Vehicle control methods, devices and vehicles

Abstract

This invention discloses a method, apparatus, and vehicle for vehicle control. The method includes: acquiring driving condition data of the vehicle during operation; determining control data corresponding to the operated object based on identification information of an object within the vehicle and the driving condition data, wherein the identification information is used to identify the operated object; and controlling the vehicle's movement based on the control data. This invention solves the technical problem of poor control performance during vehicle driving.

Description

Technical Field

[0001] This invention relates to the field of vehicles, and more specifically, to a method, apparatus, and vehicle for vehicle control. Background Technology

[0002] Currently, with the development of intelligent driving technology in automobiles, more and more driver assistance technologies are being mass-produced in passenger vehicles, and the integration level of driver assistance systems is becoming increasingly higher. Driver assistance technology is a safety technology that assists drivers in driving, improving driving safety and comfort. As driver assistance technology becomes more widespread, its continuity is constantly improving.

[0003] In related technologies, regarding the problem of vehicle driving control, due to differences in drivers' age, gender, and driving style, as well as differences in road conditions and weather, ordinary adaptive cruise control systems are difficult to meet drivers' personalized requirements for driving comfort. Therefore, there is a technical problem of poor control effect during vehicle driving.

[0004] There is currently no effective solution to the technical problem of poor control during vehicle driving that exists in the existing technology. Summary of the Invention

[0005] This invention provides a method, apparatus, and vehicle for vehicle control, to at least address the technical problem of low vehicle driving control performance.

[0006] According to one aspect of the present invention, a vehicle control method is provided, comprising: acquiring driving condition data of the vehicle during driving; determining control data corresponding to the operating object based on identification information of an operating object in the vehicle and the driving condition data, wherein the identification information is used to identify the operating object; and controlling the vehicle to drive based on the control data.

[0007] Optionally, based on the identification information of the object to be operated in the vehicle and driving condition data, control data corresponding to the object to be operated is determined, including: matching the identification information with historical identification information already recorded in the vehicle to obtain a matching result; and determining the control data corresponding to the object to be operated based on the matching result.

[0008] Optionally, based on the matching result, control data corresponding to the operation object is determined, including: in response to the matching result indicating that the identification information and historical identification information are successfully matched, style data of the operation object is determined, wherein the style data is used to characterize the driving style of the operation object; and control data corresponding to the operation object is determined based on the style data and driving condition data.

[0009] Optionally, based on style data and driving condition data, control data corresponding to the operation object is determined, including: processing the style data and driving condition data based on the target model to generate control data, wherein the target model is a neural network model.

[0010] Optionally, driving sample data and corresponding driving condition data are selected from the database, wherein the driving sample data is used to characterize the driving state data of the vehicle during driving; based on the driving condition data corresponding to the driving sample data, the driving sample data is classified to obtain multiple driving sample data groups, wherein the number of driving sample data groups is the same as the number of types of driving condition data; the sub-model is trained based on the driving sample data groups to obtain the target model.

[0011] Optionally, style data of the object being operated on can be determined based on its historical driving data.

[0012] Optionally, based on the matching result, control data corresponding to the operation object is determined, including: in response to the matching result used to characterize the anomaly in the matching of identification information and historical identification information, determining the control data as preset control data.

[0013] Optionally, based on control data, operation records of the object to be operated are generated; in response to the existence of a target number of operation records in the vehicle, the historical driving data of the object to be operated is updated.

[0014] According to another aspect of the present invention, a vehicle control apparatus is also provided, comprising: an acquisition unit for acquiring driving condition data of the vehicle during driving; a determination unit for determining control data corresponding to the operating object based on identification information of the operating object in the vehicle and the driving condition data, wherein the identification information is used to identify the operating object; and a control unit for controlling the vehicle to drive based on the control data.

[0015] According to another aspect of the present invention, a vehicle is also provided. This vehicle is used to perform the vehicle control method of the present invention.

[0016] In this embodiment of the invention, driving condition data of the vehicle during operation is acquired; based on the identification information of the object being operated on within the vehicle and the driving condition data, control data corresponding to the object being operated on is determined, wherein the identification information is used to identify the object being operated on; and based on the control data, the vehicle is controlled to drive. In other words, this embodiment of the invention determines the control data corresponding to the object being operated on by using the driving condition data of the vehicle during operation and the identification information of the object being operated on within the vehicle, and then controls the vehicle to drive according to the driving style of the object being operated on within the vehicle based on this control data, thereby solving the technical problem of poor control effect during vehicle driving and achieving the technical effect of improving the control effect during vehicle driving. Attached Figure Description

[0017] The accompanying drawings, which are included to provide a further understanding of the invention and form part of this application, illustrate exemplary embodiments of the invention and, together with their description, serve to explain the invention and do not constitute an undue limitation thereof. In the drawings:

[0018] Figure 1 This is a flowchart of a vehicle control method according to an embodiment of the present invention;

[0019] Figure 2 This is a schematic diagram of a vehicle control system according to an embodiment of the present invention;

[0020] Figure 3 This is a flowchart illustrating the learning process of a learning module according to an embodiment of the present invention;

[0021] Figure 4 This is a flowchart of an adaptive cruise control according to an embodiment of the present invention;

[0022] Figure 5 This is a schematic diagram of a vehicle control device according to an embodiment of the present invention. Detailed Implementation

[0023] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0024] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0025] Example 1

[0026] According to an embodiment of the present invention, an embodiment of a vehicle control method is provided. It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions. Furthermore, although a logical order is shown in the flowchart, in some cases the steps shown or described may be executed in a different order than that shown here.

[0027] Figure 1 This is a flowchart of a vehicle control method according to an embodiment of the present invention, such as... Figure 1 As shown, the method may include the following steps:

[0028] Step S102: Obtain driving condition data of the vehicle during driving.

[0029] In the technical solution provided by step S102 of the present invention, driving condition data can be acquired during vehicle operation. This driving condition data can include road conditions, road surface conditions, and weather conditions during vehicle operation. For example, road conditions can be smooth traffic, slow traffic, and congestion; road surface conditions can be slopes, narrow bridges, urban roads, and rural roads; and weather conditions can be sunny, foggy, rainy, snowy, and hazy. It should be noted that this is merely an example and does not impose specific limitations on the driving condition data.

[0030] For example, images of a vehicle during driving can be captured using an image acquisition device, and driving condition data of the vehicle during driving can be determined based on the captured images.

[0031] Step S104: Based on the identification information of the object to be operated in the vehicle and the driving condition data, determine the control data corresponding to the object to be operated, wherein the identification information is used to identify the object to be operated.

[0032] In the technical solution provided by step S104 of the present invention, control data corresponding to the operating object is determined based on the identification information of the operating object in the vehicle and the driving condition data. The operating object can be the driver in the main driver's seat, the identification information of the operating object can be the identity information of the driver, and the control data can be data used to characterize the driving of the vehicle, such as the vehicle speed, acceleration, braking distance, displacement of the brake lever, and steering wheel angle.

[0033] For example, the identification information of the target object may include the target object's facial image, fingerprint information, and voiceprint information. Cameras, fingerprint recognition devices, or voiceprint recognition devices can be installed on vehicles to collect the target object's identification information. It should be noted that this is only an example and does not impose specific restrictions on the identity information and the devices that collect the identity information.

[0034] Step S106: Control the vehicle's movement based on the control data.

[0035] In the technical solution of step S106 of the present invention, corresponding control data can be obtained based on driving style to control vehicle driving.

[0036] For example, vehicle speed, acceleration, braking distance, brake lever displacement, and turning radius can be controlled based on control data.

[0037] In steps S102 to S106 of this application, driving condition data of the vehicle during driving is obtained; based on the identification information of the object to be operated in the vehicle and the driving condition data, control data corresponding to the object to be operated is determined, wherein the identification information is used to identify the object to be operated; and based on the control data, the vehicle is controlled to drive. In other words, this embodiment of the invention determines the control data corresponding to the object to be operated by using the driving condition data of the vehicle during driving and the identification information of the object to be operated in the vehicle, and then controls the vehicle to drive according to the driving style of the object to be operated in the vehicle based on the control data, thereby solving the technical problem of poor control effect during vehicle driving and achieving the technical effect of improving the control effect during vehicle driving.

[0038] The method described in this embodiment will be further described below.

[0039] As an optional embodiment, step S104, based on the identification information of the object to be operated in the vehicle and the driving condition data, determines the control data corresponding to the object to be operated, including: matching the identification information with the historical identification information already recorded in the vehicle to obtain a matching result; and determining the control data corresponding to the object to be operated based on the matching result.

[0040] In this embodiment, the identification information of the object being operated in the vehicle is matched with the historical identification information already recorded in the vehicle to obtain a matching result. Based on the matching result, it can be determined whether the identification information of the object being operated has been recorded in the system. Based on the matching result, the control data corresponding to the object being operated can be determined. The historical identification information can be used to represent the identity information of the driver who has been recorded in the system.

[0041] As an optional embodiment, step S104, based on the matching result, determines the control data corresponding to the operation object, including: in response to the matching result indicating that the identification information and historical identification information are successfully matched, determining the style data of the operation object; and based on the style data and driving condition data, determining the operation data corresponding to the operation object.

[0042] In this embodiment, the identification information is matched with the historical identification information already recorded in the vehicle to obtain a matching result. When the matching result is used to indicate a successful match, it can be determined that the identity information of the operation object has been recorded in the system. The style data of the operation object can be determined based on the identification information of the operation object. The control data corresponding to the operation object can be determined based on the style data and driving condition data of the operation object. The style data is used to characterize the driving style of the operation object.

[0043] For example, driving styles can include conservative driving style, normal driving style, and aggressive driving style. The driver's style data can be determined by information such as vehicle speed, acceleration, braking distance, brake lever displacement, and steering wheel angle during the driver's driving. It should be noted that this is only an example and does not limit the specific information used to determine the style data.

[0044] For example, the vehicle speed during driving is in the range of 10-15 m / s and the acceleration is in the range of 5-10 m / s². 2 If the braking distance is 10m to 15m and the brake lever displacement is 2cm to 5cm, then the driver's driving style can be determined to be a normal driving style.

[0045] Optionally, the style data of the target vehicle can be determined by acquiring the vehicle's driving status data in real time. The driving status data may include information such as the vehicle's following distance, acceleration, speed, brake pedal opening and opening change rate. It should be noted that this is only an example and no specific restrictions are imposed on the vehicle's driving status data.

[0046] Optionally, the system can store vehicle driving status data within a certain target time period for long-term analysis and judgment of the vehicle driving status data during the operation of a certain object. This can prevent errors in driving style analysis caused by significant differences in the vehicle driving status data under special circumstances compared to normal conditions.

[0047] For example, when the system detects that the user is driving a vehicle, it acquires the vehicle's driving status data over a period of time. Based on the driving status data, it determines that the user's driving style is a normal driving style. However, if the user experiences an emergency that causes a brief change in the vehicle's driving status (such as increased speed or acceleration), the system may incorrectly determine that the user's driving style has changed to an aggressive driving style if it does not analyze the vehicle's long-term driving status.

[0048] Optionally, the system can determine the driving condition data of the detected vehicle during driving. If the current driving condition data is determined to be of the first type (e.g., smooth road conditions, urban road conditions, and sunny weather), the system can further learn from the operation data of the user under the first type of driving condition data to determine the user's style data under the first type of driving condition data. If the current driving condition data is determined to be of the second type (e.g., congested road conditions, narrow bridge or slope conditions, and heavy rain or snow), the system can classify the second type of driving condition data and further learn from the operation data of the user under each specific driving condition data after classification to determine the user's style data under each specific driving condition data under the second type of driving condition data.

[0049] For example, when a vehicle is driving on a city road on a sunny day, the system can judge the current driving condition data of the vehicle. If the current driving condition data is the first type of driving condition data, the system can further learn the driving style of the user and thus determine the style data of the user.

[0050] For example, when a vehicle encounters a narrow bridge, heavy fog, or heavy rain, the system can assess the current driving conditions. If the current driving conditions are classified as Category II driving conditions, the system can further categorize them into specific road conditions or weather conditions. For each categorized driving condition, the system can learn and store the driving style of the user under that specific driving condition, thus determining the driving style of the user under a fixed Category II driving condition.

[0051] As an optional embodiment, step S104, based on style data and driving condition data, determines control data corresponding to the operation object, including: processing the style data and driving condition data based on the target model to generate control data.

[0052] In this embodiment, the style data and driving condition data of the operating object can be processed based on the target model to generate control data, wherein the target model can be a neural network model.

[0053] Alternatively, the target model described above can be obtained by training using reinforcement learning methods in this embodiment.

[0054] Optionally, the constructed neural network model is enhanced based on the actor-critic method. The driving state data of the vehicle during the long-term driving process of the operator and the data under the driving conditions are transmitted to the target model in the system for analysis and processing. By summarizing, the driving style of the operator can be obtained, and control data corresponding to the driving style can be generated. This excludes style data caused by changes in the operator's driving style in a short period of time, thereby increasing the accuracy of style data.

[0055] As an optional embodiment, in step S104, driving sample data and driving condition data corresponding to the driving sample data are selected from the database; the driving sample data is classified based on the driving condition data corresponding to the driving sample data to obtain multiple driving sample data groups; and the sub-model is trained based on the driving sample data groups to obtain the target model.

[0056] In this embodiment, driving sample data of the operation object and driving condition data corresponding to the driving sample data stored in the system can be collected. Based on the driving condition data, the driving sample data can be classified to obtain multiple driving sample data groups. The sub-model can be trained based on the driving sample data groups to obtain the target model. The driving sample data is used to characterize the driving state data of the vehicle during driving. The number of driving sample data groups is the same as the number of types of driving condition data.

[0057] Optionally, under a certain driving condition, the driving state data of the vehicle during the driving process can be obtained. The driving state data and the corresponding driving condition data can be classified to obtain data groups of vehicle driving state data under multiple different driving conditions. Statistical methods are used to analyze the classified data, and training is performed based on the sub-models corresponding to the data groups to obtain the target model. Furthermore, control data corresponding to the target model can be obtained.

[0058] As an optional embodiment, step S104 involves determining the style data of the object being operated on based on its historical driving data.

[0059] In this embodiment, when the operator needs to activate the adaptive cruise control system while driving the vehicle, the system can identify whether the operator has been registered in the system by recognizing the operator's identification information. If the operator has been registered in the system, the system can determine the operator's historical driving data based on the operator's identity information and historical driving data. Furthermore, the system can determine the operator's style data based on the operator's historical driving data, and further determine the control data corresponding to the style data. The historical driving data can be the operator's driving data during a certain period of time in the past.

[0060] Optionally, historical driving data may include information such as vehicle speed, acceleration, braking distance, brake lever displacement, and steering wheel angle during the historical driving process. The recorded historical driving data can be stored in the vehicle and analyzed to determine the user's driving style. For example, if the vehicle has been driven at speeds above 15 m / s and accelerations between 10 and 15 m / s² more than five times, this data may be considered. 2 Within the specified range, it can be determined that the driving style of the target is an aggressive driving style.

[0061] Optionally, the style data corresponding to what conditions the driving data meets can be preset. For example, the driving requirements corresponding to different style data can be represented in the form of a table, so that the style data of the operation object can be determined based on the historical driving data of the operation object.

[0062] For example, a driver's historical driving data could include a speed of 12 m / s and an acceleration of 7 m / s². 2 If the braking distance is 13m and the brake lever displacement is 3cm, then after analysis, it can be determined that the driver's historical driving data is within the driving state data range corresponding to the normal driving style. Therefore, the driver's style data can be determined to be the normal driving style.

[0063] It should be noted that the above correspondence between driver's historical driving data and style data is only for illustrative purposes and no specific limitations are imposed here.

[0064] Optionally, the system can input the identification information of the operation object, obtain the driving data of the operation object, and determine the style data of the operation object based on the obtained driving data. When the identification information of the operation object is obtained again, the style data of the operation object can be determined based on the historical driving data of the operation object.

[0065] As an optional embodiment, step S104, based on the matching result, determines the control data corresponding to the operation object, including: in response to the matching result used to characterize the anomaly in the matching of the identification information and the historical identification information, determining the control data as preset control data.

[0066] In this embodiment, the identification information is matched with the historical identification information already recorded in the vehicle to obtain the matching result. When the matching result is used to characterize the matching anomaly, it can be determined that the identification information of the operation object has not been recorded in the system. At this time, the style data of the operation object can be set to the preset style data, and it can be determined that the control data at this time is the corresponding preset control data.

[0067] For example, when the user is driving a vehicle, the system can identify the user's identification information and match it with historical identification information. If the matching result indicates an anomaly, it is determined that the user's identification information has not been recorded in the system. At this time, the system sets the user's driving style to a normal driving style and determines that the control data at this time is the corresponding normal control parameters. Furthermore, it can determine the vehicle's speed, acceleration, and other information under the normal control data and control the vehicle's movement based on this control data.

[0068] As an optional embodiment, in step S104, an operation record of the operation object is generated based on the control data; in response to the existence of a target number of operation records in the vehicle, the historical driving data of the operation object is updated.

[0069] In this embodiment, control data of the operation object is acquired and stored. The stored control data can be used as an operation record of the operation object, and the operation record of the operation object is marked, for example, by adding a number. Each time the operation object acquires control data, the operation record is incremented by one until a target number of operation records are reached. Then, the operation data from one to the target number is updated to the database, thereby updating the historical driving data of the operation object. The target number can be a number set by the system or a number selected by the operation object according to its own needs.

[0070] For example, when an object acquires a set of control data, it stores the control data to obtain a set of operation records. When there is a target number of operation records, the stored control data can be used as the historical driving data of the object to update the historical driving data of the object. When the number of operation records reaches the target number, the number of operation records can be registered from the beginning.

[0071] Optionally, when new driving status data of the vehicle is acquired, the corresponding driving condition data can be determined. The driving status data and its corresponding driving condition data can be classified, and statistical methods can be used to analyze the classified data to obtain data analysis results under different driving condition data. If the total amount of the data analysis results reaches the target number, new driving data can be learned through a neural network model, and the historical driving data of the operation object can be updated. If the total amount of the data analysis results does not reach the target number, the new driving status data can be stored without learning, and new driving data can be acquired again next time. This can ensure that the system dynamically learns the driving style of the operation object and ensure that the driving status data updated by the system is not affected by abnormal operations of the operation object in a very short period of time.

[0072] For example, driving status data and corresponding driving condition data are classified, and statistical methods are used to analyze the classified data. These statistical methods may include data fitting and regression analysis.

[0073] This invention addresses the problem of poor control during vehicle operation by acquiring driving condition data of a vehicle in motion; determining control data corresponding to the operated object based on the identification information of the object being operated on and the driving condition data, wherein the identification information is used to identify the operated object; and controlling the vehicle's movement based on the control data. In other words, this invention determines the control data corresponding to the operated object by analyzing the driving condition data of the vehicle in motion and the identification information of the operated object within the vehicle, and then controls the vehicle to drive according to the driving style of the operated object, thereby solving the technical problem of poor control effect during vehicle driving and achieving the technical effect of improving the control effect during vehicle driving.

[0074] Example 2

[0075] The technical solutions of the embodiments of the present invention will be illustrated below with reference to preferred embodiments.

[0076] In recent years, Adaptive Cruise Control (ACC) has become widely used as an intelligent driver assistance technology. Therefore, the driving comfort of adaptive cruise control systems is particularly important, which is of great significance for researchers to study the driving styles of future vehicles and learn drivers.

[0077] In one related technology, a vehicle control method and system based on identity recognition is proposed. This method only collects the driver's identity information, compares the identity information with preset approval information, obtains the driving style matching the identity information, automatically starts the engine, queries the style attribute table and correction coefficient corresponding to the obtained driving style, obtains the current accelerator pedal opening and engine speed, finds the engine torque in the style attribute table based on the pedal opening and vehicle speed, calculates the required engine torque based on the engine torque and correction coefficient, and controls the engine torque output according to the required torque. However, this method still does not involve obtaining the driving condition data of the vehicle during driving, resulting in poor ride comfort of the vehicle's adaptive cruise control system.

[0078] In another related technology, a self-learning following system and method based on driver behavior learning and the surrounding environment is proposed. This system collects road type information, distances to surrounding target vehicles, and lane markings solely based on information gathered by the external environment perception module. This information is then output to the domain controller. When the driver is driving in different road environments, the domain controller determines the corresponding road environment and traffic flow based on the information collected by the vehicle's external environment perception module. It then collects the real-time time distance and distance between the vehicle and target vehicles to determine the driver's following distance and / or following distance.

[0079] Finally, the domain controller matches the driver's following distance or following time distance based on the current road conditions and the type of the target vehicle. However, this still does not involve an adaptive cruise control system that reflects the driver's driving style, resulting in poor ride comfort of the vehicle's adaptive cruise control system.

[0080] To address the aforementioned problems, this invention proposes an adaptive cruise control system with learning capabilities, which may include the following components: an identity recognition module, a learning module, and an adaptive cruise control module. The identity recognition module has driver information input and identity recognition functions, and can be used to set learning targets and switch control parameters online. The learning module can acquire driving condition data of the vehicle during driving, learn the driver's driving habits recorded by the identity recognition module, and thus change the control data of the adaptive cruise control system. The adaptive cruise control module can perform adaptive cruise control based on the system parameters learned by the learning module.

[0081] The methods described in the embodiments of the present invention will be further described below.

[0082] Figure 2 This is a schematic diagram of a vehicle control system according to an embodiment of the present invention, as shown below. Figure 2 As shown, the vehicle control system 200 may include an identity recognition module 201, a learning module 202, and an adaptive cruise control module 203.

[0083] In this embodiment, the identity recognition module 201 can be used to input driver information and identify the current driver based on the input driver information.

[0084] Optionally, the identity recognition module 201 may include an identification device, a display, a storage device, and a transmission device, etc. The identification device may be a camera and a fingerprint recognition device, etc. When the vehicle control system is installed in the vehicle, the driver needs to register his identity for the first time. The driver's face and fingerprint information can be registered through the camera and the fingerprint recognition device respectively. The identity information is then recorded in the storage device, which can facilitate the identification of the driver's identity information.

[0085] Optionally, the identity recognition module 201 can be configured with an administrator user function to prevent driver information from being arbitrarily modified and entered. When the administrator user is not set, whenever driver identity information is entered, the system can send a prompt message to the display asking "Do you want to set the driver device as an administrator user?" The driver can set it by clicking the "Yes" button on the display. The storage device can record the identity information of the administrator user. Once the administrator user is set, no further prompts will be sent.

[0086] Optionally, the administrator user can reset the administrator user account. This method may include: the administrator user can select the "Reset" option on the display. After the identity recognition module receives the instruction, it can identify whether the driver is the administrator user through the camera and fingerprint recognition device. If so, the current administrator user's identity information in the storage device can be cleared; if not, the identity recognition module can forcibly end the reset operation.

[0087] Optionally, after the administrator user completes the settings, the driver's identity information can be set through administrator user authorization. The administrator user authorization method can be facial recognition or fingerprint recognition, etc.

[0088] Optionally, the identity recognition module 201 can identify the current driver based on the entered driver information. The identification process may include the following steps: the identity recognition module collects the identity information of the current driver in the driver's seat through the recognition device, and can match it with the historical identity information of the driver that has been entered into the storage device. If the matching result is used to indicate that the matching is successful, the driver's identity recognition can be completed; if the matching result is used to indicate that the matching is unsuccessful, it can be said that the driver's identity information has not been entered into the storage device.

[0089] Optionally, the identity recognition module 201 can transmit the obtained driver's identity recognition result to the learning module 202 through a transmission device. The signal of the transmission device transmitting the identity recognition result can be a local area network, digital signal, Ethernet, etc. The signal of the identity recognition result is only an example and is not specifically limited.

[0090] In this embodiment, the learning module 202 can be used to acquire driving condition data of the vehicle during driving, and can determine the control data corresponding to the current driver based on the recognition result of the identity recognition module 201 and the driving condition data.

[0091] Optionally, Figure 3 This is a flowchart illustrating the learning process of a learning module according to an embodiment of the present invention, such as... Figure 3 As shown, the learning method of this learning module may include the following steps:

[0092] Step S301: The identity recognition module identifies the current driver in the driver's seat.

[0093] In the technical solution provided by step S301 of the invention, the identification device in the identity recognition module 201 detects the identity information of the current driver in the driver's seat, which may include obtaining the driver's face, fingerprints and other identity information.

[0094] Step S302: Whether to enter into the system.

[0095] In the technical solution provided by step S302 of the present invention, the identity recognition module 201 can determine whether the driver's identity information has been entered into the system by judging whether the driver's identity information matches the information in the storage device. If yes, then step S303 is performed; otherwise, step S305 is performed.

[0096] Step S303: The learning module loads the control data corresponding to the current driver.

[0097] In step S303 of the present invention, if it is determined that the driver has been registered in the system, the learning device in the learning module 202 can load the control data and learning records corresponding to the current driver.

[0098] Optionally, the learning module 202 may include a detector, a learning device, a storage device, a receiving device, and a transmission device. The detector can acquire real-time driving status data of the vehicle during driving and transmit it to the storage device. For example, the detector can acquire information such as the following distance, accelerator and brake pedal opening and opening change rate during driving, and then transmit the above driving status data of the vehicle to the storage module for recording.

[0099] Optionally, the storage device can store vehicle driving status data within a certain target time period to prevent the data storage volume from becoming too large over time. The target time can be the time selected by the driver on the display or the time set by the system itself. This is only an example and no specific limitation is made.

[0100] For example, a storage device can use a stack-like first-in-first-out (FIFO) approach to store only data within a certain time frame, such as setting the current time as a one-month period.

[0101] Optionally, the detector in the learning module 202 can also detect the driving condition data of the vehicle during driving, such as road conditions and surface conditions. The detector can transmit the acquired data of the vehicle under the current driving condition and the aforementioned driving status data of the vehicle to the learning device.

[0102] Optionally, the learning device can classify the vehicle driving status data recorded by the storage device, perform data analysis on the classified driving status data, determine the driver's style data, and use the analyzed style data as the initial input data for training the neural network model to generate control data corresponding to different style data.

[0103] For example, vehicle driving status data can be divided into three categories: conservative, normal, and aggressive. By determining which of the three categories the vehicle driving status data recorded by the storage device belongs to, the vehicle driving status data can be classified. The classified vehicle driving status data can be analyzed using statistical methods such as data fitting and regression analysis to determine the driver's style data. The driver's style data is then identified as the optimal data and can be used as the initial input data for the reinforcement learning neural network model built by the actor-critic method for training and learning. This can generate control data corresponding to different style data.

[0104] Optionally, when the learning device receives driving condition data of the vehicle during driving, it can judge the detected driving condition data of the vehicle during driving. If it is determined that the current driving condition data of the vehicle is the first type of driving condition data, the driver's long-term driving style can be further learned under the condition that the driving condition data is the first type of driving condition data, thereby determining the driver's style data. If it is determined that the current driving condition data of the vehicle is the second type of driving condition data, it is necessary to classify the abnormal situation and learn the driver's driving style under each abnormal driving condition data after classification over a long period of time.

[0105] For example, when a vehicle is driving on a slope or encounters heavy rain, the detector can transmit the detected driving condition data to the learning device. The learning device determines that the current driving condition data is of the second type. The system can classify the abnormal driving condition data into categories such as specific road conditions or specific weather conditions. For each abnormal situation after classification, the system can learn only the driving style of the driver corresponding to the abnormal driving condition data and store it separately, thereby determining the driver's driving style under fixed abnormal conditions.

[0106] Step S304: Learn the current driver's driving habits and save the new control data.

[0107] In step S304 of the present invention, learning new control parameters may include the following steps:

[0108] Optionally, whenever new vehicle driving status data is transmitted to the learning device, the driving condition data corresponding to the new driving status data can be determined first. The driving status data and the corresponding driving condition data can be classified, and statistical methods such as data fitting and regression analysis can be used to analyze the classified data. If the total amount of data analysis results reaches the target amount, the new driving data can be learned based on the neural network model constructed by the Actor-Critic method. Furthermore, the new control data can be saved. If the total amount of data analysis results does not reach the target amount, the driving data at this time will not be learned, and the driving status data can be stored in the storage module.

[0109] Optionally, the learning device can wait to acquire the next new vehicle driving status data. Once the data analysis results have accumulated to the target number, a new learning process can be restarted. This ensures that the driving data learned by the system will not change due to abnormal data in a very short period of time, and allows for dynamic learning of the driver's driving style.

[0110] Step S305: Exit learning.

[0111] In step S305 of the present invention, if the identity recognition module 201 determines that the identity information of the current driver in the driver's seat has not been entered into the system, it can transmit the information to the learning module 202 through the transmission device. After the learning module obtains the information, it can choose not to learn the driving style of the driver.

[0112] Step S306: Select to load the factory preset control data.

[0113] In step S306 of the present invention, the driver's identity information is not recorded. The learning module 202 can set the driving style of the vehicle to a normal driving style at this time, and can determine that the control data at this time is a normal control parameter.

[0114] Optionally, the learning module 202 can transmit the determined control data information to the adaptive cruise control module 203 through a transmission device. The signal that transmits the control data information can be a local area network, digital signal, Ethernet, etc. This is only an example and no specific limitation is made.

[0115] In this embodiment, the adaptive cruise control module 203 can be used to control the vehicle's movement based on the control data from the learning module 202.

[0116] Optionally, Figure 4 This is a flowchart of an adaptive cruise control according to an embodiment of the present invention, such as... Figure 4 As shown, the adaptive cruise control may include the following steps:

[0117] Step S401: The identity recognition module identifies the current driver in the driver's seat.

[0118] In the technical solution provided by the above-mentioned step S401, the identification device in the identity recognition module 201 detects the identity information of the current driver in the driver's seat, which may include obtaining the driver's face, fingerprints and other identity information.

[0119] Step S402: Has the driver been registered in the system?

[0120] In the technical solution provided by step S402 of the present invention, the identity recognition module 201 can determine whether the driver's identity information has been entered into the system by judging whether the driver's identity information matches the information in the storage device. If yes, then step S403 is performed; otherwise, step S404 is performed.

[0121] Step S403: The adaptive cruise control module acquires the control data loaded by the learning module.

[0122] In the technical solution provided by step S403 of the present invention, the adaptive cruise control module 203 may include a receiving device and a control device, wherein the receiving device is used to receive control data from the learning module, and the control device is used to control the vehicle driving based on the acquired control data.

[0123] Optionally, the receiver in the adaptive cruise control module 203 can receive control data from the learning module 202 that reflects the driver's driving style.

[0124] For example, the identity recognition module identifies whether the current driver's identity information has been entered into the system. If it has been entered, the detector of the learning module acquires the driving condition data during the current vehicle driving process. If it is determined that the current driving condition data is the first type of driving condition data, the storage device searches for the style data corresponding to the identity information and finds that it is an aggressive driving style. It further determines that the control data corresponding to the driver is an aggressive control parameter, and the transmission device of the learning module transmits the aggressive control parameter to the receiving device of the adaptive cruise control module.

[0125] Step S404: The adaptive cruise control system module reads the pre-set control data from the learning module.

[0126] In the technical solution provided by step S404 of the present invention, the identity recognition module 201 identifies whether the identity information of the current driver in the driver's seat has been entered into the system. If it has not been entered into the system, the transmission device of the learning module 202 transmits the pre-set ordinary control parameters to the receiving device in the adaptive cruise control module 203.

[0127] Optionally, when the detector in the learning module 201 detects driving condition data of the vehicle during driving, if it is determined that the current driving condition data is the second type of driving condition data, the historical driving data when the driver encounters the current driving condition data can be obtained from the storage module, and the driver's style data at this time can be determined, and the corresponding control data information can be transmitted to the adaptive cruise control system 203.

[0128] For example, when a vehicle is driving on a slope or encounters heavy rain, the detector in the learning module can transmit the current driving condition data of the vehicle to the learning device. The learning device determines that the current driving condition data is the second type of driving condition data, obtains the historical driving data in the storage module when the driver encountered the current driving condition data, and finds it to be conservative. Then, it can determine the control data information corresponding to the conservative driving style and transmit it to the receiving device in the adaptive cruise control module.

[0129] Step S405, Adaptive cruise control.

[0130] In the technical solution provided by step S405 of the present invention, the control system in the adaptive cruise control module 203 can control the vehicle driving based on the control data with the driver's driving style that has been acquired.

[0131] For example, when the identity recognition module identifies whether the current driver's identity information has been entered into the system, if it has, the detector of the learning module acquires the driving condition data during the current vehicle driving process. If the driving condition data is the first type of driving condition data, the storage device finds the style data corresponding to the identity information and determines that it is conservative. It further determines that the control data corresponding to the style data is conservative control parameters. The transmission device of the learning module transmits the control data with an aggressive driving style to the receiving device of the adaptive cruise control module. The control device in the adaptive cruise control system controls the vehicle to drive according to the conservative control data.

[0132] This invention addresses the problem of poor control during vehicle operation by acquiring driving condition data of a vehicle in motion; determining control data corresponding to the operated object based on the identification information of the object being operated on and the driving condition data, wherein the identification information is used to identify the operated object; and controlling the vehicle's movement based on the control data. In other words, this invention determines the control data corresponding to the operated object by analyzing the driving condition data of the vehicle in motion and the identification information of the operated object within the vehicle, and then controls the vehicle to drive according to the driving style of the operated object, thereby solving the technical problem of poor control effect during vehicle driving and achieving the technical effect of improving the control effect during vehicle driving.

[0133] Example 3

[0134] According to an embodiment of the present invention, a vehicle control device is also provided. It should be noted that this vehicle control device can be used to execute the vehicle control method in Embodiment 1.

[0135] Figure 5 This is a schematic diagram of a vehicle control device according to an embodiment of the present invention, such as... Figure 5 As shown, the vehicle control device 500 may include: an acquisition unit 502, a determination unit 504, and a control unit 506.

[0136] The acquisition unit 502 is used to acquire driving condition data of the vehicle during driving.

[0137] The determining unit 504 is used to determine the control data corresponding to the operating object based on the identification information of the operating object and the driving condition data of the vehicle, wherein the identification information is used to identify the operating object.

[0138] Control unit 506 is used to control the vehicle's movement based on control data.

[0139] Optionally, the determining unit 504 includes a matching module, used to carefully match the identification information with the historical identification information already recorded in the vehicle to obtain a matching result.

[0140] Optionally, the determining unit 504 includes: a first determining module, used to determine control data corresponding to the operation object.

[0141] Optionally, the determining unit 504 includes: a second determining module, configured to determine the style data of the operation object in response to a matching result indicating a successful match between the identification information and historical identification information.

[0142] Optionally, the determining unit 504 includes: a third determining module, used to determine control data corresponding to the operation object based on style data and driving condition data.

[0143] Optionally, the third determining module includes: a generation submodule, used to process style data and driving condition data based on the target model to generate control data, wherein the target model is a neural network model.

[0144] Optionally, the third determining module further includes a selection submodule, used to select driving sample data and driving condition data corresponding to the driving sample data from the database, wherein the driving sample data is used to characterize the driving state of the vehicle during driving.

[0145] Optionally, the third determining module further includes a classification submodule, used to classify the driving sample data based on the driving condition data corresponding to the driving sample data, to obtain multiple driving sample data groups, wherein the number of driving sample data groups is the same as the number of types of driving condition data.

[0146] Optionally, the third determining module further includes a training submodule, used to train the sub-model based on the driving sample data set to obtain the target model.

[0147] Optionally, the third determining module further includes a determining submodule, used to determine the style data of the operating object based on the historical driving data of the operating object.

[0148] Optionally, the determining unit 504 further includes: a fourth determining module, used to determine the control data as preset control data in response to the matching result used to characterize the anomaly between the identification information and the historical identification information.

[0149] Optionally, the device further includes a generation unit for generating an operation record of the operation object based on control data.

[0150] Optionally, the device further includes an update unit for updating the historical driving data of the operation object in response to the presence of a target number of operation records in the vehicle.

[0151] In this embodiment of the invention, the acquisition unit acquires driving condition data of the vehicle during driving, and the determination unit determines control data corresponding to the operation object based on the identification information and driving status of the operation object of the vehicle. The identification information is used to identify the operation object, and the control unit controls the vehicle to drive based on the control data, thereby solving the technical problem of poor control effect during vehicle driving and achieving the technical effect of improving the control effect during vehicle driving.

[0152] Example 4

[0153] According to an embodiment of the present invention, a vehicle is also provided for performing the vehicle control method of the present invention.

[0154] The sequence numbers of the above embodiments of the present invention are for descriptive purposes only and do not represent the superiority or inferiority of the embodiments.

[0155] In the above embodiments of the present invention, the descriptions of each embodiment have different focuses. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0156] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. The device embodiments described above are merely illustrative; for example, the division of units can be a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the displayed or discussed mutual couplings, direct couplings, or communication connections may be through some interfaces; indirect couplings or communication connections between units or modules may be electrical or other forms.

[0157] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0158] Furthermore, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0159] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes: USB flash drives, read-only memory (ROM), random access memory (RAM), portable hard drives, magnetic disks, optical disks, and other media capable of storing program code.

[0160] The above description is only a preferred embodiment of the present invention. It should be noted that for those skilled in the art, several improvements and modifications can be made without departing from the principle of the present invention, and these improvements and modifications should also be considered within the scope of protection of the present invention.

Claims

1. A vehicle control method, characterized in that, include: Acquire driving condition data of the vehicle during operation; Based on the identification information of the object being operated in the vehicle and the driving condition data, control data corresponding to the object being operated is determined, wherein the identification information is used to identify the object being operated; Based on the control data, the vehicle is controlled to move. The method for determining control data corresponding to the operating object based on the identification information of the operating object in the vehicle and the driving condition data includes: matching the identification information with historical identification information already recorded in the vehicle to obtain a matching result; in response to the matching result indicating that the identification information and the historical identification information are successfully matched, acquiring the driving data of the operating object; determining the style data of the operating object based on the driving data, wherein the style data is used to characterize the driving style of the operating object; in response to acquiring the identification information of the operating object again, determining the style data based on the historical driving data of the operating object, wherein the historical driving data is the driving data of the operating object in the past time period at the current moment; and determining control data corresponding to the operating object based on the style data and the driving condition data. Controlling the vehicle's movement based on the control data includes: controlling the vehicle to drive according to the driving style of the user based on the control data.

2. The method according to claim 1, characterized in that, Based on the style data and the driving condition data, control data corresponding to the operation object is determined, including: The style data and driving condition data are processed based on the target model to generate the control data, wherein the target model is a neural network model.

3. The method according to claim 2, characterized in that, The method further includes: Select driving sample data and corresponding driving condition data from the database, wherein the driving sample data is used to characterize the driving status data of the vehicle during driving. Based on the driving condition data corresponding to the driving sample data, the driving sample data is classified to obtain multiple driving sample data groups, wherein the number of driving sample data groups is the same as the number of types of driving condition data. The target model is obtained by training the sub-model based on the driving sample data set.

4. The method according to claim 1, characterized in that, The method further includes: In response to the matching result indicating an abnormal match between the identification information and the historical identification information, the control data is determined to be preset control data.

5. The method according to claim 1, characterized in that, The method further includes: Based on the control data, an operation record for the operation object is generated; In response to the presence of a target number of operation records in the vehicle, the historical driving data of the operation object is updated.

6. A vehicle control device, characterized in that, include: The acquisition unit is used to acquire driving condition data of the vehicle during driving. The determining unit is configured to determine control data corresponding to the operating object based on the identification information of the operating object in the vehicle and the driving condition data, wherein the identification information is used to identify the operating object; A control unit is used to control the vehicle's movement based on the control data; The determining unit is further configured to determine control data corresponding to the operating object based on the identification information of the operating object in the vehicle and the driving condition data through the following steps: matching the identification information with historical identification information already recorded in the vehicle to obtain a matching result; in response to the matching result indicating that the identification information and the historical identification information are successfully matched, acquiring the driving data of the operating object; determining the style data of the operating object based on the driving data, wherein the style data is used to characterize the driving style of the operating object; in response to acquiring the identification information of the operating object again, determining the style data based on the historical driving data of the operating object, wherein the historical driving data is the driving data of the operating object in the past time period at the current moment; and determining the control data corresponding to the operating object based on the style data and the driving condition data. The control unit is also configured to control the vehicle to drive based on the control data by means of the following steps: controlling the vehicle to drive according to the driving style of the operator based on the control data.

7. A vehicle, characterized in that, Used to perform the method according to any one of claims 1 to 5.

Images