A vehicle collision detection method and system

Abstract

The application provides a vehicle collision detection method and system; the vehicle collision detection method comprises the following steps: dividing the obtained obstacle information set into a first obstacle map and a second obstacle map according to a preset obstacle height; then modeling the current vehicle based on the first obstacle map and the second obstacle map, and fusing the modeling result with the first obstacle map and the second obstacle map to obtain a first collision detection model and a second collision detection model; further obtaining the distance relationship between the preset position of the current vehicle and the obstacle corresponding to the obstacle information set through the first collision detection model and / or the second collision detection model, and judging whether the current vehicle collides according to the distance relationship. The application can perform real-time and accurate collision risk analysis on different obstacle height types, improve the accuracy and efficiency of collision detection, and further protect the driving safety of the vehicle and the personal safety of the people in the vehicle.

Description

Technical Field

[0001] This application relates to the field of intelligent driving technology, and in particular to a vehicle collision detection method and system. Background Technology

[0002] With the rapid development of intelligent driving, the autonomous driving function of cars is becoming more and more common. While autonomous driving brings convenience to people, there are also some problems with poor experience, such as hitting the rearview mirror, running over the curb, or causing a collision. This makes some users afraid to use the autonomous driving function, which is not conducive to the development of intelligent driving.

[0003] Existing technologies can obtain the distance between a vehicle and an obstacle based on sensor data, and then perform collision detection analysis and early warning. However, the data transmitted by the sensors is inaccurate and delayed, which makes it impossible to perform collision detection in a timely manner. Furthermore, the sensors cannot perform corresponding collision detection for different vehicles based on the height of the obstacle, which may lead to the vehicle colliding with the obstacle during the journey, potentially causing personal injury or death in severe cases. Summary of the Invention

[0004] To address the aforementioned technical problems, this application provides a method and system for vehicle collision detection based on obstacle height.

[0005] Specifically, this application provides a vehicle collision detection method, including the following steps:

[0006] S100: Obtain a set of obstacle information within a preset range of the current vehicle, and divide the obstacle information set into a first obstacle map and a second obstacle map according to the preset obstacle height.

[0007] S200: Model the current vehicle based on the first obstacle map and the second obstacle map, and fuse the vehicle model with the corresponding obstacle map to obtain the first collision detection model and the second collision detection model respectively.

[0008] S300: Obtain the distance relationship between the current vehicle's preset position and the obstacle corresponding to the obstacle information set through the first collision detection model and / or the second collision detection model, and determine whether the current vehicle has collided based on the distance relationship.

[0009] The above method divides the obstacle map according to the obstacle height, then establishes a corresponding collision detection model, and uses the collision detection model to determine the distance relationship between the current vehicle and the obstacle, thereby obtaining the collision risk. It can perform real-time and accurate collision risk analysis for different obstacle height types, improve the accuracy and efficiency of collision detection, and further protect the driving safety of the vehicle and the personal safety of the occupants.

[0010] Step S100, which involves dividing the obstacle information set into a first obstacle map and a second obstacle map based on a preset obstacle height, includes:

[0011] The maximum lengths of the front and rear wheels of the current vehicle are calibrated, and the preset obstacle height is set based on the calibration results.

[0012] Determine whether the height of the obstacle corresponding to the obstacle information set is greater than the preset obstacle height. If it is greater, then classify the obstacle into the first obstacle map; otherwise, classify it into the second obstacle map.

[0013] The height of pre-set obstacles is determined based on the length of the vehicle's front and rear wheels, and obstacles of different heights are classified into different maps, making collision detection analysis more targeted and further improving the accuracy and efficiency of collision detection.

[0014] Step S200 includes:

[0015] The current vehicle is modeled to obtain a first vehicle model including the front and rear overhangs, and a second vehicle model removing the front and rear overhangs.

[0016] The first vehicle model and the second vehicle model are fused with the first obstacle map and the second obstacle map, respectively, to obtain the first collision detection model and the second collision detection model.

[0017] A vehicle model is obtained and integrated into the corresponding obstacle map to obtain a corresponding collision detection model for subsequent collision detection analysis.

[0018] The calibration is performed based on the maximum length of the front and rear wheels of the current vehicle, so that the corresponding model and collision detection model for each vehicle are corresponding and unique, making collision detection more personalized and intelligent.

[0019] Before performing step S300, the following are included:

[0020] Establish a first rectangular coordinate system with the geometric center of the current vehicle as the first origin, the width direction of the vehicle as the x-axis, and the length direction as the y-axis; and establish a second rectangular coordinate system with the midpoint of the rear axle of the current vehicle as the second origin, the width direction of the vehicle as the x-axis, and the length direction as the y-axis.

[0021] Establishing a first rectangular coordinate system and a second rectangular coordinate system not only allows for the digitization of the obstacle's position data, but also facilitates the subsequent determination of the first and second preset circular regions.

[0022] Step S300 includes:

[0023] S301: In the first collision detection model, obtain the initial obstacle coordinates in the first rectangular coordinate system.

[0024] S302: Calculate the distance from each obstacle to the first origin based on the initial obstacle coordinates and the coordinates of the first origin.

[0025] If the distance from at least one obstacle to the first origin is less than the first preset distance, then step S303 is executed; otherwise, step S305 is executed.

[0026] First, obstacles with collision risks are screened to narrow down the scope before proceeding to the next step of collision risk detection.

[0027] S303: Obtain the transformed obstacle coordinates of the obstacles within the first preset circular area in the second rectangular coordinate system.

[0028] The transformation of obstacle coordinates in the second rectangular coordinate system reduces the influence of the vehicle's heading angle on the obstacle coordinates, making the distance between the obstacle and the current vehicle more accurate and further improving the accuracy of collision detection.

[0029] S304: Calculate the distance from each obstacle in the first preset circular area to the second origin based on the coordinates of the transformed obstacle and the second origin.

[0030] If the distance from at least one obstacle within the first preset circular area to the second origin is less than the second preset distance, then it is determined that the current vehicle has collided; otherwise, step S305 is executed.

[0031] It should be noted that the second preset distance is usually preferably half the width of the vehicle, or the length of the rear overhang of the vehicle, or the distance from the rear axle to the front overhang of the vehicle; here the obstacles that may collide are further narrowed, so as to determine whether there is a collision risk for the current vehicle.

[0032] S305: Determined that there is no risk of collision with the current vehicle.

[0033] The first preset circular region is centered at the first origin and has a radius of the first preset distance.

[0034] Step S300 further includes:

[0035] S311: In the second collision detection model, obtain the initial obstacle coordinates in the first rectangular coordinate system.

[0036] S312: Calculate the distance from each obstacle to the first origin based on the initial obstacle coordinates and the coordinates of the first origin.

[0037] If the distance from at least one obstacle to the first origin is less than the third preset distance, then proceed to step S313; otherwise, proceed to step S315.

[0038] S313: Obtain the transformed obstacle coordinates of the obstacles within the second preset circular area in the second rectangular coordinate system.

[0039] S314: Calculate the distance from each obstacle in the second preset circular area to the second origin based on the coordinates of the transformed obstacle and the second origin.

[0040] If the distance from at least one obstacle within the second preset circular area to the second origin is less than the second preset distance, then it is determined that the current vehicle has collided; otherwise, step S315 is executed.

[0041] S315: Determined that there is no risk of collision with the current vehicle.

[0042] The second preset circular region is centered at the first origin and has a radius of the third preset distance.

[0043] Step S303 or step S313 specifically includes:

[0044] Obtain the vehicle's heading angle, the initial obstacle coordinates of obstacles within the first or second preset circular area in the first rectangular coordinate system, and the midpoint coordinates of the vehicle's rear axle in the first rectangular coordinate system.

[0045] The first included angle and the distance from the obstacle to the midpoint of the vehicle's rear axle are calculated based on the initial obstacle coordinates and the midpoint of the vehicle's rear axle. The first included angle is the angle between the line connecting the obstacle and the midpoint of the vehicle's rear axle and the perpendicular segment of the obstacle to the X-axis of the second rectangular coordinate system.

[0046] The second included angle is calculated based on the first included angle and the vehicle heading angle.

[0047] The transformed obstacle coordinates are calculated based on the distance from the obstacle to the midpoint of the rear axle of the vehicle and the second included angle.

[0048] Transforming obstacle coordinates eliminates the influence of the vehicle's heading angle, further helping to improve the accuracy of subsequent collision detection.

[0049] Based on the same concept, this application also provides a vehicle collision detection system, the system comprising:

[0050] First acquisition module: used to acquire a set of obstacle information within a preset range of the current vehicle.

[0051] Division module: used to divide the obstacle information set into a first obstacle map and a second obstacle map according to the preset obstacle height.

[0052] The second acquisition module is used to model the current vehicle based on the first obstacle map and the second obstacle map, and to fuse the vehicle model with the corresponding obstacle map to obtain the first collision detection model and the second collision detection model.

[0053] Judgment module: used to obtain the distance relationship between the current vehicle's preset position and the obstacle corresponding to the obstacle information set through the first collision detection model and / or the second collision detection model, and to determine whether the current vehicle has collided based on the distance relationship.

[0054] The second acquisition module includes:

[0055] Modeling unit: used to obtain the first vehicle model and the second vehicle model.

[0056] Fusion unit: used to fuse the first vehicle model and the second vehicle model with the first obstacle map and the second obstacle map respectively to obtain the first collision detection model and the second collision detection model.

[0057] The judgment module includes:

[0058] Establishment Unit: Used to establish a first rectangular coordinate system and a second rectangular coordinate system; the first rectangular coordinate system takes the geometric center of the current vehicle as the first origin, the width direction of the vehicle as the x-axis, and the length direction as the y-axis; the second rectangular coordinate system takes the midpoint of the rear axle of the current vehicle as the second origin, the width direction of the vehicle as the X-axis, and the length direction as the Y-axis.

[0059] Acquisition Unit: Used to acquire the initial obstacle coordinates in the first rectangular coordinate system in the first collision detection model or the second collision detection model.

[0060] First calculation unit: used to calculate the distance from each obstacle to the first origin based on the initial obstacle coordinates and the coordinates of the first origin, so as to obtain the transformed obstacle coordinates of the obstacles in the second preset circular area in the second rectangular coordinate system when the distance is less than the first preset distance or the third preset distance.

[0061] The second calculation unit is used to calculate the distance from each obstacle in the second preset circular area to the second origin based on the coordinates of the transformed obstacle and the second origin, so as to determine that the current vehicle has collided when the distance is less than the second preset distance.

[0062] The aforementioned system can perform accurate collision risk analysis for different obstacle height types, improving the accuracy of collision detection and further ensuring vehicle driving safety and the personal safety of occupants.

[0063] Compared with the prior art, the beneficial effects of this application are as follows:

[0064] This application divides the obstacle information set into a first obstacle map and a second obstacle map based on the obstacle height, and then establishes corresponding first and second collision detection models. The distance relationship between the current vehicle and the obstacle is determined through the first and / or second collision detection models, thereby obtaining the collision risk between the current vehicle and the obstacle. This application can perform accurate collision risk analysis for different obstacle height types, improving the accuracy of collision detection and further ensuring vehicle driving safety and the personal safety of occupants. It solves the technical problems in the prior art where inaccurate and delayed data transmitted by sensors prevents timely collision detection, and where sensors cannot perform corresponding collision detection for different vehicles based on obstacle height, leading to collisions between the vehicle and obstacles during driving. Attached Figure Description

[0065] Figure 1 This is a flowchart of the vehicle collision detection method described in this application.

[0066] Figure 2 for Figure 1 The flowchart of the method for collision detection using the first collision detection model is described.

[0067] Figure 3 for Figure 1 The flowchart of the collision detection method using the second collision detection model is described.

[0068] Figure 4 for Figure 1 The system framework diagram of the vehicle collision detection method is shown below. Detailed Implementation

[0069] This application provides a vehicle collision detection method and system to solve the technical problems in the prior art, which are inaccurate and inefficient due to the use of sensors to detect the distance between the vehicle and obstacles, and which cannot perform corresponding collision detection for different vehicles based on the height of the obstacle.

[0070] This application provides a vehicle collision detection method and system, the overall scheme of which is as follows:

[0071] Obtain a set of obstacle information within a preset range of the current vehicle, and determine whether the height of the obstacle corresponding to the obstacle information set is greater than a preset obstacle height. If it is greater, the obstacle is classified into the first obstacle map; otherwise, it is classified into the second obstacle map. Then, the current vehicle is modeled and fused based on the first obstacle map and the second obstacle map to obtain a first collision detection model and a second collision detection model, respectively. Then, the distance relationship between the geometric center of the current vehicle and the obstacle corresponding to the obstacle information set is obtained through the first collision detection model and / or the second collision detection model. If the distance from at least one obstacle to the geometric center is less than a first preset distance, the distance relationship between the midpoint of the rear axle of the current vehicle and the obstacle is obtained. If the distance from at least one obstacle to the midpoint of the rear axle of the current vehicle is less than a second preset distance, it is determined that the current vehicle has collided.

[0072] The following describes in further detail a vehicle collision detection method and system according to this application, with reference to specific embodiments and accompanying drawings.

[0073] Example 1:

[0074] Please see Figure 1 This application provides a vehicle collision detection method, including the following steps:

[0075] S100: Obtain a set of obstacle information within a preset range of the current vehicle, and divide the obstacle information set into a first obstacle map and a second obstacle map according to the preset obstacle height.

[0076] Step S100, which involves dividing the obstacle information set into a first obstacle map and a second obstacle map based on a preset obstacle height, includes:

[0077] The maximum lengths of the front and rear wheels of the current vehicle are calibrated, and the preset obstacle height is set based on the calibration results.

[0078] Determine whether the height of the obstacle corresponding to the obstacle information set is greater than the preset obstacle height. If it is greater, then classify the obstacle into the first obstacle map; otherwise, classify it into the second obstacle map.

[0079] Because different vehicles have different chassis heights and vehicle heights, the preset obstacle height is calibrated based on the actual vehicle, and no specific value for the preset obstacle height is limited here.

[0080] It should be noted that the first obstacle map can be considered as a non-intrusive map of the vehicle body, and the second obstacle map is a map intrusive to the vehicle body; where intrusive to the vehicle body means that the front and rear overhangs of the vehicle can be intruded due to limiters or low curbs, etc.

[0081] After the first obstacle map and the second obstacle map are divided, step S200 can be executed.

[0082] S200: Model the current vehicle based on the first obstacle map and the second obstacle map, and fuse the vehicle model with the corresponding obstacle map to obtain the first collision detection model and the second collision detection model respectively.

[0083] Step S200 includes:

[0084] The current vehicle is modeled to obtain a first vehicle model including the front and rear overhangs, and a second vehicle model removing the front and rear overhangs.

[0085] It should be noted that the vehicle model is not a 3D model, but a two-dimensional planar model of the vehicle's outline. The first vehicle model is the outline of the entire vehicle, including the front and rear overhangs, presented as a rounded rectangle. The front and rear wheels of the vehicle are respectively marked by four rectangles. The second vehicle model is a rectangular outline of the vehicle without the front and rear overhangs. The corners of this outline indicate the locations of the wheels.

[0086] The first vehicle model and the second vehicle model are fused with the first obstacle map and the second obstacle map, respectively, to obtain the first collision detection model and the second collision detection model.

[0087] The first or second collision detection model can represent the position of the obstacle in the obstacle information set relative to the corresponding vehicle model, wherein the obstacle is presented in the form of data points.

[0088] After obtaining the first collision detection model and the second collision detection model, step S300 can be executed.

[0089] S300: Obtain the distance relationship between the current vehicle's preset position and the obstacle corresponding to the obstacle information set through the first collision detection model and / or the second collision detection model, and determine whether the current vehicle has collided based on the distance relationship.

[0090] Before performing step S300, the following are included:

[0091] Establish a first rectangular coordinate system with the geometric center of the current vehicle as the first origin, the width direction of the vehicle as the x-axis, and the length direction as the y-axis; and establish a second rectangular coordinate system with the midpoint of the rear axle of the current vehicle as the second origin, the width direction of the vehicle as the x-axis, and the length direction as the y-axis.

[0092] Please see Figure 2 Step S300 includes:

[0093] S301: In the first collision detection model, obtain the initial obstacle coordinates (x, y, y) of the obstacle in the first rectangular coordinate system. i ,y i ).

[0094] S302: Based on the initial obstacle coordinates (x) i ,y i Calculate the distance L from each obstacle to the first origin using the coordinates (x0, y0) of the first origin. 0i ;in,

[0095] If the distance from at least one obstacle to the first origin is less than the first preset distance, then step S303 is executed; otherwise, step S305 is executed.

[0096] It should be noted that the first preset distance is the distance from the geometric center of the current vehicle to any corner of the vehicle. Since the geometric center of the vehicle is selected here, the distance from the geometric center to any corner of the vehicle is the same. In practical applications, it can be arbitrarily selected. For example, the distance from the geometric center of the current vehicle to the front right corner of the vehicle can be measured and defined as the first preset distance.

[0097] When vehicle collision detection methods are applied to automatic parking, the positional relationship between obstacles and the current vehicle is determined based on the distance between the vehicle's geometric center and any corner of the vehicle. This allows for the identification of obstacles that pose a certain risk of collision during automatic parking processes, such as forward movement, reversing, and turning.

[0098] S303: Obtain the transformed obstacle coordinates of the obstacles within the first preset circular area in the second rectangular coordinate system.

[0099] Wherein, the first preset circular region is centered at the first origin and has a radius of the first preset distance.

[0100] Step S303 specifically includes:

[0101] Obtain the vehicle's heading angle θ, and the initial obstacle coordinates (x, y) of the obstacles within the first preset circular area in the first rectangular coordinate system. n ,y n ), and the coordinates (x, y) of the midpoint of the rear axle of the vehicle in the first rectangular coordinate system.

[0102] Calculate the first included angle θ1 based on the initial obstacle coordinates and the midpoint coordinates of the vehicle's rear axle; and the distance L from the obstacle to the midpoint of the vehicle's rear axle.

[0103] in,

[0104] The first included angle θ1 is the angle between the line connecting the midpoint of the obstacle and the rear axle of the vehicle and the perpendicular segment of the obstacle to the X-axis of the second rectangular coordinate system.

[0105] The second included angle θ2 is calculated based on the first included angle and the vehicle heading angle, where θ2 = θ1 - θ.

[0106] Calculate the transformed obstacle coordinates (x) of the obstacle based on the distance L from the obstacle to the midpoint of the rear axle of the vehicle and the second included angle θ2. m ,y m ), where x m =L*sin(θ2), y m =L*cos(θ2).

[0107] S304: Calculate the distance from each obstacle in the first preset circular area to the second origin based on the coordinates of the transformed obstacle and the second origin.

[0108] If the distance from at least one obstacle within the first preset circular area to the second origin is less than the second preset distance, then it is determined that the current vehicle has collided; otherwise, step S305 is executed.

[0109] It should be noted that the second preset distance is usually preferably half the width of the vehicle, or the length of the rear overhang of the vehicle, or the distance from the rear axle to the front overhang of the vehicle.

[0110] When x m Less than half the width of the vehicle, or y m Less than the length of the vehicle's rear overhang, or y m If the distance from the rear axle to the front overhang is less than the distance between the rear axle and the front overhang, it is determined that the current vehicle has collided.

[0111] S305: Determined that there is no risk of collision with the current vehicle.

[0112] Example 2:

[0113] Please see Figure 3 This application also provides a modified example of collision detection for trespassable obstacles using the second collision detection model, wherein step S300 further includes:

[0114] S311: In the second collision detection model, obtain the initial obstacle coordinates in the first rectangular coordinate system.

[0115] S312: Calculate the distance from each obstacle to the first origin based on the initial obstacle coordinates and the coordinates of the first origin.

[0116] If the distance from at least one obstacle to the first origin is less than the third preset distance, then proceed to step S313; otherwise, proceed to step S315.

[0117] It should be noted that the third preset distance is the distance from the geometric center of the current vehicle to either the front axle or the rear axle of the vehicle.

[0118] S313: Obtain the transformed obstacle coordinates of the obstacles within the second preset circular area in the second rectangular coordinate system.

[0119] The second preset circular region is centered at the first origin and has a radius of the third preset distance.

[0120] Step S313 specifically includes:

[0121] Obtain the vehicle's heading angle, the initial obstacle coordinates of the obstacles within the second preset circular area in the first rectangular coordinate system, and the midpoint coordinates of the vehicle's rear axle in the first rectangular coordinate system.

[0122] Calculate the first included angle based on the initial obstacle coordinates and the midpoint coordinates of the vehicle's rear axle; and the distance from the obstacle to the midpoint of the vehicle's rear axle.

[0123] The first included angle is the angle between the line connecting the midpoint of the obstacle and the rear axle of the vehicle and the perpendicular segment of the obstacle to the X-axis of the second rectangular coordinate system.

[0124] The second included angle is calculated based on the first included angle and the vehicle heading angle.

[0125] The transformed obstacle coordinates are calculated based on the distance from the obstacle to the midpoint of the rear axle of the vehicle and the second included angle.

[0126] S314: Calculate the distance from each obstacle in the second preset circular area to the second origin based on the coordinates of the transformed obstacle and the second origin.

[0127] If the distance from at least one obstacle within the second preset circular area to the second origin is less than the second preset distance, then it is determined that the current vehicle has collided; otherwise, step S315 is executed.

[0128] S315: Determined that there is no risk of collision with the current vehicle.

[0129] Example 3:

[0130] Please see Figure 4 This application also provides a vehicle collision detection system, the system comprising:

[0131] First acquisition module: used to acquire a set of obstacle information within a preset range of the current vehicle.

[0132] In one feasible implementation, the obstacle information set can be acquired through target sensors, which can be sensors corresponding to LiDAR and stereo cameras. The LiDAR can be set on both sides of the bottom of the vehicle, making it symmetrical from left to right or front to back, to acquire obstacle information that is far away, low in position, and requires high detection accuracy. The stereo camera is set on the top of the vehicle to acquire obstacle information that is close to the vehicle and high in position. Combining the LiDAR and stereo camera makes the acquired obstacle information set more comprehensive and accurate, which helps to make subsequent collision detection more accurate and prevents the occurrence of collision accidents due to missed obstacle detection.

[0133] Division module: used to divide the obstacle information set into a first obstacle map and a second obstacle map according to the preset obstacle height.

[0134] Because different vehicles have different chassis heights and vehicle heights, the preset obstacle height is calibrated based on the actual vehicle and is not limited here.

[0135] The second acquisition module is used to model the current vehicle based on the first obstacle map and the second obstacle map, and to fuse the vehicle model with the corresponding obstacle map to obtain the first collision detection model and the second collision detection model.

[0136] The second acquisition module includes:

[0137] Modeling unit: used to obtain the first vehicle model and the second vehicle model.

[0138] Fusion unit: used to fuse the first vehicle model and the second vehicle model with the first obstacle map and the second obstacle map respectively to obtain the first collision detection model and the second collision detection model.

[0139] Judgment module: used to obtain the distance relationship between the current vehicle's preset position and the obstacle corresponding to the obstacle information set through the first collision detection model and / or the second collision detection model, and to determine whether the current vehicle has collided based on the distance relationship.

[0140] The judgment module includes:

[0141] Establishment Unit: Used to establish a first rectangular coordinate system and a second rectangular coordinate system; the first rectangular coordinate system takes the geometric center of the current vehicle as the first origin, the width direction of the vehicle as the x-axis, and the length direction as the y-axis; the second rectangular coordinate system takes the midpoint of the rear axle of the current vehicle as the second origin, the width direction of the vehicle as the X-axis, and the length direction as the Y-axis.

[0142] Acquisition Unit: Used to acquire the initial obstacle coordinates in the first rectangular coordinate system in the first collision detection model or the second collision detection model.

[0143] First calculation unit: used to calculate the distance from each obstacle to the first origin based on the initial obstacle coordinates and the coordinates of the first origin, so as to obtain the transformed obstacle coordinates of the obstacles in the second preset circular area in the second rectangular coordinate system when the distance is less than the first preset distance or the third preset distance.

[0144] The second calculation unit is used to calculate the distance from each obstacle in the second preset circular area to the second origin based on the coordinates of the transformed obstacle and the second origin, so as to determine that the current vehicle has collided when the distance is less than the second preset distance.

[0145] In summary, this application provides a vehicle collision detection method and system; it divides the obstacle map according to the obstacle height, then establishes a corresponding collision detection model, and uses the collision detection model to determine the distance relationship between the current vehicle and the obstacle, thereby obtaining the collision risk; it can perform real-time and accurate collision risk analysis for different obstacle height types, improving the accuracy and efficiency of collision detection, and further ensuring the driving safety of the vehicle and the personal safety of the occupants.

[0146] Although exemplary embodiments have been described herein with reference to the accompanying drawings, it should be understood that the above exemplary embodiments are merely illustrative and are not intended to limit the scope of this application. Various changes and modifications can be made therein by those skilled in the art without departing from the scope and spirit of this application. All such changes and modifications are intended to be included within the scope of this application as claimed in the appended claims.

[0147] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0148] In the several embodiments provided in this application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another device, or some features may be ignored or not executed.

[0149] The various component embodiments of this application can be implemented in hardware, or as software modules running on one or more processors, or a combination thereof. Those skilled in the art will understand that microprocessors or digital signal processors (DSPs) can be used in practice to implement some or all of the functions of some modules according to the embodiments of this application. This application can also be implemented as an apparatus program (e.g., a computer program and computer program product) for performing part or all of the methods described herein. Such an implementation of this application can be stored on a computer-readable medium, or can be in the form of one or more signals. Such signals can be downloaded from an Internet website, provided on a carrier signal, or provided in any other form.

[0150] It should be noted that, in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0151] Although the description of this application has been made in conjunction with the specific embodiments described above, it will be apparent to those skilled in the art that many substitutions, modifications, and variations can be made based on the foregoing. Therefore, all such substitutions, modifications, and variations are included within the spirit and scope of the appended claims.

Claims

1. A vehicle collision detection method characterized by, The method comprises the following steps: S100: obtaining an obstacle information set within a preset range of a current vehicle, and dividing the obstacle information set into a first obstacle map and a second obstacle map according to a preset obstacle height; S200: modeling the current vehicle based on the first obstacle map and the second obstacle map, and fusing the vehicle model with the corresponding obstacle map to obtain a first collision detection model and a second collision detection model respectively; S300: establishing a first rectangular coordinate system with a geometric center of the current vehicle as a first origin, a width direction of the vehicle as an x-axis, and a length direction as a y-axis, and establishing a second rectangular coordinate system with a midpoint of a rear axle of the current vehicle as a second origin, the width direction of the vehicle as an X-axis, and the length direction as a Y-axis; obtaining a distance relationship between a preset position of the current vehicle and obstacles corresponding to the obstacle information set through the first collision detection model and / or the second collision detection model, and determining whether the current vehicle collides according to the distance relationship; The step S300 comprises: S301: in the first collision detection model, obtaining initial obstacle coordinates of the obstacles in the first rectangular coordinate system; S302: calculating distances from the initial obstacle coordinates to the first origin according to the coordinates of the first origin; If the distance from at least one obstacle to the first origin is less than a first preset distance, step S303 is executed; otherwise, step S305 is executed; S303: obtaining transformed obstacle coordinates of the obstacles in a first preset circular region in the second rectangular coordinate system; S304: calculating distances from the transformed obstacle coordinates to the second origin according to the coordinates of the second origin; If the distance from at least one obstacle in the first preset circular region to the second origin is less than a second preset distance, it is determined that the current vehicle collides; otherwise, step S305 is executed; S305: determining that the current vehicle has no collision risk; The first preset circular region has the first origin as a center and the first preset distance as a radius.

2. The vehicle collision detection method according to claim 1, characterized by, In the step S100, the obstacle information set is divided into the first obstacle map and the second obstacle map according to the preset obstacle height, which comprises: respectively calibrating maximum lengths of front wheels and rear wheels of the current vehicle, and setting a preset obstacle height according to the calibration results; determining whether heights of obstacles corresponding to the obstacle information set are greater than the preset obstacle height, if yes, the obstacles are divided into the first obstacle map; otherwise, the obstacles are divided into the second obstacle map.

3. The vehicle collision detection method according to claim 1, characterized by, The step S200 comprises: modeling the current vehicle to obtain a first vehicle model including front and rear suspensions of the vehicle, and a second vehicle model without the front and rear suspensions of the vehicle; The first vehicle model and the second vehicle model are fused with the first obstacle map and the second obstacle map respectively to obtain the first collision detection model and the second collision detection model.

4. The vehicle collision detection method according to claim 1, characterized by, The step S300 further comprises: S311: in the second collision detection model, obtaining initial obstacle coordinates of the obstacles in the first rectangular coordinate system; S312: calculate distances from each obstacle to the first origin according to the initial obstacle coordinates and the coordinates of the first origin; if the distance from at least one obstacle to the first origin is less than a third preset distance, execute step S313; otherwise, execute step S315; S313: obtain transformed obstacle coordinates of obstacles in a second preset circular region in the second rectangular coordinate system; S314: calculate distances from each obstacle in the second preset circular region to the second origin according to the transformed obstacle coordinates and the coordinates of the second origin; if the distance from at least one obstacle in the second preset circular region to the second origin is less than a second preset distance, determine that the current vehicle is in collision; otherwise, execute step S315; S315: determine that the current vehicle is not at risk of collision; the second preset circular region has the first origin as the center and the third preset distance as the radius.

5. The vehicle collision detection method according to claim 4, characterized by, The step S303 or step S313 specifically includes: obtaining a vehicle heading angle, initial obstacle coordinates of obstacles in the first preset circular region or the second preset circular region in the first rectangular coordinate system, and a midpoint coordinate of a rear axle of the vehicle in the first rectangular coordinate system; calculate a first included angle and a distance from the obstacle to the midpoint of the rear axle of the vehicle according to the initial obstacle coordinates and the midpoint coordinate of the rear axle of the vehicle; the first included angle is an included angle between a line connecting the obstacle and the midpoint of the rear axle of the vehicle and a perpendicular segment of the obstacle and an X-axis of the second rectangular coordinate system; calculate a second included angle according to the first included angle and the vehicle heading angle; calculate transformed obstacle coordinates of the obstacle according to the distance from the obstacle to the midpoint of the rear axle of the vehicle and the second included angle.

6. A system employing the vehicle collision detection method according to any one of claims 1 to 5, characterized by The system includes: a first obtaining module: configured to obtain a set of obstacle information within a preset range of a current vehicle; a division module: configured to divide the set of obstacle information into a first obstacle map and a second obstacle map according to a preset obstacle height; a second obtaining module: configured to model the current vehicle based on the first obstacle map and the second obstacle map, and fuse the vehicle model with the corresponding obstacle map to obtain a first collision detection model and a second collision detection model; a judgment module: configured to obtain a distance relationship between a preset position of the current vehicle and obstacles corresponding to the set of obstacle information by the first collision detection model and / or the second collision detection model, and determine whether the current vehicle is in collision according to the distance relationship.

7. The system of claim 6, wherein, The second obtaining module includes: a modeling unit: configured to obtain a first vehicle model and a second vehicle model; a fusion unit: configured to fuse the first vehicle model and the second vehicle model with the first obstacle map and the second obstacle map respectively to obtain the first collision detection model and the second collision detection model.

8. The system of claim 7, wherein, The judgment module includes: an establishing unit: configured to establish a first rectangular coordinate system and a second rectangular coordinate system; the first rectangular coordinate system takes a geometric center of the current vehicle as a first origin, a width direction of the vehicle as an x-axis, and a length direction of the vehicle as a y-axis; the second rectangular coordinate system takes a midpoint of a rear axle of the current vehicle as a second origin, a width direction of the vehicle as an X-axis, and a length direction of the vehicle as a Y-axis; The acquisition unit is configured to acquire initial obstacle coordinates of the obstacles in the first rectangular coordinate system in the first collision detection model or the second collision detection model. The first calculation unit is configured to calculate distances from the obstacles to a first origin according to the initial obstacle coordinates and coordinates of the first origin, and acquire transformed obstacle coordinates of the obstacles in the second rectangular coordinate system in a second preset circular region when the distances are less than a first preset distance or a third preset distance. The second calculation unit is configured to calculate distances from the obstacles in the second preset circular region to a second origin according to the transformed obstacle coordinates and coordinates of the second origin, and determine that the current vehicle collides when the distances are less than a second preset distance.

Images