Method, device, vehicle and storage medium for driving away animals from the surroundings of a vehicle

Abstract

The application relates to a vehicle surrounding animal driving method, device, computer equipment, readable storage medium and computer program product. The method comprises the following steps: in response to the existence of target type animals in a preset area range where a vehicle is located, acquiring a surrounding environment image of the vehicle; acquiring an environment cleaning condition of an environment where the vehicle is located according to the surrounding environment image of the vehicle; acquiring an environment illumination condition of the environment where the vehicle is located, and predicting an environment risk level of the environment where the vehicle is located according to the environment illumination condition, the environment cleaning condition and a current time interval; the environment risk level is used for indicating the risk of damage of the vehicle caused by the target type animals; in a plurality of preset candidate driving strategies, a target driving strategy matched with the environment risk level is selected; and a vehicle control instruction matched with the target driving strategy is executed. By using the method, effective biological protection of the vehicle can be realized on the basis of accurate evaluation of the surrounding environment risk of the vehicle.

Description

Technical Field

[0001] This application relates to the field of vehicle technology, and in particular to a method, apparatus, vehicle, computer-readable storage medium, and computer program product for driving away animals around a vehicle. Background Technology

[0002] With the acceleration of urbanization and the popularization of urban greening, more and more small animals are appearing on roads and in parking lots, especially the increasingly rampant stray cats, stray dogs, and rodents such as rats. They often hide around or under vehicles, and their scratches and bites can damage vehicles. Furthermore, if car owners do not walk around the vehicle to check or drive away the animals before starting the car, they may also cause life-threatening injuries to the animals hiding around the vehicle.

[0003] Traditional biological animal repelling techniques mainly employ methods such as chemical repellents, physical barriers, and ultrasonic repellents. However, traditional ultrasonic animal repelling techniques often use fixed or simple trigger-based designs, relying solely on a single sensor for detection. This results in a high false trigger rate for animals and an inability to accurately perceive and assess the environment based on dynamic changes and time-related differences, leading to a lack of targeted animal repelling strategies. Summary of the Invention

[0004] Therefore, it is necessary to provide a method, device, vehicle, readable storage medium, and computer program product for repelling animals around a vehicle that can achieve effective vehicle biological protection based on an accurate assessment of the risks in the environment surrounding the vehicle.

[0005] In a first aspect, this application provides a method for repelling animals around a vehicle, the method comprising:

[0006] In response to the presence of a target type of animal within a preset area where the vehicle is located, an image of the vehicle's surrounding environment is acquired; based on the image of the vehicle's surrounding environment, the environmental cleanliness of the environment where the vehicle is located is obtained.

[0007] The ambient lighting conditions of the vehicle's environment are obtained, and the environmental risk level of the vehicle's environment is predicted based on the ambient lighting conditions, the cleanliness of the environment, and the current time interval; the environmental risk level is used to indicate the risk that the vehicle will be damaged by the target type of animal.

[0008] Among a number of pre-set candidate expulsion strategies, select the target expulsion strategy that matches the environmental risk level.

[0009] Execute vehicle control commands that match the target driving strategy.

[0010] In one embodiment, the ambient lighting conditions include ambient illuminance, and the environmental cleanliness conditions include the target object ratio, wherein the target object ratio is the area ratio of the target object in the surrounding environment image to the area of ​​the surrounding environment image, and the target object is an object that affects the environmental cleanliness around the vehicle.

[0011] The step of predicting the environmental risk level of the vehicle's environment based on the ambient lighting conditions, the environmental cleanliness, and the current time interval includes:

[0012] The ambient light intensity is mapped to a corresponding brightness risk impact coefficient, the target object proportion is mapped to a corresponding cleanliness risk impact coefficient, and the current time interval is mapped to a corresponding time period risk impact coefficient.

[0013] By combining the brightness risk impact coefficient, the cleanliness risk impact coefficient, and the time period risk impact coefficient, the environmental risk level of the environment in which the vehicle is located is determined.

[0014] The ambient light intensity is negatively correlated with the brightness risk impact coefficient, the proportion of the target object is positively correlated with the cleanliness risk impact coefficient, the current time interval includes daytime and nighttime, and the daytime period risk impact coefficient is less than the nighttime period risk impact coefficient.

[0015] In one embodiment, determining the environmental risk level of the vehicle's environment by fusing the brightness risk impact coefficient, the cleanliness risk impact coefficient, and the time period risk impact coefficient includes:

[0016] Based on the preset environmental risk weights, the brightness risk impact coefficient, the cleanliness risk impact coefficient, and the time period risk impact coefficient are weighted and summed to obtain the quantitative value of the environmental risk of the environment in which the vehicle is located.

[0017] The environmental risk level of the environment in which the vehicle is located is determined based on the comparison between the quantified environmental risk value and the preset threshold range.

[0018] In one embodiment, the environmental risk level includes a first risk level and a second risk level, wherein the first risk level is lower than the second risk level;

[0019] When the environmental risk level is the first risk level, executing vehicle control commands that match the target driving-off strategy includes:

[0020] This target type animal identification event will be recorded as an abnormal event; the target type animal identification event is an event in which the target type animal is detected within the preset area.

[0021] When the environmental risk level is the second risk level, executing vehicle control commands that match the target driving-off strategy includes:

[0022] According to the sound wave generation mode matched to the second risk level, a preset sound wave signal is output.

[0023] In one embodiment, the second risk level includes a third risk level and a fourth risk level, wherein the third risk level is lower than the fourth risk level;

[0024] When the environmental risk level is the third risk level, the step of outputting a preset sound wave signal according to the sound wave generation mode matched to the second risk level includes:

[0025] The time the target type of animal stays in the environment where the vehicle is located is detected according to a preset detection cycle;

[0026] If the target type animal stays in the environment where the vehicle is located for a longer than a preset stay time, a preset sound wave signal is emitted according to a preset signal emission period and a preset sound pressure enhancement gradient.

[0027] When the environmental risk level is the fourth risk level, the step of outputting a preset sound wave signal according to the sound wave generation mode matched to the second risk level includes:

[0028] The duration of time the target type of animal stays in the environment where the vehicle is located is continuously monitored;

[0029] If the target type animal stays in the environment where the vehicle is located for a longer than a preset stay time, at least two different preset sound wave signals are alternately emitted according to a preset sound pressure enhancement gradient.

[0030] In one embodiment, the method further includes:

[0031] If a heat source at a preset temperature is detected, the duration of the heat source is obtained;

[0032] If the duration of the heat source is greater than a preset duration, an image of the area around the vehicle is acquired;

[0033] The images surrounding the vehicle are input into a pre-trained animal category recognition model to obtain recognition results; the recognition results indicate whether there are target type animals within the preset area where the vehicle is located.

[0034] Secondly, this application provides a vehicle-around-animal repelling device, the device comprising:

[0035] The vehicle environment perception module is used to acquire an image of the vehicle's surrounding environment in response to the presence of a target type of animal within a preset area where the vehicle is located; and to acquire the environmental cleanliness of the environment where the vehicle is located based on the image of the vehicle's surrounding environment.

[0036] The risk level assessment module is used to obtain the ambient lighting conditions of the environment in which the vehicle is located, and predict the environmental risk level of the environment in which the vehicle is located based on the ambient lighting conditions, the cleanliness of the environment, and the current time interval; the environmental risk level is used to indicate the risk that the vehicle will be damaged by the target type of animal;

[0037] The deportation strategy selection module is used to select a target deportation strategy that matches the environmental risk level from a plurality of preset candidate deportation strategies.

[0038] The driving-off strategy execution module is used to execute vehicle control commands that match the target driving-off strategy.

[0039] Thirdly, this application also provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps of the above-described method for driving away animals around a vehicle.

[0040] Fourthly, this application also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the above-described method.

[0041] Fifthly, this application also provides a computer program product, including a computer program that, when executed by a processor, implements the steps of the above-described method.

[0042] The aforementioned method, apparatus, computer equipment, readable storage medium, and computer program product for repelling animals around vehicles acquire images of the vehicle's surrounding environment in response to the presence of a target type of animal within a preset area where the vehicle is located. Based on these images, the cleanliness and lighting conditions of the vehicle's surrounding environment are obtained. This allows for the perception of multimodal and multi-type information about the vehicle's surrounding environment, providing a reliable data source for subsequent assessments of vehicle environmental risks. Furthermore, based on lighting conditions, cleanliness, and the current time interval, the environmental risk level of the vehicle's surrounding environment is predicted, achieving dynamic assessment of the vehicle's surrounding environment and improving the accuracy of risk assessment. Then, from a set of preset candidate repelling strategies, a target repelling strategy matching the environmental risk level is selected, and vehicle control commands matching the target repelling strategy are executed. This allows for differentiated repelling strategies for different types of animals at different environmental risk levels, achieving graded responses to different environmental risks. This improves the repelling effect and enables effective vehicle biological protection based on accurate assessments of environmental risks around the vehicle. Attached Figure Description

[0043] To more clearly illustrate the technical solutions in the embodiments of this application or related technologies, the drawings used in the description of the embodiments of this application or related technologies will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0044] Figure 1 This is a flowchart illustrating a method for driving away animals around a vehicle in one embodiment;

[0045] Figure 2 This is a schematic diagram of the battery energy consumption management process in a method for driving away animals around a vehicle, as described in one embodiment.

[0046] Figure 3 This is a flowchart illustrating a method for driving away animals around a vehicle in another embodiment;

[0047] Figure 4 This is a structural block diagram of a vehicle-surrounding animal deterrent device in one embodiment;

[0048] Figure 5 This is an internal structural diagram of a computer device in one embodiment. Detailed Implementation

[0049] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0050] It should be noted that the terms "first," "second," etc., used in this application may be used to describe various elements, but these elements are not limited by these terms. These terms are only used to distinguish the first element from the second element. The terms "comprising" and "having," and any variations thereof, used in this application, are intended to cover non-exclusive inclusion. The term "multiple" used in this application refers to two or more.

[0051] In the field of vehicle biosafety, traditional technologies suffer from the following shortcomings: 1) Repellent devices are mostly triggered by a single sensor, resulting in a high false trigger rate and difficulty in accurately distinguishing target animals from interfering objects; 2) Fixed or simple trigger designs fail to assess risks based on dynamic changes in the parking environment (such as cleanliness and brightness) and time of day (day / night), leading to a lack of targeted rodent control strategies; 3) Fixed ultrasonic emission parameters and a single emission mode (fixed frequency / intensity) make animals adaptable, reducing the repellent effect; 4) Inefficient energy management affects the stability of the vehicle's electrical system. These problems stem from the fact that traditional technologies fail to organically combine environmental perception, risk assessment, and dynamic response, lacking a collaborative mechanism between environmental perception and dynamic risk assessment, as well as a precise triggering strategy based on multi-sensor data fusion.

[0052] Based on this, this application provides a method for driving away animals around a vehicle, which aims to achieve the coordinated operation of environmental perception and dynamic risk assessment through multi-sensor collaborative detection, dynamic environmental risk assessment and intelligent adjustment of ultrasonic parameters, thereby achieving efficient, environmentally friendly and energy-saving biological protection.

[0053] In one exemplary embodiment, such as Figure 1 As shown, a method for repelling animals around a vehicle is provided. This embodiment illustrates the method by applying it to a terminal. It is understood that this method can also be applied to a server, and further to a system including both a terminal and a server, and implemented through interaction between the terminal and the server. In this embodiment, the method includes the following steps S102 to S108. Wherein:

[0054] Step S102: In response to the presence of a target type animal within a preset area where the vehicle is located, an image of the vehicle's surrounding environment is acquired; based on the image of the vehicle's surrounding environment, the environmental cleanliness of the environment where the vehicle is located is obtained.

[0055] The target animals can be rodents such as mice and hamsters, or animals such as cats and dogs that may hide around or under the vehicle and cause damage.

[0056] In practical applications, vehicle controllers can collect real-time environmental data around the vehicle, including information on the activity of target animals, the brightness and cleanliness of the environment around the vehicle, and other parameters, by using infrared sensors (e.g., infrared thermal imaging sensors), cameras (e.g., wide-angle cameras), and light sensors (illuminance sensors or light sensors) placed in key areas such as the vehicle chassis and exterior of the engine compartment.

[0057] If a target type of animal is detected within a preset area where the vehicle is located, the vehicle can acquire images of its surrounding environment through a camera installed on the outside of the vehicle. The images of the surrounding environment are then analyzed to determine whether there is any debris or whether the area around the vehicle is clean, thus obtaining information about the cleanliness of the environment in which the vehicle is located.

[0058] Step S104: Obtain the ambient lighting conditions of the vehicle's environment, and predict the environmental risk level of the vehicle's environment based on the ambient lighting conditions, environmental cleanliness, and the current time interval.

[0059] Among them, the environmental risk level is used to indicate the risk of damage to the vehicle by the target type of animal.

[0060] In practical implementation, the vehicle controller can use a light sensor, combined with GPS positioning information, to determine the type of area where the vehicle is located (e.g., underground garage, semi-enclosed parking lot, open-air parking lot, etc.), obtain the ambient lighting conditions of the environment, and then input the ambient lighting conditions, environmental cleanliness, and current time interval (day or night) into a preset risk assessment model to determine the environmental risk level of the vehicle's environment. For example, the environmental risk level can be set to high risk, medium risk, and low risk.

[0061] Step S106: Select the target deportation strategy that matches the environmental risk level from a number of preset candidate deportation strategies.

[0062] In practical applications, the vehicle controller can select a target de-escalation strategy that matches the environmental risk level from a set of preset candidate de-escalation strategies, and execute differentiated de-escalation strategies based on the risk assessment results.

[0063] For example, in cases with a high environmental risk level, a strategy can be initiated to continuously monitor the target type of animal and activate an ultrasonic generator to emit sound wave signals at frequencies corresponding to high risk; in cases with a medium environmental risk level, a strategy can be initiated to conduct regular inspections of the target type of animal and activate an ultrasonic generator to emit sound wave signals at frequencies corresponding to medium risk; in cases with a low environmental risk level, a strategy can be initiated to only record abnormal events without intervening in the animals.

[0064] Step S108: Execute vehicle control commands that match the target driving strategy.

[0065] In practice, the vehicle controller can execute vehicle control commands that match the selected target driving strategy, which is matched with the environmental risk level.

[0066] The aforementioned method for repelling animals around vehicles acquires images of the vehicle's surrounding environment in response to the presence of target-type animals within a preset area. Based on these images, it assesses the cleanliness and lighting conditions of the vehicle's surroundings, thus perceiving multimodal and multi-type information about the vehicle's environment and providing a reliable data source for subsequent assessments of vehicle environmental risks. Furthermore, based on lighting conditions, cleanliness, and the current time interval, it predicts the environmental risk level of the vehicle's surroundings, achieving dynamic assessment and improving the accuracy of risk assessment. Then, from multiple preset candidate repelling strategies, it selects a target repelling strategy that matches the environmental risk level and executes vehicle control commands matching the target strategy. This allows for differentiated repelling strategies for different types of animals at different environmental risk levels, achieving a tiered response to different environmental risks and improving repelling effectiveness. Ultimately, it enables effective vehicle biosecurity based on accurate assessments of environmental risks.

[0067] In an exemplary embodiment, ambient lighting conditions include ambient illuminance, and environmental cleanliness conditions include the proportion of the target object. Therefore, based on ambient lighting conditions, environmental cleanliness conditions, and the current time interval, the environmental risk level of the vehicle's environment is predicted, including: mapping ambient illuminance to a corresponding brightness risk impact coefficient, mapping the proportion of the target object to a corresponding cleanliness risk impact coefficient, and mapping the current time interval to a corresponding time period risk impact coefficient; and fusing the brightness risk impact coefficient, cleanliness risk impact coefficient, and time period risk impact coefficient to determine the environmental risk level of the vehicle's environment.

[0068] The target object is defined as any object affecting the cleanliness of the environment surrounding the vehicle, such as garbage or debris. The target object percentage is the area of ​​the target object within the surrounding environment image. The inventors recognized that piles of garbage and debris around vehicles often attract small animals like rats to hide or forage nearby. These animals not only breed bacteria and insects and produce excrement, causing hygiene and health problems, but they also scratch and bite vehicle wiring, tires, and paintwork, posing a significant safety hazard. In the implementation, a pre-trained object recognition model can be used to determine the area of ​​garbage or debris covering the surrounding environment image, thus assessing the potential damage caused to the vehicle by small animals that easily hide in piles of garbage and debris.

[0069] Among them, the ambient light intensity and the brightness risk impact coefficient are negatively correlated. The inventors realized that the lower the ambient light intensity around the vehicle, the easier it is for small animals to hide, and the more easily the vehicle is damaged by small animals. The brightness risk impact coefficient in the vehicle's environmental risk level is higher.

[0070] The proportion of target objects is positively correlated with the cleanliness risk impact coefficient. That is, the larger the proportion of target objects, the more garbage or debris is piled up around the vehicle, the easier it is for small animals to hide around the vehicle, the greater the possibility of the vehicle being damaged by small animals, and the higher the cleanliness risk impact coefficient in the vehicle's environmental risk level.

[0071] The current time interval includes both day and night. The risk impact coefficient during the day is lower than that during the night. The inventors realized that small animals tend to forage at night, making vehicles more vulnerable to damage. Therefore, the higher the time interval of the vehicle's current time interval (nighttime), the higher the time-based risk impact coefficient in the vehicle's environmental risk level. For example, the vehicle's location can be determined based on GPS positioning information. Day and night can then be divided according to the time zone of that location and its sunrise and sunset times. For instance, Beijing time 06:00-18:00 can be classified as daytime.

[0072] In practical applications, after the vehicle controller obtains the ambient illuminance of the vehicle's surroundings through a light sensor, it can classify the ambient illuminance and map it to a corresponding brightness risk impact coefficient. This allows for the assessment of the potential damage to the vehicle caused by small animals hiding due to the intensity of light around it. For example, if the ambient illuminance is >50 lux, the corresponding brightness risk impact coefficient can be set to 0.2; if the ambient illuminance is between 10 and 50 lux, the corresponding brightness risk impact coefficient can be set to 0.5; and if the ambient illuminance is <10 lux, the corresponding brightness risk impact coefficient can be set to 1.0.

[0073] After the vehicle's controller captures images of the surrounding environment via a camera, it can assess the cleanliness of the environment, identify trash and debris as target objects, determine the proportion of these target objects using a pre-defined object recognition model, and then map this proportion to a corresponding cleanliness risk impact coefficient (also known as a cleanliness coefficient). For example, if the target object proportion is <10%, the corresponding cleanliness risk impact coefficient can be set to 0.2; if the target object proportion is between 10% and 30%, the corresponding cleanliness risk impact coefficient can be set to 0.5; and if the target object proportion is >30%, the corresponding cleanliness risk impact coefficient can be set to 1.0.

[0074] After obtaining the vehicle's current time interval through the onboard clock, the vehicle's controller can map the current time interval to a corresponding time-period risk impact coefficient. For example, if the current time interval is daytime, the corresponding time-period risk impact coefficient can be set to 0.3; if the current time interval is nighttime, the corresponding time-period risk impact coefficient can be set to 0.7.

[0075] Furthermore, by using a pre-set risk assessment model, which integrates the risk impact coefficients of brightness, cleanliness, and time period, the environmental risk level of the vehicle's environment can be determined.

[0076] For example, if the GPS location is a B2 level parking garage, at night, the light sensor reading is <10 lux, and the image of the surrounding environment shows debris piled up around the vehicle, this is a nighttime scene in an underground parking garage. The corresponding risk impact coefficients can be mapped as follows: cleanliness coefficient is 0.8, brightness coefficient is 0.9, and nighttime coefficient is 0.9.

[0077] For example, if the GPS location is outdoor area A, during the day, the light sensor reading is >30000 lux, and the image shows a clean environment, this is a daytime scene in an open-air parking lot. The corresponding risk impact coefficients can be mapped as follows: cleanliness coefficient is 0.2, brightness coefficient is 0.1, and daytime coefficient is 0.1.

[0078] The technical solution of this embodiment maps ambient light intensity to a corresponding brightness risk impact coefficient, the proportion of the target object to a corresponding cleanliness risk impact coefficient, and the current time interval to a corresponding time period risk impact coefficient. This combines the cleanliness and brightness of the vehicle parking environment with daytime / nighttime periods, taking into account multiple environmental factors to dynamically adjust the risk assessment parameters. Furthermore, it integrates the brightness risk impact coefficient, cleanliness risk impact coefficient, and time period risk impact coefficient to determine the environmental risk level of the vehicle's location, thus providing a core quantitative basis for the subsequent implementation of differentiated animal deterrence strategies.

[0079] In an exemplary embodiment, the environmental risk level of the vehicle's environment is determined by integrating the brightness risk impact coefficient, cleanliness risk impact coefficient, and time period risk impact coefficient. This includes: weighting and summing the brightness risk impact coefficient, cleanliness risk impact coefficient, and time period risk impact coefficient according to preset environmental risk weights to obtain a quantitative value of the environmental risk of the vehicle's environment; and determining the environmental risk level of the vehicle's environment based on the comparison between the quantitative value of the environmental risk and a preset threshold range.

[0080] In practical implementation, the vehicle controller can determine the brightness risk impact coefficient based on preset environmental risk weights using the following model: Cleanliness risk impact coefficient and the impact coefficient of time period risk By performing a weighted summation, the environmental risk quantification value of the vehicle's environment is obtained. :

[0081]

[0082] In the above model, Cleanliness weight (cleanliness weight). For brightness weight, For time period weighting, For example, they can be set as follows: .

[0083] Furthermore, the environmental risk level of the vehicle's environment can be determined based on the comparison between the quantified environmental risk value and a preset threshold range. For example, if the quantified environmental risk value is greater than or equal to a first risk threshold, the environmental risk level can be determined as high risk; if the quantified environmental risk value is less than the first risk threshold but greater than or equal to a second risk threshold, the environmental risk level is determined as medium risk; and if the quantified environmental risk value is less than the second risk threshold, the environmental risk level is determined as low risk. The first risk threshold is greater than the second risk threshold. For instance, if the first risk threshold is 0.7 and the second risk threshold is 0.4, if R ≥ 0.7, the environmental risk level is high risk; if 0.4 ≤ R < 0.7, the environmental risk level is medium risk; and if R < 0.4, the environmental risk level is low risk.

[0084] Taking the underground parking lot nighttime scene mentioned above as an example, the cleanliness coefficient is 0.8, the brightness coefficient is 0.9, and the nighttime coefficient is 0.9. Based on equation (1), the environmental risk quantification value of this scene can be calculated. The value is 0.87, therefore the scenario can be determined to be high-risk.

[0085] Taking the daytime scenario of the open-air parking lot mentioned above as an example, the cleanliness coefficient is 0.2, the brightness coefficient is 0.1, and the daytime coefficient is 0.1. Based on equation (1), the environmental risk quantification value of this scenario can be calculated. The value is 0.13, therefore the scenario can be determined to be low risk.

[0086] The technical solution of this embodiment obtains the environmental risk quantification value of the vehicle's environment by weighted summing of the brightness risk impact coefficient, cleanliness risk impact coefficient, and time period risk impact coefficient according to the preset environmental risk weights, thus clarifying the specific quantification method of environmental risk assessment; then, based on the comparison result between the environmental risk quantification value and the preset threshold range, the environmental risk level of the vehicle's environment is determined, thereby achieving an accurate assessment of the environmental risk of the vehicle's environment.

[0087] In one exemplary embodiment, the environmental risk level includes a first risk level and a second risk level, where the first risk level is lower than the second risk level. The first risk level is the low risk described above, and the second risk level includes the medium and high risks described above.

[0088] When the environmental risk level is Level 1, execute vehicle control commands that match the target deflection strategy, including recording the target type animal identification event as an anomalous event.

[0089] Among them, the target type animal recognition event can be an event in which a target type animal is identified within a preset area.

[0090] Continuing with the example of the daytime scenario in the open-air parking lot mentioned above, once the scenario is determined to be low-risk, the vehicle's controller can record the target type animal identification event as an abnormal event, without activating the shooing device or actively intervening in the target type animal.

[0091] When the environmental risk level is the second risk level, execute vehicle control commands that match the target driving strategy, including: outputting a preset sound wave signal according to the sound wave generation mode matched to the second risk level.

[0092] In practical applications, the vehicle is equipped with an adjustable-frequency ultrasonic generator. The vehicle's controller can adjust the operating frequency band of the ultrasonic generator according to different risk levels, such as 22kHz, 28kHz, 35kHz, and 45kHz. The sound pressure level of the ultrasonic generator's output signal can be gradually increased; for example, its sound pressure range can be set from 80dB (initial) to 120dB (maximum), increasing by 5dB every 10 seconds or every 5 seconds, up to the 120dB upper limit. The output sound signal can be intermittently emitted using a preset duty cycle, such as a 2-second emission / 1-second pause duty cycle, or a 5-second emission followed by a 1-second pause, or a 5-second operation followed by a 3-second interval. Simultaneously, the ultrasonic generator dynamically switches frequencies within the 22-45kHz range according to a preset pattern to prevent animal adaptation.

[0093] Based on this ultrasonic generator, the vehicle controller can control the ultrasonic generator to output a preset sound wave signal according to the sound wave generation mode matched to the second risk level, such as a dual-frequency alternating continuous emission mode and a single-frequency intermittent emission mode.

[0094] The technical solution of this embodiment records the target animal identification event as an abnormal event when the environmental risk level is the first risk level; when the environmental risk level is the second risk level, a preset sound wave signal is output according to the sound wave generation mode matched to the second risk level. This realizes the execution of vehicle control commands that match the target driving strategy for different environmental risk levels, thereby realizing an intelligent and differentiated graded response method for driving away animals around the vehicle. Compared with the traditional fixed trigger mode, it can reduce the running time of ultrasonic equipment and reduce system energy consumption.

[0095] In an exemplary embodiment, the second risk level includes a third risk level and a fourth risk level, with the third risk level being lower than the fourth risk level; the third risk level is the medium risk described above, and the fourth risk level is the high risk described above.

[0096] When the environmental risk level is level three, a preset acoustic signal is output according to the acoustic generation mode matched to level two, including: detecting the dwell time of the target animal in the vehicle environment according to a preset detection cycle; and emitting a preset ultrasonic signal according to a preset signal emission cycle and a preset sound pressure enhancement gradient when the dwell time of the target animal in the vehicle environment is longer than the preset dwell time.

[0097] In specific implementations, for medium-risk (third-risk level) scenarios, such as semi-enclosed parking lots during the day, the vehicle controller can periodically inspect the target type of animal according to a preset detection cycle, detecting the dwell time of the target type of animal in the vehicle's environment; if the dwell time of the target type of animal in the vehicle's environment is longer than the preset dwell time (default 10 seconds, configurable), a square wave modulation with an adjustable duty cycle is used to intermittently transmit ultrasonic signals of a preset waveform (such as a 35kHz / 100dB pulse wave) according to a preset signal transmission cycle, such as working for 5 seconds and then 3 seconds.

[0098] When the environmental risk level is level four, a preset sound wave signal is output according to the sound wave generation mode matched to level two, including: continuously detecting the dwell time of the target type animal in the environment where the vehicle is located; when the dwell time of the target type animal in the environment where the vehicle is located is longer than the preset dwell time, at least two different preset sound wave signals are alternately emitted according to the preset sound pressure enhancement gradient.

[0099] Continuing with the example of the underground parking lot nighttime scenario mentioned above, after determining that the scenario is high-risk (level 4 risk), the vehicle's controller can continuously monitor the target type of animal (such as a mouse) and detect the duration of the target type of animal's stay in the vehicle's environment. If a mouse is detected staying for 12 seconds, at least two different preset waveforms (such as 22kHz / 120dB continuous wave, 35kHz / 110dB or 35kHz / 115dB pulse wave) can be alternately emitted according to a preset sound pressure enhancement gradient (e.g., increasing by 5dB every 5 seconds) and continue until the target type of animal leaves the monitoring area.

[0100] The technical solution of this embodiment, through the design of ultrasonic generator with adjustable frequency band, dynamic frequency switching and sound pressure gradient enhancement, etc., the ultrasonic generator has a continuous monitoring and dual-frequency alternating signal ultrasonic generation mode for high-risk scenarios, and a timed inspection and intermittent emission ultrasonic generation mode for medium-risk scenarios. It realizes the ultrasonic generation mode matched to different environmental risk levels, and differentiates the output of preset ultrasonic signals by ultrasonic generator. This can improve the success rate of animal repelling, and at the same time effectively avoid the animal's adaptation to a single frequency.

[0101] In an exemplary embodiment, the method further includes: when a heat source at a preset temperature is detected, obtaining the duration of the heat source; when the duration of the heat source is greater than the preset duration, obtaining an image of the vehicle's surroundings; and inputting the image of the vehicle's surroundings into a pre-trained animal type recognition model to obtain a recognition result.

[0102] The identification result indicates whether the target type of animal exists within the preset area where the vehicle is located.

[0103] In practical applications, one set of infrared thermal imaging sensors (detection angle 120°) can be installed at the front, middle, and rear of the vehicle chassis. The infrared sensors use microthermometers and employ thermal imaging technology to detect biological heat sources, with a detection accuracy of ±0.05℃, a detection distance of 0.5-3 meters, and a scanning speed of 30 frames per second. In addition, one wide-angle camera (view of 180°) can be installed on each of the front bumper, left fender, right fender, and rear bumper. The visual verification of the target animal type by this camera uses an image recognition algorithm. The training set of this algorithm contains labeled rodent images, and the recognition accuracy is ≥95%.

[0104] When the infrared sensor detects a heat source at a preset temperature (e.g., 35-38℃), the duration of the heat source is recorded. If the duration exceeds the preset duration (e.g., more than 5 seconds), the vehicle-mounted camera is triggered to capture images of the vehicle's surroundings. These images are then input into a pre-trained animal type recognition model to identify animal characteristics and determine if a target animal exists within a preset area of ​​the vehicle. After dual confirmation by the infrared sensor's heat source detection and the camera's image verification, the dwell time of the target animal is recorded. If the infrared sensor's heat source detection result conflicts with the camera's visual detection result, a second scan can be automatically initiated (with a 1-second interval).

[0105] The technical solution of this embodiment detects a heat source at a preset temperature, obtains the duration of the heat source, and if the duration of the heat source is greater than the preset duration, acquires an image of the vehicle's surroundings. Then, the captured image of the vehicle's surroundings is input into a pre-trained animal type recognition model to determine the presence of the target animal. This achieves multi-sensor collaboration and dual-modal joint detection after the infrared sensor detects a heat source and triggers the camera to perform image verification, thereby improving the accuracy and precision of animal identification and reducing the false alarm rate of target animal repelling in subsequent animal repelling operations.

[0106] The method for driving away animals around a vehicle provided in this application further includes: obtaining the vehicle's battery state of charge via a CAN bus; and activating a low-power mode when the battery state of charge is less than a preset state of charge.

[0107] In the low-power mode, the target driving strategy corresponding to the high risk level is only executed when the environmental risk level is high.

[0108] In practice, the vehicle's main power supply preferentially uses a 12V low-voltage battery with an operating current ≤2A. For example... Figure 2As shown, the vehicle's controller can communicate with the vehicle's BMS (Battery Management System) via the CAN (Controller Area Network) bus to obtain the vehicle's battery state of charge (SOC). When the battery SOC is lower than the preset SOC, for example, when the battery level is below 20%, a low-power mode (energy-saving mode) is activated, maintaining monitoring only in high-risk areas and suspending unnecessary deflection tasks. When the battery SOC is greater than or equal to the preset SOC, full-function operation is maintained. Simultaneously, the operating time of devices such as sensors and ultrasonic generators can be dynamically adjusted based on the environmental risk level (e.g., 24-hour operation in high-risk areas, and reduced to 30% operating time in medium- and low-risk areas).

[0109] The technical solution of this embodiment obtains the vehicle's battery state of charge through the CAN bus. When the battery state of charge is less than the preset state of charge, a low-power mode is activated, realizing the linkage between the CAN bus and the vehicle's BMS. This can prioritize ensuring the vehicle's starting power and reduce the overall energy consumption of the vehicle.

[0110] like Figure 3 As shown, this application also provides a method for repelling animals around a vehicle, including:

[0111] Vehicle Environmental Perception Phase: Data is collected through various sensors in the onboard environmental perception system. This system, acting as the data acquisition end, consists of infrared thermal imaging sensors and wide-angle cameras deployed in key areas such as the vehicle chassis and engine compartment. The infrared sensors use thermal imaging technology to detect biological heat sources, monitoring real-time changes in thermal radiation in the vehicle chassis area. Upon detecting a heat source of 35-38℃ for more than 5 seconds, the wide-angle camera is triggered to simultaneously acquire a visible light image. Image recognition algorithms (such as the YOLOv5s algorithm) are used for visual verification of the target animal type. Dual-modal detection ensures accurate identification of the target animal type. Simultaneously, the onboard environmental perception system can collect real-time data on the vehicle's surrounding environment, including target animal activity information, GPS location information, ambient lighting conditions (ambient brightness), environmental cleanliness (characterized by the proportion of target objects), and the current time period. The collected data can be transmitted to the central processing unit via the CAN bus.

[0112] Risk Level Assessment Phase: The system receives raw data uploaded from the environmental sensing system and performs multi-dimensional analysis using built-in algorithms. This includes integrating GPS positioning information, ambient light sensor data (ambient lighting conditions, ambient light intensity, ambient brightness), image analysis results (environmental cleanliness, surrounding cleanliness, target object proportion), and parameters such as the current time period (day / night). Ambient light intensity is mapped to a corresponding brightness risk impact coefficient, the target object proportion is mapped to a corresponding cleanliness risk impact coefficient (cleanliness risk impact coefficient), and the current time interval is mapped to a corresponding time period risk impact coefficient. A weighted scoring model is then used to dynamically calculate the current environmental risk quantification value: R = ×Clean Risk Impact Coefficient+ ×Brightness Risk Impact Coefficient+ ×Time Period Risk Impact Coefficient ( The environmental risk level (high / medium / low) of the vehicle's current location is determined based on the environmental risk quantification value R. If R ≥ 0.7, it is considered high risk; if 0.4 ≤ R < 0.7, it is considered medium risk; and if R < 0.4, it is considered low risk. Furthermore, by fusing GPS positioning information with data from external environmental sensors, the risk level of the parking location is automatically marked (e.g., underground parking garages can be automatically marked as high risk).

[0113] Removal strategy selection phase: Based on the risk level, a preset strategy is automatically matched. Among multiple preset candidate removal strategies, the target removal strategy that matches the environmental risk level is selected. For high risk (R≥0.7), continuous monitoring and active scanning are initiated; for medium risk (0.4≤R<0.7), regular inspections are adopted; for low risk (R<0.4), only recording is performed without active intervention.

[0114] Execution phase of the deterrence strategy: The vehicle control commands matched to the target deterrence strategy are executed. The vehicle is equipped with an adjustable frequency ultrasonic generator (22-45kHz), employing sound pressure gradient enhancement (80dB→120dB, e.g., increasing by 5dB every 5 seconds) and intermittent transmission with a preset duty cycle (e.g., 5 seconds of sound followed by 1 second of pause). When an animal is detected staying for more than the threshold T (default 10 seconds, configurable), the corresponding deterrence mode is activated according to the environmental risk level and continues until the sound pressure reaches 120dB or the target type of animal leaves the monitoring area. After execution, the system returns to monitoring status. Simultaneously, it is linked with the vehicle's BMS via the CAN bus, prioritizing power supply from the 12V low-voltage battery, and activating energy-saving mode when the battery level is below 20%.

[0115] It should be noted that the specific limitations of the above steps can be found in the specific limitations of a method for driving away animals around a vehicle as described above.

[0116] It should be understood that although the steps in the flowcharts of the embodiments described above are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the embodiments described above may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages in other steps. It is understood that the steps in different embodiments can be freely combined as needed, and all non-contradictory solutions formed by such combinations are within the scope of protection of this application.

[0117] Based on the same inventive concept, this application also provides a vehicle-around-animal-repelling device for implementing the above-described method for repelling animals around vehicles. The solution provided by this device is similar to the solution described in the above-described method; therefore, the specific limitations of one or more vehicle-around-animal-repelling device embodiments provided below can be found in the limitations of the vehicle-around-animal-repelling method described above, and will not be repeated here.

[0118] In one exemplary embodiment, as shown in FIG4, a vehicle-around animal deterrent device is provided. It is understood that this vehicle-around animal deterrent device can also be a vehicle-around animal deterrent system. The vehicle-around animal deterrent device or vehicle-around animal deterrent system includes:

[0119] The vehicle environment perception module 410 is used to acquire images of the vehicle's surrounding environment in response to the presence of a target type of animal within a preset area where the vehicle is located; and to acquire the environmental cleanliness of the environment where the vehicle is located based on the images of the vehicle's surrounding environment.

[0120] The risk level assessment module 420 is used to obtain the ambient lighting conditions of the vehicle's environment, and predict the environmental risk level of the vehicle's environment based on the ambient lighting conditions, environmental cleanliness, and the current time interval; the environmental risk level is used to indicate the risk of the vehicle being damaged by the target type of animal;

[0121] The deportation strategy selection module 430 is used to select a target deportation strategy that matches the environmental risk level from a plurality of preset candidate deportation strategies.

[0122] The driving strategy execution module 440 is used to execute vehicle control commands that match the target driving strategy.

[0123] In one embodiment, the risk level assessment module 420 is specifically used to map ambient light intensity to a corresponding brightness risk impact coefficient, map the proportion of the target object to a corresponding cleanliness risk impact coefficient, and map the current time interval to a corresponding time period risk impact coefficient; and to determine the environmental risk level of the environment in which the vehicle is located by integrating the brightness risk impact coefficient, the cleanliness risk impact coefficient, and the time period risk impact coefficient.

[0124] In one embodiment, the risk level assessment module 420 is further configured to perform a weighted summation of the brightness risk impact coefficient, the cleanliness risk impact coefficient, and the time period risk impact coefficient according to a preset environmental risk weight, to obtain a quantitative value of the environmental risk of the environment in which the vehicle is located; and to determine the environmental risk level of the environment in which the vehicle is located based on the comparison result between the quantitative value of the environmental risk and a preset threshold range.

[0125] In one embodiment, the driving-off strategy execution module 440 is specifically used to execute vehicle control instructions matching the target driving-off strategy when the environmental risk level is the first risk level, including: recording the target type animal identification event as an abnormal event; the target type animal identification event is an event in which a target type animal is identified within a preset area; and, when the environmental risk level is the second risk level, executing vehicle control instructions matching the target driving-off strategy, including: outputting a preset sound wave signal according to the sound wave generation mode matched to the second risk level.

[0126] In one embodiment, the deterrence strategy execution module 440 is further configured to, when the environmental risk level is third risk level, output a preset acoustic signal according to an acoustic emission pattern matched to the second risk level, including: detecting the dwell time of the target type animal in the vehicle's environment according to a preset detection cycle; emitting a preset ultrasonic signal according to a preset signal emission cycle and a preset sound pressure enhancement gradient when the dwell time of the target type animal in the vehicle's environment is greater than a preset dwell time; and, when the environmental risk level is fourth risk level, outputting a preset acoustic signal according to an acoustic emission pattern matched to the second risk level, including: continuously detecting the dwell time of the target type animal in the vehicle's environment; and alternately emitting at least two different preset acoustic signals according to a preset sound pressure enhancement gradient when the dwell time of the target type animal in the vehicle's environment is greater than a preset dwell time.

[0127] In one embodiment, the device is further configured to: acquire the duration of a heat source when a heat source at a preset temperature is detected; acquire an image of the vehicle's surroundings when the duration of the heat source is greater than the preset duration; input the image of the vehicle's surroundings into a pre-trained animal type recognition model to obtain a recognition result; and the recognition result indicates whether a target type animal exists within a preset area where the vehicle is located.

[0128] The various modules in the aforementioned animal deterrent device around the vehicle can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in or independent of the processor in a computer device, or stored in the memory of a computer device as software, so that the processor can call and execute the corresponding operations of each module.

[0129] In an exemplary embodiment, a computer device is provided, which may be a server, and its internal structure diagram is shown in Figure 5. The computer device includes a processor, memory, input / output interfaces (I / O), a communication interface, a display unit, and an input device. The processor, memory, and I / O interfaces are connected via a system bus, and the communication interface, display unit, and input device are also connected to the system bus via the I / O interfaces. The processor provides computing and control capabilities. The memory includes a non-volatile storage medium and internal memory. The non-volatile storage medium stores an operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage medium. The I / O interfaces are used for exchanging information between the processor and external devices. The communication interface is used for communicating with external terminals via a network connection. When the computer program is executed by the processor, it implements a method for repelling animals around a vehicle. The display unit of the computer device is used to form a visually visible image and may be a display screen, a projection device, or a virtual reality imaging device.

[0130] Those skilled in the art will understand that the structure shown in Figure 5 is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or may combine certain components, or may have different component arrangements.

[0131] In one embodiment, a vehicle is provided, including a memory and a processor. The memory stores a computer program, and the processor executes the computer program to implement the steps of the above-described method for driving away animals around a vehicle.

[0132] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon, which, when executed by a processor, implements the steps of the above-described methods for driving away animals around a vehicle.

[0133] In one embodiment, a computer program product is provided, including a computer program that, when executed by a processor, implements the steps described in various embodiments of a method for calculating animal repellency around a vehicle.

[0134] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of the relevant data must comply with relevant regulations.

[0135] Those skilled in the art will understand that all or part of the processes in the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic resistive random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM). The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, artificial intelligence processors, etc., and are not limited to these.

[0136] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this application.

[0137] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of this patent application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this application should be determined by the appended claims.

Claims

1. A method for repelling animals around a vehicle, characterized in that, The method includes: In response to the presence of a target type of animal within a preset area where the vehicle is located, an image of the vehicle's surrounding environment is acquired; based on the image of the vehicle's surrounding environment, the environmental cleanliness of the environment where the vehicle is located is obtained. The ambient lighting conditions of the vehicle's environment are obtained, and the environmental risk level of the vehicle's environment is predicted based on the ambient lighting conditions, the cleanliness of the environment, and the current time interval; the environmental risk level is used to indicate the risk that the vehicle will be damaged by the target type of animal. Among a number of pre-set candidate expulsion strategies, select the target expulsion strategy that matches the environmental risk level. Execute vehicle control commands that match the target driving strategy.

2. The method according to claim 1, characterized in that, The ambient lighting conditions include ambient illuminance, and the environmental cleanliness conditions include the target object ratio, which is the area ratio of the target object in the surrounding environment image. The target object is an object that affects the environmental cleanliness around the vehicle. The step of predicting the environmental risk level of the vehicle's environment based on the ambient lighting conditions, the environmental cleanliness, and the current time interval includes: The ambient light intensity is mapped to a corresponding brightness risk impact coefficient, the target object proportion is mapped to a corresponding cleanliness risk impact coefficient, and the current time interval is mapped to a corresponding time period risk impact coefficient. By combining the brightness risk impact coefficient, the cleanliness risk impact coefficient, and the time period risk impact coefficient, the environmental risk level of the environment in which the vehicle is located is determined. The ambient light intensity is negatively correlated with the brightness risk impact coefficient, the proportion of the target object is positively correlated with the cleanliness risk impact coefficient, the current time interval includes daytime and nighttime, and the daytime period risk impact coefficient is less than the nighttime period risk impact coefficient.

3. The method according to claim 2, characterized in that, The environmental risk level of the vehicle's environment is determined by integrating the brightness risk impact coefficient, the cleanliness risk impact coefficient, and the time period risk impact coefficient, including: Based on the preset environmental risk weights, the brightness risk impact coefficient, the cleanliness risk impact coefficient, and the time period risk impact coefficient are weighted and summed to obtain the quantitative value of the environmental risk of the environment in which the vehicle is located. The environmental risk level of the environment in which the vehicle is located is determined based on the comparison between the quantified environmental risk value and the preset threshold range.

4. The method according to claim 1, characterized in that, The environmental risk level includes a first risk level and a second risk level, wherein the first risk level is lower than the second risk level; When the environmental risk level is the first risk level, executing vehicle control commands that match the target driving-off strategy includes: This target type animal identification event will be recorded as an abnormal event; the target type animal identification event is an event in which the target type animal is detected within the preset area. When the environmental risk level is the second risk level, executing vehicle control commands that match the target driving-off strategy includes: According to the sound wave generation mode matched to the second risk level, a preset sound wave signal is output.

5. The method according to claim 4, characterized in that, The second risk level includes a third risk level and a fourth risk level, wherein the third risk level is lower than the fourth risk level; When the environmental risk level is the third risk level, the step of outputting a preset sound wave signal according to the sound wave generation mode matched to the second risk level includes: The time the target type of animal stays in the environment where the vehicle is located is detected according to a preset detection cycle; If the target type animal stays in the environment where the vehicle is located for a longer than a preset stay time, a preset sound wave signal is emitted according to a preset signal emission period and a preset sound pressure enhancement gradient. When the environmental risk level is the fourth risk level, the step of outputting a preset sound wave signal according to the sound wave generation mode matched to the second risk level includes: The duration of time the target type of animal stays in the environment where the vehicle is located is continuously monitored; If the target type animal stays in the environment where the vehicle is located for a longer than a preset stay time, at least two different preset sound wave signals are alternately emitted according to a preset sound pressure enhancement gradient.

6. The method according to claim 1, characterized in that, The method further includes: If a heat source at a preset temperature is detected, the duration of the heat source is obtained; If the duration of the heat source is greater than a preset duration, an image of the area around the vehicle is acquired; The images surrounding the vehicle are input into a pre-trained animal category recognition model to obtain recognition results; the recognition results indicate whether there are target type animals within the preset area where the vehicle is located.

7. A device for repelling animals around a vehicle, characterized in that, The device includes: The vehicle environment perception module is used to acquire an image of the vehicle's surrounding environment in response to the presence of a target type of animal within a preset area where the vehicle is located; and to acquire the environmental cleanliness of the environment where the vehicle is located based on the image of the vehicle's surrounding environment. The risk level assessment module is used to obtain the ambient lighting conditions of the environment in which the vehicle is located, and predict the environmental risk level of the environment in which the vehicle is located based on the ambient lighting conditions, the cleanliness of the environment, and the current time interval; the environmental risk level is used to indicate the risk that the vehicle will be damaged by the target type of animal; The deportation strategy selection module is used to select a target deportation strategy that matches the environmental risk level from a plurality of preset candidate deportation strategies. The driving-off strategy execution module is used to execute vehicle control commands that match the target driving-off strategy.

8. A vehicle comprising a memory and a processor, said memory storing a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 6.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 6.

10. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 6.

Images