Vehicle control method and device, vehicle and storage medium
By acquiring vehicle scenario risk levels and driver information, and utilizing sensors and machine learning models for vehicle control, the problem of low vehicle driving safety has been solved, and the accuracy and safety of vehicle control have been improved.
Patent Information
- Application Number
- CN202511350846.2
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-09-22
- Publication Date
- 2025-12-12
AI Technical Summary
The control strategies of existing vehicle driving models cannot be dynamically adjusted, resulting in low vehicle driving safety.
By acquiring risk level information about the vehicle's location, collecting multi-source data using a set of sensors, and combining driver physiological parameters and driving habit information, machine learning models are used for identification and control, thereby achieving collaborative management of driving control information and cabin control information.
It improves the efficiency and resource matching of sensors, enhances the accuracy of control information, realizes the coordinated response of vehicle cockpit system and drive system, and improves vehicle driving safety and driving experience.
Smart Images
Figure CN121106342A_ABST
Abstract
Description
TECHNICAL FIELD
[0001] The present disclosure relates to the technical field of vehicles, and particularly relates to a vehicle control method and device, a vehicle and a storage medium. BACKGROUND
[0002] With the development of intelligent driving technology, high-order intelligent driving systems are increasingly widely applied in vehicles. However, during vehicle driving, the driving model of the vehicle can be controlled. For example, a control strategy corresponding to a vehicle speed can be obtained from a set of pre-set control strategies, but the control strategy cannot be dynamically controlled in this process, which makes the safety of vehicle driving relatively low. SUMMARY
[0003] The present disclosure provides a vehicle control method, device, vehicle and storage medium, which can simultaneously control driving control information and in-cabin control information, so that the vehicle cabin system and the driving system can be coordinated accordingly, improve the accuracy of vehicle control, and improve the safety of vehicle driving. The technical solutions of the present disclosure are as follows:
[0004] According to a first aspect of an embodiment of the present disclosure, a vehicle control method is provided, comprising:
[0005] According to the scene information corresponding to the vehicle, risk level information corresponding to the scene in which the vehicle is located is obtained;
[0006] A set of sensors corresponding to the risk level information is used to obtain a set of multi-source data, the set of multi-source data including environmental information, vehicle state information and physiological parameters of a driver identified by the vehicle;
[0007] Driver habit information corresponding to the driver identifier is obtained;
[0008] A machine learning model is used to identify the set of multi-source data and the driver habit information, obtain control information of the vehicle, and control the vehicle using the control information, wherein the control information includes driving control information and in-cabin control information of the vehicle.
[0009] According to some embodiments, the method further comprises at least one of the following:
[0010] The scene information corresponding to the vehicle is obtained by a collection device of the vehicle, the collection device including at least one of a vehicle front camera and a radar device;
[0011] The scene information corresponding to the vehicle sent by a terminal is received;
[0012] The scene information corresponding to the vehicle is obtained according to at least one of high-definition map, traffic flow data and weather forecast information.
[0013] According to some embodiments, the employing the machine learning model to identify the multi-source data set and the driving habit information, obtaining the control information of the vehicle, and employing the control information to control the vehicle comprises:
[0014] Employing a weight fusion model to obtain a first weight corresponding to the environment information, a second weight corresponding to the vehicle state information, and a third weight corresponding to the physiological parameter;
[0015] According to the first weight, the second weight, and the third weight, employing a machine learning model to identify the multi-source data set and the driving habit information, obtaining the control information of the vehicle, and employing the control information to control the vehicle.
[0016] According to some embodiments, the employing a sensor set corresponding to the risk level information to obtain a multi-source data set comprises:
[0017] In the case of the risk level information being first risk level information, employing a laser radar camera device of the vehicle to obtain the environment information of the vehicle;
[0018] Employing an in-cabin camera of the vehicle to obtain the physiological parameter of the driver identifier corresponding to the vehicle.
[0019] According to some embodiments, the employing a sensor set corresponding to the risk level information to obtain a multi-source data set comprises:
[0020] In the case of the risk level information being second risk level information, employing all sensors corresponding to the vehicle to obtain the multi-source data set.
[0021] According to some embodiments, the employing the machine learning model to identify the multi-source data set and the driving habit information, obtaining the control information of the vehicle, and employing the control information to control the vehicle comprises:
[0022] Employing an information prediction model to predict the environment information, the vehicle state information, and the physiological parameter respectively, obtaining predicted environment information, predicted vehicle state information, and predicted physiological parameter;
[0023] Employing a machine learning model to identify the predicted environment information, the predicted vehicle state information, the predicted physiological parameter, and the driving habit information, obtaining the control information of the vehicle, and employing the control information to control the vehicle.
[0024] According to some embodiments, the method further comprises:
[0025] obtain reaction capability information corresponding to the driver identifier;
[0026] issue a warning message according to the reaction capability information and the control information.
[0027] According to a second aspect of the embodiments of the present disclosure, a vehicle control apparatus is provided, comprising:
[0028] an information obtaining unit configured to obtain risk level information corresponding to a scene in which a vehicle is located according to scene information corresponding to the vehicle;
[0029] a set obtaining unit configured to obtain a multi-source data set by using a sensor set corresponding to the risk level information, the multi-source data set comprising environmental information, vehicle state information, and physiological parameters of a driver identifier corresponding to the vehicle;
[0030] The information obtaining unit is further configured to obtain driving habit information corresponding to the driver identifier.
[0031] a vehicle control unit configured to identify the multi-source data set and the driving habit information by using a machine learning model, obtain control information of the vehicle, and control the vehicle by using the control information, wherein the control information comprises driving control information and in-cabin control information of the vehicle.
[0032] According to a third aspect of the embodiments of the present disclosure, a vehicle is provided, comprising:
[0033] a processor;
[0034] a memory for storing instructions executable by the processor;
[0035] The processor is configured to execute the instructions to implement the vehicle control method according to any one of the first aspect.
[0036] According to a fourth aspect of the embodiments of the present disclosure, a server is provided, comprising:
[0037] a processor;
[0038] a memory for storing instructions executable by the processor;
[0039] The processor is configured to execute the instructions to implement the vehicle control method according to any one of the second aspect.
[0040] According to a fifth aspect of the embodiments of the present disclosure, a storage medium is provided, when instructions in the storage medium are executed by a processor of a vehicle, the vehicle is enabled to perform the vehicle control method according to any one of the first aspect.
[0041] According to a sixth aspect of the embodiments of the present disclosure, a computer program product is provided, comprising a computer program which, when executed by a processor, implements the method of any one of the preceding aspects.
[0042] The technical solutions provided by the embodiments of the present disclosure at least have the following beneficial effects:
[0043] In some or related embodiments, the risk level information corresponding to the scene where the vehicle is located is obtained according to the scene information corresponding to the vehicle; a sensor set corresponding to the risk level information is used to obtain a multi-source data set, the multi-source data set including environmental information, vehicle state information, and physiological parameters of a driver identified by the vehicle; driving habit information corresponding to the driver identified is obtained; the multi-source data set and the driving habit information are identified by using a machine learning model to obtain control information of the vehicle, and the vehicle is controlled by using the control information, wherein the control information includes driving control information and in-cabin control information of the vehicle. Therefore, the sensors corresponding to the scene where the vehicle is located can be activated, the use efficiency of the sensors can be improved, the matching of the sensors and the current scene information can be improved, the resource use efficiency can be improved, the accuracy of the control information acquisition can be improved by using the multi-source data set and the machine learning model to obtain the control information, the driving control information and the in-cabin control information can be controlled at the same time, the vehicle cabin system and the driving system can be coordinated accordingly, the accuracy of the vehicle control can be improved, and the safety of the vehicle driving can be improved.
[0044] It should be understood that the foregoing general description and the following detailed description are only exemplary and explanatory, and are not limiting to the present disclosure. BRIEF DESCRIPTION OF DRAWINGS
[0045] The accompanying drawings, which are incorporated into and form part of the specification, illustrate embodiments consistent with the present disclosure and, together with the description, serve to explain the principles of the disclosure, and do not constitute an improper limitation of the present disclosure.
[0046] Figure 1 is an example schematic diagram of a first vehicle control method according to an example embodiment;
[0047] Figure 2 is an example schematic diagram of a second vehicle control method according to an example embodiment;
[0048] Figure 3 is an example schematic diagram of a third vehicle control method according to an example embodiment;
[0049] Figure 4 is a block diagram of a vehicle control device according to an example embodiment;
[0050] Figure 5 is a block diagram of a vehicle according to an exemplary embodiment. DETAILED DESCRIPTION
[0051] In order for those skilled in the art to better understand the technical solutions of the present disclosure, the technical solutions in the embodiments of the present disclosure will be clearly and completely described below with reference to the drawings.
[0052] The present disclosure embodiments propose a vehicle control method, device, vehicle and storage medium. In some embodiments, the vehicle control method and information processing method, communication method and other terms can be replaced with each other, the vehicle control device and information processing device, communication device and other terms can be replaced with each other, and the information processing system, communication system and other terms can be replaced with each other.
[0053] The present disclosure embodiments are not exhaustive, but only illustrate some embodiments, and are not specific limitations on the protection scope of the present disclosure. In the case of no contradiction, each step in an embodiment can be implemented as an independent embodiment, and the steps can be combined arbitrarily, for example, the scheme after removing some steps in an embodiment can also be implemented as an independent embodiment, and the order of the steps in an embodiment can be exchanged arbitrarily, in addition, the optional implementation manners in an embodiment can be combined arbitrarily; in addition, the embodiments can be combined arbitrarily, for example, the steps of different embodiments or part of the steps of different embodiments can be combined arbitrarily, an embodiment can be combined with the optional implementation manners of other embodiments arbitrarily.
[0054] In each embodiment of the present disclosure, the terms and / or descriptions between the embodiments are consistent if there is no special description and logical conflict, and can be referred to each other, and the technical features in different embodiments can be combined to form a new embodiment according to their inherent logical relationship.
[0055] The terms used in the embodiments of the present disclosure are only for the purpose of describing the specific embodiments, and not as a limitation on the present disclosure.
[0056] In the embodiments of the present disclosure, unless otherwise specified, the elements expressed in singular form, such as "one", "a", "the", "above", "said", "preceding", "this" and the like, can represent "one and only one", or "one or more", "at least one" and the like. For example, in the case of using articles such as "a", "an", "the" and the like in English, the noun after the article can be understood as singular expression, or can be understood as plural expression.
[0057] In the embodiments of the present disclosure, "a plurality of" means two or more.
[0058] In some embodiments, the terms “at least one of,” “one or more of,” “a plurality of,” “multiple,” and the like can be used interchangeably.
[0059] The prefix words “first,” “second,” and the like in the embodiments of the present disclosure are merely used to distinguish different description objects, and do not constitute a limitation on the position, order, priority, quantity, or content of the description objects. The description of the description objects should refer to the description in the claims or embodiments, and should not constitute an additional limitation because of the use of the prefix words. For example, the description objects are “fields,” and the ordinal words before “fields” in “first field” and “second field” do not limit the position or order between “fields.” “First” and “second” do not limit whether the “fields” modified thereby are in the same message, nor do they limit the order of “first field” and “second field.” For another example, the description objects are “levels,” and the ordinal words before “levels” in “first level” and “second level” do not limit the priority between “levels.” For another example, the quantity of the description objects is not limited by the ordinal words, and can be one or more. For example, “first device,” where the quantity of “devices” can be one or more. In addition, the objects modified by different prefix words can be the same or different, for example, the description objects are “devices,” and “first device” and “second device” can be the same device or different devices, and their types can be the same or different. For another example, the description objects are “information,” and “first information” and “second information” can be the same information or different information, and their contents can be the same or different.
[0060] In some embodiments, a "terminal" or "terminal device" can be referred to as a "user equipment" (UE), a "user terminal," a "mobile station" (MS), a "mobile terminal" (MT), a subscriber station, a mobile unit, a subscriber unit, a wireless unit, a remote unit, a mobile device, a wireless device, a wireless communication device, a remote device, a mobile subscriber station, an access terminal, a mobile terminal, a wireless terminal, a remote terminal, a handset, a user agent, a mobile client, a client, etc.
[0061] In some embodiments, data, information, etc. can be obtained after getting user consent.
[0062] It should be noted that the terms "first", "second", and the like in the description and in the claims of the present disclosure and the above-described figures do not necessarily have an ordinal or chronological significance. It is to be understood that where appropriate, the data used herein can be interchanged, so that the embodiments of the present disclosure described herein can be carried out in sequences other than those illustrated or described herein. The implementations described in the following example embodiments are not meant to represent all implementations consistent with the present disclosure. Rather, they are simply examples of apparatuses and methods consistent with some aspects of the present disclosure as detailed in the appended claims.
[0063] Figure 1 is a flowchart of a first vehicle control method according to an example embodiment, as shown in Figure 1 The vehicle control method can be used in scenarios where multiple systems are cooperatively controlled during vehicle travel, including the following steps:
[0064] In step S11, according to the scene information corresponding to the vehicle, risk level information corresponding to the scene where the vehicle is located is obtained.
[0065] According to some embodiments, the execution subject of the embodiments of the present disclosure may, for example, be a vehicle, and specifically may, for example, be a control device of the vehicle. The vehicle is not limited to a fixed vehicle. For example, when the vehicle identification changes, the vehicle may also change accordingly. The vehicle may, for example, be a new energy vehicle. For example, when the components of the vehicle change, the vehicle may also change accordingly. For example, the vehicle may be an electric drive vehicle, or may be a fuel drive vehicle, and the embodiments of the present disclosure are not limited thereto.
[0066] In some embodiments, the scene information may, for example, be used to indicate the scene where the current vehicle is located. The scene information may, for example, include traffic flow information corresponding to the vehicle driving path, and accident information, vehicle speed information, etc. The scene information may, for example, be obtained by a camera, and may also be obtained by traffic flow data, and may also be obtained by a map, and the embodiments of the present disclosure are not limited thereto.
[0067] In some embodiments, the risk level information may, for example, be used to indicate the risk corresponding to the current vehicle driving. The risk level information is not limited to a fixed level. For example, when the determination manner of the risk level information changes, the risk level information may also change accordingly. For example, when the scene information changes, the risk level information may also change accordingly.
[0068] In some embodiments, the risk level information corresponding to the scene where the vehicle is located may be obtained according to the scene information corresponding to the vehicle.
[0069] According to some embodiments, the driver identification may, for example, be used to indicate the identification corresponding to the driver to be detected for driving ability. The driver identification is used to uniquely represent a driver. That is, different drivers may correspond to different driver identifications. The driver identification is not limited to a fixed identification. For example, when the form corresponding to the driver identification changes, the driver identification may also change accordingly. For example, when the driver changes, the driver identification may also change accordingly.
[0070] In step S12, a multi-source data set is obtained by using a sensor set corresponding to the risk level information, and the multi-source data set includes environmental information, vehicle state information, and physiological parameters of the driver corresponding to the vehicle.
[0071] In some embodiments, the sensor set may, for example, be a collective of at least one sensor corresponding to the risk level information. The sensor set is not limited to a fixed set. For example, the sensor set may, for example, change when the number of sensors included in the sensor set changes. For example, the sensor set may, for example, change when a sensor in the sensor set changes. The sensor set may, for example, include different types of sensors. For example, the sensors may, for example, collect different data. The name of the sensor set is not limited. For example, the sensor set may, for example, also be referred to as a sensor array, etc.
[0072] In some embodiments, the sensor may, for example, be a sensor installed on a vehicle for collecting data of the vehicle. The sensor is not limited to a fixed sensor. For example, the sensor may, for example, change when the sensor type is the same but the sensor identifier changes.
[0073] In some embodiments, the multi-source data set may, for example, be a collective of data collected by a plurality of collection devices. The multi-source data set is not limited to a fixed set. For example, the multi-source data set may, for example, change when the sensor set corresponding to the multi-source data set changes. For example, the multi-source data set may, for example, change when the data included in the multi-source data set changes. For example, the multi-source data set may, for example, change when the sensor set changes.
[0074] According to some embodiments, the environment information may, for example, be an environment in which the current vehicle is located. The environment information may, for example, include weather information, road condition information. The road condition information may, for example, include shape information of a driving lane, congestion information of a lane, etc. The environment information is not limited to a fixed information. For example, the environment information may, for example, change when the specific information included in the environment information changes.
[0075] In some embodiments, the vehicle state information may, for example, be information corresponding to driving of the vehicle. The vehicle state information may, for example, include SOC value and vehicle torque information, etc. The vehicle state information is not limited to a fixed information. For example, the vehicle state information may, for example, change when the type of information included in the vehicle state information changes. For example, the vehicle state information may, for example, change when a fixed information in the vehicle state information changes.
[0076] According to some embodiments, the physiological parameter is, for example, a current physiological parameter of the driver identified by the driver identifier. The physiological parameter may, for example, include heart rate data, fatigue parameter, etc. Different physiological parameters may, for example, be acquired by different sensors. The physiological parameter is not limited to a fixed parameter. The physiological parameter may, for example, change when the specific parameter corresponding to the physiological parameter changes.
[0077] According to some embodiments, the multi-source data set may, for example, be acquired by using a sensor set corresponding to the risk level information, and the multi-source data set includes environmental information, vehicle state information, and physiological parameters of the driver identified by the driver identifier corresponding to the vehicle.
[0078] In step S13, driving habit information corresponding to the driver identifier is acquired.
[0079] In some embodiments, the driving habit information may, for example, be used to indicate the driving habit of the driver identified by the driver identifier when driving the vehicle. The driving habit information is not limited to a fixed information. The driving habit information may, for example, change when the road information on which the vehicle travels changes. The driving habit information may, for example, change when the driver identifier changes.
[0080] According to some embodiments, the driving habit information may, for example, be acquired by receiving a habit setting instruction, may, for example, be acquired by analyzing historical driving behavior, or may, for example, be acquired by cloud.
[0081] In some embodiments, the driving habit information corresponding to the driver identifier may, for example, be acquired.
[0082] The execution order of steps S11, S12, and S13 is not limited. For example, steps S11 and S12 may, for example, be executed first, and then step S13 may, for example, be executed. Alternatively, step S13 may, for example, be executed first, and then steps S11 and S12 may, for example, be executed. Alternatively, steps S11 and S12 may, for example, be executed simultaneously with step S13.
[0083] In step S14, the multi-source data set and the driving habit information are identified by using a machine learning model, control information of the vehicle is acquired, and the vehicle is controlled by using the control information, wherein the control information includes driving control information and in-cabin control information of the vehicle.
[0084] According to some embodiments, the machine learning model may, for example, be a model that is trained and can be used to make control information prediction. The machine learning model does not refer to a fixed model. For example, when the model type corresponding to the machine learning model changes, the machine learning model may also change accordingly. For example, when the model parameters corresponding to the machine learning model change, the machine learning model may also change accordingly.
[0085] In some embodiments, the control information may, for example, be information used to control the vehicle. The control information may, for example, include driving control information and in-cabin control information of the vehicle. The control information does not refer to a fixed information. For example, when a certain information in the control information changes, the control information may also change accordingly. For example, when the determination manner of the control information changes, the control information may also change accordingly.
[0086] According to some embodiments, the machine learning model may be used to identify the multi-source data set and the driving habit information, obtain the control information of the vehicle, and control the vehicle by using the control information, wherein the control information includes driving control information and in-cabin control information of the vehicle.
[0087] According to some embodiments, the in-cabin control information may, for example, include control information of an air conditioner in the vehicle, control information of entertainment, control information of light, seat ventilation, and fragrance release light.
[0088] In some or related embodiments, by obtaining risk level information corresponding to the scene where the vehicle is located according to the scene information corresponding to the vehicle; using a sensor set corresponding to the risk level information to obtain a multi-source data set, the multi-source data set including environmental information, vehicle state information, and physiological parameters of a driver identified by the vehicle; obtaining driving habit information corresponding to the driver identifier; using a machine learning model to identify the multi-source data set and the driving habit information, obtaining control information of the vehicle, and controlling the vehicle by using the control information, wherein the control information includes driving control information and in-cabin control information of the vehicle. Therefore, the corresponding sensors can be activated by the scene where the vehicle is located, the use efficiency of the sensors can be improved, the matching of the sensors and the current scene information can be improved, the resource use efficiency can be improved, and the accuracy of the control information acquisition can be improved by using the multi-source data set and the machine learning model to obtain the control information. The driving control information and the in-cabin control information can be controlled at the same time, so that the vehicle cabin system and the driving system can be coordinated accordingly, the accuracy of the vehicle control can be improved, and the safety of the vehicle driving can be improved.
[0089] Figure 2 is a flowchart of a second vehicle control method according to an exemplary embodiment, as shown in Figure 2As shown, the vehicle control method can be used in a scenario of simultaneous control of the vehicle cabin system and the driving system during vehicle driving, including the following steps:
[0090] In step S21, according to the scenario information corresponding to the vehicle, the risk level information corresponding to the scenario in which the vehicle is located is obtained;
[0091] Among them, the related process is as described above, which will not be repeated here.
[0092] According to some embodiments, the method further comprises at least one of the following:
[0093] Obtaining the scenario information corresponding to the vehicle through the acquisition device of the vehicle, the acquisition device comprising at least one of a front camera and a radar device of the vehicle;
[0094] Receiving the scenario information corresponding to the vehicle sent by the terminal;
[0095] According to at least one of the high-precision map, the traffic flow data and the weather forecast information, the scenario information corresponding to the vehicle is obtained. Therefore, the scenario information corresponding to the vehicle can be obtained in different ways, which can improve the accuracy of the scenario information acquisition, improve the accuracy of the control information determination, and improve the safety of the vehicle driving and the driving experience of the driver.
[0096] In some embodiments, the camera may, for example, be a camera, which may, for example, be a camera installed beside the road, and may also be a camera installed on the vehicle. The camera installed on the vehicle is a camera for collecting road information.
[0097] In some embodiments, one of the scenario information can be obtained, or a plurality of combinations of the scenario information can be collected. Specifically, it can be determined according to the information setting instruction, and can also be determined according to the road information of the road where the vehicle is located.
[0098] According to some embodiments, the terminal may, for example, be a terminal interacting with the vehicle. The terminal is not specific to a fixed terminal. For example, when the terminal identifier changes, the terminal can also change accordingly.
[0099] In step S22, a plurality of source data sets are obtained by using a sensor set corresponding to the risk level information, and the plurality of source data sets include environmental information, vehicle state information and physiological parameters of a driver identifier corresponding to the vehicle;
[0100] Among them, the related process is as described above, which will not be repeated here.
[0101] According to some embodiments, the physiological parameters of the driver's identification corresponding to the vehicle can be obtained, for example, fatigue monitoring data corresponding to the driver's identification can be obtained from the vehicle's DMS camera, and the stress index corresponding to the driver's identification can also be obtained from the heart rate steering wheel.
[0102] According to some embodiments, obtaining vehicle status information may include, for example, obtaining vehicle weight or load through suspension load sensors, and may also include obtaining the vehicle's battery state of charge (SOC) value.
[0103] In some embodiments, environmental information may be obtained in the manner described above for obtaining scene information, but it is not limited to this.
[0104] According to some embodiments, a set of sensors corresponding to risk level information is used to acquire a multi-source data set, including:
[0105] When the risk level information is at the highest level, the vehicle's LiDAR camera device is used to acquire the vehicle's environmental information.
[0106] By using in-cabin cameras within the vehicle, physiological parameters corresponding to the driver's identity are acquired. Therefore, at low-risk levels, a subset of sensors can be used to acquire basic multi-source data sets, reducing the energy consumption that would result from using all sensors. This balances resource utilization efficiency with control information accuracy, improving both resource efficiency and the accuracy of control information acquisition.
[0107] In some embodiments, the first risk level may be a risk that is lower than the second risk level. This first risk level does not specifically refer to a fixed level. For example, when the judgment conditions corresponding to the first risk level change, the first risk level may also change accordingly. The "first" in the first risk level is used to distinguish it from the other risk levels.
[0108] According to some embodiments, when the risk level information is at the first risk level, basic sensors can be enabled, while cabin perception sensors can be in a dormant state.
[0109] According to some embodiments, a set of sensors corresponding to risk level information is used to acquire a multi-source data set, including:
[0110] When the risk level information is at the second risk level, all sensors corresponding to the vehicle are used to acquire a multi-source data set. Therefore, even at a high risk level, acquiring a multi-source data set through all sensors can improve the accuracy of multi-source data acquisition and thus enhance the accuracy of vehicle control under high-risk conditions.
[0111] According to some embodiments, the second risk level may be greater than the first risk level, meaning that the risk corresponding to the second risk level is greater than the risk corresponding to the first risk level. The "second" in the second risk level is used to distinguish it from the other risk levels.
[0112] In step S23, driving habit information corresponding to the driver's identifier is obtained;
[0113] The relevant processes are as described above and will not be repeated here.
[0114] According to some embodiments, driving habit information may be obtained, for example, from historical driving information.
[0115] In step S24, an information prediction model is used to predict environmental information, vehicle status information and physiological parameters respectively, and the predicted environmental information, predicted vehicle status information and predicted physiological parameters are obtained.
[0116] The relevant processes are as described above and will not be repeated here.
[0117] In some embodiments, for example, the acquired environmental information, vehicle state information, and physiological parameters can be predicted separately to obtain evolution information corresponding to the environmental information, change information corresponding to the vehicle state information, and change information corresponding to the physiological parameters. The evolution information corresponding to the environmental information may include, for example, predicted obstacle movement trajectories; the change information corresponding to the vehicle state may include, for example, change information of State of Charge (SOC); and the change information of the physiological parameters may include, for example, information on the trend of fatigue changes.
[0118] In step S25, the environmental information, vehicle state information, physiological parameters and driving habit information predicted by the machine learning model are used for identification to obtain vehicle control information, and the vehicle is controlled using the control information.
[0119] The relevant processes are as described above and will not be repeated here.
[0120] According to some embodiments, environmental information predicted by machine learning models, vehicle state information predicted by machine learning models, physiological parameters and driving habit information predicted by machine learning models can be used to identify and obtain vehicle control information, and the vehicle can be controlled using the control information.
[0121] In some embodiments, driving habit information may include, for example, the following: an aggressive driver may suppress acceleration intentions and fine-tune the steering angle when overtaking on a curve; a conservative driver may enhance lane departure warning sensitivity.
[0122] According to some embodiments, a machine learning model is used to identify multi-source datasets and driving habit information to obtain vehicle control information, and the vehicle is controlled using this control information, including:
[0123] A weighted fusion model is employed to obtain a first weight corresponding to environmental information, a second weight corresponding to vehicle state information, and a third weight corresponding to physiological parameters. Based on these weights, a machine learning model is used to identify the multi-source dataset and driving habit information to obtain vehicle control information. This control information, including driving control information and in-cabin control information, is then used to control the vehicle. Therefore, using a weighted fusion model to obtain weight information can improve the accuracy of control information acquisition, enhance the matching of control information with the current scenario, and improve vehicle driving safety.
[0124] In some embodiments, the weight fusion model may be a trained model that can be used to obtain weights. This weight fusion model is not specifically a fixed model. For example, when the model type corresponding to the weight fusion model changes, the weight fusion model may also change accordingly. For example, when the model parameters corresponding to the weight fusion model change, the weight fusion model may also change accordingly.
[0125] In some embodiments, for example, matrices corresponding to environmental information, vehicle status information, and physiological parameters can be obtained, and weights can be dynamically allocated based on these matrices.
[0126] According to some embodiments, for example, in situations of high environmental risk and when driver distraction is determined, weights are biased towards vehicle control, which may include, for example, deceleration and enhanced lane keeping. High environmental risk could be, for example, heavy rain or driving on curves.
[0127] In high-risk environments or in normal environments, such as when there are no obvious obstacles in the field of vision and it is certain that there are no distractions, the weighting is biased towards issuing warnings and executing driver actions.
[0128] According to some embodiments, the method further includes:
[0129] Obtain the reaction capability information corresponding to the driver's identification;
[0130] Based on reaction capability and control information, early warning information is issued. Therefore, early warnings can be given based on reaction capability and control information, improving vehicle driving safety.
[0131] According to some embodiments, for example, on uphill sections, control information can lower the vehicle body and increase torque, and can issue warning information based on the driver's reaction ability information, allowing the driver to perform driving operations in advance.
[0132] According to some embodiments, Figure 3 This is an example schematic diagram illustrating a third vehicle control method according to an exemplary embodiment, such as... Figure 3 As shown, the vehicle control method may include, for example, obtaining scene information of the vehicle's location through traffic flow data, weather forecasts, and high-precision maps; acquiring environmental information through cameras and radar based on this scene information; acquiring driver and passenger status through an in-cabin camera; acquiring driver style, i.e., driving habit information, through learning from historical data; obtaining weighted fusion model information for each piece of information; and generating corresponding control commands, which can be controlled through a powertrain chassis control module and an in-cabin control module. The powertrain chassis control module can perform at least one of the following: steering control, throttle control, braking control, and suspension control. The in-cabin control module can control the air conditioning fan, fragrance system, alarms, lights, and music / video.
[0133] In some or related embodiments, an information prediction model is used to predict environmental information, vehicle state information, and physiological parameters respectively, obtaining the predicted environmental information, predicted vehicle state information, and predicted physiological parameters. The predicted environmental information, predicted vehicle state information, predicted physiological parameters, and driving habit information are then identified using a machine learning model to obtain vehicle control information. This control information is then used to control the vehicle. Therefore, predictions can be made on multi-source datasets, adjustments can be made in advance, the matching between control information and predicted information can be improved, intervention strategies can be triggered in advance, and the accuracy of vehicle control can be improved.
[0134] A block diagram of a vehicle control device is shown according to an exemplary embodiment. (Refer to...) Figure 4 The device 400 includes:
[0135] The information acquisition unit 401 is used to acquire the risk level information corresponding to the scene where the vehicle is located based on the scene information corresponding to the vehicle.
[0136] The data acquisition unit 402 is used to acquire a multi-source data set by using a sensor set corresponding to the risk level information. The multi-source data set includes environmental information, vehicle status information, and physiological parameters of the driver's identifier corresponding to the vehicle.
[0137] The information acquisition unit 401 is also used to acquire driving habit information corresponding to the driver's identification;
[0138] The vehicle control unit 403 is used to identify multi-source data sets and driving habit information using a machine learning model, obtain vehicle control information, and use the control information to control the vehicle. The control information includes driving control information and vehicle cabin control information.
[0139] According to some embodiments, the information acquisition unit 401 is also used for at least one of the following:
[0140] The vehicle's data acquisition device acquires scene information corresponding to the vehicle. The data acquisition device includes at least one of a vehicle front-facing camera and a radar device.
[0141] Receive scene information corresponding to the vehicle sent by the terminal;
[0142] Obtain the scene information corresponding to the vehicle based on at least one of high-precision maps, traffic flow data, and weather forecast information.
[0143] According to some embodiments, the vehicle control unit 403 is used to identify multi-source datasets and driving habit information using a machine learning model, obtain vehicle control information, and use the control information to control the vehicle, specifically for:
[0144] A weighted fusion model is used to obtain the first weight corresponding to environmental information, the second weight corresponding to vehicle status information, and the third weight corresponding to physiological parameters.
[0145] Based on the first, second, and third weights, a machine learning model is used to identify multi-source datasets and driving habit information, obtain vehicle control information, and use the control information to control the vehicle.
[0146] According to some embodiments, when the set acquisition unit 402 acquires a multi-source data set using a set of sensors corresponding to the risk level information, it is specifically used for:
[0147] When the risk level information is at the highest level, the vehicle's LiDAR camera device is used to acquire the vehicle's environmental information.
[0148] The vehicle's in-cabin camera is used to obtain the physiological parameters of the driver's identifier corresponding to the vehicle.
[0149] According to some embodiments, when the set acquisition unit 402 acquires a multi-source data set using a set of sensors corresponding to the risk level information, it is specifically used for:
[0150] When the risk level information is at the second risk level, all sensors corresponding to the vehicle are used to obtain a multi-source data set.
[0151] According to some embodiments, the vehicle control unit 403 is used to identify multi-source datasets and driving habit information using a machine learning model, obtain vehicle control information, and use the control information to control the vehicle, specifically for:
[0152] An information prediction model is used to predict environmental information, vehicle status information and physiological parameters respectively, and the predicted environmental information, predicted vehicle status information and predicted physiological parameters are obtained.
[0153] The system uses machine learning models to predict environmental information, vehicle state information, physiological parameters, and driving habits to identify and obtain vehicle control information, which is then used to control the vehicle.
[0154] According to some embodiments, the vehicle control unit 403 of the method is further configured to:
[0155] Obtain the reaction capability information corresponding to the driver's identification;
[0156] Based on responsiveness and control information, early warning information is issued.
[0157] Regarding the apparatus in the above embodiments, the specific manner in which each module performs its operation has been described in detail in the embodiments related to the method, and will not be elaborated upon here.
[0158] In some or related embodiments, an information acquisition unit is used to acquire risk level information corresponding to the scene in which the vehicle is located, based on the scene information corresponding to the vehicle. An acquisition unit is used to acquire a multi-source data set using a sensor set corresponding to the risk level information. The multi-source data set includes environmental information, vehicle status information, and physiological parameters of the driver's identifier. The information acquisition unit is also used to acquire driving habit information corresponding to the driver's identifier. A vehicle control unit is used to identify the multi-source data set and driving habit information using a machine learning model to acquire vehicle control information and control the vehicle using this control information. The control information includes driving control information and in-cabin control information. Therefore, sensors corresponding to the vehicle's scene can be activated, improving sensor utilization efficiency, enhancing the matching between sensors and current scene information, and improving resource utilization efficiency. Furthermore, the acquisition of control information through multi-source data sets and machine learning models improves the accuracy of control information acquisition. Simultaneous control of driving control information and in-cabin control information allows for coordinated response between the vehicle's cabin system and drive system, improving vehicle control accuracy and driving safety.
[0159] Figure 5A schematic block diagram of an example vehicle 500 that can be used to implement embodiments of the present disclosure is shown. Vehicle 500 is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The vehicle may also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the present disclosure described and / or claimed herein.
[0160] like Figure 5 As shown, vehicle 500 includes a computing unit 501, which can perform various appropriate actions and processes based on a computer program stored in read-only memory (ROM) 502 or a computer program loaded from storage unit 508 into random access memory (RAM) 503. RAM 503 can also store various programs and data required for the operation of vehicle 500. The computing unit 501, ROM 502, and RAM 503 are interconnected via bus 504. Input / output (I / O) interface 505 is also connected to bus 504.
[0161] Multiple components in vehicle 500 are connected to I / O interface 505, including: input unit 506, such as keyboard, mouse, etc.; output unit 507, such as various types of displays, speakers, etc.; storage unit 508, such as disk, optical disk, etc.; and communication unit 509, such as network card, modem, wireless transceiver, etc. Communication unit 509 allows vehicle 500 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.
[0162] The computing unit 501 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of the computing unit 501 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. The computing unit 501 performs the various methods and processes described above, such as vehicle control methods. For example, in some embodiments, the vehicle control method may be implemented as a computer software program tangibly contained in a machine-readable medium, such as storage unit 508. In some embodiments, part or all of the computer program may be loaded and / or installed on the vehicle 500 via ROM 502 and / or communication unit 509. When the computer program is loaded into RAM 503 and executed by the computing unit 501, one or more steps of the vehicle control method described above may be performed. Alternatively, in other embodiments, the computing unit 501 may be configured to perform the vehicle control method by any other suitable means (e.g., by means of firmware).
[0163] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), payload-programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.
[0164] The program code used to implement the methods of this disclosure may be written in any combination of one or more programming languages. This program code may be provided to a processor or controller of a general-purpose computer, special-purpose computer, or other programmable data processing apparatus, such that when executed by the processor or controller, the program code causes the functions / operations specified in the flowcharts and / or block diagrams to be implemented. The program code may be executed entirely on a machine, partially on a machine, as a standalone software package partially on a machine and partially on a remote machine, or entirely on a remote machine or server.
[0165] In the context of this disclosure, a machine-readable medium can be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, apparatus, or device. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can be, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.
[0166] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device for displaying information to the user (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor); and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the computer. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).
[0167] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or middleware components (e.g., application servers), or frontend components (e.g., user computers with graphical user interfaces or web browsers through which users can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., communication networks). Examples of communication networks include local area networks (LANs), wide area networks (WANs), the Internet, and blockchain networks.
[0168] Computer systems can include clients and servers. Clients and servers are generally geographically separated and typically interact via communication networks. The client-server relationship is established by computer programs running on the respective computers and having a client-server relationship with each other. A server can be a cloud server, also known as a cloud computing server or cloud host, a hosting product within the cloud computing service system that addresses the management difficulties and weak business scalability inherent in traditional physical hosts and VPS (Virtual Private Server) services. Servers can also be servers for distributed systems or servers integrated with blockchain technology.
[0169] It should be understood that the various forms of processes shown above can be used to rearrange, add, or delete steps. For example, the steps described in this disclosure can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution disclosed in this disclosure can be achieved, and this is not limited herein.
[0170] The specific embodiments described above do not constitute a limitation on the scope of protection of this disclosure. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this disclosure should be included within the scope of protection of this disclosure.
Claims
1. A vehicle control method, characterized in that, include: Based on the scene information corresponding to the vehicle, obtain the risk level information corresponding to the scene in which the vehicle is located; Using a set of sensors corresponding to the risk level information, a multi-source data set is acquired, which includes environmental information, vehicle status information, and physiological parameters of the driver's identifier corresponding to the vehicle. Obtain driving habit information corresponding to the driver identifier; A machine learning model is used to identify the multi-source data set and the driving habit information to obtain the vehicle's control information, and the vehicle is controlled using the control information, wherein the control information includes driving control information and the vehicle's cabin control information.
2. The method according to claim 1, characterized in that, The method further includes at least one of the following: The scene information corresponding to the vehicle is obtained through the vehicle's acquisition device, which includes at least one of a vehicle front-facing camera and a radar device. The receiving terminal sends the scene information corresponding to the vehicle; The scene information corresponding to the vehicle is obtained based on at least one of high-precision maps, traffic flow data, and weather forecast information.
3. The method according to claim 1, characterized in that, The step of using a machine learning model to identify the multi-source data set and the driving habit information to obtain the vehicle's control information, and using the control information to control the vehicle, includes: A weighted fusion model is used to obtain the first weight corresponding to the environmental information, the second weight corresponding to the vehicle state information, and the third weight corresponding to the physiological parameters. Based on the first weight, the second weight, and the third weight, a machine learning model is used to identify the multi-source data set and the driving habit information to obtain the vehicle's control information, and the vehicle is controlled using the control information.
4. The method according to claim 1, characterized in that, The step of acquiring a multi-source data set by using a sensor set corresponding to the risk level information includes: When the risk level information is the first risk level information, the vehicle's environmental information is obtained using the vehicle's lidar camera device; The vehicle's in-cabin camera is used to acquire the physiological parameters of the driver's identifier corresponding to the vehicle.
5. The method according to claim 1, characterized in that, The step of acquiring a multi-source data set by using a sensor set corresponding to the risk level information includes: When the risk level information is the second risk level information, the multi-source data set is obtained by using all the sensors corresponding to the vehicle.
6. The method according to claim 1, characterized in that, The step of using a machine learning model to identify the multi-source data set and the driving habit information to obtain the vehicle's control information, and using the control information to control the vehicle, includes: An information prediction model is used to predict the environmental information, the vehicle status information, and the physiological parameters respectively, and the predicted environmental information, predicted vehicle status information, and predicted physiological parameters are obtained. The predicted environmental information, predicted vehicle state information, predicted physiological parameters, and driving habit information are identified using a machine learning model to obtain vehicle control information, and the vehicle is controlled using the control information.
7. The method according to claim 1, characterized in that, The method further includes: Obtain the reaction capability information corresponding to the driver's identifier; Based on the reaction capability information and the control information, an early warning message is issued.
8. A vehicle control device, characterized in that, include: The information acquisition unit is used to acquire the risk level information corresponding to the scene in which the vehicle is located, based on the scene information corresponding to the vehicle. The data acquisition unit is used to acquire a multi-source data set by using a sensor set corresponding to the risk level information. The multi-source data set includes environmental information, vehicle status information, and physiological parameters of the driver identifier corresponding to the vehicle. The information acquisition unit is also used to acquire driving habit information corresponding to the driver identifier; The vehicle control unit is used to identify the multi-source data set and the driving habit information using a machine learning model, obtain the vehicle's control information, and control the vehicle using the control information, wherein the control information includes driving control information and the vehicle's cabin control information.
9. A vehicle, characterized in that, include: processor; Memory used to store the processor's executable instructions; The processor is configured to execute the instructions to implement the vehicle control method as described in any one of claims 1 to 5.
10. A non-transitory computer-readable storage medium storing computer instructions, the storage medium storing the instructions, characterized in that, When the instructions are executed on the vehicle, the vehicle performs the vehicle control method as described in any one of claims 1 to 7.