Vehicle control method and device, equipment, storage medium and program product

Abstract

The invention discloses a vehicle control method and device, equipment, a storage medium and a program product. The method comprises the steps of determining a target vehicle of a current vehicle to-be-simulated driving experience; obtaining the current driving operation of the current driver received by the current vehicle; a target response parameter corresponding to the current driving operation is obtained through a driving model corresponding to the target vehicle, the driving model is obtained through imitation learning according to the sample driving operation and a sample response parameter, and the sample response parameter is obtained through conversion of an original response parameter of the target vehicle responding to the sample driving operation; the driving feedback of the current vehicle responding to the sample driving operation according to the sample response parameter is similar to the driving feedback of the target vehicle responding to the sample driving operation according to the original response parameter; and controlling the current vehicle to respond to the current driving operation according to the target response parameter. The driving experience of the vehicle can be enriched.

Description

Technical Field

[0001] This application relates to the field of vehicle technology, specifically to a vehicle control method, a vehicle control device, an electronic device, a computer-readable storage medium, and a computer program product. Background Technology

[0002] With the improvement of people's living standards and the rapid development of the social economy, the usage rate of vehicles is gradually increasing. According to the different power sources, vehicles can generally be divided into fuel vehicles (such as gasoline vehicles that use gasoline as a power source and diesel vehicles that use diesel as a power source) and electric vehicles (also known as new energy vehicles) that use electricity as a power source.

[0003] Currently, due to the differences in mechanical structure between gasoline-powered vehicles and electric vehicles, the driving experiences they provide differ significantly. Even between two different gasoline-powered vehicles or two different electric vehicles, there are certain differences in the driving experience they offer. However, the driving experience that a single vehicle can provide is usually fixed. Summary of the Invention

[0004] This application provides a vehicle control method, a vehicle control device, an electronic device, a computer-readable storage medium, and a computer product, which can enrich the driving experience that a vehicle can provide.

[0005] Firstly, the vehicle control method provided in this application includes:

[0006] Identify the target vehicle for the current vehicle to be simulated driving experience;

[0007] Get the current driving operation received by the current driver in the current vehicle;

[0008] By using a driving model corresponding to the target vehicle, the target response parameters corresponding to the current driving operation are obtained. The driving model is obtained by imitation learning based on the sample driving operation and the sample response parameters. The sample response parameters are converted from the original response parameters of the target vehicle in response to the sample driving operation. The driving feedback of the current vehicle in response to the sample driving operation according to the sample response parameters is similar to the driving feedback of the target vehicle in response to the sample driving operation according to the original response parameters.

[0009] Control the current vehicle to respond to the current driving operation according to the target response parameters.

[0010] Secondly, the vehicle control device provided in this application includes:

[0011] The vehicle determination module is used to determine the target vehicle for the current vehicle to be simulated driving experience;

[0012] The operation receiving module is used to acquire the current driving operation received by the current driver in the current vehicle;

[0013] The parameter acquisition module is used to obtain the target response parameters corresponding to the current driving operation through the driving model corresponding to the target vehicle. The driving model is obtained by imitation learning based on the sample driving operation and sample response parameters. The sample response parameters are converted from the original response parameters of the target vehicle in response to the sample driving operation. The driving feedback of the current vehicle in response to the sample driving operation according to the sample response parameters is similar to the driving feedback of the target vehicle in response to the sample driving operation according to the original response parameters.

[0014] The operation response module is used to control the current vehicle to respond to the current driving operation according to the target response parameters.

[0015] Optionally, in one embodiment, the vehicle control device provided in this application further includes a model training module, used to obtain the riding preference information of different passengers corresponding to the current vehicle; and to perform reinforcement learning on the driving model based on the riding preference information of different passengers to obtain an updated driving model matched with different passengers.

[0016] Optionally, in one embodiment, the vehicle control device provided in this application further includes a passenger determination module for determining the current passenger of the current vehicle;

[0017] The parameter acquisition module is also used to obtain the target response parameters corresponding to the current driving operation by using an updated driving model that corresponds to the target vehicle and matches the current passenger.

[0018] Optionally, in one embodiment, the vehicle control device provided in this application further includes a trend acquisition module, used to acquire the current degree of motion sickness of the current passenger, and acquire the trend of the change in the current degree of motion sickness of the current passenger based on the current degree of motion sickness;

[0019] The operation response module is used to update the target response parameters according to the trend of changes in the degree of motion sickness, and to obtain the updated target response parameters; and to control the current vehicle to respond to the current driving operation according to the updated target response parameters.

[0020] Optionally, in one embodiment, the vehicle control device provided in this application further includes a first prompting module, which, if the current level of motion sickness reaches a threshold, is used to output soothing prompts to the current passenger on how to alleviate the level of motion sickness.

[0021] Optionally, in one embodiment, the vehicle control device provided in this application further includes a second prompting module, used to obtain the current driving feedback of the current vehicle in response to the current driving operation; based on the current driving feedback, predict the probability of the current driving operation causing an increase in the current passenger's degree of motion sickness through a motion sickness risk prediction model matched with the current passenger; and if the increase probability reaches a probability threshold, generate operation prompt information based on the current driving operation and output the operation prompt information to the current driver.

[0022] Optionally, in one embodiment, the vehicle control device provided in this application further includes an environment setting module, used to obtain a first air environment setting parameter and a first setting priority corresponding to the current driver; obtain a second air environment setting parameter and a second setting priority corresponding to the current passenger; determine a target air environment setting parameter based on the first air environment setting parameter, the second air environment setting parameter, the first setting priority and the second setting priority; and set the in-vehicle air environment of the current vehicle according to the target air environment setting parameter.

[0023] Optionally, in one embodiment, the environment setting module is used to: if the first setting priority and the second setting priority are different, determine the air environment setting parameter corresponding to the one with the higher setting priority between the current passenger and the current driver as the target air environment setting parameter; or, if the first setting priority and the second setting priority are the same, merge the first air environment setting parameter and the second air environment setting parameter to obtain the target air environment setting parameter.

[0024] Optionally, in one embodiment, the target vehicle is a fuel-powered vehicle and the current vehicle is an electric vehicle. The vehicle control device provided in this application further includes a sound simulation module, which is used to generate a sound audio corresponding to the current driving operation through a sound synthesis model matched with the target vehicle; and to play the sound audio while controlling the current vehicle to respond to the current driving operation according to the target response parameters.

[0025] Optionally, in one embodiment, the vehicle control device provided in this application further includes a cabin noise reduction module, used to acquire the cabin noise audio of the current vehicle cabin; filter the cabin noise audio according to the sound wave audio to obtain the filtered noise audio; and generate a noise reduction frequency with the opposite phase to the filtered noise audio and play the noise reduction frequency.

[0026] Optionally, in one embodiment, the sound wave simulation module is further configured to acquire vibration control parameters corresponding to the sound wave audio; and to control the seat vibration of the current vehicle according to the vibration control parameters during the playback of the sound wave audio.

[0027] Thirdly, the electronic device provided in this application includes a memory and a processor. The memory stores a computer program, and the processor is used to run the computer program in the memory to implement the steps in the vehicle control method provided in this application.

[0028] Fourthly, the computer-readable storage medium provided in this application stores a computer program adapted for processor execution to implement the steps in the vehicle control method provided in this application.

[0029] Fifthly, the computer program product provided in this application includes a computer program adapted for processor execution to implement the steps in the vehicle control method provided in this application.

[0030] The vehicle control scheme provided in this application pre-learns by imitating sample driving operations and sample response parameters on a driving model. The sample response parameters are derived from the original response parameters of the target vehicle in response to the sample driving operations. The driving feedback of the current vehicle in response to the sample driving operations according to the sample response parameters is similar to the driving feedback of the target vehicle in response to the sample driving operations according to the original response parameters. This allows the driving model to capture the driving feedback of the target vehicle to the driving operations. During vehicle control, the target response parameters corresponding to the current driving operation received by the current vehicle are obtained through the driving model corresponding to the target vehicle. By controlling the current vehicle to respond to the current driving operation according to these target response parameters, driving feedback similar to that of the target vehicle can be obtained, providing a driving experience similar to that of the target vehicle. This achieves the simulation of the current vehicle's driving experience of the target vehicle, enriching the overall driving experience. Attached Figure Description

[0031] To more clearly illustrate the technical solutions in the embodiments of this application, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0032] Figure 1a This is a schematic diagram of the vehicle control system provided in an embodiment of this application;

[0033] Figure 1b This is a schematic flowchart of a vehicle control method provided in an embodiment of this application;

[0034] Figure 1c This is an example diagram of the vehicle selection interface provided in the embodiments of this application;

[0035] Figure 1dThis is an example diagram of the passenger selection interface provided in the embodiments of this application;

[0036] Figure 2 This is another schematic flowchart of the vehicle control method provided in the embodiments of this application;

[0037] Figure 3 This is a schematic diagram of the vehicle control device provided in an embodiment of this application;

[0038] Figure 4 This is a schematic diagram of the structure of the electronic device provided in the embodiments of this application. Detailed Implementation

[0039] It should be noted that the principles of this application are illustrated by example in a suitable computing environment. The following description is based on the specific embodiments of this application that are illustrated, and should not be regarded as limiting other specific embodiments not detailed herein.

[0040] In the following description of this application, "some embodiments" are referred to, which describe a subset of all possible embodiments. However, it is understood that "some embodiments" may be the same subset or different subset of all possible embodiments, and may be combined with each other without conflict.

[0041] In the following description of this application, the terms "first, second, third" are used only to distinguish similar objects and do not represent a specific order of objects. It is understood that "first, second, third" may be interchanged in a specific order or sequence where permitted, so that the embodiments of this application described herein can be implemented in an order other than that illustrated or described herein.

[0042] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. The terminology used herein is for the purpose of describing embodiments of this application only and is not intended to limit this application.

[0043] This application primarily relates to the field of vehicle technology, providing a vehicle control method, a vehicle control device, an electronic device, a computer-readable storage medium, and a computer program product. The vehicle control method can be executed by the vehicle control device or by an electronic device integrating the vehicle control device.

[0044] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the embodiments described below are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0045] Please refer to the reference. Figure 1a This application also provides a vehicle control system, which includes an electronic device 100 for executing the vehicle control method provided in this application. The electronic device 100 can be an in-vehicle device configured in a vehicle. For example, the electronic device 100 first determines the target vehicle to be simulated for the driving experience, then acquires the current driving operation received by the current driver from the current vehicle, and obtains the target response parameters corresponding to the current driving operation through a driving model. The driving model is obtained through imitation learning based on sample driving operations and sample response parameters. The sample response parameters are converted from the original response parameters of the target vehicle in response to the sample driving operation, and the driving feedback of the current vehicle responding to the sample driving operation according to the sample response parameters is similar to the driving feedback of the target vehicle responding to the sample driving operation according to the original response parameters. The current vehicle is controlled to respond to the current driving operation according to the target response parameters.

[0046] In addition, such as Figure 1a As shown, the vehicle control system may also include a memory 200 for storing relevant data during the vehicle control process, such as description information of the determined target vehicle, description information of the received current driving operation, and acquired target response parameters, etc.

[0047] It should be noted that the vehicle control system described above is merely an example, intended to more clearly illustrate the technical solutions of the embodiments of this application, and does not constitute a limitation on the technical solutions provided in the embodiments of this application. As those skilled in the art will know, with the evolution of vehicle control systems and the emergence of new business scenarios, the technical solutions provided in the embodiments of this application are also applicable to similar technical problems.

[0048] Please refer to Figure 1b , Figure 1b This is a flowchart illustrating the vehicle control method provided in this embodiment, as shown below. Figure 1b As shown, the flow of this vehicle control method can be as follows:

[0049] In step 110, identify the target vehicle for the current vehicle to be simulated driving experience.

[0050] It should be noted that the vehicle control scheme provided in this application is to give a vehicle the ability to simulate the driving experience of other vehicles. The power source of the simulated vehicle and the simulated vehicle can be the same or different. For example, the simulated vehicle can be an electric vehicle powered by electricity, and the simulated vehicle can be a fuel vehicle powered by fuel.

[0051] The term "current vehicle" refers to the vehicle controlled by the electronic device executing the vehicle control method provided in this application. In order to simulate the driving experience of other vehicles by the current vehicle, it is necessary to first determine the other vehicles to be simulated by the current vehicle, which are referred to as the target vehicles.

[0052] Optionally, in one embodiment, determining the target vehicle for the simulated driving experience of the current vehicle includes:

[0053] The vehicle selection interface is displayed, which includes the vehicle identifiers of the candidate vehicles currently available for simulation.

[0054] In response to the selection of a vehicle icon in the vehicle selection interface, the candidate vehicle corresponding to the selected vehicle icon is determined as the target vehicle for the simulated driving experience.

[0055] This application does not limit the display format of vehicle identification. It can be a vehicle identification in the form of text, an image, or a combination of text and images, etc.

[0056] For example, please refer to Figure 1c An example image of the vehicle selection interface is provided. Figure 1c As shown, the vehicle selection interface includes vehicle identifiers (including vehicle icons and vehicle names) for 6 candidate vehicles currently available for simulation, selection controls for each vehicle identifier, and a prompt message "Please select the vehicle to be simulated:" to prompt the user to select the vehicle to simulate the driving experience. When the selection control corresponding to the vehicle identifier of vehicle 6 is selected, vehicle 6 is designated as the target vehicle to be simulated.

[0057] It is understandable that simulating the driving experience of other vehicles essentially means enabling the current vehicle to provide driving feedback as consistent as possible with that other vehicle for the same driving operation. In order to achieve the simulation of the driving experience of other vehicles by the current vehicle, this application adopts imitation learning (also known as demonstration-based learning or apprenticeship learning) for each other vehicle that needs to be simulated, and pre-trains a corresponding driving model. Imitation learning is a machine learning method that learns a specific task by observing and imitating the behavior of a specific object. In this application, imitation learning is used to capture the driving feedback of other vehicles that need to be simulated for driving operations, so as to reproduce similar driving feedback in the current vehicle.

[0058] It should be noted that the premise for a current vehicle to simulate the driving experience of other vehicles is that the current vehicle's driving performance is superior to that of the other vehicles to be simulated. For example, compared to a gasoline vehicle, an electric vehicle responds faster to the accelerator pedal, thus an electric vehicle can simulate the acceleration experience of a gasoline vehicle, while a gasoline vehicle cannot simulate the accelerator pedal response of an electric vehicle. Given the constraint that the current vehicle's driving performance is superior to that of the other vehicles to be simulated, the other vehicles whose driving experience needs to be simulated are selected.

[0059] The following explanation uses the driving model of another vehicle selected for training as an example.

[0060] For the other vehicle, the historical driving operations received by that other vehicle (e.g., acceleration and release operations on the accelerator pedal, braking operations on the brake pedal, etc.) and the historical response parameters of that other vehicle in response to the historical driving operations are obtained. For a historical driving operation, the similarity between the driving feedback of the other vehicle responding to the historical driving operation according to the historical response parameters and the driving feedback of the current vehicle responding to the historical driving operation according to the sample response parameters is used as a constraint. Based on the mechanical properties of the current vehicle and the other vehicle, the historical response parameters corresponding to the other vehicle are converted into sample response parameters corresponding to the current vehicle. It should be noted that the response parameters are control parameters for vehicle-related components. For example, for acceleration operations on the accelerator pedal, the response parameters are drive control parameters for the vehicle's drive components (such as the engine of a fuel vehicle, the motor of an electric vehicle, etc.); for braking operations on the brake pedal, the response parameters are brake control parameters for the vehicle's brake components; for steering operations on the steering wheel, the response parameters are steering control parameters for the vehicle's steering components, and so on.

[0061] For example, taking the current vehicle as an electric vehicle and the other vehicle whose driving experience needs to be simulated as a gasoline vehicle, let's take the acceleration operation of the accelerator pedal as an example. Due to the different mechanical properties of the electric motor and the engine, the electric motor can instantly output 100% torque from 0 speed, while the engine needs to increase its speed to slowly output maximum torque. For example, the engine speed needs to be increased to above 2000 rpm to output 100% torque, and this process may have a delay of more than 1 second. Therefore, based on the mechanical properties of the electric motor of the current vehicle and the mechanical properties of the engine of the other vehicle, the historical response parameters of the other vehicle to the engine can be converted into sample response parameters of the current vehicle to the electric motor. This makes the acceleration force of the current vehicle when responding to the acceleration operation of the accelerator pedal according to the sample response parameters similar to the acceleration force of the other vehicle when responding to the acceleration operation of the accelerator pedal according to the historical response parameters. It is like outputting torque linearly like the other vehicle, thereby achieving the purpose of simulating the acceleration experience of the other vehicle.

[0062] As shown above, we can obtain the different types of historical driving operations received by other vehicles that need to be simulated, as well as the historical response parameters corresponding to each historical driving operation. We can then convert the historical response parameters corresponding to each historical driving operation into sample response parameters that match the current vehicle. In other words, for a historical driving operation, the driving feedback brought about by the other vehicle responding according to the historical response parameters corresponding to that historical driving operation is similar to the driving feedback brought about by the current vehicle responding according to the sample response parameters corresponding to that historical driving operation.

[0063] Furthermore, a driving model is constructed with driving operations as input and response parameters as output. The model architecture is not limited here and can be selected by those skilled in the art according to actual needs. The historical driving operations obtained above are used as sample driving operations input to the driving model. A first training loss is obtained based on the difference between the predicted response parameters output by the driving model and the sample response parameters corresponding to the historical driving operations. The type of the first training loss is not limited here and can be selected by those skilled in the art according to actual needs; for example, cross-entropy loss can be used as the first training loss. The network parameters of the driving model are updated based on the obtained first training loss until a first preset stopping condition is met. The configuration of the first preset stopping condition is not limited here and can be configured by those skilled in the art according to actual needs. For example, the first preset stopping condition can be configured as: the number of parameter updates to the driving model reaches a preset number; or it can be configured as: the first training loss of the driving model converges, and so on.

[0064] As mentioned above, a driving model for simulating other different vehicles can be trained using the current vehicle. Correspondingly, by deploying the trained driving models on electronic devices, it becomes possible to simulate the driving experience of other vehicles corresponding to those models.

[0065] In step 120, obtain the current driving operation received by the current driver from the current vehicle.

[0066] As described above, simulating the driving experience of a target vehicle essentially involves simulating the vehicle's feedback to driving operations. Therefore, after identifying the target vehicle for the simulated driving experience, the driving control components configured in the vehicle acquire the current driving operations received by the driver. These components include, but are not limited to: an accelerator pedal (also called the accelerator pedal for electric vehicles and the gas pedal for gasoline vehicles) for controlling acceleration, a brake pedal for controlling braking, and a steering wheel for controlling steering. Correspondingly, current driving operations include, but are not limited to: acceleration and release operations based on the accelerator pedal, braking and release operations based on the brake pedal, and steering and centering operations based on the steering wheel. These current driving operations can be characterized by the operational information of the corresponding driving control components, such as the accelerator pedal opening, brake pedal opening, and steering wheel angle.

[0067] In step 130, the target response parameters corresponding to the current driving operation are obtained through the driving model corresponding to the target vehicle.

[0068] As can be seen from the above description, the driving model corresponding to the target vehicle is obtained by imitation learning based on sample driving operations and sample response parameters. The sample response parameters are converted from the original response parameters of the target vehicle in response to the sample driving operations. Furthermore, the driving feedback of the current vehicle in response to the sample driving operations according to the sample response parameters is similar to the driving feedback of the target vehicle in response to the sample driving operations according to the original response parameters.

[0069] In this embodiment of the application, after obtaining the current driving operation received by the current driver of the current vehicle, the received current driving operation is input into the driving model corresponding to the target vehicle, and the response parameters output by the driving model corresponding to the current driving operation are recorded as the target response parameters.

[0070] Optionally, in one embodiment, before determining the target vehicle for the simulated driving experience, the method further includes:

[0071] Obtain the riding preference information of different passengers corresponding to the current vehicle;

[0072] Based on the different passengers' riding preferences, the driving model is subjected to reinforcement learning to obtain an updated driving model that matches different passengers.

[0073] It should be noted that, for both the driver and passengers in the same vehicle, since the driving operations are performed by the driver, the driver has certain expectations regarding the vehicle's driving feedback. However, passengers cannot know what driving operations the driver has performed, nor can they anticipate the vehicle's driving feedback, making the passenger's riding experience entirely dependent on the driver's driving operations. Therefore, in order to effectively balance the driver's driving experience and the passenger's riding experience, this embodiment of the application also applies reinforcement learning to the driving model after imitation learning, enabling it to capture passenger riding preferences.

[0074] Accordingly, in this application, for another vehicle that needs to be simulated, after completing the imitation learning of the driving model of that other vehicle, the riding preference information of different passengers corresponding to the current vehicle is also obtained. Among these, the specific passengers corresponding to the current vehicle can be configured according to actual needs.

[0075] For a passenger, the passenger's ride preference information is used to describe their ride preferences, such as preferred acceleration, acceptable acceleration, unacceptable acceleration, preferred braking, acceptable braking, unacceptable braking, preferred steering, acceptable steering, unacceptable steering, and so on.

[0076] After obtaining the riding preference information of different passengers corresponding to the current vehicle, a reward function corresponding to different passengers is constructed based on the riding preference information of different passengers. Based on the reward function corresponding to different passengers, reinforcement learning is performed on the driving model after imitation learning to obtain an updated driving model that corresponds to other vehicles and matches different passengers.

[0077] For example, suppose there are three different passengers in the current vehicle: passenger A, passenger B, and passenger C. We obtain the riding preference information for passenger A, passenger B, and passenger C respectively. Based on passenger A's riding preference information, we construct a reward function corresponding to passenger A, passenger B's riding preference information, and passenger C's riding preference information. Then, based on the reward function corresponding to passenger A, we perform reinforcement learning on the driving model after imitation learning to obtain an updated driving model matching passenger A. Similarly, based on the reward function corresponding to passenger B, we perform reinforcement learning on the driving model after imitation learning to obtain an updated driving model matching passenger B. Finally, based on the reward function corresponding to passenger C, we perform reinforcement learning on the driving model after imitation learning to obtain an updated driving model matching passenger C.

[0078] In this embodiment of the application, before obtaining the target response parameters corresponding to the current driving operation through the driving model corresponding to the target vehicle, the method further includes:

[0079] Determine the current passengers in the current vehicle;

[0080] By using the driving model corresponding to the target vehicle, the target response parameters corresponding to the current driving operation are obtained, including:

[0081] By updating the driving model that corresponds to the target vehicle and matches the current passenger, the target response parameters corresponding to the current driving operation are obtained.

[0082] In this embodiment, in addition to determining the target vehicle for the simulated driving experience, the current passenger of the current vehicle is also determined. There are no restrictions on how the current passenger of the current vehicle is determined; those skilled in the art can select an appropriate method based on actual needs.

[0083] For example, a passenger selection interface can be displayed, which includes passenger identifiers of currently available candidate passengers; in response to a selection operation of a passenger identifier in the passenger selection interface, the candidate passenger corresponding to the selected passenger identifier is identified as the current passenger. For example, please refer to... Figure 1d An example diagram of the passenger selection interface is provided. Figure 1d As shown, the passenger selection interface includes passenger identifiers for four different passengers corresponding to the current vehicle (where the passenger identifier includes a passenger icon and a passenger name), selection controls corresponding to each passenger identifier, and a prompt message "Please select the current passenger of the vehicle" to prompt the selection of the current passenger. When the selection control corresponding to the passenger identifier of passenger 4 is selected, passenger 4 is identified as the current passenger.

[0084] Accordingly, when obtaining the target response parameters corresponding to the current driving operation through the driving model corresponding to the target vehicle, the updated driving model matching the current passenger is first determined from the updated driving models corresponding to the target vehicle and matched with different passengers in the current vehicle. The target response parameters corresponding to the current driving operation are obtained through the updated driving model corresponding to the target vehicle and matched with the current passenger. That is, the current driving operation is input into the updated driving model, and the response parameters output by the updated driving model are used as the target response parameters corresponding to the current driving operation.

[0085] Optionally, in one embodiment, there are multiple current passengers. The target response parameters corresponding to the current driving operation are obtained through an updated driving model that corresponds to the target vehicle and matches the current passengers. These parameters include:

[0086] By updating the driving model that corresponds to the target vehicle and is matched with different current passengers, multiple candidate response parameters corresponding to the current driving operation are obtained;

[0087] Based on multiple candidate response parameters, determine the target response parameter corresponding to the current driving operation.

[0088] In this embodiment of the application, when there are multiple current passengers in the current vehicle, the response parameters corresponding to the current driving operation are obtained by updating the driving model that corresponds to the target vehicle and matches each current passenger, resulting in multiple candidate response parameters. Then, the target response parameters corresponding to the current driving operation are determined based on the candidate response parameters corresponding to each of the multiple current passengers.

[0089] For example, assuming that different passenger priorities are configured for the current vehicle, the target response parameter corresponding to the current driving operation can be determined based on the candidate response parameters corresponding to each current passenger and their respective passenger priorities. For instance, the candidate response parameter corresponding to the current passenger with the highest passenger priority can be determined as the target response parameter. Alternatively, weights can be assigned to each current passenger based on their passenger priority, and then the weights of each current passenger can be weighted and summed to obtain the target response parameter, and so on.

[0090] If no priority is assigned to different passengers corresponding to the current vehicle, the average of multiple candidate response parameters can be calculated as the target response parameter, or the median of multiple candidate response parameters can be selected as the target response parameter, and so on.

[0091] In step 140, the current vehicle is controlled to respond to the current driving operation according to the target response parameters.

[0092] As shown above, after obtaining the target response parameters corresponding to the current driving operation through the driving model corresponding to the target vehicle, the driving control components (such as accelerator pedal, brake pedal, steering wheel, etc.) of the current vehicle corresponding to the target response parameters are controlled to respond to the current driving operation according to the target response parameters.

[0093] For example, assuming the current driving operation is an acceleration operation based on the accelerator pedal, the current vehicle's drive components (such as the motor of an electric vehicle or the engine of a fuel vehicle) respond to the acceleration operation according to the target response parameters, thereby driving the current vehicle to accelerate and providing an acceleration force similar to that of the target vehicle in response to the acceleration operation.

[0094] For example, assuming the current driving operation is a braking operation based on the brake pedal, the braking system of the current vehicle responds to the braking operation according to the target response parameters, thereby controlling the braking of the current vehicle and providing a braking force similar to that of the target vehicle in responding to the braking operation.

[0095] For example, assuming the current driving operation is a steering operation based on the steering wheel, the current vehicle's steering components respond to the steering operation according to the target response parameters, thereby controlling the current vehicle's steering and providing a steering force similar to that of the target vehicle in responding to the steering operation.

[0096] Optionally, in one embodiment, before controlling the current vehicle to respond to the current driving operation according to the target response parameters, the method further includes:

[0097] Obtain the current level of motion sickness of the current passenger, and obtain the trend of the current level of motion sickness based on the current level of motion sickness;

[0098] Based on the target response parameters, control the current vehicle to respond to the current driving operation, including:

[0099] The target response parameters are updated based on the trend of changes in the degree of motion sickness, resulting in the updated target response parameters.

[0100] Control the current vehicle to respond to the current driving operation according to the updated target response parameters.

[0101] Motion sickness (MS), also known as motion sickness, is a vestibular nerve disorder primarily caused by transportation or rotational stimuli. Depending on the specific environment, it can be classified as car sickness, seasickness, or airsickness. The pathogenesis of motion sickness is not yet fully understood, but mainstream theories include sensory conflict, neural mismatch, otolith tilt information translation, and otolith asymmetry. Among these, vestibular system information conflict is considered a major factor in the manifestation of motion sickness symptoms. When the vestibular organs are dysfunctional or oversensitive, symptoms such as dizziness, nausea, vomiting, and paleness often occur. For example, when passengers are traveling in a vehicle, the swaying motion may cause the vestibular organs to become oversensitive, leading to motion sickness symptoms.

[0102] In this embodiment of the application, in order to further balance the driver's driving experience and the passenger's riding experience, the response parameters of the current vehicle are also updated according to the trend of the passenger's motion sickness.

[0103] Specifically, the system obtains the current level of motion sickness of the current passenger at the current moment, as well as the historical level of motion sickness at previous moments. Based on the current and historical levels of motion sickness, it statistically calculates the trend of motion sickness change for the current passenger. For example, in this embodiment, the configuration parameter update strategy is as follows: if at least one current passenger shows an upward trend in motion sickness, the target response parameters are updated with a constraint of reducing the intensity of the current vehicle's driving feedback; otherwise, no updates are made.

[0104] For example, assuming the current driving operation is an acceleration operation based on the accelerator pedal, if the current passenger's dizziness level changes in an upward trend, the target response parameters are updated to obtain updated target response parameters. This ensures that the acceleration force of the current vehicle's drive components in response to the acceleration operation according to the updated target response parameters is weaker than the acceleration force of the current vehicle's drive components in response to the acceleration operation according to the target response parameters. This allows the current vehicle to accelerate more gently, preventing the current passenger's dizziness level from continuing to increase.

[0105] For example, assuming the current driving operation is a braking operation based on the brake pedal, if the current passenger's dizziness level changes in an upward trend, the target response parameters are updated to obtain updated target response parameters. This allows the vehicle's braking components to respond to the braking operation according to the updated target response parameters, thus controlling the braking force of the current vehicle's brakes. This is weaker than if the current vehicle's braking components responded to the braking operation according to the target response parameters, thereby allowing the vehicle to brake more gently and preventing the current passenger's dizziness level from continuing to increase.

[0106] For example, assuming the current driving operation is a steering operation based on the steering wheel, if the current passenger's motion sickness level is trending upwards, the target response parameters are updated to obtain updated target response parameters. This allows the vehicle's steering components to respond to the steering operation according to the updated target response parameters, controlling the steering force of the current vehicle to be weaker than if the current vehicle's steering components responded to the steering operation according to the target response parameters, thus enabling the vehicle to turn more gently and preventing the current passenger's motion sickness level from continuing to increase.

[0107] In other embodiments, the parameter update strategy can be configured by those skilled in the art according to actual needs, and no specific limitations are imposed here.

[0108] It should be noted that, in this embodiment, a motion sickness prediction model is trained for each different passenger corresponding to the current vehicle. Specifically, with the passenger's authorization, the passenger's historical body parameters (in this embodiment, heart rate and skin conductivity are selected as body parameters, which can be collected during the passenger's historical rides using heart rate and skin conductivity acquisition devices) are obtained as sample body parameters, and the motion sickness level corresponding to the historical body parameters is obtained as the sample motion sickness level. A motion sickness prediction model is constructed with body parameters as input and motion sickness level as output. The model architecture of the motion sickness prediction model is not limited here and can be selected by those skilled in the art according to actual needs. The obtained sample body parameters are input into the motion sickness prediction model. A second training loss is obtained based on the difference between the predicted motion sickness level output by the motion sickness prediction model and the sample motion sickness level corresponding to the sample body parameters. The type of the second training loss is not limited here and can be selected by those skilled in the art according to actual needs; for example, cross-entropy loss can be used as the second training loss. The network parameters of the motion sickness prediction model are updated based on the obtained second training loss until a second preset stopping condition is met. There are no restrictions on the configuration of the second preset stopping condition here. It can be configured by those skilled in the art according to actual needs. For example, the second preset stopping condition can be configured as: the number of parameter updates of the motion sickness prediction model reaches a preset number, or the second preset stopping condition can be configured as: the training loss of the motion sickness prediction model converges, and so on.

[0109] To obtain the current level of motion sickness of a passenger at the current moment, the current heart rate and skin conductivity of the passenger at the current moment are first collected by a heart rate acquisition device and a skin conductivity acquisition device, respectively. Then, the current heart rate and skin conductivity are used as the current body parameters of the passenger at the current moment and input into the motion sickness prediction model matched with the passenger. The motion sickness level predicted by the motion sickness prediction model is used as the current level of motion sickness of the passenger at the current moment.

[0110] Optionally, in one embodiment, after obtaining the current level of motion sickness of the current passenger, the method further includes:

[0111] If the current level of motion sickness reaches the threshold, a soothing message will be displayed to the current passenger, suggesting how to alleviate the motion sickness.

[0112] The severity threshold is used to determine whether a passenger experiences motion sickness. If the passenger's motion sickness reaches the severity threshold, the passenger is deemed to be experiencing motion sickness. This application does not impose specific limitations on the value of the severity threshold; it can be determined by those skilled in the art based on actual needs.

[0113] In this embodiment of the application, if it is detected that the current passenger's current level of motion sickness has reached the threshold, it is determined that the current passenger has experienced motion sickness. At this time, a soothing prompt message is output to the current passenger to suggest how to alleviate the level of motion sickness. For example, the soothing prompt message may suggest that the current passenger take deep breaths, drink water, close their eyes to rest, listen to music, look into the distance and / or adjust the seat, etc.

[0114] Optionally, in one embodiment, after controlling the current vehicle to respond to the current driving operation according to the target response parameters, the method further includes:

[0115] Obtain the current driving feedback from the current vehicle in response to the current driving operation;

[0116] Based on current driving feedback, the probability of increased motion sickness in the current passenger is predicted by using a motion sickness risk prediction model matched with the current passenger.

[0117] If the probability increases to the probability threshold, an operation prompt message is generated based on the current driving operation and output to the current driver.

[0118] In this embodiment of the application, in order to optimize the driver's driving behavior and improve the passenger's riding experience, real-time feedback is also provided based on the driver's driving operations.

[0119] Specifically, it obtains the current driving feedback of the current vehicle in response to the current driving operation. For example, if the current driving operation is an acceleration operation based on the accelerator pedal, it obtains the current acceleration force of the current vehicle in response to the acceleration operation; if the current driving operation is a braking operation based on the brake pedal, it obtains the current braking force of the current vehicle in response to the braking operation; and if the current driving operation is a steering operation based on the steering wheel, it obtains the current steering force of the current vehicle in response to the steering operation.

[0120] It should be noted that, for different passengers corresponding to the current vehicle, the embodiments of this application have trained a motion sickness risk prediction model that matches them. The motion sickness risk prediction model is configured to take the driving feedback of the vehicle as input and the increased probability of indicating an increase in the degree of motion sickness as output. Here, there are no specific restrictions on the model architecture and training method of the motion sickness risk prediction model, which can be selected by those skilled in the art according to actual needs.

[0121] For example, a training sample set can be constructed based on the riding preference information of different passengers. For instance, for a passenger, the passenger's preferred acceleration, acceptable acceleration, unacceptable acceleration, preferred braking, acceptable braking, unacceptable braking, and preferred steering, acceptable steering, and unacceptable steering are determined based on their riding preference information. Then, the sample increase probability of the increased motion sickness level corresponding to each of the passenger's preferred acceleration, acceptable acceleration, unacceptable acceleration, preferred braking, acceptable braking, unacceptable braking, and preferred steering, acceptable steering, and unacceptable steering is calibrated. Correspondingly, the passenger's preferred acceleration, acceptable acceleration, unacceptable acceleration, preferred braking, acceptable braking, unacceptable braking, and preferred steering are used as sample driving feedback. A training sample set is constructed based on the sample driving feedback and its corresponding sample increase probability. Afterwards, a motion sickness risk prediction model can be trained based on the constructed training sample set. The training methods for training the driving model and motion sickness level prediction model in the above embodiments can be referred to accordingly, and will not be elaborated here.

[0122] After obtaining the current driving feedback from the vehicle in response to the current driving operation, this feedback is input into a motion sickness risk prediction model matched with the current passenger. The model predicts the probability that the current driving operation will increase the passenger's motion sickness level. It then identifies whether this probability reaches a threshold; if so, it determines that the current driving operation will increase the passenger's motion sickness level and generates a prompt message based on the current driving operation, outputting this prompt to the driver. For example, if the current driving operation is acceleration based on the accelerator pedal, the prompt message might be "Please gently press the accelerator pedal"; if it's braking based on the brake pedal, it might be "Please gently press the brake pedal"; if it's steering based on the steering wheel, it might be "Please gently turn the steering wheel," and so on. In this way, the prompts provide real-time feedback to the driver's driving actions, suggesting a smoother driving style to provide a better riding experience for the passenger.

[0123] Optionally, in one embodiment, the vehicle control method provided in this application further includes:

[0124] Obtain the first air environment setting parameters and the first setting priority corresponding to the current driver;

[0125] Obtain the second air environment setting parameters and the second setting priority corresponding to the current passenger;

[0126] The target air environment setting parameters are determined based on the first air environment setting parameters, the second air environment setting parameters, the first setting priority, and the second setting priority.

[0127] Set the in-vehicle air environment according to the target air environment settings.

[0128] It is understandable that, in addition to the vehicle's driving feedback affecting the driving / riding experience, the vehicle's in-vehicle air environment can also influence the driving / riding experience. Therefore, this application embodiment also configures the vehicle's in-vehicle air environment to further optimize the driving and riding experience.

[0129] Specifically, the air environment setting parameters corresponding to the current driver are obtained and denoted as the first air environment setting parameter, and the setting priority of the current driver is obtained and denoted as the first setting priority. Additionally, the air environment setting parameters corresponding to the current passenger are obtained and denoted as the second air environment setting parameter, and the setting priority of the current passenger is obtained and denoted as the second setting priority. Then, based on the first air environment setting parameter, the second air environment setting parameter, the first setting priority, and the second setting priority, the target air environment setting parameter is determined; and the in-vehicle air environment is set according to the target air environment setting parameter. It should be noted that the air environment setting parameters include, but are not limited to, setting parameters for the vehicle's interior temperature, interior humidity, interior fan speed, and interior odor.

[0130] As an optional implementation, the target air environment setting parameters are determined based on the first air environment setting parameters, the second air environment setting parameters, the first setting priority, and the second setting priority, including:

[0131] If the first setting priority and the second setting priority are different, then the air environment setting parameter corresponding to the one with the higher setting priority between the current passenger and the current driver will be determined as the target air environment setting parameter; or,

[0132] If the first setting priority and the second setting priority are the same, then the first air environment setting parameters and the second air environment setting parameters are merged to obtain the target air environment setting parameters.

[0133] The process begins by comparing the current driver's first setting priority with the current passenger's second setting priority. If they differ, the air environment setting parameter corresponding to the higher priority of the current passenger and driver is determined as the target air environment setting parameter. For example, if the current driver's first setting priority is higher than the current passenger's second setting priority, the current driver's first air environment setting parameter is determined as the target air environment setting parameter, thus setting the vehicle's air environment according to the current driver's preference. Conversely, if the current driver's first setting priority is lower than the current passenger's second setting priority, the current passenger's second air environment setting parameter is determined as the target air environment setting parameter, thus setting the vehicle's air environment according to the current passenger's preference.

[0134] Furthermore, if the current driver's first setting priority and the current passenger's second setting priority are the same, the first air environment setting parameters and the second air environment setting parameters are fused according to the configured fusion strategy to obtain the target air environment setting parameters.

[0135] For example, the fusion strategy can be configured as follows: take the average of the first air environment setting parameter and the second air environment setting parameter as the target environment setting parameter. Alternatively, the fusion strategy can be configured as follows: determine the weighting weights of the first air environment setting parameter and the second air environment setting parameter according to the current degree of motion sickness of the current passenger (for example, the higher the current degree of motion sickness of the current passenger, the greater the weighting weight of the second air environment setting parameter), and perform a weighted summation according to the weighting weights of the first air environment setting parameter and the second air environment setting parameter to obtain the target environment setting parameter, and so on.

[0136] Optionally, in one embodiment, determining the target air environment setting parameters based on the first air environment setting parameters, the second air environment setting parameters, the first setting priority, and the second setting priority includes:

[0137] If the current passenger's current level of motion sickness does not reach the threshold, the target air environment setting parameters are determined based on the first air environment setting parameters, the second air environment setting parameters, the first setting priority, and the second setting priority.

[0138] In other embodiments, if the current passenger's current level of motion sickness reaches a threshold, the second air environment setting parameter is directly used as the target air environment setting parameter.

[0139] Optionally, in one embodiment, the target vehicle is a fuel-powered vehicle, the current vehicle is an electric vehicle, and the vehicle control method further includes:

[0140] By using a sound synthesis model matched with the target vehicle, sound audio corresponding to the current driving operation is generated;

[0141] While controlling the current vehicle's response to the current driving operation according to the target response parameters, a sound effect audio is played.

[0142] Engine noise refers to the roaring sound produced by the engine of a gasoline-powered vehicle. Electric vehicles, powered by electric motors, offer a quieter driving environment compared to gasoline-powered vehicles. However, this quiet environment results in a lack of the dynamic feel of an engine, reducing the driver's experience. For passengers, this quiet environment can also create a sense of spatial disorientation, further diminishing their comfort. Therefore, to further enhance the driving and passenger experience of electric vehicles, this application, in a scenario where the target vehicle is a gasoline-powered vehicle and the current vehicle is an electric vehicle, simulates not only the driving feedback of the target vehicle but also its engine noise.

[0143] It should be noted that for each other fuel-powered vehicle that needs to be simulated, the embodiments of this application also pre-train a matching sound synthesis model. The following description takes the training of another fuel-powered vehicle that needs to be simulated as an example.

[0144] For the other fuel-powered vehicle, the historical driving operations received by the other fuel-powered vehicle for its engine are obtained, along with the historical operating state information (such as engine speed) of the fuel-powered vehicle when receiving the historical driving operations, and the historical engine noise audio of the other fuel-powered vehicle in response to the historical driving operations. In this way, the historical engine noise audio of the other vehicle to be simulated in different engine operating states in response to different historical driving operations for the engine can be obtained.

[0145] A sound wave synthesis model is constructed, taking operational status information and acceleration operations as inputs and sound wave audio as output. The model architecture of the sound wave synthesis model is not limited here and can be selected by those skilled in the art according to actual needs. The historical driving operations and corresponding historical operational status information obtained above are used as samples input into the sound wave synthesis model. A third training loss is obtained based on the difference between the predicted sound wave audio output by the sound wave synthesis model and the historical sound wave audio corresponding to the input historical driving operations and historical operational status information. The type of the third training loss is not limited here and can be selected by those skilled in the art according to actual needs. The network parameters of the sound wave synthesis model are updated based on the obtained third training loss until a third preset stopping condition is met. The configuration of the third preset stopping condition is not limited here and can be configured by those skilled in the art according to actual needs. For example, the third preset stopping condition can be configured as: the number of parameter updates to the sound wave synthesis model reaches a preset number, or the third preset stopping condition can be configured as: the third training loss of the sound wave synthesis model converges, etc.

[0146] As shown above, a sound synthesis model for simulating the sound of other different fuel vehicles can be trained for the current vehicle. Correspondingly, which trained sound synthesis models are deployed on electronic devices can be used to simulate the sound of other corresponding fuel vehicles.

[0147] Furthermore, a state mapping relationship is established between the operating state information of the current vehicle's motor and the operating state information of the target vehicle's engine, based on expert knowledge. In this embodiment, in addition to obtaining the target response parameters corresponding to the current driving operation through an acceleration model matched with the target vehicle, a sound wave video corresponding to the current driving operation is generated through a sound wave synthesis model matched with the target vehicle. If the current driving operation is a driving operation targeting the motor (e.g., an acceleration operation based on the accelerator pedal), the first operating state information of the motor when the current vehicle receives the current driving operation is obtained. Based on the established state mapping relationship, this operating state information is mapped to the second operating state information corresponding to the engine of the target vehicle. The second operating state information and the current driving operation are then input into the sound wave synthesis model matched with the target vehicle. The sound wave audio output by the sound wave synthesis model is used as the sound wave audio for the current driving operation. During the process of controlling the current vehicle to respond to the current driving operation according to the target response parameters, this sound wave audio is played to simulate the sound of the target vehicle, thereby simulating the power of the target vehicle's engine to improve the current driver's driving experience and reduce the spatial illusion of the current passengers to improve their riding experience.

[0148] Optionally, in one embodiment, the vehicle control method provided in this application further includes:

[0149] Obtain the vibration control parameters corresponding to the sound wave audio;

[0150] While playing the sound audio, the vibration of the vehicle's seat is controlled according to the vibration control parameters.

[0151] In this embodiment, while playing the sound audio, the seat of the current vehicle is simultaneously controlled to vibrate, thereby providing a tactile experience synchronized with the auditory experience, and further improving the driving experience of the driver and the riding experience of the passengers.

[0152] Specifically, the waveform characteristics of the sound wave audio can be obtained, and then vibration control parameters that conform to the waveform characteristics can be generated. This yields the vibration control parameters corresponding to the sound wave audio, and then, during the playback of the sound wave audio, the vibration of the vehicle seat can be synchronously controlled according to the obtained vibration control parameters.

[0153] Optionally, in one embodiment, the vehicle control method provided in this application further includes:

[0154] Acquire the cabin noise audio of the current vehicle's cabin;

[0155] The cabin noise audio is filtered based on the sound wave audio to obtain the filtered noise audio.

[0156] Generate a noise-reduced frequency that is out of phase with the filtered noise audio, and play the noise-reduced frequency.

[0157] It is understandable that various sources of noise exist within the cabin during vehicle operation. For example, tire noise generated from direct contact with the ground is transmitted into the cabin, and wind noise is also generated by the vehicle's movement. In addition, environmental noise from the external environment and internal noise generated by the vehicle's own operation are also transmitted into the cabin. To further improve the driving experience, this application embodiment also implements noise reduction treatment for the vehicle's cabin.

[0158] The process involves acquiring cabin audio using audio acquisition equipment installed within the vehicle's cabin. Then, a configured human voice separation strategy is employed to extract human voice audio from this cabin audio. The separated cabin audio is then considered the cabin noise audio. No restrictions are placed on the specific human voice separation strategy used; it can be selected by those skilled in the art based on actual needs, including but not limited to spectral analysis-based human voice separation strategies, source separation algorithms-based human voice separation strategies, and so on.

[0159] As can be understood from the descriptions in the above embodiments, although the sound is essentially engine noise, its presence positively impacts the driving experience. Therefore, this embodiment does not perform noise reduction on the sound. Instead, after acquiring the cabin noise audio of the current vehicle, the cabin noise audio is further filtered based on the sound audio, that is, the sound audio portion of the cabin noise audio is filtered out to obtain the filtered noise audio.

[0160] As described above, after obtaining the filtered noise audio, it undergoes phase inversion processing to generate an audio signal with the opposite phase, denoted as the noise-reduced frequency. It's understandable that when two waveforms with opposite phases are superimposed, they cancel each other out because their peaks and troughs align, causing their amplitudes to cancel each other out. Using this principle, playing the noise-reduced frequency can achieve the purpose of noise reduction in the cabin of a vehicle.

[0161] As can be seen from the above, the vehicle control scheme provided in this application pre-learns by imitating the driving model using sample driving operations and sample response parameters. The sample response parameters are obtained by converting the original response parameters of the target vehicle in response to the sample driving operations. Furthermore, the driving feedback of the current vehicle responding to the sample driving operations according to the sample response parameters is similar to the driving feedback of the target vehicle responding to the sample driving operations according to the original response parameters. This allows the driving model to capture the driving feedback of the target vehicle to the driving operations. During the process of controlling the current vehicle, the target response parameters corresponding to the current driving operation received by the current vehicle are obtained through the driving model corresponding to the target vehicle. By controlling the current vehicle to respond to the current driving operation according to these target response parameters, driving feedback similar to that of the target vehicle in responding to the current driving operation can be obtained, providing a driving experience similar to that of the target vehicle. This achieves the simulation of the current vehicle's driving experience of the target vehicle, enriching the overall driving experience.

[0162] Please refer to Figure 2 The following description uses electronic devices as the executing entity to illustrate the vehicle control method provided in this application. Figure 2 As shown, the flow of this vehicle control method can also be as follows:

[0163] In step 210, the electronic device determines the target vehicle for the current vehicle to be simulated driving experience.

[0164] The term "current vehicle" refers to the vehicle controlled by the electronic device executing the vehicle control method provided in this application. In order to simulate the driving experience of other vehicles by the current vehicle, the electronic device must first determine the other vehicles to be simulated by the current vehicle, which are referred to as the target vehicles.

[0165] In step 220, the electronic device identifies the current passenger in the current vehicle and obtains the trend of the current passenger's motion sickness level.

[0166] In addition to identifying the target vehicle for the simulated driving experience, the electronic device also identifies the current passengers in the current vehicle. No restrictions are placed on how the current passengers are identified; those skilled in the art can select an appropriate method based on actual needs.

[0167] In addition, the system obtains the current level of motion sickness of the current passenger at the current moment, the historical level of motion sickness at the current moment before the current moment, and statistically analyzes the current passenger's motion sickness trend based on the current passenger's current level of motion sickness and the historical level of motion sickness.

[0168] In 230, the electronic device acquires the current driving operation received by the current driver from the current vehicle.

[0169] As described above, simulating the driving experience of a target vehicle essentially involves simulating the vehicle's feedback to driving operations. Accordingly, after identifying the target vehicle for the simulated driving experience, the electronic equipment uses the driving control components configured in the vehicle to obtain the current driving operations received by the driver. These driving control components include, but are not limited to: an accelerator pedal (also called the accelerator pedal for electric vehicles and the gas pedal for gasoline vehicles) for controlling acceleration, a brake pedal for controlling braking, and a steering wheel for controlling steering. Correspondingly, current driving operations include, but are not limited to: acceleration and release operations based on the accelerator pedal, braking and release operations based on the brake pedal, and steering and centering operations based on the steering wheel. Current driving operations can be characterized by operational information related to the corresponding driving control components, such as the accelerator pedal opening, brake pedal opening, and steering wheel angle.

[0170] In 240, the electronic device obtains the target response parameters corresponding to the current driving operation through an updated driving model that corresponds to the target vehicle and matches the current passenger.

[0171] It is understandable that simulating the driving experience of other vehicles essentially means enabling the current vehicle to provide driving feedback as consistent as possible with that other vehicle for the same driving operation. To achieve this simulation, for each other vehicle to be simulated, this application employs imitation learning (also known as demonstration-based learning or apprenticeship learning) to pre-train a corresponding driving model. Imitation learning is a machine learning method that learns a specific task by observing and imitating the behavior of a specific object. In this application, imitation learning is used to capture the driving feedback of other vehicles to be simulated for driving operations, so that the current vehicle can reproduce similar driving feedback. For the imitation learning process of the driving model, please refer to the relevant descriptions in the above embodiments; they will not be repeated here.

[0172] It should be noted that, for both the driver and passengers in the same vehicle, since the driving operations are given by the driver, the driver has certain expectations regarding the vehicle's driving feedback. However, passengers cannot know what driving operations the driver has performed, nor can they anticipate the vehicle's driving feedback, making the passenger's riding experience entirely dependent on the driver's actions. Therefore, in order to effectively balance the driver's driving experience and the passenger's riding experience, this embodiment of the application also applies reinforcement learning to the driving model after imitation learning to obtain an updated driving model, enabling it to capture passenger riding preferences. For the reinforcement learning process of the driving model, please refer to the relevant descriptions in the above embodiments; they will not be repeated here.

[0173] As shown above, after obtaining the current driving operation, the electronic device will input the current driving operation into an updated driving model that corresponds to the target vehicle and matches the current passenger, and use the response parameters output by the updated driving model as the target response parameters corresponding to the current driving operation.

[0174] In 250, the electronic device updates the target response parameters according to the trend of changes in the degree of motion sickness, and obtains the updated target response parameters.

[0175] To further balance the driver's driving experience and the passenger's riding experience, the electronic device also updates the current vehicle's response parameters based on the changing trend of the passenger's motion sickness level. For example, the parameter update strategy in this application embodiment is as follows: if at least one current passenger's motion sickness level shows an upward trend, the target response parameters are updated with the constraint of reducing the intensity of the current vehicle's driving feedback; otherwise, no update is performed.

[0176] For example, assuming the current driving operation is an acceleration operation based on the accelerator pedal, if the current passenger's dizziness level changes in an upward trend, the target response parameters are updated to obtain updated target response parameters. This ensures that the acceleration force of the current vehicle's drive components in response to the acceleration operation according to the updated target response parameters is weaker than the acceleration force of the current vehicle's drive components in response to the acceleration operation according to the target response parameters. This allows the current vehicle to accelerate more gently, preventing the current passenger's dizziness level from continuing to increase.

[0177] For example, assuming the current driving operation is a braking operation based on the brake pedal, if the current passenger's dizziness level changes in an upward trend, the target response parameters are updated to obtain updated target response parameters. This allows the vehicle's braking components to respond to the braking operation according to the updated target response parameters, thus controlling the braking force of the current vehicle's brakes. This is weaker than if the current vehicle's braking components responded to the braking operation according to the target response parameters, thereby allowing the vehicle to brake more gently and preventing the current passenger's dizziness level from continuing to increase.

[0178] For example, assuming the current driving operation is a steering operation based on the steering wheel, if the current passenger's motion sickness level is trending upwards, the target response parameters are updated to obtain updated target response parameters. This allows the vehicle's steering components to respond to the steering operation according to the updated target response parameters, controlling the steering force of the current vehicle to be weaker than if the current vehicle's steering components responded to the steering operation according to the target response parameters, thus enabling the vehicle to turn more gently and preventing the current passenger's motion sickness level from continuing to increase.

[0179] In 260, the electronic devices control the current vehicle to respond to the current driving operation according to the updated target response parameters.

[0180] As shown above, after updating the target response parameters and obtaining the updated target response parameters, the electronic device controls the current vehicle to respond to the current driving operation according to the updated target response parameters.

[0181] For example, assuming the current driving operation is an acceleration operation based on the accelerator pedal, the current vehicle's drive components (such as the motor of an electric vehicle or the engine of a fuel vehicle) respond to the acceleration operation according to the updated target response parameters, thereby driving the current vehicle to accelerate and providing an acceleration force similar to that of the target vehicle in responding to the acceleration operation and in line with the current passenger's acceleration preferences.

[0182] For example, assuming the current driving operation is a braking operation based on the brake pedal, the braking of the current vehicle is controlled by the braking components of the current vehicle in response to the braking operation according to the target response parameters, so as to provide a braking force similar to the target vehicle's response to the braking operation and in line with the current passenger's braking preference.

[0183] For example, assuming the current driving operation is a steering operation based on the steering wheel, the current vehicle's steering components respond to the steering operation according to the target response parameters, thereby controlling the current vehicle's steering and providing a steering force similar to that of the target vehicle in responding to the steering operation and in line with the current passenger's steering preferences.

[0184] In 270, the electronic devices acquire current driving feedback from the current vehicle in response to the current driving operation.

[0185] Specifically, the electronic device obtains the current driving feedback of the current vehicle in response to the current driving operation. For example, if the current driving operation is an acceleration operation based on the accelerator pedal, it obtains the current acceleration force of the current vehicle in response to the acceleration operation; if the current driving operation is a braking operation based on the brake pedal, it obtains the current braking force of the current vehicle in response to the braking operation; and if the current driving operation is a steering operation based on the steering wheel, it obtains the current steering force of the current vehicle in response to the steering operation.

[0186] In 280, the electronic device, based on current driving feedback, predicts the increased probability that the current driving operation will lead to an increase in the current passenger's degree of motion sickness through a motion sickness risk prediction model matched with the current passenger.

[0187] It should be noted that, for different passengers corresponding to the current vehicle, the embodiments of this application have trained a motion sickness risk prediction model that matches them. The motion sickness risk prediction model is configured to take the driving feedback of the vehicle as input and the increased probability of indicating an increase in the degree of motion sickness as output. Here, there are no specific restrictions on the model architecture and training method of the motion sickness risk prediction model, which can be selected by those skilled in the art according to actual needs.

[0188] For example, a training sample set can be constructed based on the riding preference information of different passengers. For instance, for a passenger, the passenger's preferred acceleration, acceptable acceleration, unacceptable acceleration, preferred braking, acceptable braking, unacceptable braking, and preferred steering, acceptable steering, and unacceptable steering are determined based on their riding preference information. Then, the sample increase probability of the increased motion sickness level corresponding to each of the passenger's preferred acceleration, acceptable acceleration, unacceptable acceleration, preferred braking, acceptable braking, unacceptable braking, and preferred steering, acceptable steering, and unacceptable steering is calibrated. Correspondingly, the passenger's preferred acceleration, acceptable acceleration, unacceptable acceleration, preferred braking, acceptable braking, unacceptable braking, and preferred steering are used as sample driving feedback. A training sample set is constructed based on the sample driving feedback and its corresponding sample increase probability. Afterwards, a motion sickness risk prediction model can be trained based on the constructed training sample set. The training methods for training the driving model and motion sickness level prediction model in the above embodiments can be referred to accordingly, and will not be elaborated here.

[0189] After obtaining the current driving feedback of the current vehicle in response to the current driving operation, the electronic device will input the current driving feedback into the motion sickness risk prediction model matched with the current passenger, and obtain the probability that the current driving operation will increase the degree of motion sickness of the current passenger.

[0190] In 290, if the probability of increasing reaches the probability threshold, the electronic device generates operation prompt information based on the current driving operation and outputs the operation prompt information to the current driver.

[0191] The electronic device further identifies whether the increased probability reaches a probability threshold. If so, it determines that the current driving operation will increase the passenger's motion sickness and generates operation prompts based on the current driving operation, outputting these prompts to the driver. For example, if the current driving operation is acceleration based on the accelerator pedal, the prompt might be "Please gently press the accelerator pedal"; if it's braking based on the brake pedal, it might be "Please gently press the brake pedal"; if it's steering based on the steering wheel, it might be "Please gently turn the steering wheel," and so on. In this way, the operation prompts provide real-time feedback to the driver's driving actions, suggesting a smoother driving style to provide a better riding experience for the passenger.

[0192] To facilitate better implementation of the above vehicle control methods, this application also provides a corresponding vehicle control device. The meanings of the terms used are the same as in the above vehicle control methods; for specific implementation details, please refer to the descriptions in the above method embodiments.

[0193] Please refer to Figure 3 , Figure 3 This is a schematic diagram of the structure of a vehicle control device provided in an embodiment of this application. The vehicle control device may include a vehicle determination module 310, an operation receiving module 320, a parameter acquisition module 330, and an operation response module 340, wherein...

[0194] The vehicle determination module 310 is used to determine the target vehicle for the current vehicle to be simulated driving experience.

[0195] The operation receiving module 320 is used to acquire the current driving operation received by the current driver in the current vehicle;

[0196] The parameter acquisition module 330 is used to acquire the target response parameters corresponding to the current driving operation through the driving model corresponding to the target vehicle. The driving model is obtained by imitation learning based on the sample driving operation and the sample response parameters. The sample response parameters are converted from the original response parameters of the target vehicle in response to the sample driving operation. The driving feedback of the current vehicle in response to the sample driving operation according to the sample response parameters is similar to the driving feedback of the target vehicle in response to the sample driving operation according to the original response parameters.

[0197] The operation response module 340 is used to control the current vehicle to respond to the current driving operation according to the target response parameters.

[0198] Optionally, in one embodiment, the vehicle control device provided in this application further includes a model training module, used to obtain the riding preference information of different passengers corresponding to the current vehicle; and to perform reinforcement learning on the driving model based on the riding preference information of different passengers to obtain an updated driving model matched with different passengers.

[0199] Optionally, in one embodiment, the vehicle control device provided in this application further includes a passenger determination module for determining the current passenger of the current vehicle;

[0200] The parameter acquisition module 330 is also used to acquire the target response parameters corresponding to the current driving operation by means of an updated driving model that corresponds to the target vehicle and matches the current passenger.

[0201] Optionally, in one embodiment, the vehicle control device provided in this application further includes a trend acquisition module, used to acquire the current degree of motion sickness of the current passenger, and acquire the trend of the change in the current degree of motion sickness of the current passenger based on the current degree of motion sickness;

[0202] The operation response module 340 is used to update the target response parameters according to the trend of motion sickness, and obtain the updated target response parameters; and to control the current vehicle to respond to the current driving operation according to the updated target response parameters.

[0203] Optionally, in one embodiment, the vehicle control device provided in this application further includes a first prompting module, which, if the current level of motion sickness reaches a threshold, is used to output soothing prompts to the current passenger on how to alleviate the level of motion sickness.

[0204] Optionally, in one embodiment, the vehicle control device provided in this application further includes a second prompting module, used to obtain the current driving feedback of the current vehicle in response to the current driving operation; based on the current driving feedback, predict the probability of the current driving operation causing an increase in the current passenger's degree of motion sickness through a motion sickness risk prediction model matched with the current passenger; and if the increase probability reaches a probability threshold, generate operation prompt information based on the current driving operation and output the operation prompt information to the current driver.

[0205] Optionally, in one embodiment, the vehicle control device provided in this application further includes an environment setting module, used to obtain a first air environment setting parameter and a first setting priority corresponding to the current driver; obtain a second air environment setting parameter and a second setting priority corresponding to the current passenger; determine a target air environment setting parameter based on the first air environment setting parameter, the second air environment setting parameter, the first setting priority and the second setting priority; and set the in-vehicle air environment of the current vehicle according to the target air environment setting parameter.

[0206] Optionally, in one embodiment, the environment setting module is used to: if the first setting priority and the second setting priority are different, determine the air environment setting parameter corresponding to the one with the higher setting priority between the current passenger and the current driver as the target air environment setting parameter; or, if the first setting priority and the second setting priority are the same, merge the first air environment setting parameter and the second air environment setting parameter to obtain the target air environment setting parameter.

[0207] Optionally, in one embodiment, the target vehicle is a fuel-powered vehicle and the current vehicle is an electric vehicle. The vehicle control device provided in this application further includes a sound simulation module, which is used to generate a sound audio corresponding to the current driving operation through a sound synthesis model matched with the target vehicle; and to play the sound audio while controlling the current vehicle to respond to the current driving operation according to the target response parameters.

[0208] Optionally, in one embodiment, the vehicle control device provided in this application further includes a cabin noise reduction module, used to acquire the cabin noise audio of the current vehicle cabin; filter the cabin noise audio according to the sound wave audio to obtain the filtered noise audio; and generate a noise reduction frequency with the opposite phase to the filtered noise audio and play the noise reduction frequency.

[0209] Optionally, in one embodiment, the sound wave simulation module is further configured to acquire vibration control parameters corresponding to the sound wave audio; and to control the seat vibration of the current vehicle according to the vibration control parameters during the playback of the sound wave audio.

[0210] For details on the implementation of each of the above modules, please refer to the previous examples, which will not be repeated here.

[0211] This application also provides an electronic device, including a memory and a processor, wherein the processor executes the steps in the vehicle control method provided in the above embodiments by calling a computer program stored in the memory.

[0212] Please refer to Figure 4 , Figure 4 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application.

[0213] The electronic device may include components such as a processor 101 with one or more processing cores, a memory 102 with one or more computer-readable storage media, a power supply 103, and an input unit 104. Those skilled in the art will understand that... Figure 4 The electronic device structure shown does not constitute a limitation on the electronic device and may include more or fewer components than shown, or combine certain components, or have different component arrangements. Wherein:

[0214] The processor 101 is the control center of the electronic device, connecting various parts of the device via various interfaces and lines. It executes software programs and / or modules stored in the memory 102, and calls data stored in the memory 102, to perform various functions and process data. Optionally, the processor 101 may include one or more processing cores; alternatively, the processor 101 may integrate an application processor and a modem processor, wherein the application processor mainly handles the operating system, user interface, and applications, while the modem processor mainly handles wireless communication. It is understood that the modem processor may not be integrated into the processor 101.

[0215] The memory 102 can be used to store software programs and modules. The processor 101 executes various functional applications and data processing by running the software programs and modules stored in the memory 102. The memory 102 may mainly include a program storage area and a data storage area. The program storage area may store the operating system, application programs required for at least one function (such as sound playback function, image playback function, etc.), etc.; the data storage area may store data created according to the use of the electronic device, etc. In addition, the memory 102 may include high-speed random access memory, and may also include non-volatile memory, such as at least one disk storage device, flash memory device, or other volatile solid-state storage device. Accordingly, the memory 102 may also include a memory controller to provide the processor 101 with access to the memory 102.

[0216] Specifically, in this embodiment, the processor 101 loads one or more executable codes corresponding to computer programs into the memory 102, and the processor 101 executes the steps in the vehicle control method provided in this application, such as:

[0217] Identify the target vehicle for the current vehicle to be simulated driving experience;

[0218] Get the current driving operation received by the current driver in the current vehicle;

[0219] By using a driving model corresponding to the target vehicle, the target response parameters corresponding to the current driving operation are obtained. The driving model is obtained by imitation learning based on the sample driving operation and the sample response parameters. The sample response parameters are converted from the original response parameters of the target vehicle in response to the sample driving operation. The driving feedback of the current vehicle in response to the sample driving operation according to the sample response parameters is similar to the driving feedback of the target vehicle in response to the sample driving operation according to the original response parameters.

[0220] Control the current vehicle to respond to the current driving operation according to the target response parameters.

[0221] It should be noted that the electronic device provided in this application embodiment and the vehicle control method in the above embodiment belong to the same concept. The specific implementation process can be found in the above related embodiments, and will not be repeated here.

[0222] This application also provides a computer-readable storage medium storing a computer program thereon. When the computer program stored thereon is executed on the processor of the electronic device provided in the embodiments of this application, the processor of the electronic device implements the steps in the vehicle control method provided in this application. The storage medium may be a magnetic disk, an optical disk, a read-only memory (ROM), or a random access memory (RAM), etc.

[0223] This application also provides a computer program product, which includes a computer program that, when executed on the processor of the electronic device provided in the embodiments of this application, causes the processor of the electronic device to implement the steps in the vehicle control method provided in this application.

[0224] The vehicle control method, vehicle control device, electronic device, computer-readable storage medium, and computer program product provided in this application have been described in detail above. Specific examples have been used to illustrate the principles and implementation methods of this application. The descriptions of the above embodiments are only for the purpose of helping to understand the method and core ideas of this application. At the same time, for those skilled in the art, there will be changes in the specific implementation methods and application scope based on the ideas of this application. Therefore, the content of this specification should not be construed as a limitation of this application.

[0225] It should be noted that when the above embodiments of this application are applied to specific products or technologies, and user-related data is involved, user permission or consent is required, and the collection, use and processing of related data must comply with the relevant laws, regulations and standards of the relevant countries and regions.

Claims

1. A vehicle control method, characterized in that, include: Identify the target vehicle for the current vehicle to be simulated driving experience; Obtain the current driving operation received by the current driver from the current vehicle; By using a driving model corresponding to the target vehicle, target response parameters corresponding to the current driving operation are obtained. The driving model is obtained by imitation learning based on sample driving operations and sample response parameters. The sample response parameters are converted from the original response parameters of the target vehicle in response to the sample driving operation. The driving feedback of the current vehicle in response to the sample driving operation according to the sample response parameters is similar to the driving feedback of the target vehicle in response to the sample driving operation according to the original response parameters. The vehicle is controlled to respond to the current driving operation according to the target response parameters.

2. The vehicle control method according to claim 1, characterized in that, Before determining the target vehicle for the current vehicle to be simulated driving experience, the process also includes: Obtain the riding preference information of different passengers corresponding to the current vehicle; Based on the riding preference information of different passengers, the driving model is subjected to reinforcement learning to obtain an updated driving model that matches different passengers.

3. The vehicle control method according to claim 2, characterized in that, Before obtaining the target response parameters corresponding to the current driving operation through the driving model corresponding to the target vehicle, the method further includes: Determine the current passengers of the current vehicle; The step of obtaining the target response parameters corresponding to the current driving operation through the driving model corresponding to the target vehicle includes: The target response parameters corresponding to the current driving operation are obtained by updating the driving model that corresponds to the target vehicle and matches the current passenger.

4. The vehicle control method according to claim 3, characterized in that, Before controlling the current vehicle to respond to the current driving operation according to the target response parameters, the method further includes: Obtain the current degree of motion sickness of the current passenger, and obtain the trend of the change in the current degree of motion sickness of the current passenger based on the current degree of motion sickness; The step of controlling the current vehicle to respond to the current driving operation according to the target response parameters includes: The target response parameters are updated based on the trend of change in the degree of dizziness to obtain the updated target response parameters; The vehicle is controlled to respond to the current driving operation according to the updated target response parameters.

5. The vehicle control method according to claim 4, characterized in that, After obtaining the current level of motion sickness of the current passenger, the method further includes: If the current level of motion sickness reaches a threshold, a soothing message is output to the current passenger to suggest how to alleviate the motion sickness.

6. The vehicle control method according to claim 3, characterized in that, After controlling the current vehicle to respond to the current driving operation according to the target response parameters, the method further includes: Obtain the current driving feedback of the current vehicle in response to the current driving operation; Based on the current driving feedback, the probability of the current driving operation causing an increase in the current passenger's degree of motion sickness is predicted using a motion sickness risk prediction model matched with the current passenger. If the increased probability reaches a probability threshold, then an operation prompt message is generated based on the current driving operation, and the operation prompt message is output to the current driver.

7. The vehicle control method according to claim 3, characterized in that, Also includes: Obtain the first air environment setting parameters and the first setting priority corresponding to the current driver; Obtain the second air environment setting parameters and the second setting priority corresponding to the current passenger; The target air environment setting parameters are determined based on the first air environment setting parameters, the second air environment setting parameters, the first setting priority, and the second setting priority. Set the in-vehicle air environment of the current vehicle according to the target air environment setting parameters.

8. The vehicle control method according to claim 7, characterized in that, Based on the first air environment setting parameters, the second air environment setting parameters, the first setting priority, and the second setting priority, the target air environment setting parameters are determined, including: If the first setting priority and the second setting priority are different, then the air environment setting parameter corresponding to the one with the higher setting priority between the current passenger and the current driver is determined as the target air environment setting parameter; or, If the first setting priority and the second setting priority are the same, then the first air environment setting parameter and the second air environment setting parameter are merged to obtain the target air environment setting parameter.

9. The vehicle control method according to claim 1, characterized in that, The target vehicle is a gasoline-powered vehicle, the current vehicle is an electric vehicle, and the vehicle control method further includes: By using a sound synthesis model matched with the target vehicle, a sound audio corresponding to the current driving operation is generated; During the process of controlling the current vehicle to respond to the current driving operation according to the target response parameters, the sound audio is played.

10. The vehicle control method according to claim 9, characterized in that, Also includes: Acquire the cabin noise audio of the current vehicle's cabin; The cabin noise audio is filtered based on the sound wave audio to obtain the filtered noise audio. Generate a noise-reduced frequency that is out of phase with the filtered noise audio, and play the noise-reduced frequency.

11. The vehicle control method according to claim 9, characterized in that, Also includes: Obtain the vibration control parameters corresponding to the sound wave audio; During the playback of the sound audio, the vibration of the vehicle seat is controlled according to the vibration control parameters.

12. A vehicle control device, characterized in that, include: The vehicle determination module is used to determine the target vehicle for the current vehicle to be simulated driving experience; An operation receiving module is used to acquire the current driving operation received by the current driver from the current vehicle. The parameter acquisition module is used to acquire the target response parameters corresponding to the current driving operation through the driving model corresponding to the target vehicle. The driving model is obtained by imitation learning based on the sample driving operation and the sample response parameters. The sample response parameters are converted from the original response parameters of the target vehicle in response to the sample driving operation. The driving feedback of the current vehicle in response to the sample driving operation according to the sample response parameters is similar to the driving feedback of the target vehicle in response to the sample driving operation according to the original response parameters. An operation response module is used to control the current vehicle to respond to the current driving operation according to the target response parameters.

13. An electronic device, characterized in that, The system includes a memory and a processor, the memory storing a computer program, and the processor executing the computer program in the memory to implement the steps of the vehicle control method according to any one of claims 1 to 11.

14. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program adapted for execution by a processor to implement the steps of the vehicle control method according to any one of claims 1 to 11.

15. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by the processor, it implements the steps of the vehicle control method according to any one of claims 1 to 11.

Images