Collision detection method and detection device

Abstract

The invention relates to the technical field of automatic driving, and provides a collision detection method and device. According to the method, vehicle configuration information including at least one of the whole vehicle length, the whole vehicle width and axle information and position information of a vehicle in a target coordinate system are obtained, a first vehicle model is constructed in a preset coordinate system according to the vehicle configuration information, the vehicle position information and a preset expansion coefficient, and meanwhile obstacle information is obtained; the obstacle model is constructed in the target coordinate system based on the obstacle information, and when it is determined that the obstacle model is outside the first vehicle model or the obstacle model does not intersect with the first vehicle model, it is determined that the collision detection result is detection passing.

Description

Technical Field

[0001] The present application relates to the field of autonomous driving technology, and in particular to a collision detection method and detection device. Background Art

[0002] Automatic parking assist (APA) technology is widely used in assisted driving systems and advanced assisted driving systems. In related technologies, either vehicle sensors are used to obtain signals of whether the vehicle has collided, or the predicted trajectory of the obstacle needs to be obtained and the predicted trajectory is converted from the Frenet coordinate system to the Cartesian coordinate system before collision detection.

[0003] The former cannot make predictions before a collision, and the latter requires coordinate system conversion, which has high requirements on computing power and cannot be applied to platforms with lower computing power. Summary of the invention

[0004] In view of this, an embodiment of the present application provides a collision detection method and a detection device to solve the problem of how to improve the detection accuracy when performing collision detection on a platform with low computing power in the prior art.

[0005] According to a first aspect of an embodiment of the present application, a collision detection method is provided, the method being used to provide a collision detection result for a vehicle performing an automatic parking operation, comprising:

[0006] Acquiring vehicle configuration information, where the vehicle configuration information includes at least one of vehicle length, vehicle width, and axle information;

[0007] Acquire position information of the vehicle in the target coordinate system, and construct a first vehicle model in the preset coordinate system according to the vehicle configuration information, the vehicle position information and the preset expansion coefficient;

[0008] Obtain obstacle position information, and determine an obstacle model in the target coordinate system based on the obstacle position information, where the obstacle model is an obstacle point or an obstacle vector;

[0009] In response to determining that the obstacle point is outside the first vehicle model, or the obstacle vector does not intersect the first vehicle model, the collision detection result is determined to be detection passed.

[0010] A second aspect of an embodiment of the present application provides a collision detection device, including:

[0011] An acquisition module is configured to acquire vehicle configuration information, where the vehicle configuration information includes at least one of vehicle length, vehicle width, and axle information;

[0012] A vehicle model determination module is configured to obtain position information of the vehicle in a target coordinate system, and construct a first vehicle model in a preset coordinate system according to the vehicle configuration information, the vehicle position information and a preset expansion coefficient;

[0013] An obstacle model determination module is configured to obtain obstacle position information and determine an obstacle model in a target coordinate system based on the obstacle position information, where the obstacle model is an obstacle point or an obstacle vector;

[0014] The detection module is configured to determine that the collision detection result is a detection pass in response to determining that the obstacle point is outside the first vehicle model or the obstacle vector does not intersect the first vehicle model.

[0015] The beneficial effect of the embodiments of the present application compared with the prior art is as follows: the embodiments of the present application obtain vehicle configuration information including at least one of the vehicle length, vehicle width and axle information, and the position information of the vehicle in the target coordinate system, and construct a first vehicle model in the preset coordinate system according to the vehicle configuration information, the vehicle position information and the preset expansion coefficient, and simultaneously obtain obstacle information, and construct the obstacle model in the target coordinate system based on the obstacle information, and when it is determined that the obstacle model is outside the first vehicle model, or the obstacle model does not intersect with the first vehicle model, determine that the collision detection result is a detection pass. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0017] Figure 1 It is a flowchart of a collision detection method provided in an embodiment of the present application.

[0018] Figure 2 This is a schematic diagram of the automatic parking process.

[0019] Figure 3 It is a flowchart of another collision detection method provided in an embodiment of the present application.

[0020] Figure 4 It is a flowchart of another collision detection method provided in an embodiment of the present application.

[0021] Figure 5 It is a schematic diagram of dividing the first vehicle model and the second vehicle model represented by quadrilateral simulation into a nine-square grid provided in an embodiment of the present application.

[0022] Figure 6 It is a schematic diagram of dividing the third vehicle model represented by octagon simulation into a nine-square grid provided in an embodiment of the present application.

[0023] Figure 7 It is a flowchart of a method for determining whether an obstacle point is located within a vehicle model provided in an embodiment of the present application.

[0024] Figure 8 It is a flowchart of a method for determining whether an obstacle vector intersects with a vehicle model provided in an embodiment of the present application.

[0025] Fig. 9 It is a flowchart of another method for determining whether an obstacle vector intersects with a vehicle model provided in an embodiment of the present application.

[0026] Fig.10 It is a schematic diagram of a method for determining whether an obstacle point is within a quadrilateral by using vector cross product provided in an embodiment of the present application.

[0027] Fig.11 It is a schematic diagram of another method provided in an embodiment of the present application for determining whether an obstacle point is within a quadrilateral by using vector cross product.

[0028] Fig.12 It is a flowchart of another collision detection method provided in an embodiment of the present application.

[0029] Fig.13 It is a schematic diagram of a vehicle model and a simulated boundary provided in an embodiment of the present application.

[0030] Fig.14 It is a schematic diagram of a collision detection device provided in an embodiment of the present application.

[0031] Fig.15 It is a schematic diagram of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0032] In the following description, specific details such as specific system structures, technologies, etc. are provided for the purpose of illustration rather than limitation, so as to provide a thorough understanding of the embodiments of the present application. However, it should be clear to those skilled in the art that the present application may also be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to prevent unnecessary details from obstructing the description of the present application.

[0033] A collision detection method and device according to an embodiment of the present application will be described in detail below with reference to the accompanying drawings.

[0034] As mentioned above, in the related technologies, either the vehicle-mounted sensor is used to obtain a signal indicating whether the vehicle has collided, or the predicted trajectory of the obstacle is obtained and the predicted trajectory is converted from the Frenet coordinate system to the Cartesian coordinate system before collision detection. The former cannot make predictions before a collision, and the latter requires coordinate system conversion, which has high requirements for computing power and cannot be applied to platforms with low computing power.

[0035] In view of this, an embodiment of the present application provides a collision detection method, which obtains vehicle configuration information including at least one of the vehicle length, vehicle width and axle information, and the position information of the vehicle in the target coordinate system, and constructs a first vehicle model in the preset coordinate system according to the vehicle configuration information, the vehicle position information and the preset expansion coefficient, and simultaneously obtains obstacle information, and constructs the obstacle model in the target coordinate system based on the obstacle information. When it is determined that the obstacle model is outside the first vehicle model, or the obstacle model does not intersect with the first vehicle model, the collision detection result is determined to be a passed detection.

[0036] Figure 1 is a flow chart of a collision detection method provided by an embodiment of the present application. Figure 1 As shown, the method comprises the following steps:

[0037] In step S101 , vehicle configuration information is obtained.

[0038] The vehicle configuration information includes at least one of the vehicle length, vehicle width and axle information.

[0039] In step S102, the position information of the vehicle in the target coordinate system is obtained, and a first vehicle model is constructed in the preset coordinate system according to the vehicle configuration information, the vehicle position information and the preset expansion coefficient.

[0040] In step S103, the obstacle position information is obtained, and an obstacle model is determined in the target coordinate system based on the obstacle position information. The obstacle model is an obstacle point or an obstacle vector.

[0041] In step S104 , in response to determining that the obstacle point is outside the first vehicle model, or the obstacle vector does not intersect the first vehicle model, it is determined that the collision detection result is detection passed.

[0042] In some embodiments of the present application, the collision detection method is used to provide a collision detection result for a vehicle performing an automatic parking operation. In one example, the method can be executed by an onboard processing unit, or by other terminals with certain processing capabilities and connected to the vehicle, which is not limited here.

[0043] Figure 2 This is a schematic diagram of the automatic parking process. Figure 2As shown, when the vehicle performs an automatic parking operation, it may obtain the vehicle's sensory input, that is, the detection result of the vehicle's on-board sensor. The sensory input is post-perceived to determine the available parking space. If based on other factors, such as the user's choice to determine that the available parking space is not available for parking, the search for the parking space continues. On the contrary, if it is determined that the available parking space can be parked, path planning is performed, and then collision detection is performed. If the detection result is no collision, the parking operation is performed. When parking, it is necessary to continue to perform collision detection based on the perception results. If there is no collision, the parking operation continues until the parking is completed. If a collision is detected, that is, the vehicle may collide with an obstacle, the path planning needs to be re-performed.

[0044] That is to say, the parking system will continue to judge whether the vehicle will collide with obstacles during the parking process. Obstacles can include moving obstacles, stationary obstacles, road sidelines, walls, wheel chocks, etc. For low-computing platforms, the collision detection model must be simple enough and the collision detection algorithm must be fast enough to provide collision detection results to the vehicle in a timely manner.

[0045] In some embodiments of the present application, vehicle configuration information may be obtained, and the vehicle configuration information includes at least one of the vehicle length, vehicle width, and axle information. The vehicle length is the maximum length of the vehicle, the vehicle width is the maximum width of the vehicle, and the axle information may include the length of the front axle and / or rear axle of the vehicle, and the wheelbase of the vehicle. The vehicle configuration information may be pre-stored in the vehicle, or may be obtained by the vehicle from the cloud, and there is no limitation here.

[0046] In certain embodiments of the present application, the position information of the vehicle in the target coordinate system can also be obtained. The target coordinate system can be a global Cartesian coordinate system, and the position information of the vehicle in the target coordinate system can be obtained through a positioning system, such as obtaining the real-time coordinates of the vehicle from a vehicle-mounted GPS (Global Positioning System) module. Alternatively, when the vehicle performs an automatic parking task in an area with a weak GPS signal such as a basement, the position information of the vehicle in the target coordinate system can also be obtained through a vehicle perception module, such as through a vehicle-mounted laser radar, an infrared detector, or an image detection device.

[0047] When the vehicle's position information is acquired by the vehicle perception module, the target coordinate system may be a relative coordinate system generated by the vehicle using a DR (Dead Reckoning) algorithm or the like.

[0048] According to the obtained vehicle configuration information and the position information of the vehicle in the target coordinate system, a first vehicle model can be constructed in the preset coordinate system in combination with a preset expansion coefficient. The first vehicle model can be a quadrilateral model, and the expansion coefficient is used to provide redundancy for the vehicle model for collision detection to avoid the situation where the vehicle has actually collided when a collision is detected. The value of the preset expansion coefficient can be determined according to actual needs and is not limited here. In one example, the value range of the preset expansion coefficient can be 10 to 20 centimeters, for example, 15 centimeters.

[0049] In some embodiments of the present application, obstacle position information may also be obtained. The obstacle position information may be obtained by the vehicle perception module, and the obstacle position information may be used to construct an obstacle model in the relative coordinate system created by the vehicle. The obstacle model may be one or more obstacle points or one or more obstacle vectors.

[0050] Using this method, the obstacle model is directly added to the relative coordinate system created by the vehicle. There is no need to convert the coordinate system of the obstacle's position information such as trajectory. This can greatly reduce the amount of calculation for collision detection and is very friendly to low-computing power platforms.

[0051] Furthermore, the positional relationship between the constructed first vehicle model and the obstacle model can also be detected. If all obstacle points in the obstacle model are located outside the first vehicle model, and / or all obstacle vectors in the obstacle model do not intersect with the first vehicle model, it can be determined that no collision has occurred. In this case, the collision detection result may be a passed detection.

[0052] According to the technical solution provided in the embodiment of the present application, by acquiring vehicle configuration information including at least one of the vehicle length, vehicle width and axle information, and the position information of the vehicle in the target coordinate system, a first vehicle model is constructed in the preset coordinate system according to the vehicle configuration information, the vehicle position information and the preset expansion coefficient, and at the same time, obstacle information is acquired, and the obstacle model is constructed in the target coordinate system based on the obstacle information. When it is determined that the obstacle model is outside the first vehicle model, or the obstacle model does not intersect with the first vehicle model, the collision detection result is determined to be a detection pass.

[0053] In some embodiments of the present application, the preset obstacles may include wheel chocks and parking boundary obstacles, wherein the parking boundary obstacles include, for example, parking boundary lines formed by parking space lines, walls, pillars, other moving or stationary vehicles in adjacent parking spaces, and the like.

[0054] If the preset obstacle is a wheel chock, the first vehicle model is determined in the following manner: a quadrilateral surrounded by the front axle and the rear axle of the vehicle is determined as the initial vehicle model; the initial vehicle model is expanded outward by a preset expansion coefficient to obtain the first vehicle model. The initial vehicle model is expanded outward by a preset expansion coefficient, which may be that each side of the quadrilateral corresponding to the initial vehicle model is moved away from the center of the quadrilateral by the preset expansion coefficient.

[0055] That is to say, in the case where the preset obstacle is a wheel chock, the quadrilateral formed by the front and rear axles of the vehicle can be directly used as the initial vehicle model. Furthermore, in order to prevent the rear axle from pressing on the wheel chock or over the wheel chock, the quadrilateral can be expanded when constructing the quadrilateral, and the expanded quadrilateral can be used as the first vehicle model.

[0056] On the other hand, if the preset obstacle is a parking boundary, the first vehicle model is determined in the following manner: the initial vehicle model is determined by taking the center of the vehicle as the center of the quadrilateral, the entire length of the vehicle as the length of the quadrilateral, and the entire width of the vehicle as the width of the quadrilateral; the initial vehicle model is expanded outward by a preset expansion coefficient to obtain the first vehicle model.

[0057] That is to say, in the case where the preset obstacle is a parking boundary, the initial vehicle model can be determined according to the length, width and center position of the vehicle, and then the initial vehicle model is expanded outward by a preset expansion coefficient to obtain a first vehicle model, thereby preventing the vehicle from scratching against obstacles such as walls that constitute the parking boundary during the parking process.

[0058] Figure 3 is a flow chart of another collision detection method provided in an embodiment of the present application. Figure 3 Steps S301 to S304 in the embodiment shown are Figure 1 Steps S101 to S104 in the embodiment are basically the same and will not be described in detail here. Figure 3 As shown, the method also includes the following steps:

[0059] In step S305, in response to determining that the obstacle point is located within the first vehicle model, or determining that the obstacle vector intersects the first vehicle model, a collision depth between the vehicle and the obstacle is obtained.

[0060] In step S306 , in response to determining that the collision depth is less than the preset expansion coefficient, the initial vehicle model is determined to be the second vehicle model.

[0061] In step S307 , in response to determining that the obstacle point is outside the second vehicle model, or the obstacle vector does not intersect the second vehicle model, it is determined that the collision detection result is detection passed.

[0062] In certain embodiments of the present application, if it is determined that the obstacle point is located within the first vehicle model, or it is determined that the obstacle vector intersects with the first vehicle model, it can be determined that the obstacle has collided with the vehicle represented by the simulation of the first vehicle model, and the collision depth between the vehicle and the obstacle can be obtained. If it is determined that the collision depth is less than the preset expansion coefficient, it can be further determined that the initial vehicle model is the second vehicle model, and then it is detected whether the obstacle collides with the second vehicle model. In one example, if the obstacle point is located outside the second vehicle model, or the obstacle vector does not intersect with the second vehicle model, it can be determined that the vehicle has not collided with the vehicle represented by the simulation of the second vehicle model, and then the collision detection result is determined to be a pass.

[0063] Figure 4 is a flow chart of another collision detection method provided in an embodiment of the present application. Figure 4 Steps S401 to S407 in the illustrated embodiment are similar to Figure 3 Steps S301 to S307 in the illustrated embodiment are substantially the same and will not be described in detail herein. Figure 4 As shown, the method also includes the following steps:

[0064] In step S408, in response to determining that the obstacle point is located within the second vehicle model, or determining that the obstacle vector intersects the second vehicle model, the coordinates of the collision point between the vehicle and the obstacle are acquired.

[0065] The collision point is an obstacle point, or a point in the obstacle vector that is closest to the center point of the second vehicle model.

[0066] In step S409, in response to determining that the distances from the collision point to two adjacent edges in the second vehicle model are less than a preset threshold according to the collision point coordinates, a third vehicle model is constructed in the target coordinate system according to the second vehicle model and the preset segmentation coefficient.

[0067] The preset segmentation coefficient is determined according to the outer contour of the vehicle.

[0068] In step S410 , in response to determining that the obstacle point is outside the third vehicle model, or the obstacle vector does not intersect the third vehicle model, it is determined that the collision detection result is detection passed.

[0069] In step S411 , in response to determining that the obstacle point is located within the third vehicle model, or determining that the obstacle vector intersects the third vehicle model, the collision detection result is determined to be a detection failure.

[0070] In certain embodiments of the present application, if it is determined that the obstacle point is located within the second vehicle model, or it is determined that the obstacle vector intersects with the second vehicle model, it can be determined that the obstacle has collided with the vehicle simulated by the second vehicle model, and the coordinates of the collision point between the vehicle and the obstacle can be obtained. When the obstacle model is an obstacle point, the collision point is the obstacle point; on the other hand, when the obstacle model is an obstacle vector, the collision point is the point in the obstacle vector that is closest to the center point of the second vehicle model.

[0071] If the distances from the collision point to the two adjacent sides in the second vehicle model are less than a preset threshold value according to the collision point coordinates, that is, the collision point is close to the vertex of the quadrilateral of the second vehicle model represented by the quadrilateral, the collision location may be the left front position, right front position, left rear position or right rear position of the vehicle's outer contour, that is, one of the four corners of the vehicle. Since the four corners of the vehicle are usually designed to be streamlined rather than right angles, a third vehicle model can be constructed again to simulate the vehicle more accurately, and the constructed third vehicle model can be used to perform collision detection again.

[0072] In some implementations, a third vehicle model can be constructed in the target coordinate system based on the second vehicle model and the preset segmentation coefficient. The preset segmentation coefficient can be determined based on the outer contour of the vehicle. In one example, the distances required to be segmented in the length direction and the width direction of the vehicle can be determined based on the outer contour of the vehicle, and then the segmentation lines corresponding to the four vertices in the second vehicle model can be determined based on the distances, and the four vertices can be segmented respectively using the segmentation lines, and the resulting octagonal model is the third vehicle model.

[0073] That is, constructing the third vehicle model in the target coordinate system according to the second vehicle model and the preset segmentation coefficient may be to determine the cut corner position according to the preset segmentation coefficient; and to cut off the four corners of the second vehicle model at the cut corner position to obtain the third vehicle model, wherein the third vehicle model is an octagonal model.

[0074] For any vertex in the quadrilateral corresponding to the second vehicle model, its corner cutting position may include a first corner cutting point and a second corner cutting point, wherein the first corner cutting point is determined by moving the vertex along the length direction of the vehicle model by a first cutting distance, and the second corner cutting point is determined by moving the vertex along the width direction of the vehicle model by a second cutting distance. The first corner cutting point and the second corner cutting point are connected, and the triangle including the vertex is cut off from the quadrilateral, so that the corner of the quadrilateral can be cut off.

[0075] Further, if the obstacle point is outside the third vehicle model, or the obstacle vector does not intersect with the third vehicle model, the collision detection result can be determined as a pass. Conversely, if the obstacle point is inside the third vehicle model, or the obstacle vector is determined to intersect with the third vehicle model, the collision detection result can be determined as a fail.

[0076] In some embodiments of the present application, if a quadrilateral or octagon is directly used to simulate and represent the vehicle model, then if the collision fails in the collision detection, it can only be confirmed that the vehicle has collided with the obstacle, but the collision depth of the vehicle and the obstacle and the approximate area of ​​the collision are unknown. At this time, it is difficult to determine whether the collision is caused by the inability of the vehicle to pass or the collision caused by the collision area. Therefore, the quadrilateral or octagon that simulates and represents the vehicle model can be decomposed into N small quadrilaterals, and the collision between each small quadrilateral and the obstacle model can be detected separately, so that the collision area and collision depth can be quickly located when a collision is determined.

[0077] In some embodiments of the present application, the first vehicle model, the second vehicle model, and the third vehicle model may be divided into N quadrilaterals, respectively, and the N quadrilaterals include i parallelograms and j trapezoids, wherein N is a positive integer greater than 1, i is a positive integer greater than 1 and less than or equal to N, and j is a positive integer greater than or equal to 0 and less than N. The value of N is set according to actual needs, for example, it is set to 9. Further, when dividing the N quadrilaterals, the length and width of each quadrilateral are also set according to actual needs, and are not limited here.

[0078] Further, the collision depth between the vehicle and the obstacle can be determined in the following manner: in response to determining that the obstacle model is an obstacle point, the collision depth is the shortest distance between the obstacle point and the outer boundary of the first vehicle model. Alternatively, in response to determining that the obstacle model is an obstacle vector, the collision point between the vehicle and the obstacle is determined, and the collision point is the point in the obstacle vector that is closest to the center point of the first vehicle model; the shortest distance between the collision point and the outer boundary of the first vehicle model is determined as the collision depth.

[0079] That is to say, when performing collision detection, it is necessary to know the collision depth of the obstacle point or obstacle vector that has collided in order to determine the severity of the collision. For an obstacle point, the closest distance from the point to each side of the vehicle model can be used as the collision depth. For an obstacle vector, you can first find the point on the line segment corresponding to the obstacle vector that is closest to the geometric center of the vehicle, and use that point as the point with the deepest collision. Then use the closest distance from that point to each side of the vehicle model as the collision depth.

[0080] Figure 5 1 is a schematic diagram of dividing the first vehicle model and the second vehicle model represented by quadrilateral simulation into a nine-square grid provided by an embodiment of the present application. Figure 5As shown in , when performing the nine-grid division, the first segmentation distance in the length direction of the vehicle model and the second segmentation distance in the width direction of the vehicle model can be determined first. Then, starting from any vertex in the vehicle model, extending the first distance on the length line of the vehicle model and extending the second distance on the width line of the vehicle model can obtain a quadrilateral. Performing the same operation on the four vertices of the vehicle model can obtain the following Figure 5 The quadrilaterals numbered 1, 3, 7 and 9 are shown in FIG. The vertex coordinates of the quadrilaterals numbered 1, 3, 7 and 9 can be used to determine the remaining quadrilaterals numbered 2, 4, 5, 6 and 8.

[0081] In other words, the vertex coordinates of each quadrilateral in the nine-square grid can be calculated through the vertex coordinates of the vehicle model, and then each quadrilateral can be determined. This can further save computing power.

[0082] Among them, quadrilaterals 1, 3, 7 and 9 have the same length and width, representing the left front corner, right front corner, left rear corner and right rear corner of the vehicle respectively. The above-mentioned first segmentation distance and second segmentation distance can be set according to actual needs and are not limited here. In an example, the width of the vehicle model is 2.9 meters, and the second segmentation distance can be set to 0.6 meters.

[0083] Figure 6 Schematic diagram of dividing the third vehicle model represented by octagon simulation into nine squares provided by the embodiment of the present application. Figure 6 As shown, the nine-square grid includes i=5 quadrilaterals and j=4 trapezoids. The method of dividing the octagonal vehicle model into a nine-square grid is similar to the above division method. Figure 5 The method of the quadrilateral nine-square grid shown is basically the same and will not be repeated here.

[0084] Figure 7 FIG. 1 is a flow chart of a method for determining whether an obstacle point is located within a vehicle model provided in an embodiment of the present application. Figure 7 As shown, the method comprises the following steps:

[0085] In step S701 , the vehicle model is divided into N quadrilaterals.

[0086] In step S702 , a target minimum horizontal coordinate value, a target maximum horizontal coordinate value, a target minimum vertical coordinate value, and a target maximum vertical coordinate value of the target quadrilateral are determined according to the vertex coordinates of the target quadrilateral.

[0087] The target quadrilateral is any one of the N quadrilaterals.

[0088] In step S703, in response to determining that the horizontal coordinate of the obstacle point is greater than or equal to the minimum target horizontal coordinate and less than or equal to the maximum target horizontal coordinate, and the vertical coordinate of the obstacle point is greater than or equal to the minimum target vertical coordinate and less than or equal to the maximum target vertical coordinate, it is determined that the obstacle point is located within the vehicle model.

[0089] In step S704 , otherwise, it is determined that the obstacle point is outside the vehicle model.

[0090] In some embodiments of the present application, when the obstacle model is an obstacle point, determining whether the obstacle point is located within the vehicle model may be to first divide the vehicle model into N quadrilaterals, for example, into a nine-square grid. Then, the target horizontal coordinate minimum value, the target horizontal coordinate maximum value, the target vertical coordinate minimum value, and the target vertical coordinate maximum value of the target quadrilateral are determined by the vertex coordinates of the target quadrilateral, and the target quadrilateral is any one of the N quadrilaterals.

[0091] If it is determined that the horizontal coordinate of the obstacle point is greater than or equal to the minimum value of the target horizontal coordinate and less than or equal to the maximum value of the target horizontal coordinate, and the vertical coordinate of the obstacle point is greater than or equal to the minimum value of the target vertical coordinate and less than or equal to the maximum value of the target vertical coordinate, it can be determined that the obstacle point is located inside the vehicle model. Otherwise, it is determined that the obstacle point is located outside the vehicle model.

[0092] Figure 8 FIG. 1 is a flow chart of a method for determining whether an obstacle vector intersects with a vehicle model provided in an embodiment of the present application. Figure 8 As shown, the method comprises the following steps:

[0093] In step S801 , the vehicle model is divided into N quadrilaterals.

[0094] In step S802 , a target minimum horizontal coordinate value, a target maximum horizontal coordinate value, a target minimum vertical coordinate value, and a target maximum vertical coordinate value of the target quadrilateral are determined by using the vertex coordinates of the target quadrilateral.

[0095] The target quadrilateral is any one of the N quadrilaterals.

[0096] In step S803, in response to determining that the maximum horizontal coordinate of the obstacle vector is less than the target minimum horizontal coordinate, and the maximum vertical coordinate of the obstacle vector is less than the target minimum vertical coordinate, it is determined that the obstacle vector does not intersect the vehicle model.

[0097] In step S804 , in response to determining that the minimum horizontal coordinate value of the obstacle vector is greater than the target horizontal coordinate maximum value and the minimum vertical coordinate value of the obstacle vector is greater than the target vertical coordinate maximum value, it is determined that the obstacle vector does not intersect the vehicle model.

[0098] In some embodiments of the present application, when the obstacle model is an obstacle vector, determining whether the obstacle vector intersects with the vehicle model may be to first divide the vehicle model into N quadrilaterals, for example, into a nine-square grid, and then determine the target horizontal coordinate minimum value, target horizontal coordinate maximum value, target vertical coordinate minimum value, and target vertical coordinate maximum value of the target quadrilateral through the vertex coordinates of the target quadrilateral.

[0099] If the maximum horizontal coordinate of the obstacle vector is less than the minimum horizontal coordinate of the target, and the maximum vertical coordinate of the obstacle vector is less than the minimum vertical axis of the target, it can be determined that the obstacle vector does not intersect with the vehicle model. Alternatively, if it is determined that the minimum horizontal coordinate of the obstacle vector is greater than the maximum horizontal coordinate of the target, and the minimum vertical coordinate of the obstacle vector is greater than the maximum vertical axis of the target, it can also be determined that the obstacle vector does not intersect with the vehicle model.

[0100] That is to say, the quick elimination method can be used to first determine whether the obstacle vector and the vehicle model intersect. Further, if the quick elimination method is used to determine that the obstacle vector and the vehicle model do not intersect, a more accurate method needs to be used to continue to determine. In one example, vector cross product can be used to determine whether the obstacle vector and the vehicle model intersect.

[0101] Fig. 9 is a flow chart of another method for determining whether an obstacle vector intersects with a vehicle model provided by an embodiment of the present application. Fig. 9 Steps S901 to S904 in the embodiment shown are Figure 8 Steps S801 to S804 in the illustrated embodiment are substantially the same and will not be described in detail herein. Fig. 9 As shown, the method also includes the following steps:

[0102] In step S905 , a target edge in the target quadrilateral is obtained. The target edge is any edge in the target quadrilateral, and the target edge includes a first endpoint and a second endpoint.

[0103] In step S906, it is determined that the starting point and the terminal point of the obstacle vector are the third endpoint and the fourth endpoint respectively.

[0104] In step S907 , a first vector from the first endpoint to the third endpoint, a second vector from the first endpoint to the second endpoint, and a third vector from the first endpoint to the fourth endpoint are constructed.

[0105] In step S908 , in response to determining that a first product of a cross product of the first vector and the second vector has a different sign from a second product of a cross product of the third vector and the second vector, it is determined that the obstacle vector intersects the vehicle model.

[0106] In some embodiments of the present application, when using vector cross product to determine whether the obstacle vector intersects with the vehicle model, the target edge in the target quadrilateral can be obtained, and the starting point and the terminal of the obstacle vector are determined to be the third endpoint and the fourth endpoint, respectively, wherein the target edge is any edge in the target quadrilateral, and the target edge includes the first endpoint and the second endpoint. Further, a first vector from the first endpoint to the third endpoint, a second vector from the first endpoint to the second endpoint, and a third vector from the first endpoint to the fourth endpoint can be constructed.

[0107] The first product is obtained by cross-multiplying the first vector and the second vector, and the second product is obtained by cross-multiplying the third vector and the second vector. If it is determined that the signs of the first product and the second product are different, for example, the first product is positive and the second product is negative, or the first product is negative and the second product is positive, it can be determined that the obstacle vector intersects the vehicle model.

[0108] That is, the vector cross product can be used to determine whether the line segments corresponding to the vectors intersect. By determining whether the line segments corresponding to the obstacle vectors intersect with the sides of the quadrilateral, it can be determined whether the obstacle vectors intersect with the vehicle model.

[0109] It can be understood that, when the obstacle model is an obstacle point, vector cross product can also be used to determine whether the obstacle point is within the quadrilateral. Fig.10 and Fig.11 All of them are schematic diagrams of using vector cross product to determine whether an obstacle point is within a quadrilateral, provided in the embodiments of the present application. Fig.10 and Fig.11 As shown, the four vertices of the quadrilateral can be represented by A, B, C and D, and the obstacle point can be represented by O.

[0110] like Fig.10 As shown, any pair of opposite sides of the quadrilateral, such as AB and CD, can be taken to cross-multiply vectors OC and OA to obtain the third product, and to cross-multiply vectors OB and OA to obtain the fourth product. If the signs of the third product and the fourth product are different, it can be determined that the obstacle point O is outside the quadrilateral ABCD. Otherwise, continue to cross-multiply vectors OD and OA to obtain the fifth product.

[0111] like Fig.11 As shown, if the signs of the fifth product and the fourth product are still the same, then reselect the opposite sides AC and BD of the quadrilateral ABCD, and cross-multiply the vectors OA and OB to obtain the sixth product, and cross-multiply the vectors OD and OB to obtain the seventh product. When the signs of the sixth product and the seventh product are the same, continue to cross-multiply the vectors OC and OB to obtain the eighth product. If the two sets of opposite sides are traversed in this way, if it is determined that the line segments corresponding to all the vectors do not intersect, it can be determined that the obstacle point O is located within the quadrilateral ABCD.

[0112] Fig.12 FIG. 1 is a flow chart of another collision detection method provided in an embodiment of the present application. Fig.12 As shown, when performing collision detection, the collision detection tool can first read the configuration parameters and select a suitable vehicle model. In one example, the default preferred vehicle model is the first vehicle model, and the user can select other vehicle models according to actual needs, or the detection tool can automatically switch to other vehicle models according to the detection results.

[0113] The perception system is generally accurate within a range of 2 to 5 meters (there is an error of about 5 to 10 centimeters at this time), so during the parking process, the perception input will change slightly. For example, the perception accuracy of the boundary line will continue to improve as the vehicle approaches the boundary line. Especially for parking spaces with narrow rear frames, the higher the accuracy, the higher the probability of the vehicle being parked. Therefore, the collision detection algorithm will be called periodically throughout the parking process. A good collision detection model is very important for the parking system.

[0114] When constructing a vehicle model, for the wheel block boundary, the quadrilateral constructed is the quadrilateral surrounded by the front and rear axles. In order to prevent the rear axle from pressing on the wheel block or over the wheel block, the quadrilateral can be expanded when constructing it. For example, the length and width of the quadrilateral are expanded by 15 cm, so that an expanded quadrilateral is obtained, and then collision detection is performed based on the relationship between the wheel block and the quadrilateral.

[0115] For common boundary lines and points, the edge lines of the parking space frame and the road edge lines of the parking lot are judged as line segments, while the points are generally the coordinates of obstacle points provided by the ultrasonic radar. It should be noted that since the four corners of the vehicle are not right angles, an octagonal model can be constructed by modifying the coordinates of the four vertices during construction.

[0116] When determining the quadrilateral vehicle model, the coordinates of the four vertices of the quadrilateral are obtained according to the length and width of the vehicle. At the same time, in order to better adapt the collision detection model, the original quadrilateral can also be expanded, and the expansion coefficient is, for example, 10 cm, so as to ensure that the vehicle will not be scratched against the wall during parking.

[0117] When the vehicle is approximated as a quadrilateral, the four vertices of front, back, left, and right are determined based on the length and width of the vehicle, while the coordinates are constructed based on the ego vehicle coordinates. The construction principle is that if the ego vehicle has global positioning, the ego vehicle global positioning coordinates are used to construct the four corner points. If there is no global positioning in areas with weak positioning signals such as basements, relative coordinates can be generated using methods such as the DR algorithm. Expanding the original quadrilateral can obtain the expanded quadrilateral, which is the first vehicle model.

[0118] After obtaining the quadrilateral after the collision, the coordinates of the four vertices of the quadrilateral can be obtained. The coordinates of the four vertices can be the original coordinates or the coordinates after coordinate transformation. The transformation principle is to obtain the coordinates of the four vertices of the quadrilateral from the coordinates of the vehicle (relative or absolute coordinates) through the rotation matrix.

[0119] Next, in order to determine the collision area and collision depth, a nine-square grid can be constructed. When the coordinates of each vertex of the quadrilateral are known, the vertex coordinates of each small quadrilateral in the nine-square grid can be calculated based on the first segmentation distance and the second segmentation distance when dividing the nine-square grid through the vector relationship.

[0120] In actual testing, if some parking spaces are narrow, the quadrilateral model needs to be expanded to a safe distance, which will cause some obstacle points or boundary points to be judged as collisions, but in fact it is a safe distance area for collisions. In order to better simulate the vehicle, the vehicle simulation can be represented as an octagonal vehicle model. The construction method of the octagonal vehicle model is basically the same as that of the quadrilateral vehicle model. It only needs to modify the small quadrilaterals at the four vertices of the quadrilateral into trapezoids according to the actual streamline parameters of the front and rear corners of the vehicle.

[0121] By using the constructed vehicle model to perform collision detection, the detection result can be obtained. When the detection result is that a collision has occurred, information such as the collision depth can be further output.

[0122] Fig.13 Schematic diagram of a vehicle model and a simulated boundary provided in an embodiment of the present application. Fig.13 As shown in the figure, the vehicle model is represented by a quadrilateral divided into nine squares, line segment 1 is the simulated boundary, point 2 is the geometric center of the vehicle, and point 3 is the point in the simulated boundary line segment that is closest to point 2. Through calculation simulation, it can be seen that the collision depth calculated directly using the data in the relative coordinate system created by the vehicle is the same as the collision depth calculated by first converting the above values ​​to the global coordinate system through the rotation matrix and then using the data in the global coordinate system.

[0123] That is to say, since the embodiment of the present application uses vector relationships to determine the coordinate values ​​of each point in the nine-square grid and calculate the collision depth, there is no need to perform coordinate system conversion, which further improves the efficiency of collision detection on low-computing power platforms and enhances user experience.

[0124] By adopting the technical solution of the embodiment of the present application, by constructing quadrilaterals and octagons to simulate and represent the vehicle model, and constructing a nine-square grid to detect information such as the collision area and depth, APA can be assisted in collision detection conveniently and quickly. While improving the efficiency of algorithm testing, it can meet a variety of narrow boundary and narrow parking space conditions, reducing the probability of APA failure due to vehicle collision detection failure caused by too narrow boundaries. At the same time, the nine-square grid corner point coordinates calculated by vectors and geometric relationships and collision-related detection greatly reduce the algorithm's computing power consumption.

[0125] All the above optional technical solutions can be arbitrarily combined to form optional embodiments of the present application, which will not be described one by one here.

[0126] The following is an embodiment of the device of the present application, which can be used to execute the embodiment of the method of the present application. For details not disclosed in the embodiment of the device of the present application, please refer to the embodiment of the method of the present application.

[0127] Fig.14 Schematic diagram of a collision detection device provided in an embodiment of the present application. Fig.14 As shown, the device comprises:

[0128] The acquisition module 1401 is configured to acquire vehicle configuration information, where the vehicle configuration information includes at least one of the vehicle length, vehicle width and axle information.

[0129] The vehicle model determination module 1402 is configured to obtain the position information of the vehicle in the target coordinate system, and construct a first vehicle model in the preset coordinate system according to the vehicle configuration information, the vehicle position information and the preset expansion coefficient.

[0130] The obstacle model determination module 1403 is configured to obtain obstacle position information, and determine an obstacle model in the target coordinate system based on the obstacle position information. The obstacle model is an obstacle point or an obstacle vector.

[0131] The detection module 1404 is configured to determine that the collision detection result is a detection pass in response to determining that the obstacle point is outside the first vehicle model or the obstacle vector does not intersect the first vehicle model.

[0132] According to the technical solution provided in the embodiment of the present application, by acquiring vehicle configuration information including at least one of the vehicle length, vehicle width and axle information, and the position information of the vehicle in the target coordinate system, a first vehicle model is constructed in the preset coordinate system according to the vehicle configuration information, the vehicle position information and the preset expansion coefficient, and at the same time, obstacle information is acquired, and the obstacle model is constructed in the target coordinate system based on the obstacle information. When it is determined that the obstacle model is outside the first vehicle model, or the obstacle model does not intersect with the first vehicle model, the collision detection result is determined to be a detection pass.

[0133] In some embodiments, the preset obstacle includes a wheel chock and a parking boundary obstacle; in response to determining that the preset obstacle is a wheel chock, the first vehicle model is determined in the following manner: a quadrilateral surrounded by the front axle and the rear axle of the vehicle is determined as the initial vehicle model; the initial vehicle model is expanded outward by a preset expansion coefficient to obtain the first vehicle model; in response to determining that the preset obstacle is a parking boundary, the first vehicle model is determined in the following manner: the initial vehicle model is determined with the center of the vehicle as the center of the quadrilateral, the entire vehicle length of the vehicle as the length of the quadrilateral, and the entire vehicle width of the vehicle as the width of the quadrilateral; the initial vehicle model is expanded outward by a preset expansion coefficient to obtain the first vehicle model.

[0134] In some embodiments, the method further includes: in response to determining that an obstacle point is located within the first vehicle model, or determining that the obstacle vector intersects with the first vehicle model, obtaining a collision depth between the vehicle and the obstacle; in response to determining that the collision depth is less than a preset expansion coefficient, determining that the initial vehicle model is a second vehicle model; in response to determining that the obstacle point is located outside the second vehicle model, or the obstacle vector does not intersect with the second vehicle model, determining that the collision detection result is a passed detection.

[0135] In some embodiments, it also includes: in response to determining that an obstacle point is located within the second vehicle model, or determining that the obstacle vector intersects with the second vehicle model, obtaining the coordinates of the collision point between the vehicle and the obstacle, the collision point being the obstacle point, or the point in the obstacle vector that is closest to the center point of the second vehicle model; in response to determining that the distances from the collision point to two adjacent edges in the second vehicle model are both less than a preset threshold based on the collision point coordinates, constructing a third vehicle model in the target coordinate system based on the second vehicle model and a preset segmentation coefficient, the preset segmentation coefficient being determined based on the outer contour of the vehicle; in response to determining that the obstacle point is located outside the third vehicle model, or the obstacle vector does not intersect with the third vehicle model, determining that the collision detection result is a passed detection; in response to determining that the obstacle point is located within the third vehicle model, or determining that the obstacle vector intersects with the third vehicle model, determining that the collision detection result is a failed detection.

[0136] In some embodiments, a third vehicle model is constructed in a target coordinate system based on the second vehicle model and a preset segmentation coefficient, including: determining a cutting angle position based on the preset segmentation coefficient; cutting off four corners of the second vehicle model at the cutting angle position to obtain a third vehicle model; wherein the third vehicle model is an octagonal model.

[0137] In some embodiments, in response to the obstacle model being an obstacle point, determining whether the obstacle point is located within the vehicle model includes: dividing the vehicle model into N quadrilaterals, the N quadrilaterals including i parallelograms and j trapezoids, wherein N is a positive integer greater than 1, i is a positive integer greater than 1 and less than or equal to N, and j is a positive integer greater than or equal to 0 and less than N; determining a target minimum horizontal coordinate, a target maximum horizontal coordinate, a target minimum vertical coordinate, and a target maximum vertical coordinate of the target quadrilateral through the vertex coordinates of the target quadrilateral, the target quadrilateral being any one of the N quadrilaterals; in response to determining that the horizontal coordinate of the obstacle point is greater than or equal to the minimum horizontal coordinate of the target and less than or equal to the maximum horizontal coordinate of the target, and the vertical coordinate of the obstacle point is greater than or equal to the minimum vertical coordinate of the target and less than or equal to the maximum vertical coordinate of the target, determining that the obstacle point is located within the vehicle model; otherwise, determining that the obstacle point is located outside the vehicle model.

[0138] In some embodiments, in response to the obstacle model being an obstacle vector, determining whether the obstacle vector intersects with the vehicle model includes: dividing the vehicle model into N quadrilaterals, the N quadrilaterals including i parallelograms and j trapezoids, wherein N is a positive integer greater than 1, i is a positive integer greater than 1 and less than or equal to N, and j is a positive integer greater than or equal to 0 and less than N; determining a target horizontal coordinate minimum value, a target horizontal coordinate maximum value, a target vertical coordinate minimum value, and a target vertical coordinate maximum value of the target quadrilateral through vertex coordinates of the target quadrilateral, the target quadrilateral being any one of the N quadrilaterals; in response to determining that the horizontal coordinate maximum value of the obstacle vector is less than the target horizontal coordinate minimum value, and the vertical coordinate maximum value of the obstacle vector is less than the target vertical axis mark minimum value, determining that the obstacle vector does not intersect with the vehicle model; or in response to determining that the horizontal coordinate minimum value of the obstacle vector is greater than the target horizontal coordinate maximum value, and the vertical coordinate minimum value of the obstacle vector is greater than the target vertical axis mark maximum value, determining that the obstacle vector does not intersect with the vehicle model.

[0139] In some embodiments, it also includes: obtaining a target edge in a target quadrilateral, the target edge is any edge in the target quadrilateral, and the target edge includes a first endpoint and a second endpoint; determining that the starting point and the end point of the obstacle vector are the third endpoint and the fourth endpoint, respectively; constructing a first vector from the first endpoint to the third endpoint, a second vector from the first endpoint to the second endpoint, and a third vector from the first endpoint to the fourth endpoint; in response to determining that the first product of the cross product of the first vector and the second vector and the second product of the cross product of the third vector and the second vector have different signs, determining that the obstacle vector intersects with the vehicle model.

[0140] In some embodiments, obtaining a collision depth between a vehicle and an obstacle includes: in response to determining that an obstacle model is an obstacle point, the collision depth is the shortest distance between the obstacle point and an outer boundary of a first vehicle model; in response to determining that the obstacle model is an obstacle vector, determining a collision point between the vehicle and the obstacle, the collision point being the point in the obstacle vector that is closest to a center point of the first vehicle model; and determining the shortest distance between the collision point and the outer boundary of the first vehicle model as the collision depth.

[0141] It should be understood that the size of the serial numbers of the steps in the above embodiments does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0142] Fig.15 Schematic diagram of an electronic device provided in an embodiment of the present application. Fig.15 As shown, the electronic device 15 of this embodiment includes: a processor 1501, a memory 1502, and a computer program 1503 stored in the memory 1502 and executable on the processor 1501. When the processor 1501 executes the computer program 1503, the steps in the above-mentioned method embodiments are implemented. Alternatively, when the processor 1501 executes the computer program 1503, the functions of the modules / units in the above-mentioned device embodiments are implemented.

[0143] The electronic device 15 may be a desktop computer, a notebook, a PDA, a cloud server, or other electronic device. The electronic device 15 may include, but is not limited to, a processor 1501 and a memory 1502. Those skilled in the art will appreciate that Fig.15 The electronic device 15 is merely an example and does not limit the electronic device 15 , and may include more or less components than those shown in the figure, or different components.

[0144] Processor 1501 can be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc.

[0145] The memory 1502 may be an internal storage unit of the electronic device 15, for example, a hard disk or memory of the electronic device 15. The memory 1502 may also be an external storage device of the electronic device 15, for example, a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card (FlashCard), etc. equipped on the electronic device 15. The memory 1502 may also include both an internal storage unit of the electronic device 15 and an external storage device. The memory 1502 is used to store computer programs and other programs and data required by the electronic device.

[0146] Those skilled in the art can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional units and modules is used as an example. In actual applications, the above-mentioned functions can be assigned to different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiments can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of software functional units.

[0147] The above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. These modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application, and should all be included in the protection scope of the present application.

Claims

1. A collision detection method, characterized in that: The method is used to provide a collision detection result for a vehicle performing an automatic parking operation, and the method comprises: Acquiring vehicle configuration information, wherein the vehicle configuration information includes at least one of vehicle length, vehicle width, and axle information; Acquire the position information of the vehicle in the target coordinate system, and construct a first vehicle model in the preset coordinate system according to the vehicle configuration information, the vehicle position information and a preset expansion coefficient; Obtaining obstacle position information, and determining the obstacle model in the target coordinate system based on the obstacle position information, wherein the obstacle model is an obstacle point or an obstacle vector; In response to determining that the obstacle point is outside the first vehicle model, or the obstacle vector does not intersect the first vehicle model, the collision detection result is determined to be detection passed.

2. The method according to claim 1, characterized in that The preset obstacles include wheel chocks and parking boundary obstacles; In response to determining that the preset obstacle is a wheel chock, the first vehicle model is determined in the following manner: Determine a quadrilateral enclosed by the front axle and the rear axle of the vehicle as an initial vehicle model; Expanding the initial vehicle model outward by the preset expansion coefficient to obtain the first vehicle model; In response to determining that the preset obstacle is a parking boundary, the first vehicle model is determined in the following manner: An initial vehicle model is determined by taking the center of the vehicle as the center of the quadrilateral, the entire length of the vehicle as the length of the quadrilateral, and the entire width of the vehicle as the width of the quadrilateral; The initial vehicle model is expanded outward by the preset expansion coefficient to obtain the first vehicle model.

3. The method according to claim 2, characterized in that The method further comprises: In response to determining that the obstacle point is located within the first vehicle model, or determining that the obstacle vector intersects the first vehicle model, obtaining a collision depth between the vehicle and the obstacle; In response to determining that the collision depth is less than the preset expansion coefficient, determining that the initial vehicle model is a second vehicle model; In response to determining that the obstacle point is outside the second vehicle model, or the obstacle vector does not intersect the second vehicle model, the collision detection result is determined to be detection passed.

4. The method according to claim 3, characterized in that The method further comprises: In response to determining that the obstacle point is located within the second vehicle model, or determining that the obstacle vector intersects the second vehicle model, obtaining the coordinates of a collision point between the vehicle and the obstacle, the collision point being the obstacle point, or a point in the obstacle vector that is closest to a center point of the second vehicle model; In response to determining, according to the collision point coordinates, that the distances from the collision point to two adjacent edges in the second vehicle model are both less than a preset threshold, constructing a third vehicle model in the target coordinate system according to the second vehicle model and a preset segmentation coefficient, wherein the preset segmentation coefficient is determined according to an outer contour of the vehicle; In response to determining that the obstacle point is outside the third vehicle model, or the obstacle vector does not intersect the third vehicle model, determining that the collision detection result is a detection pass; In response to determining that the obstacle point is located within the third vehicle model, or determining that the obstacle vector intersects the third vehicle model, the collision detection result is determined to be detection failure.

5. The method according to claim 3, characterized in that: The step of constructing a third vehicle model in the target coordinate system according to the second vehicle model and the preset segmentation coefficient includes: Determine the cutting angle position according to the preset cutting coefficient; Cutting off four corners of the second vehicle model at the corner cutting positions to obtain the third vehicle model; Wherein, the third vehicle model is an octagonal model.

6. The method according to any one of claims 1 to 5, characterized in that In response to the obstacle model being an obstacle point, determining whether the obstacle point is located within the vehicle model includes: Divide the vehicle model into N quadrilaterals, wherein the N quadrilaterals include i parallelograms and j trapezoids, wherein N is a positive integer greater than 1, i is a positive integer greater than 1 and less than or equal to N, and j is a positive integer greater than or equal to 0 and less than N; Determine a target minimum abscissa value, a target maximum abscissa value, a target minimum ordinate value, and a target maximum ordinate value of a target quadrilateral through vertex coordinates of the target quadrilateral, wherein the target quadrilateral is any one of the N quadrilaterals; In response to determining that the horizontal coordinate of the obstacle point is greater than or equal to the minimum target horizontal coordinate value and less than or equal to the maximum target horizontal coordinate value, and the vertical coordinate of the obstacle point is greater than or equal to the minimum target vertical coordinate value and less than or equal to the maximum target vertical coordinate value, determining that the obstacle point is located within the vehicle model; Otherwise, it is determined that the obstacle point is outside the vehicle model.

7. The method according to any one of claims 1 to 5, characterized in that In response to the obstacle model being an obstacle vector, determining whether the obstacle vector intersects with the vehicle model includes: Divide the vehicle model into N quadrilaterals, wherein the N quadrilaterals include i parallelograms and j trapezoids, wherein N is a positive integer greater than 1, i is a positive integer greater than 1 and less than or equal to N, and j is a positive integer greater than or equal to 0 and less than N; Determine a target minimum abscissa value, a target maximum abscissa value, a target minimum ordinate value, and a target maximum ordinate value of a target quadrilateral through vertex coordinates of the target quadrilateral, wherein the target quadrilateral is any one of the N quadrilaterals; In response to determining that the maximum value of the horizontal coordinate of the obstacle vector is less than the target minimum value of the horizontal coordinate, and the maximum value of the vertical coordinate of the obstacle vector is less than the target minimum value of the vertical coordinate, determining that the obstacle vector does not intersect the vehicle model; or In response to determining that the minimum abscissa value of the obstacle vector is greater than the target maximum abscissa value and the minimum ordinate value of the obstacle vector is greater than the target maximum ordinate value, it is determined that the obstacle vector does not intersect the vehicle model.

8. The method according to claim 7, characterized in that The method further comprises: Acquire a target edge in the target quadrilateral, where the target edge is any edge in the target quadrilateral, and the target edge includes a first endpoint and a second endpoint; Determine that the starting point and the terminal of the obstacle vector are the third endpoint and the fourth endpoint respectively; Constructing a first vector from the first endpoint to the third endpoint, a second vector from the first endpoint to the second endpoint, and a third vector from the first endpoint to the fourth endpoint; In response to determining that a first product of a cross product of the first vector and the second vector has a different sign than a second product of a cross product of a third vector and the second vector, it is determined that the obstacle vector intersects the vehicle model.

9. The method according to claim 3, characterized in that: The obtaining of the collision depth between the vehicle and the obstacle comprises: In response to determining that the obstacle model is an obstacle point, the collision depth is the shortest distance between the obstacle point and an outer boundary of the first vehicle model; In response to determining that the obstacle model is an obstacle vector, determining a collision point between the vehicle and the obstacle, the collision point being a point in the obstacle vector that is closest to a center point of the first vehicle model; The shortest distance between the collision point and the outer boundary of the first vehicle model is determined as the collision depth.

10. A collision detection device, characterized in that: include: An acquisition module is configured to acquire vehicle configuration information, wherein the vehicle configuration information includes at least one of vehicle length, vehicle width, and axle information; A vehicle model determination module is configured to obtain position information of the vehicle in a target coordinate system, and construct a first vehicle model in the preset coordinate system according to the vehicle configuration information, the vehicle position information and a preset expansion coefficient; an obstacle model determination module, configured to obtain obstacle position information, and determine the obstacle model in the target coordinate system based on the obstacle position information, wherein the obstacle model is an obstacle point or an obstacle vector; The detection module is configured to determine that the collision detection result is a detection pass in response to determining that the obstacle point is outside the first vehicle model or the obstacle vector does not intersect the first vehicle model.

Images