A vehicle collision detection method, device, electronic equipment and storage medium

Abstract

The vehicle collision detection method in the embodiment of the present application obtains the sensing signal parameter, the drivable area and the target obstacle information, detects the vehicle body state if the sensing signal parameter is greater than or equal to the collision trigger threshold, obtains the first collision detection state, predicts the target vehicle collision state according to the collision probability of the target vehicle in the drivable area and the target obstacle, obtains the second collision detection state, and determines the target vehicle collision state based on the first collision detection state and / or the second collision detection state. The method detects the collision state by using the elastic wave sensing data, can provide feedback based on the slight collision signal, solves the problem that the existing sensor cannot detect the slight collision, predicts the target vehicle collision state based on the collision probability of the target vehicle in the drivable area and the target obstacle, combines the elastic wave sensing collision detection to determine the target vehicle collision state, and provides an effective collision avoidance strategy.

Description

Technical Field

[0001] This application relates to the field of vehicle command management, and in particular to a vehicle collision detection method, device, electronic device, and storage medium. Background Technology

[0002] In the development of autonomous driving technology, vehicle driving detection often employs sensor fusion detection technologies such as ultrasonic sensing, millimeter-wave sensing, cameras, and lidar for driving perception. During vehicle driving, in parking and reversing scenarios, it is necessary to analyze sensor data on the collision status between the vehicle and obstacles to detect collisions in a timely manner.

[0003] However, in practical applications, existing technologies mainly use accelerometers or pressure sensors. These sensors cannot detect even minor collisions. Furthermore, existing collision detection technologies primarily focus on providing warning feedback when a collision occurs, lacking the ability to predict collisions. Consequently, collision detection based on sensor data can only provide timely damage mitigation through collision feedback, rather than offering reasonable and effective collision avoidance strategies. Summary of the Invention

[0004] The purpose of this invention is to provide a vehicle collision detection method, device, electronic device, and storage medium to solve the problems that existing sensors cannot detect minor collisions and cannot provide reasonable and effective collision avoidance strategies.

[0005] This invention provides a vehicle collision detection method, comprising: acquiring sensor signal parameters, a drivable area, and target obstacle information, wherein the sensor signal parameters are acquired by multiple elastic wave sensors installed on the target vehicle; if the sensor signal parameters are greater than or equal to a collision trigger threshold, detecting the vehicle body state to obtain a first collision detection state; determining the collision probability of the target vehicle in the drivable area based on the drivable area, and determining the collision probability between the target vehicle and the target obstacle based on the target obstacle information; predicting the target vehicle collision state based on the collision probability of the target vehicle in the drivable area and the collision probability between the target vehicle and the target obstacle to obtain a second collision detection state; and determining the target vehicle collision state based on the first collision detection state and / or the second collision detection state.

[0006] In one embodiment of the present invention, predicting the collision state of a target vehicle based on the collision probability of the target vehicle in the drivable area and the collision probability of the target vehicle with the target obstacle includes: calculating the target collision confidence level based on preset weight information for the collision probability of the target vehicle in the drivable area and the collision probability of the target vehicle with the target obstacle to obtain the target collision confidence level; if the target collision confidence level is less than the target collision confidence threshold, it is determined as a second initial collision state, and the collision confirmation module is triggered to confirm the second initial collision state to obtain the confirmed second initial collision state; the confirmed second initial collision state is determined as a second collision detection state.

[0007] In one embodiment of the present invention, detecting the vehicle's body state includes: acquiring door signal transition duration parameters, horn signal transition duration parameters, hood opening status, and trunk opening status; if the door signal transition duration parameters and horn signal transition duration parameters are both greater than or equal to a preset signal transition detection threshold, and both the hood opening status and the trunk opening status are open, then it is determined to be a first initial collision state, and a collision confirmation module is triggered to confirm the first initial collision state, thereby obtaining the confirmed first initial collision state; the confirmed first initial collision state is determined as the first collision detection state.

[0008] In one embodiment of the present invention, after determining the first initial collision state, the vehicle collision detection method further includes: acquiring the confidence level of the sensing device; if the confidence level of the sensing device is greater than or equal to a preset sensing confidence threshold, then determining the first initial collision state as the first collision detection state; if the confidence level of the sensing device is less than the preset sensing confidence threshold, then triggering the collision confirmation module to confirm the collision of the first initial collision state.

[0009] In one embodiment of the present invention, determining the collision state of the target vehicle based on the first collision detection state and / or the second collision detection state includes at least one of the following: if the first collision detection state is a collision, then the vehicle collision state is determined to be a collision;

[0010] or

[0011] If there are multiple consecutive periodic detections of the second collision detection state as a collision, then the vehicle collision state is determined as a collision. The consecutive periodic detection is to periodically determine the target collision state based on the collision probability of the target vehicle in the drivable area and the collision probability of the target vehicle with the target obstacle according to a preset detection period, so as to obtain multiple consecutive periodic detections of the second collision detection state.

[0012] In one embodiment of the present invention, determining the collision probability of a target vehicle in a drivable area based on the drivable area includes: traversing the target driving points of the target vehicle in the drivable area, determining the collision risk status of each target driving point, wherein the drivable area includes multiple target driving points, and the collision risk status of each target driving point is determined based on the distance between the target driving point and the target vehicle and the driving status, wherein the collision risk status includes no risk and risky; if there is a target driving point with a risky collision status, determining the collision probability of the target vehicle in the drivable area based on the proportion of target driving points with a risky collision status among all target driving points.

[0013] In one embodiment of the present invention, determining the collision probability between the target vehicle and the target obstacle based on the target obstacle information includes: acquiring the speed and acceleration of the target vehicle; and determining the collision probability between the target vehicle and the target obstacle based on the speed, acceleration, and the target obstacle distance information and the target obstacle's moving speed information in the target obstacle information.

[0014] This invention also provides a vehicle collision detection device, comprising: a data acquisition module for acquiring multiple sensor signal parameters, a drivable area, and target obstacle information, wherein the sensor signal parameters are acquired by multiple vehicle-end elastic wave sensors; a first collision detection module for performing node state detection on a preset vehicle target detection node to obtain a first collision detection state if each of the sensor signal parameters is greater than or equal to a collision trigger threshold; a second collision detection module for determining the collision probability of the target vehicle in the drivable area based on the drivable area, and determining the collision probability between the target vehicle and the target obstacle based on the target obstacle information; determining a target collision state based on the collision probability of the target vehicle in the drivable area and the collision probability between the target vehicle and the target obstacle to obtain a second collision detection state; and a collision state determination module for determining a vehicle collision state based on the first collision detection state and / or the second collision detection state.

[0015] This invention also provides an electronic device, including: one or more processors; and a storage device for storing one or more programs, which, when executed by the one or more processors, cause the electronic device to implement the vehicle collision detection method as described in any of the above embodiments.

[0016] This invention also provides a computer-readable storage medium storing computer-readable instructions thereon, which, when executed by a computer's processor, cause the computer to perform the vehicle collision detection method as described in any of the above embodiments.

[0017] The vehicle collision detection method in this embodiment of the invention acquires sensor signal parameters, drivable area, and target obstacle information. If the sensor signal parameters are greater than or equal to a collision trigger threshold, the vehicle body state is detected to obtain a first collision detection state. Based on the target vehicle's location within the drivable area and the probability of collision with the target obstacle, the target vehicle's collision state is predicted to obtain a second collision detection state. The target vehicle's collision state is determined based on the first and / or second collision detection states. This method utilizes elastic wave sensing data to detect the collision state, which can be based on feedback from minor collision signals, solving the problem that existing sensors cannot detect minor collisions. Furthermore, by predicting the target vehicle's collision state based on its location within the drivable area and the probability of collision with the target obstacle, and combining this with elastic wave sensing collision detection to determine the target vehicle's collision state, an effective collision avoidance strategy is provided.

[0018] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and do not limit this application. Attached Figure Description

[0019] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application. It is obvious that the drawings described below are merely some embodiments of this application, and those skilled in the art can obtain other drawings based on these drawings without any inventive effort. In the drawings:

[0020] Figure 1 This is a schematic diagram illustrating an exemplary system architecture as shown in an exemplary embodiment of this application;

[0021] Figure 2 This is a flowchart illustrating a vehicle collision detection method in an exemplary embodiment of this application;

[0022] Figure 3 This is an exemplary embodiment of the present application illustrating a specific micro-collision recognition flowchart based on an elastic wave sensor;

[0023] Figure 4 This is an exemplary embodiment of the present application illustrating a specific micro-collision recognition flowchart based on fusion target and fusion drivable area;

[0024] Figure 5 This is a schematic diagram of a vehicle collision detection device shown in an exemplary embodiment of this application;

[0025] Figure 6 This is a schematic diagram illustrating a specific micro-collision protection system in a low-speed scenario, as shown in an exemplary embodiment of this application;

[0026] Figure 7 This is a schematic diagram of the structure of a computer system for an electronic device, as illustrated in an exemplary embodiment of this application. Detailed Implementation

[0027] The embodiments of the present invention will be described below with reference to the accompanying drawings and specific examples. Those skilled in the art can easily understand other advantages and effects of the present invention from the content disclosed in this specification. The present invention can also be implemented or applied through other different specific embodiments, and various details in this specification can be modified or changed based on different viewpoints and applications without departing from the spirit of the present invention. It should be understood that the preferred embodiments are only for illustrating the present invention and not for limiting the scope of protection of the present invention.

[0028] It should be noted that the illustrations provided in the following embodiments are only schematic representations of the basic concept of the present invention. Therefore, the illustrations only show the components related to the present invention and are not drawn according to the actual number, shape and size of the components in the actual implementation. In the actual implementation, the form, quantity and proportion of each component can be arbitrarily changed, and the layout of the components may also be more complex.

[0029] In the following description, numerous details are explored to provide a more thorough explanation of embodiments of the invention. However, it will be apparent to those skilled in the art that embodiments of the invention may be practiced without these specific details. In other embodiments, well-known structures and devices are shown in block diagram form rather than in detail to avoid obscuring embodiments of the invention.

[0030] The term "and / or" used in this application describes the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, or B existing alone. The character " / " generally indicates that the related objects before and after it are in an "or" relationship.

[0031] First, it's important to clarify that an elastic wave sensor is a type of sensor used to detect surface deformation and motion. In the field of autonomous driving, elastic wave sensors are commonly used to detect the environment surrounding a vehicle, providing the data needed for navigation and obstacle avoidance. Unlike traditional sensor technologies, elastic wave sensors utilize the propagation of mechanical waves within materials to detect the motion and deformation of objects. This type of sensor generates mechanical waves by emitting high-frequency sound waves or ultrasonic waves and measures the reflection and scattering of the object by receiving the waves that propagate back. In autonomous vehicles, elastic wave sensors can be used to detect the position and motion of obstacles and other vehicles on the road, enabling the vehicle to perform obstacle avoidance and drive safely.

[0032] Confidence is a measure of how well a hypothesis is true if it is true. It is typically used to assess the reliability of an inference or estimate. In statistics, confidence is often used to evaluate the reliability of a statistical inference. For example, in hypothesis testing, a value is calculated to determine whether the sample data supports or opposes the hypothesis. If the value is small, it usually indicates sufficient evidence to reject the hypothesis, meaning the confidence in the hypothesis is low; conversely, if the value is large, we usually cannot reject the hypothesis, meaning our confidence in the hypothesis is high.

[0033] This application also provides the following beneficial effects: detecting the vehicle's body state allows for threshold screening of the vehicle's elastic wave sensing data sources, preventing accidental sensor data from affecting the false confirmation of the collision state; calculating the target collision confidence level based on preset weight information for the collision probability of the target vehicle in the drivable area and the collision probability of the target vehicle with the target obstacle effectively quantifies the probability of collision prediction, improving the accuracy of collision prediction; determining the confidence level of the sensing device reduces the impact of false detections caused by sensor malfunctions, improving detection accuracy; determining the target vehicle's collision state based on the first and / or second collision detection states improves the reliability of the detection results and avoids undesirable results caused by the failure of a single detection method; this application also adds a collision confirmation module, using a traditional collision detection device as redundant detection for the above two collision detection states, improving the accuracy of the detection results and ensuring the necessity of the results.

[0034] Figure 1 This is a schematic diagram illustrating an exemplary system architecture as shown in an exemplary embodiment of this application.

[0035] Reference Figure 1As shown, the system architecture may include a vehicle-mounted terminal 101 and a computer device 102. The vehicle-mounted terminal 101 acquires sensor signal parameters, drivable area, and target obstacle information, and then provides this information to the computer device 102 for processing. The computer device 102 may be at least one of a microcomputer, an embedded computer, or a network computer. Those skilled in the art can implement the following in the computer device 102: if the sensor signal parameters are greater than or equal to a collision trigger threshold, detect the vehicle's body state to obtain a first collision detection state; determine the collision probability of the target vehicle within the drivable area based on the drivable area, and determine the collision probability between the target vehicle and the target obstacle based on the target obstacle information; predict the target vehicle's collision state based on the collision probability of the target vehicle within the drivable area and the collision probability between the target vehicle and the target obstacle to obtain a second collision detection state; and determine the target vehicle's collision state based on the first collision detection state and / or the second collision detection state.

[0036] Indicatively, after acquiring the sensor signal parameters, drivable area, and target obstacle information from the vehicle terminal 101, the computer device 102 detects the vehicle's body state if the sensor signal parameters are greater than or equal to the collision trigger threshold, obtaining a first collision detection state. Based on the target vehicle's location within the drivable area and the probability of collision with the target obstacle, the computer device 102 predicts the target vehicle's collision state, obtaining a second collision detection state. The target vehicle's collision state is then determined based on the first and / or second collision detection states. This method utilizes elastic wave sensing data to detect the collision state, which can be based on feedback from minor collision signals, solving the problem that existing sensors cannot detect minor collisions. Furthermore, by predicting the target vehicle's collision state based on its location within the drivable area and the probability of collision with the target obstacle, and combining this with elastic wave sensing collision detection to determine the target vehicle's collision state, this method provides an effective collision avoidance strategy.

[0037] Figure 2 This is a flowchart illustrating an exemplary embodiment of the present application of a vehicle collision detection method, which can... Figure 1 This is executed within the system architecture of the vehicle-side 101 and computer device 102 shown. (Refer to...) Figure 2 As shown, the flowchart of this vehicle collision detection method includes at least steps S210 to S250, which are described in detail below:

[0038] In step S210, sensor signal parameters, drivable area, and target obstacle information are acquired.

[0039] In one embodiment of this application, the sensing signal parameters are acquired by a plurality of elastic wave sensors disposed on the target vehicle.

[0040] In one embodiment of this application, multiple elastic wave sensors are installed at the vehicle end to optimize the detection results of elastic waves and effectively avoid missed identification by the elastic wave sensors. In another embodiment of this application, the elastic wave sensors are distributed as follows: the elastic wave sensors are installed at the front, rear, doors, hood, and trunk of the vehicle.

[0041] In step S220, if the sensing signal parameter is greater than or equal to the collision trigger threshold, the vehicle body state is detected to obtain the first collision detection state.

[0042] In one embodiment of this application, the door signal transition duration parameter, the horn signal transition duration parameter, the hood opening state, and the trunk opening state are obtained. If the door signal transition duration parameter and the horn signal transition duration parameter are both greater than or equal to a preset signal transition detection threshold, and the hood opening state and the trunk opening state are both open, then it is determined to be the first initial collision state, and the collision confirmation module is triggered to confirm the first initial collision state, thereby obtaining the confirmed first initial collision state, and the confirmed first initial collision state is determined as the first collision detection state.

[0043] In one embodiment of this application, after determining the first initial collision state, the method further includes obtaining the confidence level of the sensing device. If the confidence level of the sensing device is greater than or equal to a preset sensing confidence threshold, the first initial collision state is determined as the first collision detection state.

[0044] In one embodiment of this application, if the confidence level of the sensing device is less than a preset sensing confidence threshold, the collision confirmation module is triggered to confirm the first initial collision state.

[0045] In one embodiment of this application, the collision confirmation module is confirmed by sensing signals from a surround-view + ultrasonic sensor (4V12U). This collision confirmation module includes two operating states: a normal operating mode and a collision confirmation mode. In normal operating mode, the collision confirmation module filters out low-lying obstacles on the ground that will not cause front-to-back collisions, such as curbs, wheel chocks, tree branches, locked parking locks, and road debris, ensuring that accidental braking does not occur during driving or parking. In collision confirmation mode, the collision confirmation module detects all low-lying obstacles on the ground, preventing the failure to confirm obstacles such as pedestrians, animals, and billboards that may have fallen due to a collision, thus greatly reducing the risk of secondary crushing of objects after a collision.

[0046] In step S230, the collision probability of the target vehicle in the drivable area is determined based on the drivable area, and the collision probability between the target vehicle and the target obstacle is determined based on the target obstacle information.

[0047] In one embodiment of this application, determining the collision probability of a target vehicle in a drivable area based on the drivable area includes traversing the target driving points of the target vehicle in the drivable area, determining the collision risk status of each target driving point, wherein the drivable area includes multiple target driving points, and the collision risk status of the target driving point is determined based on the distance between the target driving point and the target vehicle and the driving status, wherein the collision risk status includes no risk and risky, and if there is a target driving point with a risky collision status, the collision probability of the target vehicle in the drivable area is determined based on the proportion of the target driving point with a risky collision status among all target driving points.

[0048] In one embodiment of this application, the speed and acceleration of the target vehicle are obtained, and the collision probability between the target vehicle and the target obstacle is determined based on the speed, acceleration, and the target obstacle distance information and the target obstacle's moving speed information in the target obstacle information.

[0049] In step S240, the collision state of the target vehicle is predicted based on the collision probability of the target vehicle in the drivable area and the collision probability of the target vehicle with the target obstacle, and a second collision detection state is obtained.

[0050] In one embodiment of this application, the target collision confidence score is calculated based on the collision probability of the target vehicle in the drivable area and the collision probability of the target vehicle with the target obstacle, according to preset weight information. In another embodiment of this application, the collision probability of the target vehicle in the drivable area and the collision probability of the target vehicle with the target obstacle are weighted according to the collision probability accuracy. An exemplary weight setting in this embodiment is 0.5. Assuming the collision probability of the target vehicle in the drivable area is Ai, and the collision probability of the target vehicle with the target obstacle is Bi, the micro-collision trigger confidence score is calculated as: C = 0.5Ai + 0.5Bi, where if C > 50%, the prediction result is that a collision has occurred.

[0051] In one embodiment of this application, if the target collision confidence is less than the target collision confidence threshold, it is determined to be a second initial collision state, and the collision confirmation module is triggered to confirm the second initial collision state, obtain the confirmed second initial collision state, and determine the confirmed second initial collision state as the second collision detection state.

[0052] In one embodiment of this application, if the target collision confidence level is greater than or equal to the target collision confidence threshold, it is determined to be a second initial collision state, and the above-mentioned second initial collision state is confirmed as a second collision detection state.

[0053] In one embodiment of this application, when the collision confirmation module is triggered to confirm the second initial collision state, the collision confirmation module switches from normal working mode to micro-collision confirmation mode, controls the vehicle to brake and remain stationary, and opens the fault warning prompt.

[0054] In one embodiment of this application, when the detection results of the second collision detection state are all "no collision" for a preset number of consecutive cycles, the collision confirmation module switches its working mode from the micro-collision confirmation mode to the normal working mode, allowing the vehicle to start again and the system to return to normal working status. In this embodiment, the preset number of cycles is 5 cycles.

[0055] In one embodiment of this application, when a collision occurs within a preset number of detection cycles in the second collision detection state, the vehicle is prohibited from driving, a warning is issued that a collision may occur, and the user is requested to take over.

[0056] In one embodiment of this application, if there are multiple consecutive periodic detections of a second collision detection state as a collision, the vehicle is prohibited from driving and specific operations including but not limited to braking, locking, raising windows, turning off the engine, and turning on hazard lights are performed to notify the user that a collision has occurred and request the user to take over.

[0057] In step S250, the collision state of the target vehicle is determined based on the first collision detection state and / or the second collision detection state.

[0058] In one embodiment of this application, if the first collision detection state is a collision, then the vehicle collision state is determined to be a collision.

[0059] In one embodiment of this application, if there are multiple consecutive periodic detection second collision detection states that are collisions, then the vehicle collision state is determined to be a collision. The consecutive periodic detection is to periodically determine the target collision state based on the collision probability of the target vehicle in the drivable area and the collision probability of the target vehicle with the target obstacle according to a preset detection period, so as to obtain multiple consecutive periodic detection second collision detection states.

[0060] Please see Figure 3 , Figure 3 This is an exemplary embodiment of the present application illustrating a specific micro-collision recognition flowchart based on an elastic wave sensor. The micro-collision recognition flowchart based on the elastic wave sensor can be specifically implemented as follows: Figure 1 Executed within the system architecture shown, and specifically by Figure 1 The computer device 102 shown executes the micro-collision recognition process based on the elastic wave sensor. Figure 2 It can be executed in the environment shown, but can also be implemented in other implementation environments. No specific implementation environment is restricted here.

[0061] like Figure 3 As shown, in a specific embodiment of this application, the process judgment specifically includes:

[0062] (1) Receive the elastic wave sensor signal and determine whether the elastic wave sensor trigger flag is triggered;

[0063] If 1-1) is true, then jump to (2).

[0064] 1-2) No, then skip to (3).

[0065] (2) Determine whether the door signal transition time of this vehicle is ≥1s;

[0066] If 2-1) is true, then jump (4).

[0067] 2-2) No, then skip (3). In this case, one possible reason is that the door switch causes severe vibration of the vehicle body, which leads to the micro-collision sensor being falsely triggered.

[0068] (3) The micro-collision sensor flag is set to no collision;

[0069] (4) Determine whether the vehicle's horn signal transition time is ≥1s;

[0070] If 4-1 is true, then jump (5).

[0071] 4-2) No, then skip (3). In this case, one possible reason is that the vehicle horn causes severe vibration of the vehicle body, which leads to false triggering of the micro-collision sensor.

[0072] (5) Determine whether the vehicle's hood switch is open;

[0073] If 5-1) is true, then jump (3). In this case, one possible reason is that the front hood of the vehicle shakes during driving, causing the vehicle body to vibrate violently, which leads to the micro-collision sensor being falsely triggered.

[0074] 5-2) No, then skip to (6);

[0075] (6) Determine whether the vehicle's trunk is open;

[0076] If 6-1) is true, then jump (3). In this case, one possible reason is that the trunk lid shakes during the driving process, causing the vehicle body to vibrate violently, which leads to the micro-collision sensor being falsely triggered.

[0077] 6-2) No, then skip to (7);

[0078] (7) Determine whether the trigger confidence level of the elastic wave sensor is high;

[0079] If 7-1 is true, then jump (8).

[0080] 7-2) No, then skip to (9);

[0081] (8) The micro-collision sensor flag is set to collision;

[0082] (9) The 4V12U switches from normal working mode to micro-collision confirmation mode to determine whether the collision status confirmation signal sent by the collision status confirmation module is a collision.

[0083] If 9-1 is true, then jump (8).

[0084] 9-2) No, then skip to (3).

[0085] In one specific embodiment of this application, the 4V12U is consistent with the collision confirmation module in the above embodiment, the micro-collision sensor flag is consistent with the first collision detection state in the above embodiment, and the signal information of the elastic wave sensor trigger flag and elastic wave sensor trigger confidence output by the elastic wave sensor is consistent with the sensing signal parameters in the above embodiment.

[0086] Please see Figure 4 , Figure 4 This is an exemplary embodiment of the present application illustrating a specific micro-collision recognition flowchart based on a fused target and a fused drivable region. This micro-collision recognition flowchart based on a fused target and a fused drivable region can be specifically implemented as follows: Figure 1 Executed within the system architecture shown, and specifically by Figure 1 The computer device 102 shown executes the micro-collision recognition process based on the fused target and the fused drivable area. Figure 2 The implementation is shown in the environment shown, but it can also be implemented in other implementation environments. No specific implementation environment is restricted here.

[0087] like Figure 4 As shown, in a specific embodiment of this application, the process judgment specifically includes:

[0088] (1) Receive the output signal of the fused drivable area and calculate the collision probability of the drivable area;

[0089] (2) Receive the output signal of the fused target and calculate the target collision probability;

[0090] (3) The micro-collision recognition strategy module receives the collision probability of the drivable area and the collision probability of the target, and determines whether the micro-collision recognition strategy flag indicates a collision.

[0091] If 3-1) is true, then jump (4).

[0092] 3-2) No, then skip to (5).

[0093] (4) Determine whether the micro-collision strategy trigger confidence level ≥ 50% issued by the micro-collision recognition strategy module is valid;

[0094] If 4-1) is true, then jump (6).

[0095] 4-2) No, then skip to (7);

[0096] (5) The micro-collision strategy flag is set to no collision;

[0097] (6) The micro-collision strategy flag is set to collision;

[0098] (7) The 4V12U switches from normal working mode to micro-collision confirmation mode to determine whether the collision status confirmation signal sent by the collision status confirmation module is a collision.

[0099] If 7-1 is true, then jump (6).

[0100] 7-2) No, then skip to (5).

[0101] In one specific embodiment of this application, the fused target is consistent with the target obstacle information in the aforementioned embodiment, the fused drivable area is consistent with the drivable area in the aforementioned embodiment, the micro-collision sensor flag is consistent with the first collision detection state in the aforementioned embodiment, the micro-collision strategy flag is consistent with the second collision detection state in the aforementioned embodiment, and the micro-collision trigger flag is consistent with the target vehicle collision state in the aforementioned embodiment.

[0102] The vehicle collision detection method in this embodiment of the invention acquires sensor signal parameters, drivable area, and target obstacle information. If the sensor signal parameters are greater than or equal to a collision trigger threshold, the vehicle body state is detected to obtain a first collision detection state. Based on the target vehicle's location within the drivable area and the probability of collision with the target obstacle, a second collision detection state is predicted. The target vehicle collision state is then determined based on the first and / or second collision detection states. This method utilizes elastic wave sensing data to detect the collision state, which can be based on feedback from minor collision signals, solving the problem that existing sensors cannot detect minor collisions. Furthermore, by predicting the target vehicle collision state based on its location within the drivable area and the probability of collision with the target obstacle, and combining this with elastic wave sensing collision detection to determine the target vehicle collision state, an effective collision avoidance strategy is provided. Other beneficial effects include: detecting the vehicle body state can utilize vehicle elastic wave sensing data to... By checking the sensor data thresholds, the system can avoid misconceptions about collision status caused by accidental sensor data. Calculating the target collision confidence level based on preset weights for the collision probability of the target vehicle in the drivable area and the probability of the target vehicle colliding with the target obstacle effectively quantifies the probability of collision prediction, improving the accuracy of collision prediction. Determining the confidence level of the sensor device can mitigate the impact of false detections caused by sensor malfunctions, improving detection accuracy. Determining the target vehicle's collision status based on the first and / or second collision detection states improves the reliability of the detection results and avoids ineffective detection results caused by the failure of a single detection method. This application also adds a collision confirmation module, utilizing a traditional collision detection device as redundant detection for the two collision detection states, improving the accuracy of the detection results and ensuring the validity of the results.

[0103] The following describes an embodiment of the apparatus described in this application, which can be used to execute the vehicle collision detection method described in the above embodiments of this application. For details not disclosed in the apparatus embodiments of this application, please refer to the embodiments of the vehicle collision detection method described in the above applications.

[0104] Figure 5 This is a schematic diagram illustrating a vehicle collision detection device according to an exemplary embodiment of this application. The device can be applied to… Figure 2 The implementation environment shown is not limited to this embodiment. This device can also be applied to other exemplary implementation environments and specifically configured in other devices.

[0105] like Figure 5As shown, the exemplary vehicle collision detection device includes: a data acquisition module 501, a first collision detection module 502, a second collision detection module 503, and a collision state determination module 504.

[0106] The system includes a data acquisition module 501, which acquires multiple sensor signal parameters, drivable area, and target obstacle information. The sensor signal parameters are acquired by multiple vehicle-side elastic wave sensors. A first collision detection module 502 is used to perform node state detection on a preset vehicle target detection node if each sensor signal parameter is greater than or equal to a collision trigger threshold, thereby obtaining a first collision detection state. A second collision detection module 503 is used to determine the collision probability of the target vehicle in the drivable area based on the drivable area, and to determine the collision probability between the target vehicle and the target obstacle based on the target obstacle information. The system then determines the target collision state based on the collision probability between the target vehicle and the target obstacle, thereby obtaining a second collision detection state. A collision state determination module 504 is used to determine the vehicle collision state based on the first collision detection state and / or the second collision detection state.

[0107] Please see Figure 6 , Figure 6 This is a schematic diagram illustrating a specific micro-collision protection system in a low-speed scenario, as shown in an exemplary embodiment of this application. The aforementioned specific system can be specifically applied in, for example... Figure 2 The computer device 102 in the system architecture shown can also be applied in other specific implementation environments where this solution can be implemented, and the specific implementation environment is not limited here.

[0108] like Figure 6 As shown, in a specific embodiment of this application, the system includes four parts: a micro-collision recognition strategy module based on an elastic wave sensor, a micro-collision recognition strategy module based on fusion target and fusion drivable area, a collision state confirmation module, and a micro-collision arbitration module. The input signals of a micro-collision protection system in a low-speed scenario are the elastic wave sensor trigger flag and elastic wave sensor trigger confidence level output by the vehicle-mounted elastic wave sensor, the surround view + ultrasonic sensor (4V12U) signal, the fusion target signal, and the fusion drivable area signal. The output signal of a micro-collision protection system in a low-speed scenario is the micro-collision trigger flag.

[0109] In one specific embodiment of this application, the system identifies and detects micro-collision sensors in a micro-collision identification strategy module based on the elastic wave sensor trigger flag and trigger confidence level output by the elastic wave sensor, and outputs the micro-collision sensor flag signal after confirmation by the collision state confirmation module; and identifies and predicts micro-collision strategies in a micro-collision identification strategy module based on the fused target signal and the fused drivable area signal, and outputs the micro-collision strategy flag signal after confirmation by the collision state confirmation module.

[0110] In one specific embodiment of this application, the micro-collision arbitration module performs collision state identification and arbitration based on the signals of the micro-collision sensor flag bit and the micro-collision strategy flag bit, and then outputs the signal of the micro-collision trigger flag bit.

[0111] In one specific embodiment of this application, the elastic wave sensor trigger flag and elastic wave sensor trigger confidence signal information output by the above elastic wave sensor are consistent with the sensing signal parameters in the aforementioned embodiment, the fused target is consistent with the target obstacle information in the aforementioned embodiment, the fused drivable area is consistent with the drivable area in the aforementioned embodiment, the micro-collision sensor flag is consistent with the first collision detection state in the aforementioned embodiment, the micro-collision strategy flag is consistent with the second collision detection state in the aforementioned embodiment, and the micro-collision trigger flag is consistent with the target vehicle collision state in the aforementioned embodiment.

[0112] Embodiments of this application also provide an electronic device, including: one or more processors; and a storage device for storing one or more programs, which, when executed by one or more processors, cause the electronic device to implement the vehicle collision detection method provided in the above embodiments.

[0113] Figure 7 This is a schematic diagram illustrating the structure of a computer system for an electronic device, as shown in an exemplary embodiment of this application. It should be noted that... Figure 7 The computer system 700 of the electronic device shown is merely an example and should not impose any limitation on the functionality and scope of use of the embodiments of this application.

[0114] like Figure 7As shown, the computer system 700 includes a Central Processing Unit (CPU) 701, which can perform various appropriate actions and processes based on a program stored in a Read-Only Memory (ROM) 702 or a program loaded from storage into Random Access Memory (RAM) 703, such as performing the methods described in the above embodiments. The RAM 703 also stores various programs and data required for system operation. The CPU 701, ROM 702, and RAM 703 are interconnected via a bus. An Input / Output (I / O) interface 705 is also connected to the bus 704.

[0115] The following components are connected to I / O interface 705: an input section 706 including a keyboard, mouse, etc.; an output section 707 including a cathode ray tube (CRT), liquid crystal display (LCD), etc., and speakers, etc.; a storage section 708 including a hard disk, etc.; and a communication section 709 including a network interface card such as a LAN (Local Area Network) card, modem, etc. The communication section performs communication processing via a network such as the Internet. A drive is also connected to I / O interface 705 as needed. A removable medium 711, such as a disk, optical disk, magneto-optical disk, semiconductor memory, etc., is installed on drive 710 as needed so that computer programs read from it can be installed into storage section 708 as needed.

[0116] Specifically, according to embodiments of this application, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments of this application include a computer program product comprising a computer program carried on a computer-readable medium, the computer program including a computer program for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via communication section 709, and / or installed from removable medium 711. When the computer program is executed by central processing unit (CPU) 701, it performs various functions defined in the system of this application.

[0117] It should be noted that the computer-readable medium shown in the embodiments of this application can be a computer-readable signal medium or a computer-readable storage medium, or any combination of the two. A computer-readable storage medium can be, for example, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of a computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM), flash memory, optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In this application, a computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, carrying a computer-readable computer program. Such propagated data signals can take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. Computer-readable signal media can also be any computer-readable medium other than computer-readable storage media, which can send, propagate, or transmit a program for use by or in connection with an instruction execution system, apparatus, or device. The computer program contained on the computer-readable medium can be transmitted using any suitable medium, including but not limited to wireless, wired, etc., or any suitable combination thereof.

[0118] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this application. Each block in a flowchart or block diagram may represent a module, segment, or portion of code, which contains one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in a block diagram or flowchart, and combinations of blocks in a block diagram or flowchart, may be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0119] In the corresponding figures of the above embodiments, connecting lines can represent the connection relationship between various components, indicating more constitutive signal paths and / or one or more ends of some lines having arrows to indicate the main information flow direction. Connecting lines are an identifier and are not a limitation on the scheme itself, but rather the use of these lines in combination with one or more exemplary embodiments helps to more easily connect circuits or logic units. Any signal represented (determined by design requirements or preferences) can actually include one or more signals that can be transmitted in any direction and can be implemented in any suitable type of signal scheme.

[0120] The units described in the embodiments of this application can be implemented in software or hardware, and the described units can also be located in a processor. The names of these units do not necessarily limit the specific unit itself.

[0121] Another aspect of this application provides a computer-readable storage medium having a computer program stored thereon that, when executed by a processor, implements the method described above. This computer-readable storage medium may be included in the electronic device described in the above embodiments, or it may exist independently and not assembled into the electronic device.

[0122] It should be noted that although several modules or units for the device used to perform actions have been mentioned in the detailed description above, this division is not mandatory. In fact, according to the embodiments of this application, the features and functions of two or more modules or units described above can be embodied in one module or unit. Conversely, the features and functions of one module or unit described above can be further divided and embodied by multiple modules or units.

[0123] Through the above description of the embodiments, those skilled in the art will readily understand that the exemplary embodiments described herein can be implemented by software or by combining software with necessary hardware. Therefore, the technical solutions according to the embodiments of this application can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (such as a CD-ROM, USB flash drive, external hard drive, etc.) or on a network, including several instructions to cause a computing device (such as a personal computer, server, touch terminal, or network device, etc.) to execute the method according to the embodiments of this application.

[0124] It should be noted that this application can be used in a wide range of general-purpose or special-purpose computing system environments or configurations. For example: personal computers, server computers, handheld or portable devices, tablet devices, multiprocessor systems, microprocessor-based systems, set-top boxes, programmable consumer electronics devices, network PCs, minicomputers, mainframe computers, distributed computing environments including any of the above systems or devices, etc.

[0125] Other embodiments of this application will readily occur to those skilled in the art upon consideration of the specification and practice of the embodiments disclosed herein. This application is intended to cover any variations, uses, or adaptations of this application that follow the general principles of this application and include common knowledge or customary techniques in the art not disclosed herein.

[0126] It should be understood that the above content is only a preferred exemplary embodiment of this application and is not intended to limit the implementation of this application. Those skilled in the art can easily make corresponding modifications or alterations based on the main concept and spirit of this application. Therefore, the scope of protection of this application should be the scope of protection claimed in the claims.

Claims

1. A vehicle collision detection method, characterized in that, The vehicle collision detection method includes: The sensor signal parameters, drivable area, and target obstacle information are acquired by multiple elastic wave sensors installed on the target vehicle. If the sensor signal parameters are greater than or equal to the collision trigger threshold, the door signal transition duration parameters, horn signal transition duration parameters, hood opening status, and trunk opening status are acquired. If both the door signal transition duration parameters and the horn signal transition duration parameters are greater than or equal to the preset signal transition detection threshold, and both the hood opening status and the trunk opening status are open, then it is determined to be the first initial collision state, and the collision confirmation module is triggered to confirm the first initial collision state based on the surround view sensor and the ultrasonic sensor, to obtain the confirmed first initial collision state, and the confirmed first initial collision state is determined as the first collision detection state. The collision probability of the target vehicle in the drivable area is determined based on the drivable area, and the collision probability between the target vehicle and the target obstacle is determined based on the target obstacle information. The collision state prediction of the target vehicle is based on the collision probability of the target vehicle in the drivable area and the collision probability of the target vehicle with the target obstacle. This includes calculating the target collision confidence based on the collision probability of the target vehicle in the drivable area and the collision probability of the target vehicle with the target obstacle according to preset weight information, and obtaining the target collision confidence. When the target collision confidence is less than the target collision confidence threshold, it is determined to be the second initial collision state, and the collision confirmation module is triggered to confirm the second initial collision state, obtain the confirmed second initial collision state, and determine the confirmed second initial collision state as the second collision detection state. The collision state of the target vehicle is determined based on the first collision detection state and the second collision detection state.

2. The vehicle collision detection method according to claim 1, characterized in that, After determining the first initial collision state, the vehicle collision detection method further includes: Obtain the confidence level of the sensing device; If the confidence level of the sensing device is greater than or equal to a preset sensing confidence threshold, then the first initial collision state is determined as the first collision detection state. If the confidence level of the sensing device is less than the preset sensing confidence threshold, the collision confirmation module is triggered to confirm the first initial collision state.

3. The vehicle collision detection method according to any one of claims 1-2, characterized in that, Determining the collision probability of the target vehicle within the drivable area based on the drivable area includes: Traverse the target driving points of the target vehicle in the drivable area, and determine the collision risk status of each target driving point. The drivable area includes multiple target driving points. The collision risk status of the target driving point is determined based on the distance between the target driving point and the target vehicle and the driving status. The collision risk status includes no risk and risk. If there is a target driving point with a collision risk status, the collision probability of the target vehicle in the drivable area is determined based on the proportion of target driving points with a collision risk status among all the target driving points.

4. The vehicle collision detection method according to any one of claims 1-2, characterized in that, Determining the collision probability between the target vehicle and the target obstacle based on the target obstacle information includes: Obtain the speed and acceleration of the target vehicle; The collision probability between the target vehicle and the target obstacle is determined based on the speed, acceleration, and the target obstacle distance and movement speed information in the target obstacle information.

5. A vehicle collision detection device, characterized in that, The vehicle collision detection device includes: The data acquisition module is used to acquire multiple sensor signal parameters, drivable area and target obstacle information. The sensor signal parameters are acquired by multiple vehicle-mounted elastic wave sensors. The first collision detection module is used to acquire door signal transition duration parameters, horn signal transition duration parameters, hood opening status, and trunk opening status if each of the sensor signal parameters is greater than or equal to a collision trigger threshold; if the door signal transition duration parameters and horn signal transition duration parameters are both greater than or equal to a preset signal transition detection threshold, and the hood opening status and trunk opening status are both open, then it is determined to be the first initial collision state, and the collision confirmation module is triggered to confirm the first initial collision state based on the surround view sensor and ultrasonic sensor, to obtain the confirmed first initial collision state, and the confirmed first initial collision state is determined as the first collision detection state; The second collision detection module is used to determine the collision probability of the target vehicle in the drivable area based on the drivable area, and to determine the collision probability between the target vehicle and the target obstacle based on the target obstacle information; to predict the collision state of the target vehicle based on the collision probability of the target vehicle in the drivable area and the collision probability between the target vehicle and the target obstacle, including calculating the target collision confidence based on the collision probability of the target vehicle in the drivable area and the collision probability between the target vehicle and the target obstacle according to preset weight information, and obtaining the target collision confidence; when the target collision confidence is less than the target collision confidence threshold, it is determined as the second initial collision state, and the collision confirmation module is triggered to confirm the second initial collision state, obtain the confirmed second initial collision state, and determine the confirmed second initial collision state as the second collision detection state; The collision state determination module is used to determine the vehicle collision state based on the first collision detection state and the second collision detection state.

6. An electronic device, characterized in that, include: One or more processors; A storage device for storing one or more programs, which, when executed by one or more processors, cause the electronic device to implement the vehicle collision detection method as described in any one of claims 1 to 4.

7. A computer-readable storage medium, characterized in that, It stores computer-readable instructions that, when executed by the computer's processor, cause the computer to perform the vehicle collision detection method as described in any one of claims 1 to 4.

Images