Collision detection method, device, electronic device and storage medium

Abstract

The present application provides a collision detection method, device, electronic device and storage medium, the method comprising: obtaining the motion trajectory of at least one obstacle relative to the current vehicle; establishing a trailer motion model, wherein the trailer motion model is used to simulate the motion trajectory of the tractor and trailer; performing feature matching between at least one obstacle and the trailer motion model, and obtaining at least one matching target obstacle, wherein each target obstacle in the at least one target obstacle represents a trailer; and labeling the collision area of ​​each target obstacle to obtain the collision area. The present application can predict the collision area of ​​the trailer during movement.

Description

Technical Field

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

[0002] Identifying obstacles and effectively avoiding collisions in autonomous vehicles is a necessary condition for autonomous driving. The main difficulties in trailer motion posture prediction and collision detection are as follows:

[0003] First, trailers / articulated trucks generally consist of two parts: the tractor part and the trailer part. It is difficult to predict the motion posture and trajectory. Second, trailers / articulated trucks are mostly large vehicles with high danger, and they need to be accurate when used as obstacles for collision detection risk. (CN 114661039 A) A method for determining the posture and driving of a logistics vehicle and its trailer provides a method for obtaining the posture information and chassis information of the trailer through the vehicle sensor, and bringing the information into the kinematic model of the logistics vehicle to obtain the posture information of the trailer, and establish the drivable area of ​​the vehicle according to the trailer and the trailer for collision detection. This method is mainly based on the collision and trailer posture determination when the vehicle is a trailer vehicle, and does not handle the identification and collision detection processing mechanism of obstacles as trailers or articulated trucks. (CN 113329927 A) A method for obtaining trailer posture data using laser radar is proposed in trailer tracking based on laser radar. This patent is mainly used to detect the posture of the trailer for tractor alignment or other information, and cannot be used to identify the entire motion posture of a trailer vehicle or an articulated vehicle. Summary of the invention

[0004] In view of this, embodiments of the present application provide a collision detection method, device, electronic device, and storage medium, which can predict the collision area of ​​a trailer during movement.

[0005] The technical solution of the embodiment of the present application is implemented as follows:

[0006] In a first aspect, an embodiment of the present application provides a collision detection method, comprising the following steps:

[0007] Obtaining a motion trajectory of at least one obstacle relative to the current vehicle;

[0008] Establishing a trailer motion model, wherein the trailer motion model is used to simulate the motion trajectory of the tractor and the trailer;

[0009] Performing feature matching between the at least one obstacle and the trailer motion model, and acquiring at least one matching target obstacle, wherein each target obstacle in the at least one target obstacle represents a trailer;

[0010] The collision area of ​​each target obstacle is labeled to obtain the collision area.

[0011] In a possible implementation manner, obtaining a motion trajectory of at least one obstacle relative to the current vehicle includes:

[0012] Acquiring point cloud information of the at least one obstacle through a vehicle-mounted radar sensor, wherein the point cloud information uses the current vehicle as a reference object;

[0013] Based on the point cloud information, calibrate the outline of the at least one obstacle by using a rectangular calibration frame to obtain at least one rectangular calibration frame;

[0014] Obtain a motion trajectory of each rectangular calibration frame in the at least one rectangular calibration frame relative to the current vehicle.

[0015] In a possible implementation manner, obtaining a motion trajectory of each rectangular calibration frame in the at least one rectangular calibration frame relative to the current vehicle includes:

[0016] For each rectangular calibration frame, collect the rectangular calibration frames at two consecutive moments, and take the intersection of the center lines of the rectangular calibration frames at the two moments as the centroid, wherein the center line is the center line along the direction of movement;

[0017] The center of mass position of the rectangular calibration frame at n moments is continuously obtained, and the center of mass position at n moments is used as the motion trajectory, wherein n is a positive integer.

[0018] In a possible implementation, establishing the trailer motion model includes:

[0019] A rectangular coordinate system is established, wherein the speed of the tractor is v, the angle between the moving direction of the tractor and the horizontal axis is θ, the trailer is hinged to the tractor through a hinge point, the angle between the moving direction of the trailer and the horizontal axis is α, the length of the trailer is L, and the angle between the extension line of the moving direction of the trailer from the hinge point and the tractor is theta;

[0020] Determine the motion step length of the tractor as S0=v*t0, where t0 is the motion sampling frequency, t2=t1+t0, t1 is the initial time of a sampling frequency, and t2 is the end time of a sampling frequency, then:

[0021] θ'=θt2-θt1;

[0022] α'=αt2-αt1;

[0023] And establish the trailer motion model:

[0024] theta'=S0*sinθt1 / L+θ';

[0025] theta' = θ' - α';

[0026] Wherein, θ' represents the angle change value of θ, α' represents the angle change value of α, and theta' represents the angle change value of theta.

[0027] In a possible implementation manner, performing feature matching between the at least one obstacle and the trailer motion model and acquiring at least one matching target obstacle includes:

[0028] Detecting whether there are two intersecting obstacles among the at least one obstacle at the same time;

[0029] When there are two intersecting obstacles, the center lines of the two intersecting obstacles along the trajectory direction are obtained respectively, and the intersection of the two center lines is used as a hinge point, and the two intersecting obstacles are used as a target obstacle.

[0030] In a possible implementation manner, the labeling process of the collision area of ​​each target obstacle to obtain the collision area includes:

[0031] The target obstacle is subjected to convex optimization processing to obtain a polygon capable of enveloping the target obstacle, wherein the convex polygon is a convex polygon.

[0032] In a possible implementation, the method further includes:

[0033] Based on the collision area, a driving route of the current vehicle is formulated, or based on the collision area, the collision area is displayed on a vehicle navigation interface, and an alarm is issued when the distance between the current vehicle and the collision area is less than a preset distance threshold.

[0034] In a second aspect, an embodiment of the present application further provides a collision detection device, the device comprising:

[0035] An acquisition module, used to acquire a motion trajectory of at least one obstacle relative to the current vehicle;

[0036] An establishing module, used for establishing a trailer motion model, wherein the trailer motion model is used for simulating the motion trajectory of the tractor and the trailer;

[0037] A matching module, configured to perform feature matching between the at least one obstacle and the trailer motion model, and obtain at least one matched target obstacle, wherein each of the at least one target obstacle represents a trailer;

[0038] The labeling module is used to label the collision area of ​​each target obstacle to obtain the collision area.

[0039] In a third aspect, an embodiment of the present application further provides an electronic device, comprising: a processor, a storage medium and a bus, wherein the storage medium stores machine-readable instructions executable by the processor, and when the electronic device is running, the processor communicates with the storage medium through the bus, and the processor executes the machine-readable instructions to execute the collision detection method described in any one of the first aspects.

[0040] In a fourth aspect, an embodiment of the present application further provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the collision detection method described in any one of the first aspects is executed.

[0041] The embodiments of the present application have the following beneficial effects:

[0042] Through the obstacle point cloud information obtained by radar, the motion trajectory, contour features, and posture information of each obstacle are extracted. Through the kinematic model of the trailer, the trailer vehicle in the obstacle is extracted, and the outer contour of the trailer for collision detection is obtained based on the extracted trailer vehicle features. Then, the collision contour of the vehicle at each trajectory point is generated through the own vehicle trajectory, and then the trailer contour is intersected with the contour of each trajectory point of the vehicle to determine whether the vehicle and the trailer collide and the position of the vehicle at the time of collision. The trailer vehicle in the obstacle detected by the autonomous driving vehicle can be effectively identified; and by processing the outer contours of the trailer and the trailer to obtain the collision outer contour of the trailer, the collision detection effect in the blind area of ​​the large trailer vehicle is improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for use in the embodiments will be briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present application and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.

[0044] Figure 1 It is a flowchart of steps S101-S104 provided in an embodiment of the present application;

[0045] Figure 2 It is a flowchart of steps S1011-S1013 provided in an embodiment of the present application;

[0046] Figure 3 It is a flowchart of steps S10131-S10132 provided in an embodiment of the present application;

[0047] Figure 4 It is a flowchart of steps S1031-S1032 provided in an embodiment of the present application;

[0048] Figure 5 is a schematic diagram of the structure of a collision detection device provided in an embodiment of the present application;

[0049] Figure 6 It is a schematic diagram of the composition structure of an electronic device provided in an embodiment of the present application;

[0050] Figure 7 is a schematic diagram of the centroid position provided in an embodiment of the present application;

[0051] Figure 8 is a schematic diagram of a trailer motion model provided in an embodiment of the present application;

[0052] Fig. 9 is a schematic diagram of a hinge point provided in an embodiment of the present application;

[0053] Fig.10 It is a schematic diagram of collision area marking provided in an embodiment of the present application. DETAILED DESCRIPTION

[0054] To make the purpose, technical scheme and advantages of the embodiments of the present application clearer, the technical scheme in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. It should be understood that the drawings in the present application only serve the purpose of explanation and description and are not used to limit the scope of protection of the present application. In addition, it should be understood that the schematic drawings are not drawn in real proportion. The flowchart used in this application shows the operations implemented according to some embodiments of the present application. It should be understood that the operations of the flowchart can be implemented out of sequence, and the steps without logical context can be reversed in order or implemented simultaneously. In addition, those skilled in the art can add one or more other operations to the flowchart under the guidance of the content of the present application, or remove one or more operations from the flowchart.

[0055] In the following description, reference is made to “some embodiments”, which describe a subset of all possible embodiments, but it will be understood that “some embodiments” may be the same subset or different subsets of all possible embodiments and may be combined with each other without conflict.

[0056] In addition, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. The components of the embodiments of the present application described and shown in the drawings here can be arranged and designed in various configurations. Therefore, the following detailed description of the embodiments of the present application provided in the drawings is not intended to limit the scope of the application claimed for protection, but merely represents the selected embodiments of the present application. Based on the embodiments of the present application, all other embodiments obtained by those skilled in the art without making creative work belong to the scope of protection of the present application.

[0057] In the following description, the terms "first\second\third" involved are merely used to distinguish similar objects and do not represent a specific ordering of the objects. It can be understood that "first\second\third" can be interchanged with a specific order or sequence where permitted, so that the embodiments of the present application described herein can be implemented in an order other than that illustrated or described herein.

[0058] It should be noted that the term "comprising" will be used in the embodiments of the present application to indicate the existence of the features declared thereafter, but does not exclude the addition of other features.

[0059] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art to which this application belongs. The terms used herein are for the purpose of describing the embodiments of this application and are not intended to limit this application.

[0060] See also Figure 1 , Figure 1 is a flow chart of steps S101-S104 of the collision detection method provided in the embodiment of the present application, which will be combined with Figure 1 Steps S101-S104 are shown for explanation.

[0061] Step S101, obtaining a motion trajectory of at least one obstacle relative to the current vehicle;

[0062] Step S102, establishing a trailer motion model, wherein the trailer motion model is used to simulate the motion trajectory of the tractor and the trailer;

[0063] Step S103, performing feature matching between the at least one obstacle and the trailer motion model, and acquiring at least one matching target obstacle, wherein each target obstacle in the at least one target obstacle represents a trailer;

[0064] Step S104: labeling the collision area of ​​each target obstacle to obtain the collision area.

[0065] The above-mentioned collision detection method extracts the motion trajectory, contour features, and position and posture information of each obstacle through the obstacle point cloud information obtained by the radar. The trailer vehicle in the obstacle is extracted through the kinematic model of the trailer, and the outer contour of the trailer for collision detection is obtained based on the extracted trailer vehicle features. The collision contour of the vehicle at each trajectory point is then generated through the trajectory of the vehicle. The contour of the trailer is then intersected with the contour of each trajectory point of the vehicle to determine whether the vehicle and the trailer collide and the position of the vehicle at the time of collision. The trailer vehicle in the obstacle detected by the autonomous driving vehicle can be effectively identified; and by processing the outer contours of the trailer and the trailer to obtain the collision outer contour of the trailer, the collision detection effect in the blind spot of the large vehicle of the trailer is improved.

[0066] The above exemplary steps of the embodiments of the present application are described below respectively.

[0067] In step S101, a motion trajectory of at least one obstacle relative to the current vehicle is obtained.

[0068] In some embodiments, see Figure 2 , Figure 2 is a flowchart of steps S1011-S1013 provided in an embodiment of the present application, Figure 1 The illustrated step S101 can be implemented through steps S1011 - S1013 , which will be described in conjunction with each step.

[0069] In step S1011, point cloud information of the at least one obstacle is acquired by a vehicle-mounted radar sensor, wherein the point cloud information uses the current vehicle as a reference.

[0070] In step S1012, based on the point cloud information, the outline of the at least one obstacle is calibrated by a rectangular calibration frame to obtain at least one rectangular calibration frame.

[0071] In step S1013, a motion trajectory of each rectangular calibration frame in the at least one rectangular calibration frame relative to the current vehicle is obtained.

[0072] In some embodiments, see Figure 3 , Figure 3 is a flowchart of steps S10131-S10132 provided in an embodiment of the present application, Figure 2 The illustrated step S1013 can be implemented through steps S10131 - S10132 , which will be described in conjunction with each step.

[0073] In step S10131, for each rectangular calibration frame, the rectangular calibration frames at two consecutive moments are collected, and the intersection of the center lines of the rectangular calibration frames at the two moments is taken as the centroid, wherein the center line is the center line along the movement direction.

[0074] In step S10132, the centroid position of the rectangular calibration frame at n moments is continuously obtained, and the centroid position at n moments is used as the motion trajectory, where n is a positive integer.

[0075] Here, the point cloud information of the obstacle is first obtained from the radar sensor. The point cloud information is the coordinates relative to the position of the vehicle.

[0076] Secondly, the obstacle information is calibrated through a rectangular calibration box to calibrate its outline. The outline needs to ensure that the point cloud information of the obstacle is a minimum rectangular box within the rectangular calibration box. The outer contour of the rectangular calibration box is represented by the four vertices of the rectangle; the calibration box can be obtained by connecting these four vertices in sequence.

[0077] Finally, get the centroid position of each rectangular calibration frame. This centroid position is the centroid position of each obstacle. Figure 7 , Figure 7 Schematic diagram of the centroid position provided in the embodiment of the present application, using one obstacle as a schematic diagram for illustration.

[0078] 1) Collect the rectangular calibration frame at two consecutive moments and obtain the center line of the rectangular calibration frame (along the direction of movement). The intersection of the center lines at two consecutive moments is the center of mass position.

[0079] 2) By analogy, we can obtain the center of mass position at n consecutive moments, that is, the movement trajectory of the obstacle

[0080] 3) The direction and position information of the obstacle can be obtained based on the direction of the vehicle and the direction of the calibration frame. The position and direction of the vehicle are obtained through positioning information.

[0081] 4) Follow steps 1), 2), and 3) to obtain the motion trajectory and orientation information of each obstacle detected.

[0082] In step S102, a trailer motion model is established, wherein the trailer motion model is used to simulate the motion trajectories of the tractor and the trailer.

[0083] In some embodiments, establishing the trailer motion model includes:

[0084] A rectangular coordinate system is established, wherein the speed of the tractor is v, the angle between the moving direction of the tractor and the horizontal axis is θ, the trailer is hinged to the tractor through a hinge point, the angle between the moving direction of the trailer and the horizontal axis is α, the length of the trailer is L, and the angle between the extension line of the moving direction of the trailer from the hinge point and the tractor is theta;

[0085] Determine the motion step length of the tractor as S0=v*t0, where t0 is the motion sampling frequency, t2=t1+t0, t1 is the initial time of a sampling frequency, and t2 is the end time of a sampling frequency, then:

[0086] θ'=θt2-θt1;

[0087] α'=αt2-αt1;

[0088] And establish the trailer motion model:

[0089] theta'=S0*sinθt1 / L+θ';

[0090] theta' = θ' - α';

[0091] Wherein, θ' represents the angle change value of θ, α' represents the angle change value of α, and theta' represents the angle change value of theta.

[0092] See also Figure 8 , Figure 8 : is a schematic diagram of a trailer motion model provided by an embodiment of the present application. As shown in the figure, in a plane rectangular coordinate system, the horizontal axis is the X axis, the vertical axis is the Y axis, the speed of the tractor is v, the angle between the moving direction of the tractor and the horizontal axis is θ, the trailer is hinged to the tractor through a hinge point, the angle between the moving direction of the trailer and the horizontal axis is α, the length of the trailer is L, and the angle between the extension line of the moving direction of the trailer from the hinge point and the tractor is theta;

[0093] Determine the motion step length of the tractor as S0=v*t0, where t0 is the motion sampling frequency, t2=t1+t0, t1 is the initial time of a sampling frequency, and t2 is the end time of a sampling frequency, then:

[0094] θ'=θt2-θt1;

[0095] α'=αt2-αt1;

[0096] The motion and position orientation information of the two obstacles must satisfy the following two formulas:

[0097] theta'=S0*sinθt1 / L+θ';

[0098] theta' = θ' - α';

[0099] Wherein, θ' represents the angle change value of θ, α' represents the angle change value of α, and theta' represents the angle change value of theta.

[0100] In step S103, feature matching is performed between the at least one obstacle and the trailer motion model, and at least one matching target obstacle is acquired, wherein each target obstacle in the at least one target obstacle represents a trailer.

[0101] In some embodiments, see Figure 4 , Figure 4 is a flowchart of steps S1031-S1032 provided in an embodiment of the present application, Figure 1 The illustrated step S103 can be implemented through steps S1031 - S1032 , which will be described in conjunction with each step.

[0102] In step S1031, it is detected whether there are two intersecting obstacles among the at least one obstacle at the same time.

[0103] In step S1032, when there are two intersecting obstacles, the center lines of the two intersecting obstacles along the trajectory direction are obtained respectively, and the intersection of the two center lines is used as a hinge point, and the two intersecting obstacles are used as a target obstacle.

[0104] Here, it is detected whether the two obstacles intersect at the same time: that is, whether the rectangular calibration frames of the two obstacles intersect (obtained by whether each edge of the obstacle intersects, and each edge and the line segment connecting two consecutive vertices).

[0105] If there is an intersection, the hinge point of the two obstacles is obtained. The following is a method for obtaining the hinge point: obtain the center lines of the two intersecting obstacles along the trajectory direction respectively, and the intersection of the two center lines is the hinge point, see Fig. 9 , Fig. 9 is a schematic diagram of a hinge point provided in an embodiment of the present application, Fig. 9 The middle intersection point is the hinge point of the two obstacles.

[0106] Then the obstacles are matched in pairs to see whether they satisfy the kinematic model of the trailer. If so, they are marked as trailers.

[0107] Finally, repeat the above steps until all obstacles are traversed.

[0108] In step S104, the collision area of ​​each target obstacle is labeled to obtain a collision area.

[0109] In some embodiments, the labeling process of the collision area of ​​each target obstacle to obtain the collision area includes:

[0110] The target obstacle is subjected to convex optimization processing to obtain a polygon capable of enveloping the target obstacle, wherein the convex polygon is a convex polygon.

[0111] See also Fig.10 , Fig.10 is a schematic diagram of the collision area marking provided in the embodiment of the present application, such as Fig.10 As shown in the figure, the four points of the calibration box of the trailer and the trailer are marked, the four vertices of the trailer are ABCD, and the four vertices of the trailer are EFGH. The trailer is convexly optimized to obtain the collision outer contour of the trailer, and the polygon that can envelop the trailer and the trailer is obtained, that is, the convex polygon of the continuous vertices of AEBFGD in the figure below. According to the trajectory of the vehicle, a rectangular calibration box of the vehicle is generated for each trajectory point, and the rectangular calibration box of the vehicle at each trajectory point is detected to see whether it intersects with the polygonal outer contour of the trailer. If they intersect, there will be a collision at the location of the trajectory point.

[0112] In some embodiments, the method further comprises:

[0113] Based on the collision area, a driving route of the current vehicle is formulated, or based on the collision area, the collision area is displayed on a vehicle navigation interface, and an alarm is issued when the distance between the current vehicle and the collision area is less than a preset distance threshold.

[0114] Here, the driving route of the current vehicle can be formulated for unmanned driving based on the obtained collision area to prevent collision, or, in manual driving state, based on the collision area, the collision area is displayed on the vehicle navigation interface, and when the distance between the current vehicle and the collision area is less than a preset distance threshold, an alarm is issued to alert the driver.

[0115] In summary, the embodiments of the present application have the following beneficial effects:

[0116] Through the obstacle point cloud information obtained by radar, the motion trajectory, contour features, and posture information of each obstacle are extracted. Through the kinematic model of the trailer, the trailer vehicle in the obstacle is extracted, and the outer contour of the trailer for collision detection is obtained based on the extracted trailer vehicle features. Then, the collision contour of the vehicle at each trajectory point is generated through the own vehicle trajectory, and then the trailer contour is intersected with the contour of each trajectory point of the vehicle to determine whether the vehicle and the trailer collide and the position of the vehicle at the time of collision. The trailer vehicle in the obstacle detected by the autonomous driving vehicle can be effectively identified; and by processing the outer contours of the trailer and the trailer to obtain the collision outer contour of the trailer, the collision detection effect in the blind area of ​​the large trailer vehicle is improved.

[0117] Based on the same inventive concept, an embodiment of the present application also provides a collision detection device corresponding to the collision detection method in the first embodiment. Since the principle of solving the problem by the device in the embodiment of the present application is similar to the above-mentioned collision detection method, the implementation of the device can refer to the implementation of the method, and the repeated parts will not be repeated.

[0118] like Figure 5 As shown, Figure 5 : is a schematic diagram of the structure of a collision detection device 500 provided in an embodiment of the present application. The collision detection device 500 includes:

[0119] An acquisition module 501 is used to acquire a motion trajectory of at least one obstacle relative to the current vehicle;

[0120] Establishing module 502, for establishing a trailer motion model, wherein the trailer motion model is used to simulate the motion trajectory of the tractor and the trailer;

[0121] A matching module 503 is used to perform feature matching between the at least one obstacle and the trailer motion model, and obtain at least one matching target obstacle, wherein each target obstacle in the at least one target obstacle represents a trailer;

[0122] The labeling module 504 is used to label the collision area of ​​each target obstacle to obtain the collision area.

[0123] Those skilled in the art should understand that Figure 5 The implementation functions of each unit in the collision detection device 500 shown can be understood by referring to the relevant description of the aforementioned collision detection method. Figure 5 The functions of each unit in the collision detection device 500 shown may be implemented by a program running on a processor, or may be implemented by a specific logic circuit.

[0124] In a possible implementation, the acquisition module acquires a motion trajectory of at least one obstacle relative to the current vehicle, including:

[0125] Acquiring point cloud information of the at least one obstacle through a vehicle-mounted radar sensor, wherein the point cloud information uses the current vehicle as a reference object;

[0126] Based on the point cloud information, calibrate the outline of the at least one obstacle by using a rectangular calibration frame to obtain at least one rectangular calibration frame;

[0127] Obtain a motion trajectory of each rectangular calibration frame in the at least one rectangular calibration frame relative to the current vehicle.

[0128] In a possible implementation manner, the acquisition module 501 acquires the motion trajectory of each rectangular calibration frame in the at least one rectangular calibration frame relative to the current vehicle, including:

[0129] For each rectangular calibration frame, collect the rectangular calibration frames at two consecutive moments, and take the intersection of the center lines of the rectangular calibration frames at the two moments as the centroid, wherein the center line is the center line along the direction of movement;

[0130] The center of mass position of the rectangular calibration frame at n moments is continuously obtained, and the center of mass position at n moments is used as the motion trajectory, wherein n is a positive integer.

[0131] In a possible implementation, the building module 502 builds a trailer motion model, including:

[0132] A rectangular coordinate system is established, wherein the speed of the tractor is v, the angle between the moving direction of the tractor and the horizontal axis is θ, the trailer is hinged to the tractor through a hinge point, the angle between the moving direction of the trailer and the horizontal axis is α, the length of the trailer is L, and the angle between the extension line of the moving direction of the trailer from the hinge point and the tractor is theta;

[0133] Determine the motion step length of the tractor as S0=v*t0, where t0 is the motion sampling frequency, t2=t1+t0, t1 is the initial time of a sampling frequency, and t2 is the end time of a sampling frequency, then:

[0134] θ'=θt2-θt1;

[0135] α'=αt2-αt1;

[0136] And establish the trailer motion model:

[0137] theta'=S0*sinθt1 / L+θ';

[0138] theta' = θ' - α';

[0139] Wherein, θ' represents the angle change value of θ, α' represents the angle change value of α, and theta' represents the angle change value of theta.

[0140] In a possible implementation manner, the matching module 503 performs feature matching on the at least one obstacle and the trailer motion model, and obtains at least one matching target obstacle, including:

[0141] Detecting whether there are two intersecting obstacles among the at least one obstacle at the same time;

[0142] When there are two intersecting obstacles, the center lines of the two intersecting obstacles along the trajectory direction are obtained respectively, and the intersection of the two center lines is used as a hinge point, and the two intersecting obstacles are used as a target obstacle.

[0143] In a possible implementation, the labeling module 504 labels the collision area of ​​each target obstacle to obtain the collision area, including:

[0144] The target obstacle is subjected to convex optimization processing to obtain a polygon capable of enveloping the target obstacle, wherein the convex polygon is a convex polygon.

[0145] In a possible implementation, the marking module 504 further includes:

[0146] Based on the collision area, a driving route of the current vehicle is formulated, or based on the collision area, the collision area is displayed on a vehicle navigation interface, and an alarm is issued when the distance between the current vehicle and the collision area is less than a preset distance threshold.

[0147] The above-mentioned collision detection device extracts the motion trajectory, contour features, and posture information of each obstacle through the obstacle point cloud information obtained by the radar. The trailer vehicle in the obstacle is extracted through the kinematic model of the trailer, and the outer contour of the trailer for collision detection is obtained according to the extracted trailer vehicle features. Then, the collision contour of the vehicle at each trajectory point is generated through the own vehicle trajectory, and then the trailer contour is intersected with the contour of each trajectory point of the vehicle to determine whether the vehicle and the trailer collide and the position of the vehicle at the time of collision. The trailer vehicle in the obstacle detected by the autonomous driving vehicle can be effectively identified; and by processing the outer contours of the trailer and the trailer to obtain the collision outer contour of the trailer, the collision detection effect in the blind spot of the large vehicle of the trailer is improved.

[0148] like Figure 6 As shown, Figure 6 The present invention provides a schematic diagram of the structure of an electronic device 600, wherein the electronic device 600 includes:

[0149] A processor 601, a storage medium 602 and a bus 603, wherein the storage medium 602 stores machine-readable instructions executable by the processor 601. When the electronic device 600 is running, the processor 601 communicates with the storage medium 602 via the bus 603, and the processor 601 executes the machine-readable instructions to perform the steps of the collision detection method described in the embodiment of the present application.

[0150] In actual application, the components in the electronic device 600 are coupled together via the bus 603. It is understood that the bus 603 is used to realize the connection and communication between these components. In addition to the data bus, the bus 603 also includes a power bus, a control bus, and a status signal bus. However, for the sake of clarity, Figure 6 Various buses are labeled as bus 603.

[0151] The above electronic device obtains obstacle point cloud information through radar, and extracts the motion trajectory, contour features, and position and posture information of each obstacle. The trailer vehicle is extracted from the obstacle through the kinematic model of the trailer, and the outer contour of the trailer for collision detection is obtained based on the extracted trailer vehicle features. The collision contour of the vehicle at each trajectory point is then generated through the trajectory of the vehicle, and the contour of the trailer is intersected with the contour of each trajectory point of the vehicle to determine whether the vehicle and the trailer collide and the position of the vehicle at the time of collision. The trailer vehicle can be effectively identified among the obstacles detected by the autonomous driving vehicle; and by processing the outer contours of the trailer and the trailer to obtain the collision outer contour of the trailer, the collision detection effect in the blind spot of large vehicles with trailers is improved.

[0152] The embodiment of the present application further provides a computer-readable storage medium, which stores executable instructions. When the executable instructions are executed by at least one processor 601, the collision detection method described in the embodiment of the present application is implemented.

[0153] In some embodiments, the storage medium can be a magnetic random access memory (FRAM), a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), a flash memory, a magnetic surface storage, an optical disk, or a compact disc read-only memory (CD-ROM); it can also be various devices including one or any combination of the above memories.

[0154] In some embodiments, executable instructions may be in the form of a program, software, software module, script or code, written in any form of programming language (including compiled or interpreted languages, or declarative or procedural languages), and may be deployed in any form, including as a stand-alone program or as a module, component, subroutine or other unit suitable for use in a computing environment.

[0155] As an example, executable instructions may, but do not necessarily, correspond to a file in a file system, may be stored as part of a file that stores other programs or data, for example, in one or more scripts in a HyperText Markup Language (HTML) document, in a single file dedicated to the program in question, or in multiple coordinated files (for example, files storing one or more modules, subroutines, or code portions).

[0156] By way of example, executable instructions may be deployed to be executed on one computing device, or on multiple computing devices located at one site, or on multiple computing devices distributed across multiple sites and interconnected by a communication network.

[0157] The computer-readable storage medium extracts the motion trajectory, contour features, and position information of each obstacle through the obstacle point cloud information obtained by the radar. The trailer vehicle in the obstacle is extracted through the kinematic model of the trailer, and the outer contour of the trailer for collision detection is obtained according to the extracted trailer vehicle features, and then the collision contour of the vehicle at each trajectory point is generated through the own vehicle trajectory, and then the trailer contour is intersected with the contour of each trajectory point of the vehicle to determine whether the vehicle and the trailer collide and the position of the vehicle at the time of collision. The trailer vehicle in the obstacle detected by the autonomous driving vehicle can be effectively identified; and by processing the outer contours of the trailer and the trailer to obtain the collision outer contour of the trailer, the collision detection effect in the blind area of ​​the large vehicle of the trailer is improved.

[0158] In the several embodiments provided in the present application, it should be understood that the disclosed methods and electronic devices can be implemented in other ways. The device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as: multiple units or components can be combined, or can be integrated into another system, or some features can be ignored or not executed. In addition, the coupling, direct coupling, or communication connection between the components shown or discussed can be through some interfaces, and the indirect coupling or communication connection of the devices or units can be electrical, mechanical or other forms.

[0159] The modules described as separate components may or may not be physically separated, and the components shown as modules may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0160] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0161] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a non-volatile computer-readable storage medium that is executable by a processor. Based on this understanding, the technical solution of the present application can essentially be embodied in the form of a software product, or in other words, the part that contributes to the prior art or the part of the technical solution. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, a platform server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: various media that can store program codes, such as USB flash drives, mobile hard disks, ROM, RAM, magnetic disks, or optical disks.

[0162] The above are only specific implementations of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. A collision detection method, characterized in that: The following steps are involved: Obtaining a motion trajectory of at least one obstacle relative to the current vehicle; A plane rectangular coordinate system of the trailer motion model is established, wherein the speed of the tractor is v, the angle between the tractor's motion direction and the horizontal axis is θ, the trailer is articulated with the tractor through an articulation point, the angle between the trailer's motion direction and the horizontal axis is α, the length of the trailer is L, and the angle between the extension line of the trailer from the articulation point along the motion direction and the tractor is theta; Determine the motion step length of the tractor as S0=v*t0, where t0 is the motion sampling frequency, t2=t1+t0, t1 is the initial time of a sampling frequency, and t2 is the end time of a sampling frequency, then: θ'=θt2-θt1; α'=αt2-αt1; The trailer motion model is established: theta'=S0*sinθt1 / L+θ'; theta'=θ'-α'; wherein θ' represents the angle change value of θ, α' represents the angle change value of α, and theta' represents the angle change value of theta; Performing feature matching between the at least one obstacle and the trailer motion model, and acquiring at least one matching target obstacle, wherein each target obstacle in the at least one target obstacle represents a trailer; The collision area of ​​each target obstacle is marked to obtain the collision area; The performing feature matching between the at least one obstacle and the trailer motion model and acquiring at least one matching target obstacle includes: Detecting whether there are two intersecting obstacles among the at least one obstacle at the same time; When there are two intersecting obstacles, the center lines of the two intersecting obstacles along the trajectory direction are obtained respectively, and the intersection of the two center lines is used as a hinge point, and the two intersecting obstacles are used as a target obstacle.

2. The method according to claim 1, characterized in that The obtaining of the motion trajectory of at least one obstacle relative to the current vehicle comprises: Acquiring point cloud information of the at least one obstacle through a vehicle-mounted radar sensor, wherein the point cloud information uses the current vehicle as a reference object; Based on the point cloud information, calibrate the outline of the at least one obstacle by using a rectangular calibration frame to obtain at least one rectangular calibration frame; Obtain a motion trajectory of each rectangular calibration frame in the at least one rectangular calibration frame relative to the current vehicle.

3. The method according to claim 2, characterized in that The obtaining of the motion trajectory of each rectangular calibration frame in the at least one rectangular calibration frame relative to the current vehicle comprises: For each rectangular calibration frame, collect the rectangular calibration frames at two consecutive moments, and take the intersection of the center lines of the rectangular calibration frames at the two moments as the centroid, wherein the center line is the center line along the direction of movement; The center of mass position of the rectangular calibration frame at n moments is continuously obtained, and the center of mass position at n moments is used as the motion trajectory, wherein n is a positive integer.

4. The method according to claim 1, characterized in that: The process of labeling the collision area of ​​each target obstacle to obtain the collision area includes: The target obstacle is subjected to convex optimization processing to obtain a polygon capable of enveloping the target obstacle, wherein the polygon is a convex polygon.

5. The method according to claim 1, characterized in that The method further comprises: Based on the collision area, a driving route of the current vehicle is formulated, or based on the collision area, the collision area is displayed on a vehicle navigation interface, and an alarm is issued when the distance between the current vehicle and the collision area is less than a preset distance threshold.

6. A collision detection device, characterized in that: The device comprises: An acquisition module, used to acquire a motion trajectory of at least one obstacle relative to the current vehicle; Establish a module for establishing a plane rectangular coordinate system of a trailer motion model, wherein the speed of the tractor is v, the angle between the tractor's motion direction and the horizontal axis is θ, the trailer is hinged to the tractor through a hinge point, the angle between the trailer's motion direction and the horizontal axis is α, the length of the trailer is L, and the angle between the extension line of the trailer from the hinge point along the motion direction and the tractor is theta; determine the motion step length of the tractor as S0=v*t0, wherein t0 is the motion sampling frequency, t2=t1+t0, t1 is the initial time of a sampling frequency, and t2 is the end time of a sampling frequency, then: θ'=θt2-θt1; α'=αt2-αt1; establish the trailer motion model: theta'=S0*sinθt1 / L+θ'; theta'=θ'-α'; wherein θ' represents the angle change value of θ, α' represents the angle change value of α, and theta' represents the angle change value of theta; A matching module, used for performing feature matching between the at least one obstacle and the trailer motion model, and obtaining at least one matching target obstacle, wherein each target obstacle in the at least one target obstacle represents a trailer; performing feature matching between the at least one obstacle and the trailer motion model, and obtaining at least one matching target obstacle, comprises: detecting whether there are two intersecting obstacles in the at least one obstacle at the same time; when there are two intersecting obstacles, respectively obtaining the center lines of the two intersecting obstacles along the trajectory direction, and taking the intersection of the two center lines as a hinge point, and taking the two intersecting obstacles as a target obstacle; The labeling module is used to label the collision area of ​​each target obstacle to obtain the collision area.

7. The device according to claim 6, characterized in that To obtain the motion trajectory of at least one obstacle relative to the current vehicle, the acquisition module: Acquiring point cloud information of the at least one obstacle through a vehicle-mounted radar sensor, wherein the point cloud information uses the current vehicle as a reference object; Based on the point cloud information, calibrate the outline of the at least one obstacle by using a rectangular calibration frame to obtain at least one rectangular calibration frame; Obtain a motion trajectory of each rectangular calibration frame in the at least one rectangular calibration frame relative to the current vehicle.

8. An electronic device, characterized in that: include: A processor, a storage medium and a bus, wherein the storage medium stores machine-readable instructions executable by the processor, and when the electronic device is running, the processor communicates with the storage medium via the bus, and the processor executes the machine-readable instructions to perform the collision detection method as described in any one of claims 1 to 5.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the collision detection method according to any one of claims 1 to 5 is executed.

Images