Vehicle early warning method, device, and storage medium

Abstract

The present application relates to the technical field of automobiles, and provides a vehicle early warning method, a device, and a storage medium. The method comprises: acquiring vehicle traveling data, wherein the vehicle traveling data comprises vehicle related data of a vehicle during traveling, and / or environment related data of the surrounding environment of the vehicle; performing anomaly detection processing on the vehicle traveling data to obtain an anomaly detection result, wherein the anomaly detection result is used for representing whether there is an anomaly during the traveling of the vehicle; and when it is determined, on the basis of the anomaly detection result, that there is an anomaly during the traveling of the vehicle, activating a vehicle-mounted unmanned aerial vehicle, which is provided on the vehicle, for early warning. According to the method of the present application, early warning can be performed by the vehicle-mounted unmanned aerial vehicle, thereby widening an early warning range, and preventing further loss of life and property.

Description

Vehicle early warning method, device and storage medium

[0001] This application claims priority to the Chinese patent application filed with the China Patent Office on April 3, 2024, with application number 202410408905.6 and application name “Vehicle Warning Method, Device and Storage Medium”, the entire contents of which are incorporated by reference into this application. Technical Field

[0002] The present application relates to the field of automotive technology, and more specifically, to a vehicle early warning method, device, and storage medium. Background Art

[0003] As the volume of traffic on the road continues to increase, abnormal phenomena in vehicle driving, such as vehicle accidents and road congestion, are becoming more and more frequent.

[0004] At present, when an abnormality occurs during the driving of a vehicle, traffic participants can generally be warned by flashing the lights, honking the horn, placing a tripod or using ice cream cones.

[0005] For example, in the event of a vehicle accident, a person could place a tripod or popsicle cone to warn other traffic participants. However, this warning method not only poses safety risks but also can lead to increased loss of life and property. Another example is the use of hazard lights to warn other traffic participants in a congested road, but the warning range is limited and ineffective. Summary of the Invention

[0006] The purpose of this application is to provide a vehicle warning method, device and storage medium to solve the technical problems in the existing technology that some warning methods have certain safety risks, and the existing warning methods have a small warning range and limited warning effect.

[0007] In a first aspect, the present application provides a vehicle early warning method, comprising:

[0008] Acquiring vehicle driving data; wherein the vehicle driving data includes vehicle-related data of the vehicle during driving, and / or environment-related data of the vehicle's surrounding environment;

[0009] Performing anomaly detection processing on the vehicle driving data to obtain an anomaly detection result; wherein the anomaly detection result is used to indicate whether there is an anomaly in the driving process of the vehicle;

[0010] When it is determined based on the abnormality detection result that there is an abnormality in the driving process of the vehicle, the vehicle-mounted drone configured for the vehicle is activated to issue an early warning.

[0011] In one example, obtaining vehicle driving data includes:

[0012] Determine the vehicle-related data based on first data collected by each sensor of the vehicle; and obtain the environment-related data based on second data within a first distance range collected by each sensor of the vehicle and third data within a second distance range collected by each sensor of the vehicle-mounted drone; wherein the first data is used to indicate the vehicle's own state; and the second data and the third data are used to indicate the vehicle's surrounding environment;

[0013] The vehicle driving data is determined based on the vehicle-related data and the environment-related data.

[0014] In one example, performing anomaly detection processing on the vehicle driving data to obtain an anomaly detection result includes:

[0015] Performing anomaly detection processing on the vehicle-related data to obtain a first detection result; wherein the first detection result indicates whether there is an abnormality in the vehicle during the driving process of the vehicle;

[0016] Anomaly detection processing is performed on the environment-related data to obtain a second detection result; wherein the second detection result indicates whether there is any abnormality in the surrounding environment during the driving process of the vehicle.

[0017] In one example, the abnormality detection result represents the first detection result; and when it is determined based on the abnormality detection result that there is an abnormality in the driving process of the vehicle, activating a vehicle-mounted drone configured for the vehicle to issue an early warning includes:

[0018] If it is determined based on the first detection result that an abnormality occurs in the vehicle during driving, generating a first warning message based on the first detection result;

[0019] The vehicle-mounted drone is started to hover at a first target position behind the vehicle; and the vehicle-mounted drone projects the first warning information.

[0020] In one example, the abnormality detection result represents the second detection result; and when it is determined based on the abnormality detection result that there is an abnormality in the driving process of the vehicle, activating a vehicle-mounted drone configured for the vehicle to issue an early warning includes:

[0021] If it is determined based on the second detection result that there is an abnormality in the surrounding environment during the driving of the vehicle, generating a second warning message based on the second detection result;

[0022] The vehicle-mounted drone is started to hover at a second target position in the environment surrounding the vehicle; and the vehicle-mounted drone projects the second warning information.

[0023] In one example, the vehicle warning method further includes:

[0024] Based on the second detection result, a third warning message is generated; and the third warning message is displayed on a display interface of the vehicle to warn the driver of the vehicle.

[0025] In one example, the vehicle warning method further includes:

[0026] When it is determined based on the abnormality detection result that an abnormality exists in the environment surrounding the vehicle, early warning sound data matching the abnormality detection result is determined; and the vehicle-mounted drone broadcasts the early warning sound data.

[0027] In a second aspect, the present application provides a vehicle warning device, comprising:

[0028] A perception module, configured to obtain vehicle driving data; wherein the vehicle driving data includes vehicle-related data of the vehicle during driving and / or environment-related data of the vehicle's surrounding environment;

[0029] a detection module, configured to perform anomaly detection processing on the vehicle driving data to obtain an anomaly detection result; wherein the anomaly detection result is used to indicate whether there is an anomaly in the driving process of the vehicle;

[0030] The early warning module is used to start the vehicle-mounted drone configured for the vehicle to issue an early warning when it is determined that there is an abnormality in the driving process of the vehicle based on the abnormality detection result.

[0031] In one example, the perception module is used to:

[0032] Determine the vehicle-related data based on first data collected by each sensor of the vehicle; and obtain the environment-related data based on second data within a first distance range collected by each sensor of the vehicle and third data within a second distance range collected by each sensor of the vehicle-mounted drone; wherein the first data is used to indicate the vehicle's own state; and the second data and the third data are used to indicate the vehicle's surrounding environment;

[0033] The vehicle driving data is determined based on the vehicle-related data and the environment-related data.

[0034] In one example, the detection module is used to:

[0035] Performing anomaly detection processing on the vehicle-related data to obtain a first detection result; wherein the first detection result indicates whether there is an abnormality in the vehicle during the driving process of the vehicle;

[0036] Anomaly detection processing is performed on the environment-related data to obtain a second detection result; wherein the second detection result indicates whether there is any abnormality in the surrounding environment during the driving process of the vehicle.

[0037] In one example, the early warning module includes:

[0038] a first warning submodule configured to generate a first warning message based on the first detection result if, when the abnormality detection result represents the first detection result, it is determined based on the first detection result that the vehicle has an abnormality during driving;

[0039] The vehicle-mounted drone is started to hover at a first target position behind the vehicle; and the vehicle-mounted drone projects the first warning information.

[0040] In one example, the early warning module includes:

[0041] a second warning submodule configured to generate a second warning message based on the second detection result if, based on the second detection result, it is determined that an abnormality exists in the surrounding environment during the driving of the vehicle when the abnormality detection result represents the second detection result;

[0042] The vehicle-mounted drone is started to hover at a second target position in the environment surrounding the vehicle; and the vehicle-mounted drone projects the second warning information.

[0043] In one example, the second early warning submodule is further used to:

[0044] Based on the second detection result, a third warning message is generated; and the third warning message is displayed on a display interface of the vehicle to warn the driver of the vehicle.

[0045] In one example, the early warning module includes:

[0046] The third warning submodule is used to determine warning sound data that matches the abnormality detection result when it is determined that there is an abnormality in the vehicle surrounding environment based on the abnormality detection result; and to enable the vehicle-mounted drone to broadcast the warning sound data.

[0047] In a third aspect, the present application provides an electronic device, comprising: a processor, and a memory communicatively connected to the processor;

[0048] The memory stores computer-executable instructions;

[0049] The processor executes the computer-executable instructions stored in the memory to implement the method described in the first aspect.

[0050] In a fourth aspect, the present application provides a computer-readable storage medium, wherein the computer-readable storage medium stores computer-executable instructions, and when the computer-executable instructions are executed by a processor, they are used to implement the method described in the first aspect.

[0051] In a fifth aspect, the present application provides a computer program product, comprising: computer-executable instructions, which are used to implement the method described in the first aspect when executed by a processor.

[0052] In a sixth aspect, the present application provides a vehicle, comprising the electronic device described in the third aspect.

[0053] In a seventh aspect, the present application provides a computer program, comprising: when the computer program is executed by a processor, implementing the method described in the first aspect.

[0054] The vehicle early warning method, device and storage medium provided by the present application can obtain vehicle driving data during the driving process of the vehicle, and determine whether there is any abnormality in the driving process of the vehicle by performing anomaly detection on the vehicle driving data. When it is determined that there is an abnormality in the driving process of the vehicle, the vehicle-mounted drone configured for the vehicle can be activated for early warning. This vehicle early warning method can not only improve the vehicle's perception and early warning capabilities by obtaining vehicle driving data in a larger range, but also replace the traditional early warning method (for example, manually placing a tripod, ice cream cone, etc.) for early warning by activating the vehicle-mounted drone, thereby improving the early warning range and early warning efficiency, thereby improving the effectiveness of vehicle early warning. At the same time, it can also protect the personal safety of the driver / passenger and prevent the driver / passenger from being injured during the early warning. BRIEF DESCRIPTION OF THE DRAWINGS

[0055] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0056] FIG1 is a flow chart of a vehicle warning method provided in an embodiment of the present application;

[0057] FIG2 is a flow chart of another vehicle warning method provided in an embodiment of the present application;

[0058] FIG3 is a schematic structural diagram of a vehicle equipped with a vehicle-mounted drone according to an embodiment of the present application;

[0059] FIG4 is a schematic diagram of controlling a vehicle-mounted drone to provide hovering warning according to an embodiment of the present application;

[0060] FIG5 is a schematic diagram of a process for performing anomaly detection processing on environment-related data according to an embodiment of the present application;

[0061] FIG6 is a schematic structural diagram of a vehicle warning device provided in an embodiment of the present application;

[0062] FIG7 is a schematic structural diagram of another vehicle warning device provided in an embodiment of the present application;

[0063] FIG8 is a schematic structural diagram of an electronic device provided in an embodiment of the present application.

[0064] The above drawings illustrate specific embodiments of the present application, which will be described in more detail below. These drawings and the textual description are not intended to limit the scope of the present application in any way, but rather to illustrate the concepts of the present application to those skilled in the art by reference to specific embodiments. DETAILED DESCRIPTION

[0065] The term "and / or" herein simply describes an association relationship, indicating that three relationships can exist. For example, A and / or B can represent the existence of A alone, the simultaneous existence of A and B, and the existence of B alone. In addition, the term "at least one" herein refers to any combination of at least two of any one or more of a plurality of items. For example, "at least one of A, B, and C" can represent any one or more elements selected from the set consisting of A, B, and C.

[0066] As the volume of traffic on the road continues to increase, abnormal phenomena such as vehicle accidents and road congestion are becoming more and more frequent. Therefore, timely and effective early warning is particularly important when there are abnormalities in the vehicle or its surrounding environment.

[0067] At present, the perception and warning of abnormalities in the vehicle and its surrounding environment are mainly achieved through the sensors installed in the vehicle itself and the driver's driving experience. This perception method has a limited perception range, which in turn affects the vehicle's perception ability.

[0068] When an abnormality is detected in the vehicle or its surroundings, traffic participants are generally warned by hazard lights, honking the horn, placing a tripod or placing ice cream cones. For example, it can be used to warn pedestrians around the vehicle and vehicles around the vehicle.

[0069] For example, when a vehicle is involved in an accident, a person (e.g., the driver / passenger of the vehicle) can place a tripod or ice cream cone to warn traffic participants. However, this warning method not only poses safety risks but also easily increases the loss of life and property.

[0070] For example, in the event of road congestion, double flashes can be used to alert traffic participants. However, this warning method has a small warning range and cannot provide an effective warning.

[0071] The vehicle warning method, device and storage medium provided in this application can realize data communication between the vehicle and the on-board drone through wireless communication connection between the vehicle and the on-board drone configured in the vehicle, thereby solving the above technical problems of the existing technology based on the on-board drone configured in the vehicle.

[0072] In one example, a communication connection can be established between a vehicle and a vehicle-mounted drone through a wireless local area network (for example, WiFi technology), or through a dedicated communication protocol (for example, CAN bus protocol, software-defined radio SDR technology, etc.). There is no limitation on the wireless communication connection method between the vehicle and the vehicle-mounted drone, which is subject to achievable implementation.

[0073] The following specific embodiments describe in detail the technical solution of the present application and how the technical solution of the present application solves the above-mentioned technical problems. The following specific embodiments can be combined with each other, and the same or similar concepts or processes may not be repeated in some embodiments. The embodiments of the present application will be described below in conjunction with the accompanying drawings.

[0074] FIG1 is a flow chart of a vehicle early warning method provided in an embodiment of the present application. As shown in FIG1 , the vehicle early warning method includes:

[0075] S101. Acquire vehicle driving data; wherein the vehicle driving data includes vehicle-related data during the driving process of the vehicle and / or environment-related data of the vehicle's surrounding environment.

[0076] In one example, the vehicle driving data can be collected by various sensors installed on the vehicle and / or various sensors in an onboard drone configured for the vehicle. For example, the sensors may include radar, lidar, ultrasonic sensors, visual sensors, inertial navigation, etc. The type and number of sensors are not limited here and are based on practicality.

[0077] In one example, the vehicle driving data may be determined by acquiring data from an application installed in the vehicle system. For example, the vehicle driving data may be determined by acquiring navigation data in a navigation application installed in the vehicle system.

[0078] In one example, the data collected by the sensor can be directly determined as vehicle driving data, or the data collected by the sensor can be preprocessed by a controller installed on the vehicle to obtain vehicle driving data. For example, the data collected by the speed sensor can be directly determined as vehicle driving data, or the current vehicle speed can be calculated based on the data collected by the visual sensor and the calculated current vehicle speed can be determined as vehicle driving data.

[0079] In one example, the vehicle-related data included in the vehicle driving data can be used to indicate the status of the vehicle itself, and the environment-related data included in the vehicle driving data is used to indicate road participants and roads in the vehicle's surrounding environment.

[0080] At this time, the vehicle driving data includes but is not limited to: the vehicle's own status data, relevant data of traffic participants around the vehicle (for example, traffic participants may include but are not limited to pedestrians, other moving vehicles, etc., where pedestrians include people walking and people riding bicycles), and road data of the road on which the vehicle is traveling (for example, road data may include but is not limited to road signs, road obstacles, etc.).

[0081] Among them, the vehicle's own status data can be used to determine whether the vehicle itself has an abnormality. At this time, the vehicle's own status data can indicate at least the following information: vehicle startup status, vehicle position, vehicle speed, vehicle direction, the working status of the vehicle's sensors (used to determine whether the vehicle's sensors are working normally), the vehicle's driving system's operating signal (used to determine whether the driving system is operating normally), etc.

[0082] In one example, the acquired vehicle driving data may be determined based on the driving scenario of the vehicle. For example, the acquired vehicle driving data may be determined based on the distance traveled by the vehicle or the road condition of the vehicle.

[0083] For example, when the vehicle has traveled a long distance, the vehicle-mounted drone configured for the vehicle can be activated to collect environmental-related data of the vehicle's surroundings. At this time, the vehicle driving data obtained includes vehicle-related data and environmental-related data; when the vehicle has traveled a short distance, only the data collected by various sensors on the vehicle can be obtained. At this time, the vehicle driving data obtained is vehicle-related data.

[0084] In another example, when the road condition on which the vehicle is traveling is relatively congested, or when it is detected that the road condition on which the vehicle is traveling is relatively dangerous (for example, the road on which the vehicle is traveling is a winding mountain road, on the edge of a cliff, etc.), the vehicle-mounted drone configured for the vehicle can be activated to collect environmental-related data of the vehicle's surroundings. At this time, the acquired vehicle driving data includes vehicle-related data and environmental-related data; when there are fewer traffic participants on the road on which the vehicle is traveling, only the data collected by various sensors on the vehicle can be acquired. At this time, the acquired vehicle driving data only includes vehicle-related data.

[0085] In one example, in addition to determining the acquired vehicle driving data based on the vehicle's driving scenario, the vehicle driving data may also be determined by detecting a user trigger operation. For example, if a user trigger is detected to initiate an onboard drone operation, and the onboard drone is determined to be activated, the acquired vehicle driving data may include both vehicle-related data and environment-related data. If a user trigger is not detected to initiate an onboard drone operation, and the onboard drone is determined to be inactivated, the acquired vehicle driving data may include only vehicle-related data.

[0086] S102 , performing anomaly detection processing on the vehicle driving data to obtain an anomaly detection result; wherein the anomaly detection result is used to indicate whether there is an anomaly in the vehicle driving process.

[0087] The presence of an abnormality during vehicle operation can be understood as whether the vehicle is abnormal during operation and / or whether the vehicle's surrounding environment is abnormal. For example, a vehicle breakdown / accident indicates a vehicle abnormality; an accident / congestion / road collapse indicates an abnormality in the vehicle's surrounding environment.

[0088] In one example, an anomaly detection algorithm may be used to perform anomaly detection on vehicle driving data to obtain an anomaly detection result.

[0089] In one example, when anomaly detection is performed on vehicle driving data based on an anomaly detection algorithm, the following detection processes may be included but are not limited to: dynamic object detection, drivable area detection, lane line detection, road surface detection, vehicle detection, road surface detection, drivable area detection, traffic flow analysis, traffic scene recognition, etc. At this time, corresponding anomaly detection algorithms can be used for different detection processes. For example, when detecting dynamic objects, the anomaly detection method may be an optical flow method, a frame difference method, a Kalman filter method, a convolutional neural network algorithm, etc.; or, when detecting drivable areas (or for detecting lane lines), the anomaly detection algorithm may be an edge detection algorithm, a Gabor filter, a convolutional neural network algorithm, etc.; or, when detecting vehicles, the anomaly detection algorithm may be a nearest neighbor classification algorithm, a Gaussian mixture model, etc.

[0090] In one example, the embodiment of the present application can also train a neural network model (for example, a CNN network, a YOLO network, etc.) by setting a training data set, so as to perform one or more anomaly detections on vehicle driving data based on the trained neural network model, for example, performing road surface detection, detecting lane lines on the road surface, vehicles involved in traffic accidents on the road surface, collapsed roads, etc.

[0091] In one example, the anomaly detection algorithm in the embodiments of the present application may also be a detection method that compares the status data of various vehicle sensors with preset anomaly detection status data to determine whether the vehicle has experienced an abnormality. For example, a vehicle collision sensor monitors the vehicle in real time to determine whether it has experienced a collision. In the event of a collision, its status information changes from normal status information to collision prompt information. If the vehicle controller detects the collision prompt information, it will determine that the preset anomaly detection status data has been detected, and thus determine that the vehicle has experienced an abnormality.

[0092] S103: When it is determined based on the abnormality detection result that there is an abnormality in the vehicle's driving process, the vehicle-mounted drone configured for the vehicle is activated to issue an early warning.

[0093] In one example, if an abnormality is determined in the vehicle's driving process based on the abnormality detection results, the driver / passenger of the vehicle can trigger the vehicle-mounted drone start-up command in the vehicle to start the vehicle-mounted drone configured for early warning. The vehicle-mounted drone can also be started for early warning according to the pre-set vehicle-mounted drone start-up rules.

[0094] In one example, a vehicle-mounted drone start-up instruction can be generated according to a pre-set vehicle-mounted drone start-up rule to start the vehicle-mounted drone for early warning.

[0095] In one example, a pre-set vehicle-mounted drone startup rule can be used to indicate a generation rule for a vehicle-mounted drone startup instruction. At this time, the generation rule for the vehicle-mounted drone startup instruction corresponds to a vehicle-mounted drone startup warning method.

[0096] In one example, the method of initiating an early warning by the vehicle-mounted drone may include at least one of the following: a passive early warning method, an active early warning method, and an emergency early warning method.

[0097] Among them, the passive start warning method can be understood as a method of generating a vehicle-mounted drone start command after detecting the user's start warning operation to start the vehicle-mounted drone for warning. For details, please refer to the following methods:

[0098] Method 1: The voice acquisition module collects the driver / passenger's voice data corresponding to the preset voice data, and then performs voice recognition on the voice data to obtain the voice content. At this time, the vehicle-mounted drone start command can be generated based on the voice content.

[0099] Method 2: Generate a vehicle-mounted drone launch command by receiving driver / passenger operation data. The operation data can be determined by triggering a trigger button on the central control screen, triggering the operating space on the vehicle's steering wheel, or triggering the remote control terminal corresponding to the vehicle-mounted drone.

[0100] For example, if an abnormality is detected during the vehicle's driving process, a pop-up window will be displayed on the vehicle's display interface (e.g., the central control screen) indicating the abnormality, and a button indicating whether to activate the vehicle's onboard drone for early warning will be displayed in the pop-up window. After the user triggers the button to activate the vehicle's onboard drone for early warning, it is determined that the user's activation operation for early warning has been detected, and a vehicle-mounted drone activation instruction can be generated.

[0101] Method 3: Generate a vehicle drone launch command based on the driver / passenger's gestures captured by the vehicle's built-in camera. For example, after capturing the driver / passenger's "index finger up" gesture, a vehicle drone launch command is generated.

[0102] Among them, the active start-up warning method can be understood as a method in which, if no user start-up warning operation is detected within a preset time period, a vehicle-mounted drone start-up instruction is automatically generated, and the vehicle-mounted drone is automatically started for warning. For example, if, based on the abnormality detection results, it is determined that there is an abnormality in the vehicle's driving process, an abnormality reminder message is displayed in a pop-up window on the vehicle's display interface, and an operation button for whether to start the vehicle-mounted drone for warning is displayed in the pop-up window. If no user triggering the start-up of the vehicle-mounted drone for warning is detected within a preset time period (for example, 5 seconds, 10 seconds, etc., the preset time period is not specifically limited here), it is determined that the user start-up warning operation has not been detected. In this case, a vehicle-mounted drone start-up instruction can be directly generated after the preset time period to start the vehicle-mounted drone for warning.

[0103] In one example, after detecting that the user triggers an operation button for not starting the vehicle-mounted drone for warning, the vehicle-mounted drone is not started for warning.

[0104] In one example, an emergency warning method can be understood as directly generating a vehicle-mounted drone activation command to launch the vehicle-mounted drone for early warning if, based on anomaly detection results, an abnormality is determined to exist during vehicle operation, and the abnormality type is a preset type. For example, if a vehicle accident is detected during driving and the vehicle's airbags deploy, a vehicle-mounted drone activation command can be directly generated to launch the vehicle-mounted drone for early warning, thereby improving early warning efficiency and avoiding further accidents.

[0105] In one example, after generating a vehicle-mounted drone start-up instruction, the vehicle-mounted drone start-up instruction can be sent to the vehicle-mounted drone via wireless communication (e.g., SDR communication) to start the vehicle-mounted drone for early warning.

[0106] In one example, when a vehicle-mounted drone issues an early warning, the early warning may be issued in at least one of the following ways: hovering warning, hovering warning, projecting warning information, broadcasting warning information, etc.

[0107] It can be seen from the above description that the embodiment of the present application can obtain vehicle driving data during the driving process of the vehicle, and determine whether there is any abnormality in the driving process of the vehicle by performing anomaly detection on the vehicle driving data. When it is determined that there is an abnormality in the driving process of the vehicle, the vehicle-mounted drone configured for the vehicle can be activated for early warning. This vehicle early warning method can not only improve the vehicle's perception and early warning capabilities by obtaining vehicle driving data in a larger range, but also replace the traditional early warning method (for example, manually placing a tripod, ice cream cone, etc.) for early warning by activating the vehicle-mounted drone, thereby improving the early warning range and early warning efficiency, and thus improving the effectiveness of the vehicle early warning. At the same time, it can also protect the personal safety of the driver / passenger and prevent the driver / passenger from being injured during the early warning.

[0108] FIG2 is a flow chart of another vehicle warning method provided in an embodiment of the present application. As shown in FIG2 , the vehicle warning method includes:

[0109] S201. Determine vehicle-related data based on first data collected by each sensor of the vehicle; and obtain environment-related data based on second data within a first distance range collected by each sensor of the vehicle and third data within a second distance range collected by each sensor on the vehicle-mounted drone.

[0110] The first data is used to indicate the vehicle's own state; the second data and the third data are used to indicate the vehicle's surrounding environment.

[0111] In one example, the first distance range is smaller than the second distance range. There is no limitation on the values ​​of the first distance range and the second distance range, which are subject to practicability.

[0112] S202: Determine vehicle driving data based on vehicle-related data and environment-related data.

[0113] In one example, when the vehicle-mounted drone is started to collect environment-related data, the first data collected by the vehicle, the second data collected by the vehicle, and the third data collected by the vehicle-mounted drone can be determined as vehicle driving data; when the vehicle-mounted drone is not started to collect environment-related data, the first data collected by the vehicle and the second data collected by the vehicle can be determined as vehicle driving data.

[0114] This implementation method can obtain data within different distance ranges through the vehicle and the vehicle-mounted drone, and then obtain vehicle driving data, which can improve the vehicle's perception range and thus improve the vehicle's perception ability.

[0115] In one example, Figure 3 is a schematic diagram of the structure of a vehicle equipped with an onboard drone, as provided in an embodiment of the present application. As shown in Figure 3, the vehicle warning system provided in an embodiment of the present application can include two parts: the vehicle and the onboard drone. In this case, the vehicle's perception system can acquire vehicle-related data collected by various sensors on the vehicle, while the onboard drone's perception system can acquire environmental data collected by various sensors on the vehicle.

[0116] In one example, after the perception system of the vehicle obtains vehicle-related data, the steps described in the following S203 can be executed.

[0117] S203: Perform abnormality detection on the vehicle-related data to obtain a first detection result.

[0118] The first detection result indicates whether there is any abnormality in the vehicle during driving. For example, abnormality detection processing can be performed on vehicle-related data to determine whether the vehicle has a fault or whether the vehicle has been involved in a traffic accident.

[0119] In one example, assuming that the vehicle-related data is the vehicle position and vehicle driving direction mentioned above, when it is detected that the vehicle position deviates from the distance threshold range of the normal driving path and the vehicle's driving direction has not changed, it is determined that the vehicle has a fault.

[0120] Alternatively, assuming that the vehicle-related data is the operating signal of the driving system of the above-mentioned vehicle, the operating signal of the driving system of the vehicle can be detected. For example, the collected operating signal of the driving system of the vehicle can be compared with a preset signal mapping table. If it is determined that the operating signal of the driving system of the vehicle is an abnormal operating signal, it is determined that the vehicle has a fault.

[0121] In another example, assuming the vehicle-related data includes the operating status of the vehicle's sensors and the vehicle's startup status, if the operating status of the vehicle's sensors indicates that the vehicle is not operating properly and the startup status indicates that the vehicle has started, then it is determined that the vehicle has been involved in a traffic accident. In this case, the vehicle's sensors may have been damaged by the traffic accident and are therefore not operating properly. Alternatively, if the vehicle's collision is directly determined based on the vehicle's collision sensor signal, then the vehicle is determined to have been involved in a traffic accident.

[0122] S204: If it is determined based on the first detection result that there is an abnormality in the vehicle during driving, a first warning message is generated based on the first detection result.

[0123] In one example, the first warning information may represent the first detection result. For example, when the first detection result represents that the vehicle has been involved in a traffic accident, the first warning information may represent accident information.

[0124] In one example, the first warning information may also represent detailed information of the first detection result. For example, when the first detection result represents that a vehicle accident has occurred, the first warning information may also represent detailed information of the accident. For example, the detailed information of the accident may be: a collision of a minor degree (such as a scratch, a bump, etc.), a collision of a severe degree (such as a door falling off, a car body overturning, etc.), etc.

[0125] At this time, the first warning information can be expressed in text (for example, the first warning information can be the text "an accident occurred" or "accident"), or it can be expressed in image / logo (for example, the first warning information can be an accident logo or a picture of the accident scene), etc. There is no limitation on the expression of the first warning information here, and it is subject to the ability to express the first detection result.

[0126] In addition, the first warning information may be two-dimensional information or three-dimensional information. There is no limitation on the expression form of the first warning information, which is subject to practicability.

[0127] In one example, after the first warning information is generated, the first warning information can be transmitted to the vehicle-mounted drone by wireless transmission (for example, WiFi technology, software-defined radio SDR technology, etc.) through the data transmission system included in the vehicle part and the vehicle-mounted drone part shown in Figure 3, so that the projection interaction system of the vehicle-mounted drone can perform a projection warning based on the first warning information. For details, see the steps described in S205 below.

[0128] S205: Start the vehicle-mounted drone and make it hover at a first target position behind the vehicle; and make the vehicle-mounted drone project a first warning message.

[0129] In one example, the first target position may be the same as or different from the position of a traditional tripod / ice cream cone, and the first target position is not specifically limited here.

[0130] In one example, the first target position can be determined based on the detailed information of the first detection result represented by the first warning information. For example, if the above detailed information represents that a collision has occurred and the degree is mild, the first target position is determined based on the first numerical value; if the above detailed information represents that a collision has occurred and the degree is severe, the first target position is determined based on the second numerical value. At this time, the first numerical value can be less than or equal to the second numerical value.

[0131] In one example, the first warning information may be expressed differently when the first target position is different. For example, when the first target position is far from the rear of the vehicle, the first warning information may be three-dimensional information (in this case, the first warning information may be modeled to obtain a three-dimensional model, and the three-dimensional model may be determined as the three-dimensional information corresponding to the first warning information); when the first target position is close to the rear of the vehicle, the first warning information may be two-dimensional information.

[0132] In another example, two-dimensional information corresponding to the first warning information and three-dimensional stereoscopic information corresponding to the first warning information can also be projected simultaneously at the first target position. There is no limitation on the expression method of the first warning information, which is subject to practicability.

[0133] In one example, before starting a vehicle-mounted drone and making it hover at a first target position behind the vehicle, it is necessary to first determine that the power of the vehicle-mounted drone is turned on and is in a state that can be started. When the vehicle determines that the power of the vehicle-mounted drone is turned on and is in a state that can be started, the vehicle-mounted drone start-up command and the determined first target position are sent to the vehicle-mounted drone, so that the vehicle-mounted drone issues a hovering warning.

[0134] See Figure 4, which is a schematic diagram of controlling a vehicle-mounted drone for hover warning according to an embodiment of the present application. As shown in Figure 4, after the vehicle-mounted drone's data transmission module receives the vehicle-mounted drone start command and the pre-set first target position transmitted by the vehicle's data transmission module, it sends the command to the trajectory planning module via the mission decision module.

[0135] At this time, the visual marker (such as the AprilTag array) can be observed by the visual sensor installed on the vehicle-mounted drone. At this time, the position and posture of the visual marker can be transformed into the world coordinate system based on the positioning result of the vehicle-mounted drone in the world coordinate system, and then smoothed using the Kalman linear filter to generate the position and speed of the vehicle with the visual marker in the world coordinate system. At this time, the vehicle-mounted drone uses the installed visual sensors (for example, binocular cameras), inertial measurement units and global navigation satellite systems (GNSS) for combined positioning, and then obtains the position and speed feedback of the vehicle-mounted drone through the extended Kalman filter. Then, the obtained position and speed are sent to the flight control module of the vehicle-mounted drone.

[0136] At the same time, the image data collected by the visual sensor installed on the vehicle-mounted drone can also be converted into a bird's-eye view through a local map generation method (for example, the HDMapNet model) to obtain a corresponding depth map. At this time, semantic recognition can also be performed on the image data collected by the visual sensor, and then a local map can be constructed based on the semantic recognition results and the depth map. Then, the local map can be sent to the trajectory planning module so that the trajectory planning module can obtain the planned path of the vehicle-mounted drone according to a preset trajectory planning method (for example, the MINCO trajectory planning method) and a preset first target position.

[0137] Then, the planned path of the vehicle-mounted drone is sent to the flight control module, so that the flight control module can control the attitude of the vehicle-mounted drone according to the posture, speed and planned path of the vehicle-mounted drone, so that the vehicle-mounted drone hovers to the first target position behind the vehicle, and the vehicle-mounted drone projects the first warning information.

[0138] In one example, the projection interaction system of a vehicle-mounted drone may include a projection device installed on the drone. At this time, after receiving the first warning information, the projection interaction system of the vehicle-mounted drone (i.e., the projection device) projects the first warning information. There is no limitation on the model of the projection device here, as long as it can project two-dimensional first warning information and / or three-dimensional first warning information.

[0139] In one example, after a vehicle-mounted drone hovering warning is issued, the flight status of the vehicle-mounted drone can also be monitored in real time to ensure that the vehicle-mounted drone can hover to the first target position behind the vehicle and project the first warning information.

[0140] In the above embodiment, when the vehicle senses that the surrounding environment / the vehicle itself is dangerous / abnormal, the vehicle-mounted drone can be started and hovered at a safe distance behind the vehicle to project a first warning message to remind traffic participants. This not only makes vehicle warning more convenient and quick, but also avoids the manual placement of warning signs and avoids further loss of life and property.

[0141] In addition, this implementation method can also provide timely and effective warnings through vehicle-mounted drone warnings in scenarios where a vehicle is involved in a traffic accident and it is impossible to manually place warning signs.

[0142] In one example, after the perception system of the vehicle-mounted drone obtains environment-related data, the steps described in the following S206 can be executed.

[0143] S206: Perform anomaly detection processing on the environment-related data to obtain a second detection result.

[0144] The second detection result indicates whether there is any abnormality in the surrounding environment during the driving process of the vehicle. For example, it can be determined whether the road in the surrounding environment is congested, whether the road in the surrounding environment has collapsed, or whether an accident has occurred in the surrounding environment.

[0145] In one example, when the environment-related data represents a road in the environment surrounding the vehicle, a second detection result can be obtained by detecting and processing the second data obtained by the vehicle and the third data obtained by the vehicle-mounted drone.

[0146] In one example, Figure 5 is a flow chart of an anomaly detection and processing process for environment-related data provided in an embodiment of the present application. As shown in Figure 5, after the vehicle obtains the second data, the second data can be detected and processed by the SOC (System-on-a-Chip) chip installed in the vehicle. For example, the second data can be processed by road surface detection, lane line detection, drivable area monitoring, dynamic object detection, etc. to obtain data detection results.

[0147] The detection processing algorithm can refer to the content described in S102 above, and will not be described in detail here.

[0148] At this time, the data detection results can indicate the labeled image data. For example, the data detection results can include labeled lane lines, dynamic objects, road surface information (for example, road signs, traffic accident warning signs, accident sites, collapsed roads, etc.), drivable areas, etc.

[0149] In one example, the image data annotated by the data detection results can be aggregated to obtain an aggregated result, and a data analysis result corresponding to the second data can be determined based on the aggregated result. For example, the aggregated result can include the type of lane line, the number and location of dynamic objects, the location and number of traffic accident warning signs, the location and number of traffic accident sites, the location and number of collapsed road surfaces, the size and location of the drivable area, etc.

[0150] In one example, data acquired by sensors other than visual sensors installed on the vehicle may also be processed to obtain a data analysis result corresponding to the second data. For example, information such as the vehicle's current speed and acceleration, collected by a speed sensor or acceleration sensor installed on the vehicle, may be processed to determine whether the vehicle is moving slowly or stagnant, and the data analysis result may be determined based on the determination of whether the vehicle is moving slowly or stagnant.

[0151] Afterwards, a first processing result may be determined based on the data analysis result and the data detection result. For example, the first processing result may include the number and position of dynamic objects in the surrounding environment, whether the vehicle is currently in a stagnant state, etc.

[0152] As shown in FIG5 , after acquiring the third data, the vehicle-mounted drone can transmit the third data to the vehicle via a wireless transmission method (e.g., Ethernet). At this time, the third data can be detected and processed by the SOC chip installed in the vehicle. For example, the third data can be processed by traffic scene recognition, traffic flow analysis, drivable area detection, road surface detection, vehicle detection, etc. to obtain a second processing result. At this time, the second processing result can indicate the annotated image data and the data analysis result. At this time, the annotated image data can include vehicles annotated with rectangular frames, road surface markings annotated with rectangular frames, traffic signs annotated with circular frames, drivable areas annotated with rectangular frames, etc. The data analysis result can include a traffic flow analysis result. For example, when the vehicle detection result indicates that the number of vehicles is greater than a preset threshold, the traffic flow analysis result can be that the traffic volume is large.

[0153] It should be noted that the embodiment of the present application does not specifically limit the annotation format of the image data.

[0154] In one example, after obtaining the first processing result and the second processing result, a second detection result can be obtained based on the first processing result and the second processing result. In this case, the second detection result may include the annotated image data and a summary result after summarizing the annotated information in the annotated image data.

[0155] In one example, after obtaining the second detection result, after performing relative pose estimation, the second detection result can be fused with the high-precision map using coordinate system alignment and map fusion methods to obtain a fused map. The detection result identifier corresponding to the second detection result is annotated in the fused map. For example, if the second detection result indicates that the number of vehicles is greater than a preset threshold, a congestion identifier is generated and annotated in the fused map. At this point, the fused map can be displayed on the vehicle's central control screen, and at least a portion of the second detection result can be displayed on the vehicle's central control screen.

[0156] In another example, when the environment-related data is navigation data in a navigation application installed in the vehicle system, the second detection result can be obtained by analyzing the navigation data.

[0157] S207: If it is determined based on the second detection result that there is an abnormality in the surrounding environment during the driving of the vehicle, a second warning message is generated based on the second detection result.

[0158] In one example, after obtaining the second detection result, it can be determined based on the second detection result whether there are any abnormalities in the surrounding environment during the vehicle's travel. For example, if the second detection result determines that there are many other vehicles on the road the current vehicle is traveling on, and the current vehicle is traveling slowly or stagnant, then it indicates that congestion has occurred. For another example, if the second detection result determines that there is a collapse sign, then it is determined that the road in the surrounding environment of the current vehicle has collapsed. For another example, if the second detection result determines that there is an accident vehicle, then it indicates that an accident has occurred in the surrounding environment of the vehicle.

[0159] In one example, if an abnormality exists in the surrounding environment during vehicle driving, the second warning information generated may represent the second detection result. For example, if the second detection result indicates road congestion, the second warning information may represent congestion information; if the second detection result indicates road collapse, the second warning information may represent collapse information, etc. In this case, the second warning information may be expressed in text, images, or logos. There is no limitation on the expression method of the second warning information, as long as it can express the second detection result.

[0160] In one example, the second warning information may further include detailed information about the second detection result. For example, if the second detection result indicates congestion information, the second warning information may further include detailed information about the congestion. For example, the detailed information about the congestion may include: congestion occurs, the degree of congestion is mild, and the length is X meters; congestion occurs, the degree of congestion is severe, and the length is Y meters. The values ​​of X and Y are positive integers, and there is no specific limitation on the values ​​of X and Y.

[0161] In addition, the second warning information may be two-dimensional information or three-dimensional information. There is no limitation on the expression form of the second warning information, which is subject to practicability.

[0162] In one example, the expression method / form of the first warning information and the second warning information may be the same or different, which is not specifically limited here.

[0163] In one example, after the second warning information is generated, a projection interactive system of the vehicle-mounted drone can be used to project an early warning based on the second warning information. For details, see the step described in S208 below.

[0164] S208: Start the vehicle-mounted drone, causing it to hover at a second target position in the environment surrounding the vehicle; and cause the vehicle-mounted drone to project a second warning message.

[0165] In one example, the implementation process of starting a vehicle-mounted drone, making the vehicle-mounted drone hover to a second target position in the vehicle's surrounding environment, and making the vehicle-mounted drone project a second warning message can refer to the above-mentioned implementation process of starting a vehicle-mounted drone, making the vehicle-mounted drone hover to a first target position behind the vehicle, and making the vehicle-mounted drone project a first warning message, which will not be repeated here.

[0166] In one example, the second target position may be the same as or different from the first target position. The relationship between the first target position and the second target position is not limited here.

[0167] In one example, the second target location can be determined based on the second detection result. For example, if the second detection result indicates congestion information, the second target location can be determined based on the third value; if the second detection result indicates collapse information, the second target location can be determined based on the fourth value. In this case, the third value can be greater than or equal to the fourth value.

[0168] In another example, the second target position can also be determined based on the detailed information of the second detection result represented by the second warning information. For example, when the above detailed information indicates that congestion occurs, the degree is mild, and the length is X meters, the second target position is determined based on the fifth value; when the above detailed information indicates that congestion occurs, the degree is severe, and the length is Y meters, the second target position is determined based on the sixth value. At this time, the fifth value may be less than or equal to the sixth value.

[0169] In one example, the second warning message may be presented differently depending on the second target location. For example, if the second target location is farther from the rear of the vehicle, the second warning message may be three-dimensional; if the second target location is closer to the rear of the vehicle, the second warning message may be two-dimensional.

[0170] In one example, when the types of the second detection results represented by the second warning information are different, different expressions can be used to project the second warning information. For example, when the second warning information represents congestion information, the second warning information can be an image expression; when the second warning information represents collapse information, the second warning information can be an identification expression.

[0171] In one example, when a vehicle-mounted drone is hovered at a first target position (or a second target position), the visual sensor installed on the vehicle-mounted drone can be used to perceive obstacle information on the hovering route of the vehicle-mounted drone. After detecting the obstacle information, the visual sensor can be used to obtain data such as the position and speed of the obstacle information, and the trajectory information of the obstacle can be predicted based on the position and speed of the obstacle information. Based on the trajectory information of the obstacle, the route for the vehicle-mounted drone can be replanned so that the vehicle-mounted drone can perform hovering warning according to the replanned route.

[0172] In one example, after the second warning information is generated, the second warning information can also be transmitted to the vehicle through the data transmission system included in the vehicle part and the vehicle-mounted drone part shown in Figure 3 using a wireless transmission method (for example, WiFi technology, software-defined radio SDR technology, etc.), so that the vehicle's display interaction system can issue an early warning based on the second warning information. For details, see the steps described in S209 below.

[0173] S209: Generate a third warning message based on the second detection result; and display the third warning message on a display interface of the vehicle to warn the driver of the vehicle.

[0174] In one example, the third warning information can be used to indicate the type of the second detection result. For example, when the second detection result indicates road congestion, the third warning information can be a congestion sign; when the second detection result indicates road collapse, the third warning information can be a collapse sign; when the second detection result indicates an accident in the surrounding environment, the third warning information can be an accident sign, etc.

[0175] In one example, the vehicle's display interaction system can be used to display a third warning message. At this time, the vehicle's display interaction system can receive the third warning message and display the third warning message on the vehicle's instrument screen, or it can be displayed on the vehicle's central control screen. There is no limitation on the display interface of the third warning message, so long as it can provide a warning to the driver.

[0176] In one example, after the third warning is displayed on the vehicle's display interface, the vehicle's voice system can also broadcast the abnormality details represented by the second detection result, so that even if the driver does not see or understand the third warning information, he or she can still receive the abnormality details.

[0177] In the above-mentioned embodiment, the vehicle-mounted drone can be used to detect and warn of abnormalities in the vehicle's surrounding environment, thereby expanding the vehicle's warning range and enabling the driver to perceive abnormal information of the surrounding environment outside the field of vision in advance, thereby calming the driver's emotions and improving driving safety to a certain extent.

[0178] In one example, when it is determined based on the abnormality detection result that there is an abnormality in the vehicle's surrounding environment, when the vehicle-mounted drone is started for early warning, the steps described in S210 below may also be executed.

[0179] S210: Determine warning sound data that matches the abnormality detection result; and enable the vehicle-mounted drone to broadcast the warning sound data.

[0180] In one example, the warning sound data may be voice data that matches the warning information (eg, the first warning information / the second warning information), or may be sound data that matches the abnormality detection result. For example, the sound data may be a whistle, a ringing bell, or the like.

[0181] This implementation method can enable traffic participants to obtain warning information more directly through sound broadcasting, thereby improving the efficiency of traffic participants in obtaining warning information.

[0182] FIG6 is a schematic diagram of the structure of a vehicle warning device provided in an embodiment of the present application. As shown in FIG6 , the vehicle warning device 600 includes:

[0183] The perception module 601 is used to obtain vehicle driving data; wherein the vehicle driving data includes vehicle-related data during the vehicle's driving process and / or environment-related data of the vehicle's surrounding environment.

[0184] The detection module 602 is used to perform anomaly detection processing on the vehicle driving data to obtain an anomaly detection result; wherein the anomaly detection result is used to indicate whether there is an anomaly in the vehicle driving process.

[0185] The early warning module 603 is used to start the vehicle-mounted drone configured for the vehicle to issue an early warning when it is determined that there is an abnormality in the vehicle's driving process based on the abnormality detection result.

[0186] FIG7 is a schematic diagram of the structure of another vehicle warning device provided in an embodiment of the present application. As shown in FIG7 , the vehicle warning device 700 includes:

[0187] The perception module 701 is used to obtain vehicle driving data; wherein the vehicle driving data includes vehicle-related data during the vehicle's driving process and / or environment-related data of the vehicle's surrounding environment.

[0188] The detection module 702 is used to perform anomaly detection processing on the vehicle driving data to obtain an anomaly detection result; wherein the anomaly detection result is used to indicate whether there is an anomaly in the vehicle driving process.

[0189] The early warning module 703 is used to start the vehicle-mounted drone configured for the vehicle to issue an early warning when it is determined that there is an abnormality in the vehicle's driving process based on the abnormality detection result.

[0190] In one example, the perception module 701 is configured to:

[0191] Determining vehicle-related data based on first data collected by various sensors of the vehicle; and obtaining environment-related data based on second data within a first distance range collected by various sensors of the vehicle and third data within a second distance range collected by various sensors of the vehicle-mounted drone; wherein the first data is used to indicate the vehicle's own state; and the second and third data are used to indicate the vehicle's surrounding environment;

[0192] Based on the vehicle-related data and the environment-related data, vehicle driving data is determined.

[0193] In one example, the detection module 702 is configured to:

[0194] Performing abnormality detection processing on vehicle-related data to obtain a first detection result; wherein the first detection result indicates whether there is any abnormality in the vehicle during the driving process of the vehicle;

[0195] Anomaly detection processing is performed on the environment-related data to obtain a second detection result; wherein the second detection result indicates whether there is any abnormality in the surrounding environment during the driving process of the vehicle.

[0196] In one example, the early warning module 703 includes:

[0197] The first warning submodule 7031 is configured to generate a first warning message based on the first detection result if, based on the first detection result, it is determined that the vehicle is abnormal during driving, when the abnormal detection result represents the first detection result;

[0198] The vehicle-mounted drone is started to hover at a first target position behind the vehicle; and the vehicle-mounted drone projects a first warning message.

[0199] In one example, the early warning module 703 includes:

[0200] The second warning submodule 7032 is configured to generate a second warning message based on the second detection result if, based on the second detection result, it is determined that the surrounding environment is abnormal during the vehicle's driving process;

[0201] The vehicle-mounted drone is started to hover at a second target position in the environment surrounding the vehicle; and the vehicle-mounted drone projects a second warning message.

[0202] In one example, the second early warning submodule 7032 is further configured to:

[0203] Based on the second detection result, a third warning message is generated; and the third warning message is displayed on a display interface of the vehicle to warn the driver of the vehicle.

[0204] In one example, the early warning module 703 includes:

[0205] The third warning submodule 7033 is used to determine warning sound data that matches the abnormality detection result when it is determined that there is an abnormality in the vehicle's surrounding environment based on the abnormality detection result; and to enable the vehicle-mounted drone to broadcast the warning sound data.

[0206] FIG8 is a schematic structural diagram of an electronic device provided in an embodiment of the present application. As shown in FIG8 , the electronic device 800 includes: a memory 801 and a processor 802 .

[0207] Memory 801 is a memory used to store computer-executable instructions executable by processor 802 .

[0208] The processor 802 is configured to execute the method provided in the above embodiment.

[0209] The electronic device further includes a receiver 803 and a transmitter 804. The receiver 803 is used to receive instructions and data sent by an external device, and the transmitter 804 is used to send instructions and data to the external device.

[0210] The present application also provides a computer-readable storage medium having computer-executable instructions stored thereon. When executed by a processor, the computer-executable instructions execute the steps of the vehicle warning method in the above-described method embodiment. The storage medium may be a volatile or non-volatile computer-readable storage medium.

[0211] An embodiment of the present application also provides a computer program product, which carries computer execution instructions. The instructions included in the computer execution instructions can be used to execute the steps of the vehicle warning method in the above method embodiment. For details, please refer to the above method embodiment and will not be repeated here.

[0212] An embodiment of the present application also provides a vehicle, which includes the above-mentioned electronic device.

[0213] An embodiment of the present application also provides a computer program, including: when the computer program is executed by a processor, the vehicle warning method in the above method embodiment is implemented.

[0214] It should be noted that for the aforementioned method embodiments, for the sake of simplicity, they are all expressed as a series of action combinations, but those skilled in the art should be aware that this application is not limited by the order of the actions described, because according to this application, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in this specification are all optional embodiments, and the actions and modules involved are not necessarily required by this application.

[0215] It should be further noted that, although the various steps in the flowchart are shown in sequence as indicated by the arrows, these steps are not necessarily performed in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order restriction on the execution of these steps, and these steps may be performed in other orders. Moreover, at least a portion of the steps in the flowchart may include multiple sub-steps or multiple stages, and these sub-steps or stages are not necessarily performed at the same time, but may be performed at different times. The execution order of these sub-steps or stages is not necessarily to be performed in sequence, but may be performed in turn or alternately with other steps or at least a portion of the sub-steps or stages of other steps.

[0216] It should be understood that the above-described device embodiments are merely illustrative, and the device of the present application may also be implemented in other ways. For example, the division of units / modules in the above-described embodiments is merely a logical functional division, and actual implementations may employ other division methods. For example, multiple units, modules, or components may be combined or integrated into another system, or some features may be omitted or not implemented.

[0217] In addition, unless otherwise specified, the functional units / modules in the various embodiments of the present application may be integrated into a single unit / module, each unit / module may exist physically separately, or two or more units / modules may be integrated together. The aforementioned integrated units / modules may be implemented in the form of hardware or software program modules.

[0218] If the integrated unit / module is implemented in hardware, the hardware may be digital circuits, analog circuits, etc. The physical implementation of the hardware structure includes, but is not limited to, transistors, memristors, etc. Unless otherwise specified, the processor may be any appropriate hardware processor, such as a CPU, GPU, FPGA, DSP, and ASIC. Unless otherwise specified, the storage unit may be any appropriate magnetic storage medium or magneto-optical storage medium, such as resistive random access memory (RRAM), dynamic random access memory (DRAM), static random access memory (SRAM), enhanced dynamic random access memory (EDRAM), high-bandwidth memory (HBM), hybrid memory cube (HMC), etc.

[0219] If the integrated unit / module is implemented in the form of a software program module and sold or used as an independent product, it can be stored in a computer-readable memory. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, which is stored in a memory and includes a number of instructions for enabling an electronic device (which can be a personal computer, server or network device, etc.) to execute all or part of the steps of the various embodiments of the present application. The aforementioned memory includes various media that can store program codes, such as a USB flash drive, a read-only memory (ROM), a random access memory (RAM), a mobile hard disk, a magnetic disk or an optical disk.

[0220] In the above embodiments, the description of each embodiment has its own emphasis. For parts not described in detail in a particular embodiment, please refer to the relevant description of other embodiments. The technical features of the above embodiments can be combined in any way. To keep the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0221] Those skilled in the art will readily appreciate other embodiments of the present invention after considering the specification and practicing the invention disclosed herein. This application is intended to cover any variations, uses, or adaptations of the present invention that follow the general principles of this application and include common knowledge or customary techniques in the art not disclosed herein. The description and examples are to be considered as exemplary only, and the true scope and spirit of the present application are indicated by the following claims.

[0222] It should be understood that the present application is not limited to the exact structure described above and shown in the drawings, and that various modifications and changes may be made without departing from the scope thereof. The scope of the present application is limited only by the appended claims.

Claims

1. A vehicle early warning method, characterized in that: The vehicle early warning method comprises: Acquiring vehicle driving data; wherein the vehicle driving data includes vehicle-related data of the vehicle during driving, and / or environment-related data of the vehicle's surrounding environment; Performing anomaly detection processing on the vehicle driving data to obtain an anomaly detection result; wherein the anomaly detection result is used to indicate whether there is an anomaly in the driving process of the vehicle; When it is determined based on the abnormality detection result that there is an abnormality in the driving process of the vehicle, the vehicle-mounted drone configured for the vehicle is activated to issue an early warning.

2. The vehicle warning method according to claim 1, characterized in that: Obtain vehicle driving data, including: Determine the vehicle-related data based on first data collected by each sensor of the vehicle; and obtain the environment-related data based on second data within a first distance range collected by each sensor of the vehicle and third data within a second distance range collected by each sensor of the vehicle-mounted drone; wherein the first data is used to indicate the vehicle's own state; and the second data and the third data are used to indicate the vehicle's surrounding environment; The vehicle driving data is determined based on the vehicle-related data and the environment-related data.

3. The vehicle warning method according to claim 1 or 2, characterized in that: Performing anomaly detection processing on the vehicle driving data to obtain an anomaly detection result includes: Performing anomaly detection processing on the vehicle-related data to obtain a first detection result; wherein the first detection result indicates whether there is an abnormality in the vehicle during the driving process of the vehicle; Anomaly detection processing is performed on the environment-related data to obtain a second detection result; wherein the second detection result indicates whether there is any abnormality in the surrounding environment during the driving process of the vehicle.

4. The vehicle warning method according to claim 3, characterized in that: The abnormal detection result represents the first detection result; When it is determined based on the abnormality detection result that an abnormality exists in the driving process of the vehicle, the vehicle-mounted drone configured for the vehicle is activated to issue an early warning, including: If it is determined based on the first detection result that an abnormality occurs in the vehicle during driving, generating a first warning message based on the first detection result; The vehicle-mounted drone is started to hover at a first target position behind the vehicle; and the vehicle-mounted drone projects the first warning information.

5. The vehicle warning method according to claim 3, characterized in that: The abnormal detection result represents the second detection result; When it is determined based on the abnormality detection result that an abnormality exists in the driving process of the vehicle, the vehicle-mounted drone configured for the vehicle is activated to issue an early warning, including: If it is determined based on the second detection result that there is an abnormality in the surrounding environment during the driving of the vehicle, generating a second warning message based on the second detection result; The vehicle-mounted drone is started to hover at a second target position in the environment surrounding the vehicle; and the vehicle-mounted drone projects the second warning information.

6. The vehicle warning method according to claim 5, characterized in that: The vehicle early warning method further includes: Based on the second detection result, a third warning message is generated; and the third warning message is displayed on a display interface of the vehicle to warn the driver of the vehicle.

7. The vehicle warning method according to any one of claims 1 to 6, characterized in that: The vehicle early warning method further includes: When it is determined based on the abnormality detection result that an abnormality exists in the environment surrounding the vehicle, early warning sound data matching the abnormality detection result is determined; and the vehicle-mounted drone broadcasts the early warning sound data.

8. An electronic device, characterized in that: include: a processor, and a memory communicatively connected to the processor; The memory stores computer-executable instructions; The processor executes the computer-executable instructions stored in the memory to implement the vehicle warning method according to any one of claims 1 to 7.

9. A computer-readable storage medium, characterized in that The computer-readable storage medium stores computer-executable instructions, which, when executed by a processor, are used to implement the vehicle warning method according to any one of claims 1 to 7.

10. A vehicle, characterized in that: The vehicle includes the electronic device according to claim 8.

11. A computer program product, characterized in that The computer program product includes: computer-executable instructions, which are used to implement the vehicle warning method according to any one of claims 1 to 7 when executed by a processor.

12. A computer program, characterized in that include: When the computer program is executed by a processor, the vehicle warning method according to any one of claims 1 to 7 is implemented.

13. A vehicle warning device, characterized in that: include: A perception module, configured to obtain vehicle driving data; wherein the vehicle driving data includes vehicle-related data of the vehicle during driving and / or environment-related data of the vehicle's surrounding environment; a detection module, configured to perform anomaly detection processing on the vehicle driving data to obtain an anomaly detection result; wherein the anomaly detection result is used to indicate whether there is an anomaly in the driving process of the vehicle; The early warning module is used to start the vehicle-mounted drone configured for the vehicle to issue an early warning when it is determined that there is an abnormality in the driving process of the vehicle based on the abnormality detection result.

14. The vehicle warning device according to claim 13, characterized in that: The perception module is used to: Determine the vehicle-related data based on first data collected by each sensor of the vehicle; and obtain the environment-related data based on second data within a first distance range collected by each sensor of the vehicle and third data within a second distance range collected by each sensor of the vehicle-mounted drone; wherein the first data is used to indicate the vehicle's own state; and the second data and the third data are used to indicate the vehicle's surrounding environment; The vehicle driving data is determined based on the vehicle-related data and the environment-related data.

15. The vehicle warning device according to claim 13 or 14, characterized in that: The detection module is used for: Performing anomaly detection processing on the vehicle-related data to obtain a first detection result; wherein the first detection result indicates whether there is an abnormality in the vehicle during the driving process of the vehicle; Anomaly detection processing is performed on the environment-related data to obtain a second detection result; wherein the second detection result indicates whether there is any abnormality in the surrounding environment during the driving process of the vehicle.

16. The vehicle warning device according to claim 15, characterized in that: The early warning module includes: a first warning submodule configured to generate a first warning message based on the first detection result if, when the abnormality detection result represents the first detection result, it is determined based on the first detection result that the vehicle has an abnormality during driving; The vehicle-mounted drone is started to hover at a first target position behind the vehicle; and the vehicle-mounted drone projects the first warning information.

17. The vehicle warning device according to claim 15, characterized in that: The early warning module includes: a second warning submodule configured to generate a second warning message based on the second detection result if, based on the second detection result, it is determined that an abnormality exists in the surrounding environment during the driving of the vehicle when the abnormality detection result represents the second detection result; The vehicle-mounted drone is started to hover at a second target position in the environment surrounding the vehicle; and the vehicle-mounted drone projects the second warning information.

18. The vehicle warning device according to claim 17, characterized in that: The second early warning submodule is further used for: Based on the second detection result, a third warning message is generated; and the third warning message is displayed on a display interface of the vehicle to warn the driver of the vehicle.

19. The vehicle warning device according to any one of claims 13 to 18, characterized in that: The early warning module also includes: The third warning submodule is used to determine warning sound data that matches the abnormality detection result when it is determined that there is an abnormality in the vehicle surrounding environment based on the abnormality detection result; and to enable the vehicle-mounted drone to broadcast the warning sound data.

Images