle in communication. Fig.10 A collision detection device for a vehicle autonomous driving system is shown.

[0212] like Fig.11 As shown, Fig.11is a schematic diagram of the structure of an electronic device provided by an optional embodiment of the present invention, such as Fig.11 As shown, the electronic device may include: at least one processor 61, such as a CPU (Central Processing Unit), at least one communication interface 63, a memory 64, and at least one communication bus 62. The communication bus 62 is used to realize the connection and communication between these components. The communication interface 63 may include a display screen (Display), a keyboard (Keyboard), and the optional communication interface 63 may also include a standard wired interface and a wireless interface. The memory 64 may be a high-speed RAM memory (Random Access Memory) or a non-volatile memory (non-volatile memory), such as at least one disk storage. The memory 64 may optionally be at least one storage device located away from the aforementioned processor 61. The processor 61 may be combined with Fig.10 In the described device, the memory 64 stores an application program, and the processor 61 calls the program code stored in the memory 64 to execute any of the above method steps.

[0213] The communication bus 62 may be a peripheral component interconnect (PCI) bus or an extended industry standard architecture (EISA) bus. The communication bus 62 may be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Fig.11 Only one thick line is used in the diagram, but this does not mean that there is only one bus or only one type of bus.

[0214] Among them, the memory 64 may include a volatile memory (English: volatile memory), such as a random access memory (English: random-access memory, abbreviated: RAM); the memory may also include a non-volatile memory (English: non-volatile memory), such as a flash memory (English: flash memory), a hard disk drive (English: hard disk drive, abbreviated: HDD) or a solid-state drive (English: solid-state drive, abbreviated: SSD); the memory 64 may also include a combination of the above types of memory.

[0215] The processor 61 may be a central processing unit (CPU), a network processor (NP), or a combination of a CPU and a NP.

[0216] The processor 61 may further include a hardware chip. The hardware chip may be an application-specific integrated circuit (ASIC), a programmable logic device (PLD), or a combination thereof. The PLD may be a complex programmable logic device (CPLD), a field-programmable gate array (FPGA), a generic array logic (GAL), or any combination thereof.

[0217] Optionally, the memory 64 is also used to store program instructions. The processor 61 can call the program instructions to implement the present application Figure 5-8 The collision detection method for a vehicle autonomous driving system shown in the embodiment.

[0218] The embodiment of the present invention also provides a non-transitory computer storage medium, which stores computer executable instructions, and the computer executable instructions can execute the collision detection method for the vehicle automatic driving system in any of the above method embodiments. Among them, the storage medium can be a disk, an optical disk, a read-only memory (ROM), a random access memory (RAM), a flash memory, a hard disk (HDD) or a solid-state drive (SSD), etc.; the storage medium can also include a combination of the above types of memory.

[0219] Although the embodiments of the present invention have been described in conjunction with the accompanying drawings, those skilled in the art may make various modifications and variations without departing from the spirit and scope of the present invention, and such modifications and variations are all within the scope defined by the appended claims.

Claims

1. A collision detection method for a vehicle automatic driving system, characterized in that: The method comprises: Obtain a first target position block diagram corresponding to the target vehicle in the target coordinate system; Obtaining a second target position corresponding to each vertex in the target obstacle in the target coordinate system; Detect whether a line between any two adjacent second target positions intersects with a frame diagram of the first target position; When a line connecting any two adjacent second target positions intersects with a frame diagram of the first target position, it is determined that a collision occurs between the target vehicle and the target obstacle; Wherein, the step of obtaining a first target position diagram corresponding to the target vehicle in the target coordinate system includes: Acquire the positioning point of the target vehicle, take the positioning point as the origin of the target coordinate system, take the driving direction of the target vehicle as the longitudinal axis, and take the axis perpendicular to the driving direction of the target vehicle as the transverse axis, and establish the target coordinate system; Obtaining the real position of each edge of the target vehicle in the target coordinate system; Generate the first target position frame diagram according to the real positions corresponding to the respective edges; The step of generating the first target position diagram according to the real positions corresponding to the edges includes: Obtaining a safety distance corresponding to the target vehicle; According to the real position corresponding to each of the edges, each of the edges is moved outward by the safety distance to generate a target position corresponding to each of the edges in the target vehicle; Connecting the target positions corresponding to the edges to generate the first target position block diagram; Wherein, obtaining the second target position corresponding to each vertex in the target obstacle in the target coordinate system includes: Acquire first original position information of the positioning point of the target vehicle in an original geodetic coordinate system; Acquire the second original position of each vertex in the target obstacle in the original earth coordinate system; According to the relationship between the first original position information and the second original position, converting the second original position corresponding to each vertex into the second target position corresponding to each vertex; The converting the second original position corresponding to each vertex into the second target position corresponding to each vertex according to the relationship between the first original position information and the second original position includes: Obtaining a deflection angle of the positioning point of the target vehicle relative to the original geodetic coordinate system; Generate a rotation matrix from the original geodetic coordinate system to the target coordinate system according to the relationship between the deflection angle and the original geodetic coordinate system and the target coordinate system; The second target positions are obtained by using the relationship between the rotation matrix, the second original position and the first original position information.

2. The method according to claim 1, characterized in that The detecting whether a line between any two adjacent second target positions intersects with a frame diagram of the first target position includes: Acquire a first horizontal coordinate range corresponding to the first target position frame diagram; Connect any two adjacent second target positions to generate a target line segment, and determine a second horizontal coordinate range corresponding to the target line segment; When the first horizontal coordinate range has no intersection with the second horizontal coordinate range, it is determined that the target line segment does not intersect with the first target position frame.

3. The method according to claim 2, characterized in that The method further comprises: When the first horizontal coordinate range and the second horizontal coordinate range have an intersection, determining a third horizontal coordinate range where the first horizontal coordinate range and the second horizontal coordinate range intersect; Determine a first ordinate range corresponding to the first target position frame diagram corresponding to the third abscissa range; Determine a second ordinate range corresponding to the target line segment corresponding to the third abscissa range; When the first ordinate range and the second ordinate range have an intersection, determining that the target line segment intersects with the first target position frame diagram; When there is no intersection between the first ordinate range and the second ordinate range, it is determined that the target line segment does not intersect with the first target position frame.

4. A collision detection device for a vehicle automatic driving system, characterized in that: The device comprises: The first acquisition module is used to acquire a first target position frame diagram corresponding to the target vehicle in the target coordinate system; wherein, the acquisition of the first target position frame diagram corresponding to the target vehicle in the target coordinate system includes: acquiring the positioning point of the target vehicle, taking the positioning point as the origin of the target coordinate system, the driving direction of the target vehicle as the longitudinal axis, and the horizontal axis perpendicular to the driving direction of the target vehicle to establish the target coordinate system; acquiring the real position of each edge in the target vehicle in the target coordinate system; generating the first target position frame diagram according to the real position corresponding to each edge; wherein, generating the first target position frame diagram according to the real position corresponding to each edge includes: acquiring the safety distance corresponding to the target vehicle; according to the real position corresponding to each edge, moving each edge outward by the safety distance to generate the target position corresponding to each edge in the target vehicle; connecting the target positions corresponding to each edge to generate the first target position frame diagram; A second acquisition module is used to acquire the second target position corresponding to each vertex in the target obstacle in the target coordinate system; wherein, the acquiring the second target position corresponding to each vertex in the target obstacle in the target coordinate system includes: acquiring the first original position information of the positioning point of the target vehicle in the original geodetic coordinate system; acquiring the second original position of each vertex in the target obstacle in the original geodetic coordinate system; according to the relationship between the first original position information and the second original position, converting the second original position corresponding to each vertex into the second target position corresponding to each vertex; wherein, according to the relationship between the first original position information and the second original position, converting the second original position corresponding to each vertex into the second target position corresponding to each vertex includes: acquiring the deflection angle of the positioning point of the target vehicle relative to the original geodetic coordinate system; generating a rotation matrix from the original geodetic coordinate system to the target coordinate system according to the relationship between the deflection angle and the original geodetic coordinate system and the target coordinate system; and obtaining each second target position by using the relationship between the rotation matrix, the second original position and the first original position information; A detection module, used for detecting whether a line between any two adjacent second target positions intersects with a frame diagram of the first target position; The determination module is used to determine that a collision occurs between the target vehicle and the target obstacle when a line connecting any two adjacent second target positions intersects with a frame diagram of the first target position.

5. An electronic device, characterized in that: It comprises a memory and a processor, wherein the memory stores computer instructions, and the processor executes the collision detection method for a vehicle automatic driving system as described in any one of claims 1 to 3 by executing the computer instructions.

6. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a computer to execute the collision detection method for a vehicle automatic driving system according to any one of claims 1 to 3.

Images