Vehicle control method and related apparatus

Abstract

A vehicle control method and a related apparatus, which are applied to the technical field of vehicles. The vehicle control method comprises: acquiring vehicle information of a first vehicle and information of a first airborne object; determining a collision severity between the first airborne object and the first vehicle on the basis of the vehicle information of the first vehicle and the information of the first airborne object; and controlling the first vehicle on the basis of the collision severity so that a predetermined component of the first vehicle sustains an impact of the first airborne object, wherein the first airborne object is located outside the first vehicle. According to the method, upon determining a collision severity, a first vehicle is controlled on the basis of the collision severity, so that a predetermined component of the first vehicle sustains an impact of a first airborne object, such that when a collision between the first airborne object and the first vehicle cannot be avoided, impact occurs, to the greatest extent possible, at a position within a relatively safe region of a vehicle body of the first vehicle, thereby reducing the threat posed by the first airborne object to the driving safety of the first vehicle, and improving vehicle driving safety.

Description

Vehicle control methods and related devices Technical Field

[0001] This application relates to the field of vehicle technology, and in particular to a vehicle control method and related apparatus. Background Technology

[0002] With the development of vehicle technology, the number of vehicles is continuously increasing, and traffic accidents are also increasing accordingly. For example, in high-speed scenarios, there may be flying objects such as stones scattered by the vehicle in front, floating debris, tires that have detached and bounced into the air, or even oncoming vehicles, which may hit the vehicle body, especially the windshield and other vulnerable areas that are closely related to safe driving, posing a safety threat to the driver and passengers.

[0003] Therefore, how to reduce the threat posed by incoming air objects to vehicle safety is an urgent problem that needs to be solved. Summary of the Invention

[0004] This application provides a vehicle control method and related apparatus that can reduce the threat of airborne objects to vehicle driving safety and improve vehicle driving safety.

[0005] In a first aspect, embodiments of this application provide a vehicle control method, which includes, but is not limited to, the following steps:

[0006] The system acquires vehicle information of the first vehicle and information about the first airborne object outside the first vehicle. Based on the vehicle information of the first vehicle and information about the first airborne object, it determines the collision level between the first airborne object and the first vehicle. Based on the collision level, it controls the first vehicle to withstand the impact of the first airborne object on a preset component of the first vehicle.

[0007] This application provides a vehicle control method. Upon detecting a first aerial object, the method determines the collision level between the aerial object and the first vehicle based on information about the aerial object and the vehicle's information. Optionally, the collision level can be used to assess information including, but not limited to, one or more of the following: the probability of a collision between the aerial object and the first vehicle; whether the collision can be avoided; and which specific component of the first vehicle the aerial object will impact. After determining the collision level, the method further controls the first vehicle to ensure that preset components of the first vehicle withstand the impact of the aerial object. This ensures that, in the event that a collision is unavoidable, the impact point occurs within a safe area of ​​the vehicle's body, thereby reducing the threat posed by the aerial object to the vehicle's driving safety and improving overall vehicle safety.

[0008] In one possible implementation, the aforementioned preset component is a second component, and the aforementioned control of the first vehicle based on the collision level to make the preset component of the first vehicle withstand the impact of the first airborne object can be achieved in ways including but not limited to the following:

[0009] The collision level is determined in relation to a first component of the first vehicle, and the first vehicle is controlled to withstand the impact of a first airborne object on a second component of the first vehicle, wherein the first component and the second component are different.

[0010] In this embodiment, when the collision level assessment indicates that a first airborne object will specifically collide with a first component of the first vehicle, considering the relatively low safety of the first component after impact and the potential significant threat to the vehicle's occupants, the vehicle control method in this embodiment can control the first vehicle to prevent the first component from colliding with the first airborne object, while allowing a second component of the first vehicle to withstand the impact. Compared to the first component being impacted, the second component is relatively safe and poses a smaller threat to the vehicle's occupants. Therefore, by ensuring that the impact contact point occurs in a safer area of ​​the first vehicle's body, the threat posed by the first airborne object to the vehicle's driving safety can be reduced, thereby improving vehicle driving safety.

[0011] In one possible implementation, the second component has a greater degree of rigidity than the first component, and / or the cost of the second component is lower than the cost of the first component.

[0012] In this embodiment, when the collision between the first airborne object and the first vehicle is deemed unavoidable based on the aforementioned collision level assessment, the collision priority of the second component of the first vehicle is higher than that of the first component. Optionally, factors related to the collision priority of the first vehicle's components may include, but are not limited to, any one or more of the following: the rigidity of the component and the cost of the component. For example, when the rigidity of the second component is greater than that of the first component, the safety of the second component in an impact is necessarily higher than that of the first component. Therefore, the collision priority of the second component is higher than that of the first component. Controlling the first vehicle so that its second component withstands the impact of the first airborne object can reduce the threat posed by the first airborne object to the driving safety of the first vehicle and improve driving safety. Furthermore, when the cost of the second component is lower than that of the first component, the damage caused by the impact of the second component is necessarily lower than that caused by the impact of the first component. Therefore, the collision priority of the second component is higher than that of the first component. Controlling the first vehicle so that its second component withstands the impact of the first airborne object can reduce the repair costs of the first vehicle after the impact.

[0013] In one possible implementation, the collision priority of the first component and / or the second component can be configured.

[0014] In this embodiment, the impact priority of different components on the first vehicle can be marked based on factors such as rigidity and cost. Optionally, the impact priorities of multiple components can be sorted to determine the collision priority of each component on the first vehicle when a collision between the first airborne object and the first vehicle is unavoidable. Optionally, the collision priority of components on a vehicle may differ depending on factors such as the vehicle model and brand; this embodiment does not impose such limitations. Therefore, the impact priorities of the first and / or second components can be configured by the user or preset by the vehicle manufacturer during the production of the first vehicle; this embodiment does not impose such limitations. Through this embodiment, the first vehicle can be controlled so that components with higher impact priorities bear the impact of the first airborne object, ensuring that the impact contact occurs in a safe area of ​​the vehicle body. This reduces the threat posed by the first airborne object to the driving safety of the first vehicle, improves driving safety, and reduces the repair costs of the first vehicle after a collision.

[0015] In one possible implementation, the first component includes at least one of the following: a windshield of the first vehicle, a door side window of the first vehicle, a lighting module of the first vehicle, a rearview mirror of the first vehicle, and a sensing module deployed on the body of the first vehicle.

[0016] In one possible implementation, the second component includes at least one of the following: the frame of the first vehicle, the hood of the first vehicle, the door of the first vehicle, and the bumper of the first vehicle.

[0017] In one possible implementation, controlling the first vehicle to withstand the impact of a first airborne object on a predetermined component of the first vehicle includes:

[0018] Control one or more of the speed, direction, and attitude of the first vehicle to ensure that a pre-defined component of the first vehicle withstands the impact of the first airborne object.

[0019] In one possible implementation, the vehicle information of the first vehicle includes one or more of the following: the speed of the first vehicle, the direction of travel of the first vehicle, and the body posture of the first vehicle.

[0020] In this embodiment, the vehicle posture of the first vehicle can include the vehicle body posture of the first vehicle under different driving scenarios during driving. For example, in the scenario of driving uphill, the front of the first vehicle tilts upward. Or, when driving on a sloping road surface that is higher on the left and lower on the right, the body of the first vehicle tilts to the right, and so on. This application embodiment does not limit this.

[0021] In one possible implementation, the collision level between the first aerial object and the first vehicle is determined based on the vehicle information of the first vehicle and the information of the first aerial object. This can be achieved in ways including, but not limited to, the following:

[0022] Based on the information of the first aerial object, the trajectory of the first aerial object is determined. Based on the trajectory of the first aerial object and the vehicle information of the first vehicle, the collision level is determined.

[0023] In this embodiment, a specific implementation for determining the collision level is also provided. Specifically, the collision level can be determined based on the trajectory of the first airborne object and the vehicle information of the first vehicle. This collision level can assess information including, but not limited to, any one or more of the following: the probability of the first airborne object colliding with the first vehicle; whether the collision can be avoided; and which component of the first vehicle the first airborne object will specifically impact. Optionally, the higher the probability of the first airborne object colliding with the first vehicle, the higher the collision level. Optionally, the more difficult it is to avoid the collision between the first airborne object and the first vehicle, the higher the collision level. Optionally, the lower the rigidity of the component of the first vehicle the first airborne object will impact, the higher the collision level. By determining the collision level in this embodiment, vehicle control decisions can be made more effectively. Even if a collision between the first airborne object and the first vehicle is unavoidable, the impact point should be placed in a safe area of ​​the vehicle body, thereby reducing the threat posed by the airborne object to the vehicle's driving safety and improving overall vehicle safety.

[0024] In one possible implementation, determining the trajectory of the first aerial object based on its information can be achieved in ways including, but not limited to, the following:

[0025] Based on the information of the first incoming object, the danger level of the first incoming object is determined, and if the danger level is greater than a first threshold, the trajectory of the first incoming object is determined.

[0026] This embodiment provides a possible specific implementation for determining the trajectory of a first aerial object. Specifically, based on information about the first aerial object, the hazard posed by the first aerial object to the driving of a first vehicle is assessed, thereby determining the hazard level of the first aerial object. Optionally, the first aerial object may include, but is not limited to, any one or more of the following: stones scattered by a vehicle in front, tires that have detached from a vehicle in front and bounced into the air, small birds in flight, oncoming vehicles, etc., and this application embodiment does not impose any limitations on these. Optionally, the higher the hazard posed by the first aerial object to the driving of the first vehicle, the higher its corresponding hazard level. When the hazard level is greater than a first threshold, the trajectory of the first aerial object is determined. The first threshold is not a fixed value and can be adjusted for different vehicle models, different driving scenarios, and other factors to ensure the safety of vehicle driving. Through this application embodiment, aerial objects can be detected, low-hazard-level aerial objects (indicating a low hazard to vehicle driving) can be filtered out, and high-hazard-level aerial objects can be tracked to enable timely vehicle control operations and ensure the safety of vehicle driving.

[0027] In one possible implementation, the information on the first aerial object includes the masking information of the first aerial object; the determination of the hazard level of the first aerial object based on the information on the first aerial object can be achieved in ways including but not limited to the following:

[0028] The mask information of the first incoming aerial object is input into the classification network model to determine the type of the first incoming aerial object. Based on the type of the first incoming aerial object, the hazard level of the first incoming aerial object is determined. The classification network model is used to classify the type of object.

[0029] In this embodiment, mask information of the first aerial object can be obtained based on a visual perception scheme (e.g., image frames captured by a camera), and the type of the first aerial object can be determined using a classification network model. Based on the type of the first aerial object, its hazard level can be determined. Through this embodiment, aerial objects can be detected, low-hazard-level objects (indicating a lower risk to vehicle operation) can be filtered out, and high-hazard-level objects can be tracked to enable timely vehicle control operations and ensure vehicle safety.

[0030] In one possible implementation, the information of the first aerial object includes a first image frame and a second image frame, wherein the first image frame and the second image frame are two consecutive adjacent images of the first aerial object during its movement; the determination of the trajectory of the first aerial object can be achieved in ways including but not limited to the following:

[0031] Based on the first image frame and the second image frame, a third image frame and a fourth image frame are obtained; the third image frame is an image frame scaled down from the first image frame by a first ratio, and the fourth image frame is an image frame scaled down from the second image frame by a first ratio.

[0032] The first image frame and the second image frame are input into the first optical flow network model to obtain the first optical flow; the first optical flow network model is used to predict the next frame or multiple frames of images corresponding to the first image frame and the second image frame.

[0033] The third and fourth image frames are input into the second optical flow network model to obtain the second optical flow; the second optical flow network model is used to predict the next frame or multiple frames corresponding to the third and fourth image frames.

[0034] By fusing the first optical flow and the second optical flow, the trajectory of the first incoming object in the air is obtained.

[0035] In this embodiment, based on a visual perception scheme (e.g., image frames captured by a camera), two consecutive adjacent frames of images of the first flying object during its movement can be obtained. The optical flow information of the first flying object is predicted by using an optical flow network model. Based on the predicted optical flow information, the trajectory of the first flying object can be identified, tracked, and predicted, so as to make corresponding vehicle control operations in a timely manner and ensure the safety of vehicle driving.

[0036] In one possible implementation, the first optical flow network model includes a first sub-network model, a second sub-network model, a third sub-network model, and a first optical flow feature fusion model; the input of the first image frame and the second image frame into the first optical flow network model to obtain the first optical flow can be implemented in ways including but not limited to the following:

[0037] The first image frame and the second image frame are input into the first sub-network model to obtain the first sub-optical flow.

[0038] Based on the first sub-optical flow, the second image frame is mapped to the first image frame to obtain the fifth image frame.

[0039] The first sub-optical flow, the fifth image frame, the first mapping error between the fifth image frame and the first image frame, the first image frame, and the second image frame are input into the second sub-network model to obtain the second sub-optical flow.

[0040] Based on the second sub-optical flow, the second image frame is mapped to the first image frame to obtain the sixth image frame.

[0041] The first and second image frames are input into the third sub-network model to obtain the third sub-optical flow.

[0042] Based on the third sub-optical flow, the second image frame is mapped to the first image frame to obtain the seventh image frame.

[0043] The second sub-optical flow, the third sub-optical flow, the first image frame, the second image frame, the sixth image frame, the seventh image frame, the second mapping error between the sixth image frame and the first image frame, and the third mapping error between the seventh image frame and the first image frame are input into the first optical flow feature fusion model to obtain the first optical flow.

[0044] In this embodiment, image frames of the first airborne object during its movement can be obtained based on a visual perception scheme (e.g., image frames captured by a camera). The optical flow information of the first airborne object is predicted by using an optical flow network model and an optical flow feature fusion model. Based on the predicted optical flow information, the trajectory of the first airborne object can be identified, tracked, and predicted so as to make corresponding vehicle control operations in a timely manner and ensure the safety of vehicle driving.

[0045] In one possible implementation, the fusion of the first optical flow and the second optical flow to obtain the trajectory of the first aerial object can be achieved in ways including but not limited to the following:

[0046] Upsampling is performed on the second optical flow, and the first optical flow and the upsampled second optical flow are input into the second optical flow feature fusion model to obtain the motion trajectory of the first airborne object.

[0047] In this embodiment, upsampling is used to enlarge the reduced image frame to its original size before subsequent fusion. Through this application embodiment, to accommodate aerial objects of different sizes, the original image frame can be scaled by a certain proportion to improve the recognition accuracy of aerial objects of different sizes, thereby improving the accuracy of tracking and recognizing the motion trajectory of aerial objects.

[0048] In one possible implementation, the information on the first incoming object includes its motion characteristics; based on this information, the hazard level of the first incoming object is determined, which can be achieved through methods including but not limited to the following:

[0049] Based on the motion characteristics of the first incoming object, the type of the first incoming object is determined, and based on the type of the first incoming object, the hazard level of the first incoming object is determined.

[0050] In this embodiment, motion characteristic information of the first aerial object can be obtained based on radar sensing schemes (such as data obtained from one or more of lidar, millimeter-wave radar, and ultrasonic radar, etc.), the type of the first aerial object can be determined, and the hazard level of the first aerial object can be determined based on its type. Through this embodiment, aerial objects can be detected, low-hazard-level aerial objects (indicating a low risk to vehicle operation) can be filtered out, and high-hazard-level aerial objects can be tracked to enable timely vehicle control operations and ensure vehicle driving safety.

[0051] In one possible implementation, the vehicle control method described above may also include, but is not limited to, the following steps:

[0052] Based on the collision level, a first alert message is issued, which is used to inform the first user of relevant information about the first incoming airborne object.

[0053] In this embodiment, a first warning message can be issued based on the collision level to remind the driver to pay attention to the direction of origin and hazard level of the incoming aerial object. Optionally, the first warning message can be presented through one or more of other warning methods, including but not limited to image and video display, voice broadcast, etc., and this application embodiment does not limit this. The first warning message in this application embodiment provides a more targeted warning, and is more likely to prompt the driver to pay attention to and take appropriate vehicle control actions in a timely manner for aerial objects with a high hazard level, ensuring the safety of vehicle operation.

[0054] In one possible implementation, the issuance of a first warning message based on the collision level can be achieved in ways including but not limited to the following:

[0055] Obtain the first user information corresponding to the first user inside the first vehicle. Based on the collision level and the first user information, if the vector angle between the first user's line of sight and the trajectory of the first flying object is greater than a second threshold, issue a first warning message.

[0056] In this embodiment, the vector angle between the trajectory direction of the first flying object and the line of sight of the first user is used to determine whether the first user is paying enough attention to the first flying object. If the vector angle is greater than a second threshold, it can be considered that the first user is not paying enough attention to the first flying object. Then, a first prompt message is issued to promptly remind the first user to pay attention to the source direction and danger level of the flying object, so as to make corresponding vehicle control operations in a timely manner and ensure the safety of vehicle driving.

[0057] In one possible implementation, the vehicle control method described above may also include, but is not limited to, the following steps:

[0058] A second warning message is issued to alert the surrounding area of ​​the first vehicle that a collision has occurred.

[0059] In this embodiment, when the first vehicle collides with the first airborne object, a second warning message can be issued to alert those around the first vehicle to the collision and prevent secondary accidents. Optionally, the second warning message may be implemented in ways including, but not limited to, activating hazard lights to warn oncoming vehicles; this embodiment does not limit this.

[0060] In one possible implementation, the vehicle control method described above may also include, but is not limited to, the following steps:

[0061] The collision information is sent to the associated account of the first vehicle. The collision information includes information about the first vehicle before and after the collision.

[0062] In this embodiment, when the first vehicle collides with the first airborne object, collision information can be sent to the associated account of the first vehicle, key collision information (such as video and / or images comparing the first vehicle before and after the collision) can be recorded, and materials can be automatically organized and sent to the associated account of the first vehicle to facilitate subsequent liability determination and compensation.

[0063] In one possible implementation, the vehicle control method described above may also include, but is not limited to, the following steps:

[0064] Send an alarm message to report the impact of the first vehicle and request rescue.

[0065] In one possible implementation, the sending of alarm information can be achieved in ways including but not limited to the following:

[0066] An alarm request is sent to the user inside the first vehicle. Upon receiving a response message to the alarm request, an alarm message is sent. The alarm request is used to inquire with the user inside the first vehicle whether to sound an alarm.

[0067] Secondly, embodiments of this application provide a method for identifying flying objects, which is applied to a first vehicle. The method for identifying flying objects specifically includes, but is not limited to, the following steps:

[0068] Information about a first aerial object is acquired, and based on this information, the trajectory of the first aerial object is determined. The first aerial object is located outside the first vehicle.

[0069] This application provides a method for identifying flying objects, which can determine the trajectory of a first flying object based on its information. This method enables the detection and trajectory tracking of flying objects, allowing for timely vehicle control operations and ensuring vehicle safety.

[0070] In one possible implementation, determining the trajectory of the first aerial object based on its information can be achieved in ways including, but not limited to, the following:

[0071] Based on the information of the first incoming object, the danger level of the first incoming object is determined, and if the danger level is greater than a first threshold, the trajectory of the first incoming object is determined.

[0072] This embodiment provides a possible specific implementation for determining the trajectory of a first aerial object. Specifically, based on information about the first aerial object, the hazard posed by the first aerial object to the driving of a first vehicle is assessed, thereby determining the hazard level of the first aerial object. Optionally, the first aerial object may include, but is not limited to, any one or more of the following: stones scattered by a vehicle in front, tires that have detached from a vehicle in front and bounced into the air, small birds in flight, oncoming vehicles, etc., and this application embodiment does not impose any limitations on these. Optionally, the higher the hazard posed by the first aerial object to the driving of the first vehicle, the higher its corresponding hazard level. When the hazard level is greater than a first threshold, the trajectory of the first aerial object is determined. The first threshold is not a fixed value and can be adjusted for different vehicle models, different driving scenarios, and other factors to ensure the safety of vehicle driving. Through this application embodiment, aerial objects can be detected, low-hazard-level aerial objects (indicating a low hazard to vehicle driving) can be filtered out, and high-hazard-level aerial objects can be tracked to enable timely vehicle control operations and ensure the safety of vehicle driving.

[0073] In one possible implementation, the information on the first aerial object includes the masking information of the first aerial object; the determination of the hazard level of the first aerial object based on the information on the first aerial object can be achieved in ways including but not limited to the following:

[0074] The mask information of the first incoming aerial object is input into the classification network model to determine the type of the first incoming aerial object. Based on the type of the first incoming aerial object, the hazard level of the first incoming aerial object is determined. The classification network model is used to classify the type of object.

[0075] In this embodiment, mask information of the first aerial object can be obtained based on a visual perception scheme (e.g., image frames captured by a camera), and the type of the first aerial object can be determined using a classification network model. Based on the type of the first aerial object, its hazard level can be determined. Through this embodiment, aerial objects can be detected, low-hazard-level objects (indicating a lower risk to vehicle operation) can be filtered out, and high-hazard-level objects can be tracked to enable timely vehicle control operations and ensure vehicle safety.

[0076] In one possible implementation, the information of the first aerial object includes a first image frame and a second image frame, wherein the first image frame and the second image frame are two consecutive adjacent images of the first aerial object during its movement; the determination of the trajectory of the first aerial object can be achieved in ways including but not limited to the following:

[0077] Based on the first image frame and the second image frame, a third image frame and a fourth image frame are obtained; the third image frame is an image frame scaled down from the first image frame by a first ratio, and the fourth image frame is an image frame scaled down from the second image frame by a first ratio.

[0078] The first image frame and the second image frame are input into the first optical flow network model to obtain the first optical flow; the first optical flow network model is used to predict the next frame or multiple frames of images corresponding to the first image frame and the second image frame.

[0079] The third and fourth image frames are input into the second optical flow network model to obtain the second optical flow; the second optical flow network model is used to predict the next frame or multiple frames corresponding to the third and fourth image frames.

[0080] By fusing the first optical flow and the second optical flow, the trajectory of the first incoming object in the air is obtained.

[0081] In this embodiment, based on a visual perception scheme (e.g., image frames captured by a camera), two consecutive adjacent frames of images of the first flying object during its movement can be obtained. The optical flow information of the first flying object is predicted by using an optical flow network model. Based on the predicted optical flow information, the trajectory of the first flying object can be identified, tracked, and predicted, so as to make corresponding vehicle control operations in a timely manner and ensure the safety of vehicle driving.

[0082] In one possible implementation, the first optical flow network model includes a first sub-network model, a second sub-network model, a third sub-network model, and a first optical flow feature fusion model; the input of the first image frame and the second image frame into the first optical flow network model to obtain the first optical flow can be implemented in ways including but not limited to the following:

[0083] The first image frame and the second image frame are input into the first sub-network model to obtain the first sub-optical flow.

[0084] Based on the first sub-optical flow, the second image frame is mapped to the first image frame to obtain the fifth image frame.

[0085] The first sub-optical flow, the fifth image frame, the first mapping error between the fifth image frame and the first image frame, the first image frame, and the second image frame are input into the second sub-network model to obtain the second sub-optical flow.

[0086] Based on the second sub-optical flow, the second image frame is mapped to the first image frame to obtain the sixth image frame.

[0087] The first and second image frames are input into the third sub-network model to obtain the third sub-optical flow.

[0088] Based on the third sub-optical flow, the second image frame is mapped to the first image frame to obtain the seventh image frame.

[0089] The second sub-optical flow, the third sub-optical flow, the first image frame, the second image frame, the sixth image frame, the seventh image frame, the second mapping error between the sixth image frame and the first image frame, and the third mapping error between the seventh image frame and the first image frame are input into the first optical flow feature fusion model to obtain the first optical flow.

[0090] In this embodiment, image frames of the first airborne object during its movement can be obtained based on a visual perception scheme (e.g., image frames captured by a camera). The optical flow information of the first airborne object is predicted by using an optical flow network model and an optical flow feature fusion model. Based on the predicted optical flow information, the trajectory of the first airborne object can be identified, tracked, and predicted so as to make corresponding vehicle control operations in a timely manner and ensure the safety of vehicle driving.

[0091] In one possible implementation, the fusion of the first optical flow and the second optical flow to obtain the trajectory of the first aerial object can be achieved in ways including but not limited to the following:

[0092] Upsampling is performed on the second optical flow, and the first optical flow and the upsampled second optical flow are input into the second optical flow feature fusion model to obtain the motion trajectory of the first airborne object.

[0093] In this embodiment, upsampling is used to enlarge the reduced image frame to its original size before subsequent fusion. Through this application embodiment, to accommodate aerial objects of different sizes, the original image frame can be scaled by a certain proportion to improve the recognition accuracy of aerial objects of different sizes, thereby improving the accuracy of tracking and recognizing the motion trajectory of aerial objects.

[0094] In one possible implementation, the information on the first incoming aerial object includes the motion characteristic information of the first incoming aerial object; the determination of the hazard level of the first incoming aerial object based on the information on the first incoming aerial object can be achieved by means including but not limited to the following:

[0095] Based on the motion characteristics of the first incoming object, the type of the first incoming object is determined, and based on the type of the first incoming object, the hazard level of the first incoming object is determined.

[0096] In this embodiment, motion characteristic information of the first aerial object can be obtained based on radar sensing schemes (such as data obtained from one or more of lidar, millimeter-wave radar, and ultrasonic radar, etc.), the type of the first aerial object can be determined, and the hazard level of the first aerial object can be determined based on its type. Through this embodiment, aerial objects can be detected, low-hazard-level aerial objects (indicating a low risk to vehicle operation) can be filtered out, and high-hazard-level aerial objects can be tracked to enable timely vehicle control operations and ensure vehicle driving safety.

[0097] Thirdly, embodiments of this application provide a vehicle control device, which includes a unit for performing the method as described in any of the first aspects.

[0098] In one possible design, the device includes:

[0099] The processing unit is used to acquire vehicle information of the first vehicle and information of a first aerial object outside the first vehicle, wherein the first aerial object is located outside the first vehicle.

[0100] The processing unit is further configured to determine the collision level between the first airborne object and the first vehicle based on the vehicle information of the first vehicle and the information of the first airborne object.

[0101] The processing unit is further configured to control the first vehicle based on the collision level so that a preset component of the first vehicle withstands the impact of the first airborne object.

[0102] In one possible implementation, the device further includes a communication unit;

[0103] The processing unit is specifically used to obtain vehicle information of the first vehicle and information of the first aerial object through the communication unit, wherein the first aerial object is located outside the first vehicle.

[0104] Regarding the processing unit and communication unit described in the third aspect and any possible implementation, the steps performed thereon can be referred to the corresponding implementations in the first aspect.

[0105] For the technical effects of the third aspect and any possible implementation, please refer to the description of the technical effects corresponding to the first aspect and the corresponding implementation.

[0106] Optionally, in the vehicle control device described in the third aspect above and any possible embodiment:

[0107] In one implementation, the vehicle control device is a vehicle control equipment. When the vehicle control device is a vehicle control equipment, the communication unit can be a transceiver or an input / output interface; the processing unit can be at least one processor. Optionally, the transceiver can be a transceiver circuit. Optionally, the input / output interface can be an input / output circuit.

[0108] In another implementation, the vehicle control device is a chip (system) or circuit used in vehicle control equipment. When the vehicle control device is a chip (system) or circuit used in vehicle control equipment, the communication unit can be a communication interface (input / output interface), interface circuit, output circuit, input circuit, pin, or related circuit on the chip (system) or circuit; the processing unit can be at least one processor, processing circuit, or logic circuit.

[0109] Fourthly, embodiments of this application provide an airborne object identification device, which includes a unit for performing the method as described in any of the second aspects.

[0110] In one possible design, the device includes:

[0111] A processing unit is used to acquire information about a first aerial object located outside the first vehicle;

[0112] The processing unit is also used to determine the trajectory of the first airborne object based on the information of the first airborne object.

[0113] In one possible implementation, the device further includes a communication unit;

[0114] The processing unit is specifically used to obtain information about the first aerial object through the communication unit.

[0115] Regarding the processing unit and communication unit described in the fourth aspect and any possible implementation, the steps performed thereon can be referred to the corresponding implementation in the second aspect.

[0116] For the technical effects of the fourth aspect and any possible implementation, please refer to the description of the technical effects corresponding to the second aspect and the corresponding implementation.

[0117] Optionally, in the aerial object identification device described in the fourth aspect above and any possible implementation:

[0118] In one implementation, the airborne object identification device is an airborne object identification equipment. When the airborne object identification device is an airborne object identification equipment, the communication unit can be a transceiver or an input / output interface; the processing unit can be at least one processor. Optionally, the transceiver can be a transceiver circuit. Optionally, the input / output interface can be an input / output circuit.

[0119] In another implementation, the airborne object identification device is a chip (system) or circuit used in an airborne object identification device. When the airborne object identification device is a chip (system) or circuit used in an airborne object identification device, the communication unit can be a communication interface (input / output interface), interface circuit, output circuit, input circuit, pins, or related circuits on the chip (system) or circuit; the processing unit can be at least one processor, processing circuit, or logic circuit.

[0120] Fifthly, embodiments of this application provide a vehicle control device including a processor. The processor is coupled to a memory and can be used to execute instructions in the memory to implement the methods described in the first aspect and any of the possible implementations. Optionally, the vehicle control device further includes a memory. Optionally, the vehicle control device further includes a communication interface, and the processor is coupled to the communication interface.

[0121] Sixthly, embodiments of this application provide an airborne object identification device, which includes a processor. The processor is coupled to a memory and can be used to execute instructions in the memory to implement the methods described in the second aspect and any of the possible implementations. Optionally, the airborne object identification device further includes a memory. Optionally, the airborne object identification device further includes a communication interface, and the processor is coupled to the communication interface.

[0122] In a seventh aspect, embodiments of this application provide a chip, including: logic circuitry and a communication interface. The communication interface is used to receive or transmit information; the logic circuitry is used to receive or transmit information through the communication interface, causing the chip to execute the methods of any one of the first to second aspects and any possible implementations described above.

[0123] Eighthly, embodiments of this application provide a computer-readable storage medium for storing a computer program (also referred to as code or instructions); when the computer program is run on a computer, the methods of any of the first to second aspects and any of the possible implementations described above are implemented.

[0124] Ninthly, embodiments of this application provide a computer program product, the computer program product comprising: a computer program (also referred to as code or instructions); and, when the computer program is run, causing a computer to perform the method of any one of the first to second aspects and any possible implementation thereof.

[0125] In a tenth aspect, embodiments of this application provide a system comprising a vehicle control device and an airborne object identification device, wherein the vehicle control device is used to perform the methods described in the first aspect and any possible implementation thereof, and the airborne object identification device is used to perform the methods described in the second aspect and any possible implementation thereof.

[0126] Eleventhly, embodiments of this application provide a terminal, the terminal including at least one vehicle control device as described in the third aspect, or an airborne object recognition device as described in the fourth aspect, or a vehicle control device as described in the fifth aspect, or an airborne object recognition device as described in the sixth aspect, or a chip as described in the seventh aspect, or a system as described in the tenth aspect.

[0127] Optionally, the terminal can be a means of transportation, such as a car, truck, aircraft, drone, slow transport vehicle, spacecraft, or ship, or any other possible means of transportation used in any possible scenario. This application embodiment does not limit this.

[0128] Optionally, the terminal is used to implement the method described in any one of the first or second aspects and any possible implementation.

[0129] Furthermore, in the process of performing the methods described in any of the first to second aspects and any possible embodiments described above, the processes related to sending and / or receiving information in the above methods can be understood as the process of the processor outputting information, and / or the process of the processor receiving input information. When outputting information, the processor can output the information to a transceiver (or communication interface, or transmitting module) so that the transceiver can transmit it. After the information is output by the processor, it may need to undergo other processing before reaching the transceiver. Similarly, when the processor receives input information, the transceiver (or communication interface, or transmitting module) receives the information and inputs it to the processor. Furthermore, after the transceiver receives the information, the information may need to undergo other processing before being input to the processor.

[0130] Based on the above principles, for example, the information sent mentioned in the aforementioned method can be understood as information output by the processor. Similarly, the information received can be understood as information received by the processor from input.

[0131] Optionally, unless otherwise specified, the operations of transmitting, sending, and receiving involved by the processor can be more generally understood as processor output and receiving, input, and other operations, unless they contradict their actual function or internal logic in the relevant description.

[0132] Optionally, in performing the methods described in the first aspect and any possible implementation above, the processor may be a processor specifically designed to perform these methods, or it may be a processor that performs these methods by executing computer instructions stored in memory, such as a general-purpose processor. The memory may be a non-transitory memory, such as read-only memory (ROM), which may be integrated with the processor on the same chip or disposed on different chips. This application does not limit the type of memory or the arrangement of the memory and processor.

[0133] In one possible implementation, at least one of the aforementioned memories is located outside the device.

[0134] In yet another possible implementation, at least one of the aforementioned memories is located within the device.

[0135] In another possible implementation, a portion of the memory of the at least one memory is located inside the device, while another portion is located outside the device.

[0136] In this application, the processor and memory may also be integrated into a single device, that is, the processor and memory can be integrated together. Attached Figure Description

[0137] To more clearly illustrate the technical solutions of the embodiments of this application, the drawings used in the embodiments of this application will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0138] Figure 1 is a schematic flowchart of a vehicle control method provided in an embodiment of this application;

[0139] Figure 2 is a flowchart illustrating an aerial object identification method provided in an embodiment of this application;

[0140] Figure 3 is a flowchart illustrating another vehicle control method provided in an embodiment of this application;

[0141] Figure 4 is a flowchart illustrating another method for identifying aerial objects provided in an embodiment of this application;

[0142] Figure 5 is a flowchart illustrating another vehicle control method provided in an embodiment of this application;

[0143] Figure 6 is a flowchart illustrating another vehicle control method provided in an embodiment of this application;

[0144] Figure 7 is a structural schematic diagram of a vehicle control device provided in an embodiment of this application;

[0145] Figure 8 is a structural schematic diagram of an aerial object identification device provided in an embodiment of this application;

[0146] Figure 9 is a schematic diagram of the structure of an electronic device provided in an embodiment of this application;

[0147] Figure 10 is a schematic diagram of the structure of a chip provided in an embodiment of this application. Detailed Implementation

[0148] To make the objectives, technical solutions, and advantages of this application clearer, the embodiments of this application will be described below with reference to the accompanying drawings.

[0149] The terms "first" and "second," etc., used in the specification, claims, and drawings of this application are used to distinguish different objects, not to describe a specific order. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or apparatus that includes a series of steps or units is not limited to the listed steps or units, but may optionally include steps or units not listed, or may optionally include other steps or units inherent to these processes, methods, products, or apparatuses.

[0150] The term "embodiment" as used herein means that a specific feature, structure, or characteristic described in connection with an embodiment may be included in at least one embodiment of this application. The appearance of this phrase in various places in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment mutually exclusive with other embodiments. Those skilled in the art will explicitly and implicitly understand that, unless otherwise specified or logically conflicting, the terminology and / or descriptions between the various embodiments of this application are consistent and can be mutually referenced, and technical features in different embodiments can be combined to form new embodiments based on their inherent logical relationships.

[0151] It should be understood that in this application, "at least one (item)" means one or more, "more than one" means two or more, "at least two (items)" means two or three or more, and "and / or" is used to describe the relationship between related objects, indicating that there can be three relationships. For example, "A and / or B" can mean: only A exists, only B exists, and A and B exist simultaneously, where A and B can be singular or plural. The character " / " generally indicates that the related objects before and after are in an "or" relationship. "At least one (item) of the following" or similar expressions refer to any combination of these items, including any combination of single or plural items. For example, at least one (item) of a, b, or c can mean: a, b, c, "a and b", "a and c", "b and c", or "a and b and c", where a, b, and c can be single or multiple.

[0152] It should be noted that, in this application, "instruction" can include direct instruction, indirect instruction, explicit instruction, and implicit instruction. When describing a certain instruction information for the purpose of instructing A, it can be understood that the instruction information carries A, directly instructs A, or indirectly instructs A.

[0153] In this application, the information indicated by the instruction information is called the information to be instructed. In specific implementations, there are many ways to indicate the information to be instructed, such as, but not limited to, directly indicating the information to be instructed, such as the information to be instructed itself or its index. It can also indirectly indicate the information to be instructed by indicating other information, where there is a correlation between the other information and the information to be instructed. It can also indicate only a part of the information to be instructed, while the other parts are known or pre-agreed upon. For example, the instruction of specific information can be achieved by using a pre-agreed (e.g., protocol-defined) arrangement of various information, thereby reducing instruction overhead to some extent. The information to be instructed can be sent as a whole or divided into multiple sub-information units, and the sending period and / or timing of these sub-information units can be the same or different. This application does not limit the specific sending method. The sending period and / or timing of these sub-information units can be predefined, for example, according to a protocol, or configured by the transmitting device by sending configuration information to the receiving device.

[0154] It should be noted that in this application, "send" can be understood as "output" and "receive" can be understood as "input". "Send information to A", where "to A" simply indicates the direction of information transmission, and A is the destination, does not limit "send information to A" to a direct transmission over the air interface. "Send information to A" includes sending information directly to A, as well as sending information indirectly to A through a transmitter. Therefore, "send information to A" can also be understood as "outputting information destined for A". Similarly, "receive information from A" indicates that the source of the information is A, including receiving information directly from A, as well as receiving information indirectly from A through a receiver. Therefore, "receive information from A" can also be understood as "inputting information from A".

[0155] This application provides a vehicle control method and related apparatus, applicable to the field of vehicle technology, such as a vehicle control method for rapid avoidance of aerial objects in high-speed scenarios. To better understand the technical solution of this application, the relevant terms and concepts that may be involved in the embodiments of this application are introduced below.

[0156] Flying objects: Objects moving from a distance in the sky at a certain speed toward the vehicle and its surroundings.

[0157] Optical flow is a method used in computer vision to detect moving objects. It analyzes the changes in pixels over time in an image sequence and the correspondence between adjacent frames to find the correspondence between the previous frame and the current frame, thereby calculating the motion information of objects between adjacent frames.

[0158] With the development of vehicle technology, the number of vehicles is continuously increasing, and traffic accidents are also increasing accordingly. For example, the relatively good road conditions on highways can lead to a decrease in driver alertness, and the monotonous scenery on highways can easily cause visual fatigue. However, in highway scenarios, there may be flying objects such as stones scattered from the vehicle in front, floating debris, tires that have detached and bounced into the air, or even oncoming vehicles, which may hit the vehicle body, especially vulnerable areas such as the windshield, which are closely related to safe driving, posing a safety threat to the driver and passengers.

[0159] Therefore, how to reduce the threat posed by incoming air objects to vehicle safety is an urgent problem that needs to be solved.

[0160] Therefore, this application provides a vehicle control method applicable to the vehicle field, such as a vehicle control method for rapid avoidance of aerial objects in high-speed scenarios. This method can reduce the threat posed by aerial objects to vehicle safety and improve vehicle driving safety. Specifically, it can be manifested in the following aspects:

[0161] On the one hand, due to the high speed of vehicles on highways, when faced with the threat of collision from flying objects, the vehicle control method in this application embodiment can quickly make a safety decision, determine whether the flying object is dangerous, and if so, try to avoid colliding with the vehicle.

[0162] On the other hand, if an object flying in the air inevitably collides with the vehicle, when the collision occurs, the vehicle control method in this application embodiment will decide to adjust the vehicle speed and vehicle posture to make the collision occur in the highest priority collision relatively safe area.

[0163] On the other hand, if an object flying into the air collides with the vehicle, the vehicle control method in this application embodiment will detect the safety of the personnel and the damage to the vehicle, and decide whether to call for rescue based on the actual situation. It will also fix key impact images and video sequences, automatically organize the materials and send them to the associated account corresponding to the current driver's account, so as to facilitate liability determination and compensation.

[0164] Please refer to Figure 1, which is a flowchart illustrating a vehicle control method provided in an embodiment of this application. This vehicle control method is applied in the field of vehicle technology, such as a vehicle control method for rapid avoidance of aerial objects in high-speed scenarios.

[0165] Specifically, the vehicle control method includes, but is not limited to, the following steps:

[0166] S101: The vehicle control device acquires vehicle information of the first vehicle and information of the first aerial object.

[0167] Optionally, the vehicle information of the first vehicle includes one or more of the following: the speed of the first vehicle, the direction of travel of the first vehicle, and the body posture of the first vehicle.

[0168] For example, the vehicle posture of the first vehicle may include the vehicle body posture under different driving scenarios during driving. For instance, in a driving scenario on an uphill slope, the front of the first vehicle tilts upwards. Or, when driving on a sloping road surface that is higher on the left and lower on the right, the entire body of the first vehicle tilts to the right, and so on. This application embodiment does not limit this.

[0169] Optionally, the first airborne object includes, but is not limited to, an object moving from a distance in the sky at a certain speed toward the vehicle and its surroundings.

[0170] For example, the first airborne object may include, but is not limited to, any one or more of the following: stones scattered by the vehicle in front, tires that have fallen off the vehicle in front and bounced into the air, small birds flying in the air, oncoming vehicles, falling leaves, plastic bags, etc., and this application embodiment does not limit this.

[0171] It is understood that the vehicle control device in the embodiments of this application may be a device equipped with a processor / chip that can execute computer execution instructions, or it may be a processor / chip that can execute computer execution instructions. Optionally, the vehicle control device may be an electronic device, or it may be a processor / chip within an electronic device, used to execute the vehicle control method in the embodiments of this application to reduce the threat of airborne objects to vehicle driving safety and improve vehicle driving safety.

[0172] Optionally, the vehicle control device and vehicle control method in the embodiments of this application can be applied to, but are not limited to, vehicle systems. The vehicle equipped with the vehicle system is an intelligent driving vehicle and can be replaced by a terminal device. The terminal device can be, but is not limited to, vehicles such as commercial vehicles, passenger cars, trains, industrial vehicles (such as forklifts, trailers, tractors, etc.), engineering vehicles (such as excavators, bulldozers, cranes, etc.), robots, etc. The embodiments of this application do not specifically limit this.

[0173] S102: The vehicle control device determines the collision level between the first airborne object and the first vehicle based on the vehicle information of the first vehicle and the information of the first airborne object.

[0174] It is understood that, after detecting the first flying object, the vehicle control method in this application embodiment will determine the collision level between the first flying object and the first vehicle based on the information of the first flying object and the vehicle information of the first vehicle.

[0175] Optionally, the collision rating can be used to assess information including but not limited to one or more of the following: the likelihood of a collision between the first airborne object and the first vehicle; whether a collision between the first airborne object and the first vehicle can be avoided; and which specific component of the first vehicle the first airborne object will collide with.

[0176] Optionally, the higher the probability of the first airborne object colliding with the first vehicle, the higher the collision level.

[0177] Optionally, the more difficult it is to avoid a collision between the first airborne object and the first vehicle, the higher the collision level.

[0178] Optionally, the higher the collision level, the less rigid the first airborne object will be when it collides with a component on the first vehicle.

[0179] Optionally, when evaluating multiple pieces of information simultaneously, the collision rating can be associated with the priority of these pieces of information. For example, in scenario one, the probability of the first airborne object colliding with the first vehicle is high, but the first airborne object will specifically impact a rigid component of the first vehicle. As another example, in scenario two, the probability of the first airborne object colliding with the first vehicle is low, but the first airborne object will specifically impact a less rigid component of the first vehicle. In scenarios one and two, if the priority of collision probability is set higher than the priority of the rigidity of the colliding component, then the collision rating of scenario one can be considered higher than that of scenario two. Conversely, in scenarios one and two, if the priority of the rigidity of the colliding component is set higher than the priority of collision probability, then the collision rating of scenario two can be considered higher than that of scenario one.

[0180] Optionally, the correlation between the collision level and the priority of the above-mentioned information can be adjusted according to different driving scenarios, and this application embodiment does not limit this.

[0181] S103: The vehicle control device controls the first vehicle based on the collision level so that a preset component of the first vehicle is subjected to the impact of the first airborne object.

[0182] Optionally, the vehicle control device may specifically control one or more of the first vehicle's speed, direction of travel, and vehicle posture, so that preset components of the first vehicle can withstand the impact of the first airborne object.

[0183] It is understood that, after determining the collision level, the vehicle control method in this application embodiment will also control the first vehicle based on the collision level so that the preset components of the first vehicle can withstand the impact of the first airborne object. In the event that the collision between the first airborne object and the first vehicle is unavoidable, the impact contact point will be made to occur in a safe area of ​​the first vehicle body as much as possible, so as to reduce the threat of the first airborne object to the driving safety of the first vehicle and improve the driving safety of the vehicle.

[0184] In one possible embodiment, the step S103 described above, which controls the first vehicle based on the collision level to ensure that a preset component of the first vehicle withstands the impact of the first airborne object, can be implemented in ways including but not limited to the following:

[0185] The collision level is determined to be related to a first component of the first vehicle, and the first vehicle is controlled to withstand the impact of the first airborne object on a second component of the first vehicle.

[0186] The first component and the second component are different.

[0187] It is understandable that when the collision level can be used to assess whether the first airborne object will collide with the first component of the first vehicle, considering that the first component has low safety after being hit and may pose a significant threat to the occupants of the vehicle, the vehicle control method in this application embodiment can control the first vehicle to avoid the impact of the first airborne object on the first component of the first vehicle, while allowing the second component of the first vehicle to bear the impact of the first airborne object.

[0188] Understandably, the second component is safer after being hit compared to the first component, and poses less of a threat to the occupants of the vehicle. Therefore, by ensuring that the impact point occurs in a safe area of ​​the vehicle body, the threat posed by the first airborne object to the vehicle's driving safety can be reduced, thereby improving the vehicle's driving safety.

[0189] Optionally, when the collision between the first airborne object and the first vehicle is determined to be unavoidable through the above-mentioned collision level assessment, the collision priority of the second component of the first vehicle shall be higher than the collision priority of the first component of the first vehicle.

[0190] Further optionally, the factors relating to the collision priority of the components of the first vehicle may specifically include, but are not limited to, any one or more of the following:

[0191] The rigidity of the component, and the cost of the component.

[0192] Example 1:

[0193] When the rigidity of the second component is greater than that of the first component, the safety of the second component in the event of an impact is necessarily higher than that of the first component.

[0194] For example, the first component may include, but is not limited to, any one or more of the windshield of the first vehicle and the side window of the door of the first vehicle. The second component may include, but is not limited to, any one or more of the frame of the first vehicle, the hood of the first vehicle, the door of the first vehicle, and the bumper of the first vehicle.

[0195] Therefore, the collision priority of the second component is higher than that of the first component. Controlling the first vehicle so that the second component of the first vehicle can withstand the impact of the first airborne object can reduce the threat of the first airborne object to the driving safety of the first vehicle and improve the driving safety of the vehicle.

[0196] Example 2:

[0197] When the cost of the second component is lower than the cost of the first component, the damage caused by the impact on the second component will necessarily be lower than the damage caused by the impact on the first component.

[0198] For example, the first component may include, but is not limited to, any one or more of the following: the lighting module of the first vehicle, the rearview mirror of the first vehicle, and the sensing module deployed on the body of the first vehicle. The second component may include, but is not limited to, any one or more of the following: the frame of the first vehicle, the hood of the first vehicle, the door of the first vehicle, and the bumper of the first vehicle.

[0199] Therefore, the collision priority of the second component is higher than that of the first component. Controlling the first vehicle so that the second component of the first vehicle can withstand the impact of the first airborne object can reduce the maintenance cost of the first vehicle after the collision.

[0200] Example 3:

[0201] When the rigidity of the second component is greater than that of the first component, but the cost of the second component is higher than that of the first component, the collision priority between the first and second components can be correlated with the priority of component rigidity and component cost. If the priority of component rigidity is set higher than that of component cost, then the collision priority of the second component can be considered higher than that of the first component. Conversely, if the priority of component cost is set higher than that of component rigidity, then the collision priority of the first component can be considered higher than that of the second component.

[0202] Optionally, the relationship between the collision priority of a component and the priority of its rigidity and cost can be adjusted according to different driving scenarios, and this application embodiment does not impose any restrictions on this.

[0203] Optionally, in the above-described Exemplary One to Exemplary Three, the factors related to the collision priority of the components of the first vehicle may also include the difficulty of vehicle control, and between the first component and the second component, the component that has sufficient time or is easier to control should be prioritized for collision.

[0204] Optionally, the collision priority of the first component and / or the second component can be configured.

[0205] It is understood that the vehicle control method in this application embodiment can also mark the impact priority of different components on the first vehicle based on factors such as rigidity and cost.

[0206] Optionally, the impact priorities of multiple components can be sorted to determine the collision priority of each component on the first vehicle when a collision between the first airborne object and the first vehicle is unavoidable.

[0207] Optionally, depending on factors such as the vehicle model and brand, the collision priority of vehicle components may differ, and this application embodiment does not impose any restrictions on this.

[0208] Optionally, the collision priority for the first component and / or the second component can be configured by the user or preset by the vehicle manufacturer when producing the first vehicle. This application embodiment does not limit this.

[0209] Through the embodiments of this application, the first vehicle can be controlled so that the components of the first vehicle with higher collision priority bear the impact of the first airborne object, and the impact contact point occurs in a safe area of ​​the first vehicle body as much as possible. This can reduce the threat of the first airborne object to the driving safety of the first vehicle, improve the driving safety of the vehicle, and also reduce the repair cost of the first vehicle after the collision.

[0210] Optionally, the aforementioned first component includes, but is not limited to, one or more of the following: the windshield of the first vehicle, the side window of the first vehicle door, the lighting module of the first vehicle, the rearview mirror of the first vehicle, and the sensing module deployed on the body of the first vehicle. This application embodiment does not limit this.

[0211] Optionally, the second component mentioned above includes, but is not limited to, one or more of the following: the frame of the first vehicle, the hood of the first vehicle, the door of the first vehicle, and the bumper of the first vehicle. This application embodiment does not limit this.

[0212] In one possible embodiment, the collision level between the first airborne object and the first vehicle is determined in step S102 based on the vehicle information of the first vehicle and the information of the first airborne object. This can be achieved in ways including but not limited to the following:

[0213] Based on the information of the first aerial object, the trajectory of the first aerial object is determined. Based on the trajectory of the first aerial object and the vehicle information of the first vehicle, the collision level is determined.

[0214] It is understood that the vehicle control method in this application embodiment can determine the collision level based on the trajectory of the first airborne object and the vehicle information of the first vehicle. The collision level can be used to evaluate and obtain information including but not limited to any one or more of the following: the probability of the first airborne object colliding with the first vehicle, whether the collision between the first airborne object and the first vehicle can be avoided, and which part of the first vehicle the first airborne object will specifically collide with.

[0215] Optionally, the higher the probability of the first airborne object colliding with the first vehicle, the higher the collision level. Optionally, the more difficult it is to avoid a collision between the first airborne object and the first vehicle, the higher the collision level. Optionally, the higher the collision level is if the first airborne object specifically collides with a less rigid component of the first vehicle.

[0216] The collision level determined in the embodiments of this application can make more effective vehicle control decisions, so that when a collision between the first airborne object and the first vehicle is unavoidable, the impact contact point is made to occur in a safe area of ​​the first vehicle body as much as possible, thereby reducing the threat of the first airborne object to the driving safety of the first vehicle and improving the driving safety of the vehicle.

[0217] In one possible embodiment, determining the trajectory of the first aerial object based on its information can be achieved in ways including, but not limited to, the following:

[0218] Based on the information of the first incoming object, the danger level of the first incoming object is determined, and if the danger level is greater than a first threshold, the trajectory of the first incoming object is determined.

[0219] Understandably, based on information about the first incoming object, the danger posed by the first incoming object to the driving of the first vehicle is assessed, thereby determining the danger level of the first incoming object.

[0220] Optionally, the first incoming object may include, but is not limited to, any one or more of the following: stones scattered by the vehicle in front, tires that have fallen off the vehicle in front and bounced into the air, small birds flying in the air, oncoming vehicles, falling leaves, plastic bags, etc., and this application embodiment does not limit this.

[0221] Among them, the danger levels of stones scattered by the vehicle in front, tires that have fallen off the vehicle in front and bounced into the air, small birds flying in the air, and oncoming vehicles are higher than those of falling leaves and plastic bags.

[0222] Optionally, the higher the danger posed by the first aerial object to the driving of the first vehicle, the higher its corresponding danger level.

[0223] It is understandable that the trajectory of the first incoming airborne object is determined when the danger level is greater than the first threshold.

[0224] The first threshold is not a fixed value; it can be adjusted for different vehicle models, driving scenarios, and other factors to ensure vehicle driving safety.

[0225] Through the embodiments of this application, airborne objects can be detected, low-risk airborne objects (meaning those posing a low risk to vehicle operation) can be filtered out, and high-risk airborne objects can be tracked to enable timely vehicle control operations and ensure vehicle driving safety.

[0226] In one possible embodiment, determining the hazard level of the first aerial object based on its information can be achieved in ways including, but not limited to, the following:

[0227] Method 1: Visual perception scheme.

[0228] The information about the first aerial object mentioned above includes the mask information of the first aerial object.

[0229] The mask information of the first aerial object is input into the classification network model to determine the type of the first aerial object, and then the hazard level of the first aerial object is determined based on the type of the first aerial object.

[0230] Among them, the classification network model is used to classify the types of objects.

[0231] It is understood that the embodiments of this application are based on a visual perception scheme to identify the first aerial object and determine its hazard level. For example, the mask information of the first aerial object can be obtained by capturing image frames with a camera, and the type of the first aerial object can be determined by using a classification network model, thereby determining the hazard level of the first aerial object based on its type.

[0232] Through the embodiments of this application, airborne objects can be detected, low-risk airborne objects (meaning those posing a low risk to vehicle operation) can be filtered out, and high-risk airborne objects can be tracked to enable timely vehicle control operations and ensure vehicle driving safety.

[0233] Method 2: Radar sensing solution.

[0234] The information about the first aerial object mentioned above includes the motion characteristics of the first aerial object.

[0235] Based on the motion characteristics of the first incoming object, the type of the first incoming object is determined, and then based on the type of the first incoming object, the hazard level of the first incoming object is determined.

[0236] It is understood that the embodiments of this application are based on radar sensing schemes to identify the first airborne object and determine its hazard level. For example, the motion characteristic information of the first airborne object can be obtained by any one or more detection radars, including but not limited to lidar, millimeter-wave radar, and ultrasonic radar, to determine the type of the first airborne object, and thus determine the hazard level of the first airborne object based on its type.

[0237] Through the embodiments of this application, airborne objects can be detected, low-risk airborne objects (meaning those posing a low risk to vehicle operation) can be filtered out, and high-risk airborne objects can be tracked to enable timely vehicle control operations and ensure vehicle driving safety.

[0238] It should be understood that the above methods one and two are merely illustrative examples of two possible implementations for determining the hazard level of a first airborne object, and should not be construed as limiting the embodiments of this application.

[0239] It should be understood that any new embodiments obtained by reasonable modifications or additions to the above-described methods one to two are all within the protection scope of the embodiments of this application.

[0240] In one possible embodiment, the determination of the trajectory of the first aerial object can be achieved in ways including but not limited to the following:

[0241] Method A: Visual perception scheme.

[0242] The information of the first flying object includes a first image frame and a second image frame, which are two consecutive adjacent images of the first flying object during its movement.

[0243] Step 1: Based on the first image frame and the second image frame, obtain the third image frame and the fourth image frame; the third image frame is the image frame of the first image frame scaled down by a first ratio, and the fourth image frame is the image frame of the second image frame scaled down by a first ratio.

[0244] Step 2: Input the first image frame and the second image frame into the first optical flow network model to obtain the first optical flow; the first optical flow network model is used to predict the next frame or multiple frames corresponding to the first image frame and the second image frame.

[0245] Optionally, the aforementioned first optical flow network model includes a first sub-network model, a second sub-network model, a third sub-network model, and a first optical flow feature fusion model.

[0246] Optionally, step 2 above can be implemented by including but not limited to the following steps:

[0247] The first image frame and the second image frame are input into the first sub-network model to obtain the first sub-optical flow.

[0248] Based on the first sub-optical flow, the second image frame is mapped to the first image frame to obtain the fifth image frame.

[0249] The first sub-optical flow, the fifth image frame, the first mapping error between the fifth image frame and the first image frame, the first image frame, and the second image frame are input into the second sub-network model to obtain the second sub-optical flow.

[0250] Based on the second sub-optical flow, the second image frame is mapped to the first image frame to obtain the sixth image frame.

[0251] The first and second image frames are input into the third sub-network model to obtain the third sub-optical flow.

[0252] Based on the third sub-optical flow, the second image frame is mapped to the first image frame to obtain the seventh image frame.

[0253] The second sub-optical flow, the third sub-optical flow, the first image frame, the second image frame, the sixth image frame, the seventh image frame, the second mapping error between the sixth image frame and the first image frame, and the third mapping error between the seventh image frame and the first image frame are input into the first optical flow feature fusion model to obtain the first optical flow.

[0254] Step 3: Input the third and fourth image frames into the second optical flow network model to obtain the second optical flow; the second optical flow network model is used to predict the next frame or multiple frames corresponding to the third and fourth image frames.

[0255] Optionally, the method of obtaining the second optical flow in step 3 is similar to the method of obtaining the first optical flow in step 2 above. For details, please refer to the relevant description of step 2 above, which will not be repeated here.

[0256] Step 4: Combine the first optical flow and the second optical flow to obtain the trajectory of the first aerial object.

[0257] Optionally, the second optical flow can be upsampled, and the first optical flow and the upsampled second optical flow can be input into the second optical flow feature fusion model to obtain the motion trajectory of the first airborne object.

[0258] The purpose of upsampling is to enlarge the shrunken image frame to its original size before subsequent fusion.

[0259] Understandably, in order to accommodate aerial objects of different sizes, the original image frames can be scaled up by a certain proportion to improve the recognition accuracy of aerial objects of different sizes, thereby improving the accuracy of tracking and recognizing the motion trajectory of aerial objects.

[0260] It is understood that the embodiments of this application are based on a visual perception scheme to identify the first flying object and determine its trajectory. For example, by capturing image frames with a camera, two consecutive adjacent frames of the first flying object during its movement can be obtained. Then, an optical flow network model is used to predict the optical flow information of the first flying object. Based on the predicted optical flow information, the trajectory of the first flying object can be identified, tracked, and predicted to enable timely vehicle control operations and ensure vehicle driving safety.

[0261] Method B: Radar sensing scheme.

[0262] The information about the first aerial object mentioned above includes the motion characteristics of the first aerial object.

[0263] Based on the motion characteristics of the first aerial object, the trajectory of the first aerial object is determined.

[0264] It is understood that the embodiments of this application are based on radar perception to identify the first airborne object and determine its trajectory. For example, the motion characteristic information of the first airborne object can be obtained by any one or more detection radars, including but not limited to lidar, millimeter-wave radar, and ultrasonic radar, to determine its trajectory. The trajectory of the first airborne object can then be identified, tracked, and predicted to enable timely vehicle control operations and ensure vehicle driving safety.

[0265] It should be understood that the above methods A to B are merely two possible embodiments for illustrative purposes of determining the trajectory of a first airborne object, and should not be construed as limiting the embodiments of this application.

[0266] It should be understood that any new embodiments obtained by reasonable modifications or additions to the above-described methods A to B are all within the protection scope of the embodiments of this application.

[0267] In one possible embodiment, the vehicle control method described above may also include, but is not limited to, the following steps:

[0268] Based on the collision level, issue the first warning message.

[0269] The first notification information is used to inform the first user of relevant information about the first incoming object.

[0270] Optionally, the first prompt information can be presented through any one or more of other prompting methods, including but not limited to image and video display, voice broadcast, etc., and the embodiments of this application do not limit this.

[0271] It is understood that the vehicle control method in this application embodiment can issue a first warning message based on the collision level to remind the driver to pay attention to the source direction and danger level of flying objects.

[0272] The first prompt information in this application embodiment is more targeted, and it can better prompt drivers to pay attention to and take appropriate vehicle control operations in a timely manner for high-risk flying objects, so as to ensure the safety of vehicle driving.

[0273] In one possible embodiment, the issuance of a first warning message based on the collision level can be implemented in ways including but not limited to the following:

[0274] Obtain the first user information corresponding to the first user inside the first vehicle. Based on the collision level and the first user information, if the vector angle between the first user's line of sight and the trajectory of the first flying object is greater than a second threshold, issue a first warning message.

[0275] It is understood that the vehicle control method in this application embodiment can determine whether the first user is paying enough attention to the first flying object by the vector angle between the trajectory direction of the first flying object and the line of sight of the first user. If the vector angle is greater than a second threshold, it can be considered that the first user is not paying enough attention to the first flying object, and a first prompt message is issued to promptly remind the first user to pay attention to the source direction and danger level of the flying object, so as to make corresponding vehicle control operations in a timely manner and ensure the safety of vehicle driving.

[0276] In one possible embodiment, the vehicle control method described above may also include, but is not limited to, the following steps:

[0277] A second notification message is issued.

[0278] The second notification message is used to alert the surrounding area of ​​the first vehicle that a collision has occurred.

[0279] Optionally, the second prompt message may be implemented in ways including but not limited to turning on the hazard indicator light to warn oncoming vehicles, and this application embodiment does not limit this.

[0280] Understandably, when the first vehicle collides with the first flying object, a second warning message can be issued to alert those around the first vehicle to the collision and prevent secondary accidents.

[0281] In one possible embodiment, the vehicle control method described above may also include, but is not limited to, the following steps:

[0282] Send collision information to the account associated with the first vehicle.

[0283] The impact information includes information before and after the first vehicle's impact.

[0284] Understandably, when the first vehicle collides with the first flying object, the system can also send collision information to the first vehicle's associated account, record key collision information (such as video and / or images comparing the first vehicle before and after the collision), and automatically compile materials and send them to the first vehicle's associated account to facilitate subsequent liability determination and compensation.

[0285] In one possible embodiment, the vehicle control method described above may also include, but is not limited to, the following steps:

[0286] Send an alarm message to report the impact of the first vehicle and request rescue.

[0287] Optionally, the above-mentioned sending of alarm information can be achieved through methods including but not limited to the following:

[0288] An alarm request is sent to the user inside the first vehicle, and upon receiving a response message to the alarm request, an alarm message is sent.

[0289] The alarm request is used to ask the user inside the first vehicle whether to call the alarm.

[0290] Please refer to Figure 2, which is a flowchart illustrating an aerial object recognition method provided in an embodiment of this application. This aerial object recognition method is applied in the field of vehicle technology, such as an aerial object recognition method for rapid obstacle avoidance scenarios in high-speed environments.

[0291] Specifically, the method for identifying incoming aerial objects includes, but is not limited to, the following steps:

[0292] S201: The aerial object identification device acquires information about the first aerial object.

[0293] The first aerial object is located outside the first vehicle.

[0294] Optionally, the first airborne object includes, but is not limited to, an object moving from a distance in the sky at a certain speed toward the vehicle and its surroundings.

[0295] For example, the first airborne object may include, but is not limited to, any one or more of the following: stones scattered by the vehicle in front, tires that have fallen off the vehicle in front and bounced into the air, small birds flying in the air, oncoming vehicles, falling leaves, plastic bags, etc., and this application embodiment does not limit this.

[0296] It is understood that the airborne object recognition device in the embodiments of this application may be a device equipped with a processor / chip that can execute computer execution instructions, or it may be a processor / chip that can execute computer execution instructions. Optionally, the airborne object recognition device may be an electronic device, or it may be a processor / chip within an electronic device, used to execute the airborne object recognition method in the embodiments of this application, so as to reduce the threat of airborne objects to vehicle driving safety and improve vehicle driving safety.

[0297] Optionally, the aerial object recognition device and method in the embodiments of this application can be applied to, but are not limited to, vehicle systems. The vehicle equipped with the vehicle system is an intelligent driving vehicle and can be replaced by a terminal device. The terminal device can be, but is not limited to, vehicles such as commercial vehicles, passenger cars, trains, industrial vehicles (such as forklifts, trailers, tractors, etc.), engineering vehicles (such as excavators, bulldozers, cranes, etc.), robots, etc. The embodiments of this application do not specifically limit this.

[0298] S202: The aerial object identification device determines the trajectory of the first aerial object based on the information of the first aerial object.

[0299] Through the embodiments of this application, flying objects can be detected and their trajectories tracked, so as to make corresponding vehicle control operations in a timely manner and ensure the safety of vehicle driving.

[0300] In one possible embodiment, determining the trajectory of the first aerial object based on its information in step S202 can be achieved in ways including but not limited to the following:

[0301] Based on the information of the first incoming object, the danger level of the first incoming object is determined, and if the danger level is greater than a first threshold, the trajectory of the first incoming object is determined.

[0302] Understandably, based on information about the first incoming object, the danger posed by the first incoming object to the driving of the first vehicle is assessed, thereby determining the danger level of the first incoming object.

[0303] Optionally, the first incoming object may include, but is not limited to, any one or more of the following: stones scattered by the vehicle in front, tires that have fallen off the vehicle in front and bounced into the air, small birds flying in the air, oncoming vehicles, falling leaves, plastic bags, etc., and this application embodiment does not limit this.

[0304] Among them, the danger levels of stones scattered by the vehicle in front, tires that have fallen off the vehicle in front and bounced into the air, small birds flying in the air, and oncoming vehicles are higher than those of falling leaves and plastic bags.

[0305] Optionally, the higher the danger posed by the first aerial object to the driving of the first vehicle, the higher its corresponding danger level.

[0306] It is understandable that the trajectory of the first incoming airborne object is determined when the danger level is greater than the first threshold.

[0307] The first threshold is not a fixed value; it can be adjusted for different vehicle models, driving scenarios, and other factors to ensure vehicle driving safety.

[0308] Through the embodiments of this application, airborne objects can be detected, low-risk airborne objects (meaning those posing a low risk to vehicle operation) can be filtered out, and high-risk airborne objects can be tracked to enable timely vehicle control operations and ensure vehicle driving safety.

[0309] In one possible embodiment, determining the hazard level of the first aerial object based on its information can be achieved in ways including, but not limited to, the following:

[0310] Method 1: Visual perception scheme.

[0311] For details, please refer to the relevant explanation of "Method 1: Visual Perception Scheme" above, which will not be repeated here.

[0312] Method 2: Radar sensing solution.

[0313] For details, please refer to the relevant explanation of "Method 2: Radar Sensing Scheme" above, which will not be repeated here.

[0314] Through the embodiments of this application, airborne objects can be detected, low-risk airborne objects (meaning those posing a low risk to vehicle operation) can be filtered out, and high-risk airborne objects can be tracked to enable timely vehicle control operations and ensure vehicle driving safety.

[0315] In one possible embodiment, the determination of the trajectory of the first aerial object can be achieved in ways including but not limited to the following:

[0316] Method A: Visual perception scheme.

[0317] For details, please refer to the relevant explanation of "Method A: Visual Perception Scheme" above, which will not be repeated here.

[0318] Method B: Radar sensing scheme.

[0319] For details, please refer to the relevant explanation of "Method B: Radar Sensing Scheme" above, which will not be repeated here.

[0320] Through the embodiments of this application, the trajectory of a first airborne object can be determined, and the trajectory of the first airborne object can be identified, tracked, and predicted so as to make corresponding vehicle control operations in a timely manner and ensure the safety of vehicle driving.

[0321] This application also provides a vehicle control method, as detailed in Figure 3, which is a flowchart illustrating another vehicle control method provided in an embodiment of this application. This vehicle control method is applied in the field of vehicle technology, such as a vehicle control method for rapid avoidance of aerial objects in high-speed scenarios.

[0322] It is understood that the steps in the embodiments of this application can be regarded as reasonable modifications or supplements to the embodiments in FIG1 or FIG2 above; or, it is understood that the vehicle control method in the embodiments of this application can also be regarded as an embodiment that can be executed independently, and this application does not limit it.

[0323] It is understood that the vehicle control device involved in the vehicle control method provided in this application embodiment can refer to the relevant description of the vehicle control device involved in the vehicle control method shown in Figure 1 above, and will not be repeated here.

[0324] It is understood that the vehicle control method and vehicle control device provided in this application are applied to a perception system and a vehicle control system, which can quickly detect and identify the hazard factor of flying objects, and then make corresponding decisions. If it is determined to be a dangerous object, the vehicle speed and body posture are adjusted by the control system to try to avoid the flying object from colliding with the vehicle; if it is determined that a collision between the flying object and the vehicle is unavoidable, the vehicle speed and body posture are adjusted by the control system to try to prevent the collision from occurring in a relatively safe (rigid) area, rather than in areas that affect the safety of people, such as the windshield and side windows, or in expensive and easily damaged areas such as headlights.

[0325] As shown in Figure 3, the vehicle control method includes, but is not limited to, the following steps:

[0326] It uses sensing devices to collect external sequences and detect objects flying in the air.

[0327] Among them, sensing devices include visual sensing devices or other types of sensors (such as millimeter-wave radar, lidar, ultrasonic radar, etc.).

[0328] The sensing equipment detects objects flying into the air around the vehicle and identifies whether the objects are dangerous.

[0329] If the incoming object is identified as not a hazardous object (such as a falling leaf, plastic bag, etc.), the process ends without further action.

[0330] Once an incoming object is identified as a hazardous object (such as stones scattered by the vehicle in front, or a tire that has fallen off the vehicle in front and bounced into the air), the trajectory of the incoming object is tracked and predicted.

[0331] Based on the in-vehicle sequence collected by sensing devices, the driver's line of sight is estimated.

[0332] Whether the driver has noticed the flying object is determined by the vector angle between the direction of the object's trajectory and the driver's line of sight.

[0333] If the driver fails to notice an incoming object, a voice announcement will be made to remind the driver of the hazard, informing them of the object's direction and hazard level (the hazard level can be obtained using a visual perception-based solution). Optionally, the driver may be reminded of the object's direction, such as left, right, front, rear, left front, left rear, right front, right rear, and the corresponding upper, middle, and lower parts, etc. This application embodiment does not impose any limitations on this.

[0334] It obtains information such as vehicle speed, direction, and body posture, and judges whether there is a risk of collision based on this information and the trajectory of flying objects.

[0335] If there is no risk of collision, the operation ends without further action. If there is a risk of collision, an obstacle avoidance decision is made, and hazard lights are activated to warn oncoming vehicles.

[0336] The obstacle avoidance decision determines whether a collision can be avoided.

[0337] If the obstacle avoidance decision determines that a collision can be avoided, it sends instructions to the vehicle control system to adjust the direction, change lanes, adjust the speed, brake, and adjust the vehicle's posture to avoid a collision.

[0338] If, after obstacle avoidance decision-making, it is determined that an incoming object will inevitably collide with the vehicle, a decision is made regarding whether manual intervention is required. If no manual intervention is required, instructions are sent to the vehicle control system to adjust the direction, speed, and vehicle attitude, ensuring that the collision occurs within the highest possible priority safe (rigid) zone. The rigid zones vary depending on the brand and type of vehicle. The vehicle control method in this embodiment can mark several zones on the vehicle, and the driver or user can then mark and sort these rigid zones to determine their collision priority.

[0339] During automatic obstacle avoidance, if changes in brake or accelerator pedal pressure are detected, or the steering wheel angle exceeds a threshold, it is determined that manual intervention is required, and the automatic obstacle avoidance mode is exited.

[0340] After obstacle avoidance is completed, it's necessary to determine if a collision occurred. If no collision occurred, the process ends without further action. If a collision occurred, damage detection can be performed using a frame difference-based method based on the vehicle's external sequence to identify whether the vehicle is damaged. An alarm voice prompt will then be triggered, asking if assistance is needed, or if there is no response after N attempts, an emergency assistance alarm will be activated.

[0341] If vehicle damage is detected, key evidence, such as key collision videos and photos, is secured, and the claims materials are automatically compiled and sent to the vehicle's associated account for easier claims processing.

[0342] Through the embodiments of this application, when a vehicle is driving on a highway or other scenarios and encounters flying objects, it can quickly detect any flying objects that may affect driving safety, such as stones scattered by the vehicle in front, floating obstructions, tires that have detached and bounced into the air, or even oncoming vehicles. It will try to avoid collisions by making decisions and adjusting, for example, vehicle speed, direction, and vehicle posture. If a collision is unavoidable, it will make decisions and adjust, for example, vehicle speed, direction, and vehicle posture, so that the impact contacts a relatively safe area of ​​the vehicle body, rather than impacting areas such as the windshield, side windows, etc.

[0343] This application also provides a method for identifying aerial objects, as detailed in Figure 4, which is a flowchart illustrating another aerial object identification method provided in an embodiment of this application. This aerial object identification method is applied in the field of vehicle technology, such as aerial object identification in high-speed scenarios involving rapid avoidance of aerial objects.

[0344] It is understood that the steps in the embodiments of this application can be regarded as reasonable modifications or supplements to the embodiments in Figure 1, Figure 2 or Figure 3 above; or, it is understood that the aerial object identification method in the embodiments of this application can also be regarded as an embodiment that can be executed independently, and this application does not limit it.

[0345] It is understood that the aerial object recognition device involved in the aerial object recognition method provided in this application embodiment can refer to the relevant description of the aerial object recognition device involved in the vehicle control method shown in Figure 1 above, and will not be repeated here.

[0346] It is understood that the aerial object recognition method and aerial object recognition device provided in this application are applied to the perception system and the aerial object recognition system, and can detect aerial objects based on the vehicle external visual perception scheme. After detecting aerial objects that affect driving safety, obstacle avoidance decisions are made and corresponding processing is implemented.

[0347] As shown in Figure 4, this method for identifying incoming aerial objects includes, but is not limited to, the following steps:

[0348] The background of the video sequence captured by the visual perception device on the vehicle is changing when it is traveling at high speed, while the background of the flying object is moving relative to the sequence. This belongs to the moving object detection model with dynamic background.

[0349] The airborne object identification method in this application uses a supervised optical flow prediction network based on machine learning to predict the optical flow of airborne objects, locates the position / trajectory of airborne objects based on the predicted optical flow characteristics, and identifies hazardous objects and their corresponding coefficients based on a hazardous object classification network.

[0350] The optical flow prediction network consists of two main networks. The first network takes two adjacent frames of a video sequence at their original size as input, while the second network takes two adjacent frames of a video sequence scaled down to half their original size as input. The optical flow features output by the two networks are then fused to better extract features from different sizes. Each network comprises three sub-networks, each using an encoding / decoding structure. Each sub-network consists of multiple convolutional layers and rectified linear unit (ReLU) activation function layers, outputting predicted optical flow information which serves as the input to the next network. This correlation calculation can be viewed as performing a convolution operation on the features of two consecutive frames in the video sequence in the spatial dimension.

[0351] If we define two consecutive frames in a video sequence as the previous frame (frame n) and the next frame (frame n+1), the algorithm process is described as follows:

[0352] a. The optical flow prediction subnetwork net1 / net'1 predicts and outputs the optical flow of the moving target, and uses the optical flow information to map the later frame (frame n+1) of two consecutive images back to the previous frame image.

[0353] b. Calculate the mapping error between the original previous frame and the mapped previous frame image, and use the mapping error, the mapped previous frame image, the predicted optical flow of the moving target, the original previous frame image, and the next frame image as inputs to the optical flow prediction subnetwork net2 / net'2.

[0354] c. The input to the optical flow prediction subnetwork net3 / net'3 is the same two frames of images, and the predicted output is the optical flow of the moving target.

[0355] d. Based on the optical flow output from the optical flow prediction subnetworks net3 / net'3 and net2 / net'2 respectively, map the subsequent frame image to the previous frame image, and calculate the mapping error respectively.

[0356] e. Input the two optical flows obtained in step d, the mapped previous frame image, the mapping error, and the original previous and next frame images into the optical flow prediction feature fusion network, and output the final optical flow.

[0357] f. By fusing optical flow information and background modeling, the position and trajectory of objects flying in the air can be obtained.

[0358] g. Obtain the mask of the moving incoming object, input it into the hazard classification network, and obtain the hazard category and corresponding hazard coefficient. Specifically:

[0359] (1) Based on big data analysis of airborne objects colliding with vehicles in high-speed scenarios, dangerous objects are classified and their risk level coefficients are evaluated according to multiple dimensions such as their own degree of danger, the casualties caused, and the damage to the vehicles, and a dataset is created.

[0360] (2) Train a machine learning model for classifying hazardous materials based on the dataset.

[0361] (3) The trained hazardous object classification model is used as a post-processing for airborne object detection. This allows us to know the risk coefficient of the airborne object and filter out non-hazardous airborne objects, such as fallen leaves and floating plastic bags.

[0362] h. Filter out harmless incoming air objects and track the motion trajectory of dangerous incoming air objects.

[0363] Optionally, once the incoming airborne object is identified as a dangerous object (such as stones scattered by the vehicle in front, tires that have fallen off the vehicle in front and bounced into the air), the trajectory of the incoming airborne object is tracked and predicted.

[0364] Please refer to Figure 5 for details. Figure 5 is a flowchart illustrating another vehicle control method provided in this application embodiment. This vehicle control method is applied in the field of vehicle technology, such as a vehicle control method for rapid avoidance of aerial objects in high-speed scenarios.

[0365] It is understood that the steps in the embodiments of this application can be regarded as reasonable modifications or supplements to the embodiments in Figure 1, Figure 2, Figure 3 or Figure 4 above; or, it is understood that the vehicle control method in the embodiments of this application can also be regarded as an embodiment that can be executed independently, and this application does not limit it.

[0366] It is understood that the vehicle control device involved in the vehicle control method provided in this application embodiment can refer to the relevant description of the vehicle control device involved in the vehicle control method shown in Figure 1 above, and will not be repeated here.

[0367] It is understood that the vehicle control method and vehicle control device provided in this application are applied to a perception system and a vehicle control system, which can quickly detect and identify the hazard factor of flying objects, and then make corresponding decisions. If it is determined to be a dangerous object, the vehicle speed and body posture are adjusted by the control system to try to avoid the flying object from colliding with the vehicle; if it is determined that a collision between the flying object and the vehicle is unavoidable, the vehicle speed and body posture are adjusted by the control system to try to prevent the collision from occurring in a relatively safe (rigid) area, rather than in areas that affect the safety of people, such as the windshield and side windows, or in expensive and easily damaged areas such as headlights.

[0368] As shown in Figure 5, the vehicle control method includes, but is not limited to, the following steps:

[0369] Based on the in-vehicle sequence collected by sensing devices, the driver's line of sight is estimated.

[0370] Whether the driver has noticed the flying object is determined by the vector angle between the direction of the object's trajectory and the driver's line of sight.

[0371] If the driver fails to notice an incoming object, a voice announcement will be made to remind the driver of the hazard, informing them of the object's direction and hazard level (the hazard level can be obtained using a visual perception-based solution). Optionally, the driver may be reminded of the object's direction, such as left, right, front, rear, left front, left rear, right front, right rear, and the corresponding upper, middle, and lower parts, etc. This application embodiment does not impose any limitations on this.

[0372] It obtains information such as vehicle speed, direction, and body posture, and judges whether there is a risk of collision based on this information and the trajectory of flying objects.

[0373] If there is no risk of collision, the operation ends without further action. If there is a risk of collision, an obstacle avoidance decision is made, and hazard lights are activated to warn oncoming vehicles.

[0374] The obstacle avoidance decision determines whether a collision can be avoided.

[0375] If the obstacle avoidance decision determines that a collision can be avoided, it sends instructions to the vehicle control system to adjust the direction, change lanes, adjust the speed, brake, and adjust the vehicle's posture to avoid a collision.

[0376] If, after obstacle avoidance decision-making, it is determined that an incoming object will inevitably collide with the vehicle, a decision is made regarding whether manual intervention is required. If no manual intervention is required, instructions are sent to the vehicle control system to adjust the direction, speed, and vehicle attitude, ensuring that the collision occurs within the highest possible priority safe (rigid) zone. The rigid zones vary depending on the brand and type of vehicle. The vehicle control method in this embodiment can mark several zones on the vehicle, and the driver or user can then mark and sort these rigid zones to determine their collision priority.

[0377] During automatic obstacle avoidance, if changes in brake or accelerator pedal pressure are detected, or the steering wheel angle exceeds a threshold, it is determined that manual intervention is required, and the automatic obstacle avoidance mode is exited.

[0378] After obstacle avoidance is completed, it's necessary to determine if a collision occurred. If no collision occurred, the process ends without further action. If a collision occurred, damage detection can be performed using a frame difference-based method based on the vehicle's external sequence to identify whether the vehicle is damaged. An alarm voice prompt will then be triggered, asking if assistance is needed, or if there is no response after N attempts, an emergency assistance alarm will be activated.

[0379] If vehicle damage is detected, key evidence, such as key collision videos and photos, is secured, and the claims materials are automatically compiled and sent to the vehicle's associated account for easier claims processing.

[0380] Through the embodiments of this application, when a vehicle is driving on a highway or other scenarios and encounters flying objects, it can quickly detect any flying objects that may affect driving safety, such as stones scattered by the vehicle in front, floating obstructions, tires that have detached and bounced into the air, or even oncoming vehicles. It will try to avoid collisions by making decisions and adjusting, for example, vehicle speed, direction, and vehicle posture. If a collision is unavoidable, it will make decisions and adjust, for example, vehicle speed, direction, and vehicle posture, so that the impact contacts a relatively safe area of ​​the vehicle body, rather than impacting areas such as the windshield, side windows, etc.

[0381] This application also provides a vehicle control method, as detailed in Figure 6, which is a flowchart illustrating another vehicle control method provided in an embodiment of this application. This vehicle control method is applied in the field of vehicle technology, such as a vehicle control method for rapid avoidance of aerial objects in high-speed scenarios.

[0382] It is understood that the steps in the embodiments of this application can be regarded as reasonable modifications or supplements to the embodiments in Figures 1, 2, 3, 4 or 5 above; or, it is understood that the vehicle control method in the embodiments of this application can also be regarded as an embodiment that can be executed independently, and this application does not limit it.

[0383] It is understood that the vehicle control device involved in the vehicle control method provided in this application embodiment can refer to the relevant description of the vehicle control device involved in the vehicle control method shown in Figure 1 above, and will not be repeated here.

[0384] It is understood that the vehicle control method and vehicle control device provided in this application are applied to a perception system and a vehicle control system, which can quickly detect and identify the hazard factor of flying objects, and then make corresponding decisions. If it is determined to be a dangerous object, the vehicle speed and body posture are adjusted by the control system to try to avoid the flying object from colliding with the vehicle; if it is determined that a collision between the flying object and the vehicle is unavoidable, the vehicle speed and body posture are adjusted by the control system to try to prevent the collision from occurring in a relatively safe (rigid) area, rather than in areas that affect the safety of people, such as the windshield and side windows, or in expensive and easily damaged areas such as headlights.

[0385] As shown in Figure 6, the vehicle control method includes, but is not limited to, the following steps:

[0386] Information about the airspace outside the vehicle is collected using radar sensing equipment.

[0387] Among them, radar sensing devices include, but are not limited to, any one or more of lidar, millimeter-wave radar, and ultrasonic radar.

[0388] Radar sensing equipment detects objects flying in the air and identifies them based on their motion characteristics.

[0389] The sensing equipment detects objects flying into the air around the vehicle and identifies whether the objects are dangerous.

[0390] If the incoming object is identified as not a hazardous object (such as a falling leaf, plastic bag, etc.), the process ends without further action.

[0391] Once an incoming object is identified as a hazardous object (such as stones scattered by the vehicle in front, or a tire that has fallen off the vehicle in front and bounced into the air), the trajectory of the incoming object is tracked and predicted.

[0392] Based on the in-vehicle sequence collected by sensing devices, the driver's line of sight is estimated.

[0393] Whether the driver has noticed the flying object is determined by the vector angle between the direction of the object's trajectory and the driver's line of sight.

[0394] If the driver fails to notice an incoming object, a voice announcement will be made to remind the driver of the hazard, informing them of the object's direction and hazard level (the hazard level can be obtained using a visual perception-based solution). Optionally, the driver may be reminded of the object's direction, such as left, right, front, rear, left front, left rear, right front, right rear, and the corresponding upper, middle, and lower parts, etc. This application embodiment does not impose any limitations on this.

[0395] It obtains information such as vehicle speed, direction, and body posture, and judges whether there is a risk of collision based on this information and the trajectory of flying objects.

[0396] If there is no risk of collision, the operation ends without further action. If there is a risk of collision, an obstacle avoidance decision is made, and hazard lights are activated to warn oncoming vehicles.

[0397] The obstacle avoidance decision determines whether a collision can be avoided.

[0398] If the obstacle avoidance decision determines that a collision can be avoided, it sends instructions to the vehicle control system to adjust the direction, change lanes, adjust the speed, brake, and adjust the vehicle's posture to avoid a collision.

[0399] If, after obstacle avoidance decision-making, it is determined that an incoming object will inevitably collide with the vehicle, a decision is made regarding whether manual intervention is required. If no manual intervention is required, instructions are sent to the vehicle control system to adjust the direction, speed, and vehicle attitude, ensuring that the collision occurs within the highest possible priority safe (rigid) zone. The rigid zones vary depending on the brand and type of vehicle. The vehicle control method in this embodiment can mark several zones on the vehicle, and the driver or user can then mark and sort these rigid zones to determine their collision priority.

[0400] During automatic obstacle avoidance, if changes in brake or accelerator pedal pressure are detected, or the steering wheel angle exceeds a threshold, it is determined that manual intervention is required, and the automatic obstacle avoidance mode is exited.

[0401] After obstacle avoidance is completed, it's necessary to determine if a collision occurred. If no collision occurred, the process ends without further action. If a collision occurred, damage detection can be performed using a frame difference-based method based on the vehicle's external sequence to identify whether the vehicle is damaged. An alarm voice prompt will then be triggered, asking if assistance is needed, or if there is no response after N attempts, an emergency assistance alarm will be activated.

[0402] If vehicle damage is detected, key evidence, such as key collision videos and photos, is secured, and the claims materials are automatically compiled and sent to the vehicle's associated account for easier claims processing.

[0403] Through the embodiments of this application, when a vehicle is driving on a highway or other scenarios and encounters flying objects, it can quickly detect any flying objects that may affect driving safety, such as stones scattered by the vehicle in front, floating obstructions, tires that have detached and bounced into the air, or even oncoming vehicles. It will try to avoid collisions by making decisions and adjusting, for example, vehicle speed, direction, and vehicle posture. If a collision is unavoidable, it will make decisions and adjust, for example, vehicle speed, direction, and vehicle posture, so that the impact contacts a relatively safe area of ​​the vehicle body, rather than impacting areas such as the windshield, side windows, etc.

[0404] The methods of the embodiments of this application have been described in detail above. The following provides an apparatus for implementing any one of the methods in the embodiments of this application. For example, an apparatus is provided that includes a unit (or means) for implementing the steps performed by the device in any of the above methods.

[0405] Please refer to Figure 7, which is a structural schematic diagram of a vehicle control device provided in an embodiment of this application.

[0406] As shown in Figure 7, the vehicle control device 70 may include a communication unit 701 and a processing unit 702. The communication unit 701 and the processing unit 702 may be software, hardware, or a combination of both.

[0407] The communication unit 701 can implement sending and / or receiving functions, and can also be described as a transceiver unit. The communication unit 701 can also be a unit integrating an acquisition unit and a sending unit, wherein the acquisition unit is used to implement the receiving function, and the sending unit is used to implement the sending function. Optionally, the communication unit 701 can be used to receive information sent by other devices, and can also be used to send information to other devices.

[0408] In one possible design, the vehicle control device 70 may correspond to the vehicle control device in the method embodiments shown in Figures 1 to 6 above. For example, the vehicle control device 70 may be an electronic device or a chip within an electronic device. The vehicle control device 70 may include units for performing the operations performed by the vehicle control device in the method embodiments shown in Figures 1 to 6 above, and each unit in the vehicle control device 70 is respectively for implementing the operations performed by the vehicle control device in the method embodiments shown in Figures 1 to 6 above. The descriptions of each unit are as follows:

[0409] Processing unit 702 is used to acquire vehicle information of the first vehicle and information of the first aerial object, wherein the first aerial object is located outside the first vehicle.

[0410] The processing unit 702 is further configured to determine the collision level between the first airborne object and the first vehicle based on the vehicle information of the first vehicle and the information of the first airborne object.

[0411] The processing unit 702 is further configured to control the first vehicle based on the collision level so that a preset component of the first vehicle withstands the impact of the first airborne object.

[0412] In one possible implementation, the device further includes a communication unit 701;

[0413] The processing unit 702 is specifically used to obtain vehicle information of the first vehicle and information of the first aerial object through the communication unit 701, wherein the first aerial object is located outside the first vehicle.

[0414] Regarding the communication unit 701 and processing unit 702 described in this design, the steps they perform can be referred to the implementation methods corresponding to the vehicle control device in the method embodiments shown in Figures 1 to 6 above.

[0415] Regarding the technical effects of the implementation methods performed by the communication unit 701 and the processing unit 702 described in this design, please refer to the description of the technical effects corresponding to the method embodiments shown in Figures 1 to 6 above.

[0416] According to embodiments of this application, the various units in the device shown in FIG7 can be individually or entirely merged into one or more other units, or some of the units can be further divided into multiple functionally smaller units. This achieves the same operation without affecting the technical effect of the embodiments of this application. The above units are based on logical function division. In practical applications, the function of one unit can also be implemented by multiple units, or the function of multiple units can be implemented by one unit. In other embodiments of this application, the electronic device may also include other units. In practical applications, these functions can also be implemented with the assistance of other units, and can be implemented collaboratively by multiple units.

[0417] It should be noted that the implementation of each unit can also refer to the corresponding descriptions of the method embodiments shown in Figures 1 to 6 above.

[0418] The vehicle control device 70 described in Figure 7 can reduce the threat of airborne objects to vehicle driving safety and improve vehicle driving safety.

[0419] Please refer to Figure 8, which is a structural schematic diagram of an aerial object identification device provided in an embodiment of this application.

[0420] As shown in Figure 8, the airborne object identification device 80 may include a communication unit 801 and a processing unit 802. The communication unit 801 and the processing unit 802 may be software, hardware, or a combination of both.

[0421] The communication unit 801 can implement sending and / or receiving functions, and can also be described as a transceiver unit. The communication unit 801 can also be a unit integrating an acquisition unit and a sending unit, wherein the acquisition unit is used to implement the receiving function, and the sending unit is used to implement the sending function. Optionally, the communication unit 801 can be used to receive information sent by other devices, and can also be used to send information to other devices.

[0422] In one possible design, the airborne object identification device 80 may correspond to the airborne object identification device in the method embodiments shown in Figures 1 to 6. For example, the airborne object identification device 80 may be an electronic device or a chip within an electronic device. The airborne object identification device 80 may include units for performing the operations performed by the airborne object identification device in the method embodiments shown in Figures 1 to 6. Each unit in the airborne object identification device 80 is respectively responsible for implementing the operations performed by the airborne object identification device in the method embodiments shown in Figures 1 to 6. The descriptions of each unit are as follows:

[0423] Processing unit 802 is used to acquire information about a first aerial object, the first aerial object being located outside the first vehicle;

[0424] The processing unit 802 is also used to determine the trajectory of the first airborne object based on the information of the first airborne object.

[0425] In one possible implementation, the device further includes a communication unit 801;

[0426] The processing unit 802 is specifically used to obtain information about the first aerial object through the communication unit 801.

[0427] Regarding the communication unit 801 and processing unit 802 described in this design, the steps they perform can be referred to the implementation methods corresponding to the aerial object identification device in the method embodiments shown in Figures 1 to 6 above.

[0428] Regarding the technical effects of the implementation methods performed by the communication unit 801 and the processing unit 802 described in this design, please refer to the description of the technical effects corresponding to the method embodiments shown in Figures 1 to 6 above.

[0429] According to embodiments of this application, the various units in the device shown in FIG8 can be individually or entirely merged into one or more other units, or some of the units can be further divided into multiple functionally smaller units. This achieves the same operation without affecting the technical effect of the embodiments of this application. The above units are based on logical function division. In practical applications, the function of one unit can also be implemented by multiple units, or the function of multiple units can be implemented by one unit. In other embodiments of this application, the electronic device may also include other units. In practical applications, these functions can also be implemented with the assistance of other units, and can be implemented collaboratively by multiple units.

[0430] It should be noted that the implementation of each unit can also refer to the corresponding descriptions of the method embodiments shown in Figures 1 to 6 above.

[0431] The aerial object recognition device 80 described in Figure 8 can reduce the threat of aerial objects to vehicle driving safety and improve vehicle driving safety.

[0432] If the vehicle control device 70 and / or the aerial object recognition device 80 mentioned above can be electronic devices, please refer to the structural schematic diagram of the electronic device shown in Figure 9.

[0433] It should be understood that the electronic device 90 shown in FIG9 is only an example. The electronic device in the embodiments of this application may also include other components, or include components that have similar functions to the various components in FIG9, or may not include all the components in FIG9.

[0434] The electronic device 90 includes a transceiver interface 901 and at least one processor 902.

[0435] The electronic device 90 can correspond to a vehicle control device and / or an aerial object recognition device. A transceiver interface 901 is used for transmitting and receiving signals, and at least one processor 902 executes program instructions, causing the electronic device 90 to implement the corresponding flow of the method executed by the corresponding device in the above method embodiments.

[0436] In one possible design, the electronic device 90 may correspond to the vehicle control device in the method embodiments shown in Figures 1 to 6 above. For example, the electronic device 90 may be a vehicle control device or a chip within the vehicle control device. The electronic device 90 may include components for performing the operations performed by the vehicle control device in the above method embodiments, and each component in the electronic device 90 is specifically designed to implement the operations performed by the vehicle control device in the above method embodiments. Specifically, it may be as follows:

[0437] Processor 902 is used to acquire vehicle information of the first vehicle and information of the first aerial object, wherein the first aerial object is located outside the first vehicle;

[0438] The processor 902 is further configured to determine the collision level between the first airborne object and the first vehicle based on the vehicle information of the first vehicle and the information of the first airborne object.

[0439] The processor 902 is further configured to control the first vehicle based on the collision level so that a preset component of the first vehicle withstands the impact of the first airborne object.

[0440] In one possible implementation, the device further includes a transceiver interface 901;

[0441] The processor 902 is specifically used to obtain vehicle information of the first vehicle and information of the first aerial object through the transceiver interface 901, wherein the first aerial object is located outside the first vehicle.

[0442] Regarding the transceiver interface 901 and at least one processor 902 described in this design, the steps they perform can be referred to the implementation corresponding to the vehicle control device in the method embodiments shown in Figures 1 to 6 above.

[0443] For the technical effects of the implementation methods performed by the transceiver interface 901 and at least one processor 902 described in this design, please refer to the description of the technical effects corresponding to the method embodiments shown in Figures 1 to 6 above.

[0444] In another possible design, the electronic device 90 may correspond to the airborne object identification device in the method embodiments shown in Figures 1 to 6 above. For example, the electronic device 90 may be an airborne object identification device or a chip within that device. The electronic device 90 may include components for performing the operations performed by the airborne object identification device in the above method embodiments, and each component in the electronic device 90 is specifically designed to implement the operations performed by the airborne object identification device in the above method embodiments. Specifically, it may be as follows:

[0445] Processor 902 is used to acquire information about a first aerial object located outside the first vehicle;

[0446] The processor 902 is also used to determine the trajectory of the first airborne object based on the information of the first airborne object.

[0447] In one possible implementation, the device further includes a transceiver interface 901;

[0448] The processor 902 is specifically used to acquire information about the first incoming airborne object through the transceiver interface 901.

[0449] Regarding the transceiver interface 901 and at least one processor 902 described in this design, the steps they perform can be referred to the implementation corresponding to the aerial object identification device in the method embodiments shown in Figures 1 to 6 above.

[0450] For the technical effects of the implementation methods performed by the transceiver interface 901 and at least one processor 902 described in this design, please refer to the description of the technical effects corresponding to the method embodiments shown in Figures 1 to 6 above.

[0451] The electronic device 90 described in Figure 9 can reduce the threat of airborne objects to vehicle driving safety and improve vehicle driving safety.

[0452] For cases where the vehicle control device 70 and / or the aerial object recognition device 80 can be a chip or a chip system, please refer to the schematic diagram of the chip structure shown in Figure 10.

[0453] As shown in Figure 10, chip 100 includes processor 1001 and interface 1002. The number of processors 1001 can be one or more, and the number of interfaces 1002 can be multiple. It should be noted that the functions of processor 1001 and interface 1002 can be implemented through hardware design, software design, or a combination of both; no restrictions are placed here.

[0454] Optionally, the chip 100 may also include a memory 1003 for storing necessary program instructions and data.

[0455] In this application, processor 1001 can be used to call the implementation program of the vehicle control method provided in one or more embodiments of this application in a vehicle control device from memory 1003, and / or call the implementation program of the airborne object recognition method provided in one or more embodiments of this application in an airborne object recognition device, and execute the instructions included in the program. Interface 1002 can be used to output the execution result of processor 1001. In this application, interface 1002 can specifically be used to output various messages or information of processor 1001.

[0456] For the vehicle control method and / or airborne object recognition method provided by one or more embodiments of this application, please refer to the various embodiments shown in Figures 1 to 6 above, which will not be repeated here.

[0457] The processor in this application embodiment can be a central processing unit (CPU), but it can also be other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor can be a microprocessor or any conventional processor.

[0458] The memory in this application embodiment is used to provide storage space, in which data such as operating system and computer programs can be stored. The memory includes, but is not limited to, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM), or compact disc read-only memory (CD-ROM).

[0459] According to the method provided in the embodiments of this application, the embodiments of this application also provide a computer-readable storage medium storing a computer program. When the computer program is run on one or more processors, it can implement the method shown in Figures 1 to 6.

[0460] According to the method provided in the embodiments of this application, the embodiments of this application also provide a computer program product, which includes a computer program. When the computer program runs on a processor, it can implement the methods shown in Figures 1 to 6.

[0461] This application provides a system including a vehicle control device and an airborne object recognition device. The vehicle control device is used to execute the implementation method corresponding to the vehicle control device in the method embodiments shown in Figures 1 to 6, and the airborne object recognition device is used to execute the implementation method corresponding to the airborne object recognition device in the method embodiments shown in Figures 1 to 6.

[0462] This application embodiment also provides a mobile terminal, which includes at least one vehicle control device 70, or an airborne object recognition device 80, or an electronic device 90, or a chip 100, or a system.

[0463] Optionally, the mobile terminal can be a means of transportation, such as a car, truck, aircraft, drone, slow transport vehicle, spacecraft, or ship, or any other possible means of transportation used in any possible scenario. This application embodiment does not limit this.

[0464] Optionally, the mobile terminal is used to implement the methods shown in Figures 1 to 6 above.

[0465] This application also provides a processing apparatus, including a processor and an interface; the processor is used to execute the method in any of the above method embodiments.

[0466] It should be understood that the above-described processing device can be a chip. The units in the various device embodiments and the electronic devices in the method embodiments correspond completely, with corresponding modules or units executing corresponding steps. For example, the communication unit (transceiver) executes the receiving or sending steps in the method embodiments, while other steps besides sending and receiving can be executed by the processing unit (processor). The specific functions of each unit can be found in the corresponding method embodiments. There can be one or more processors.

[0467] It is understood that in the embodiments of this application, the electronic device may perform some or all of the steps in the embodiments of this application. These steps or operations are merely examples, and the embodiments of this application may also perform other operations or variations thereof. Furthermore, the steps may be performed in different orders as presented in the embodiments of this application, and it is not necessarily necessary to perform all the operations in the embodiments of this application.

[0468] In the several embodiments provided in this application, it should be understood that the disclosed systems, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between apparatuses or units may be electrical, mechanical, or other forms.

[0469] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0470] In addition, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0471] If the aforementioned functions are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the contributing part, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0472] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any changes or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application.

Claims

1. A vehicle control method, characterized in that, The vehicle control method includes: Obtain vehicle information of the first vehicle and information of the first aerial object outside the first vehicle; Based on the vehicle information of the first vehicle and the information of the first aerial object, the collision level between the first aerial object and the first vehicle is determined. Based on the collision level, the first vehicle is controlled to withstand the impact of the first airborne object on a predetermined component of the first vehicle.

2. The vehicle control method according to claim 1, characterized in that, The preset component is a second component, and the step of controlling the first vehicle to withstand the impact of the first airborne object based on the collision level includes: The collision level is determined to be related to a first component of the first vehicle; The first vehicle is controlled such that a second component of the first vehicle withstands the impact of the first airborne object, the first component and the second component being different.

3. The vehicle control method according to claim 2, characterized in that, The second component has a higher degree of rigidity than the first component, and / or the cost of the second component is lower than the cost of the first component.

4. The vehicle control method according to claim 2 or 3, characterized in that, The collision priority of the first component and / or the second component is configurable.

5. The vehicle control method according to any one of claims 2 to 4, characterized in that, The first component includes at least one of the following: the windshield of the first vehicle, the side window of the door of the first vehicle, the lighting module of the first vehicle, the rearview mirror of the first vehicle, and the sensing module deployed on the body of the first vehicle.

6. The vehicle control method according to any one of claims 2 to 5, characterized in that, The second component includes at least one of the following: the frame of the first vehicle, the hood of the first vehicle, the door of the first vehicle, and the bumper of the first vehicle.

7. The vehicle control method according to any one of claims 1 to 6, characterized in that, Controlling the first vehicle to cause a preset component of the first vehicle to withstand the impact of the first airborne object includes: Control one or more of the first vehicle's speed, direction of travel, and vehicle posture to ensure that the preset component of the first vehicle withstands the impact of the first airborne object.

8. The vehicle control method according to any one of claims 1 to 7, characterized in that, The vehicle information of the first vehicle includes one or more of the following: the speed of the first vehicle, the direction of travel of the first vehicle, and the body posture of the first vehicle.

9. The vehicle control method according to any one of claims 1 to 8, characterized in that, The step of determining the collision level between the first aerial object and the first vehicle based on the vehicle information of the first vehicle and the information of the first aerial object includes: Based on the information of the first aerial object, determine the trajectory of the first aerial object; The collision level is determined based on the trajectory of the first airborne object and the vehicle information of the first vehicle.

10. The vehicle control method according to claim 9, characterized in that, Determining the trajectory of the first airborne object based on its information includes: Based on the information of the first aerial object, determine the hazard level of the first aerial object; If the danger level is greater than the first threshold, the trajectory of the first airborne object is determined.

11. The vehicle control method according to claim 10, characterized in that, The information of the first aerial object includes the mask information of the first aerial object; The determination of the hazard level of the first aerial object based on its information includes: The mask information of the first aerial object is input into the classification network model to determine the type of the first aerial object. The classification network model is used to classify the type of the object. Based on the type of the first aerial object, the hazard level of the first aerial object is determined.

12. The vehicle control method according to any one of claims 9 to 11, characterized in that, The information of the first flying object includes a first image frame and a second image frame, wherein the first image frame and the second image frame are two consecutive adjacent images of the first flying object during its movement. Determining the trajectory of the first aerial object includes: Based on the first image frame and the second image frame, a third image frame and a fourth image frame are obtained; the third image frame is an image frame of the first image frame scaled down by a first ratio, and the fourth image frame is an image frame of the second image frame scaled down by the first ratio. The first image frame and the second image frame are input into the first optical flow network model to obtain the first optical flow; the first optical flow network model is used to predict the next frame or multiple frames of images corresponding to the first image frame and the second image frame. The third image frame and the fourth image frame are input into the second optical flow network model to obtain the second optical flow; the second optical flow network model is used to predict the next frame or multiple frames corresponding to the third image frame and the fourth image frame. By fusing the first optical flow and the second optical flow, the trajectory of the first airborne object is obtained.

13. The vehicle control method according to claim 12, characterized in that, The process of fusing the first optical flow and the second optical flow to obtain the trajectory of the first airborne object includes: Upsampling is performed on the second optical flow; The first optical flow and the upsampled second optical flow are input into the second optical flow feature fusion model to obtain the trajectory of the first airborne object.

14. The vehicle control method according to claim 10, characterized in that, The information of the first aerial object includes the motion characteristic information of the first aerial object; The determination of the hazard level of the first aerial object based on its information includes: Based on the motion characteristics of the first aerial object, the type of the first aerial object is determined; Based on the type of the first aerial object, the hazard level of the first aerial object is determined.

15. The vehicle control method according to any one of claims 1 to 14, characterized in that, The vehicle control method further includes: Based on the collision level, a first alert is issued, which is used to alert the first user to relevant information about the first airborne object.

16. The vehicle control method according to claim 15, characterized in that, The step of issuing a first warning message based on the collision level includes: Obtain the first user information corresponding to the first user inside the first vehicle; Based on the collision level and the first user information, if the vector angle between the first user's line of sight and the trajectory of the first airborne object is greater than a second threshold, the first prompt message is issued.

17. The vehicle control method according to any one of claims 1 to 16, characterized in that, The vehicle control method further includes: A second warning message is issued, which is used to alert the surrounding area of ​​the first vehicle that a collision has occurred.

18. The vehicle control method according to any one of claims 1 to 17, characterized in that, The vehicle control method further includes: The collision information is sent to the associated account of the first vehicle. The collision information includes information about the first vehicle before the collision and information about the first vehicle after the collision.

19. The vehicle control method according to any one of claims 1 to 18, characterized in that, The vehicle control method further includes: Send an alarm message, which is used to report the collision of the first vehicle and request rescue.

20. The vehicle control method according to claim 19, characterized in that, The sending of alarm information includes: An alarm request is sent to the user inside the first vehicle, the alarm request being used to inquire with the user inside the first vehicle whether to sound an alarm. Upon receiving a response message to the alarm request, the alarm information is sent.

21. A vehicle control device, characterized in that, Includes units for performing the method as described in any one of claims 1 to 20.

22. A vehicle control device, characterized in that, Includes a processor for performing the method as described in any one of claims 1 to 20.

23. A chip, characterized in that, It includes logic circuits and interfaces, wherein the logic circuits and the interfaces are coupled; The interface is used for inputting and / or outputting information, and the logic circuit is used for performing the method as described in any one of claims 1 to 20.

24. A terminal, characterized in that, Includes the vehicle control device as described in claim 21, or the vehicle control device as described in claim 22, or the chip as described in claim 23.

25. A computer-readable storage medium, characterized in that, The computer-readable storage medium is used to store a computer program, which, when executed, performs the method as described in any one of claims 1 to 20.

26. A computer program product, characterized in that, The computer program product includes a computer program, which, when executed, performs the method as described in any one of claims 1 to 20.

Images