Vehicle simulation method and system

Abstract

A simulation method for an electric vehicle (EV) includes creating a simulation model associating a plurality of target behaviors of a target vehicle with the EV (402); obtaining a plurality of vehicle parameters (412) of the EV to generate a set of EV control parameters (430); obtaining a plurality of configuration parameters of the target vehicle (414); providing a set of simulated target vehicle controls using a simulation model (402) based on the set of EV control parameters (430) and a plurality of configuration parameters (414) of the target vehicle, where the simulation model (402) is a neural network trained to reflect a relationship between the set of EV control parameters (430) and the set of simulated target vehicle controls; and outputting the set of simulated target vehicle controls to the EV such that the EV is controlled to achieve the plurality of target behaviors of the target vehicle based on the set of simulated target vehicle controls.

Description

Technical Field

[0001] The present disclosure relates to the technical field of electric vehicles (EVs), and more particularly to a vehicle simulation method and system for simulating the target behavior of a target vehicle on an electric vehicle. Background Art

[0002] Electric vehicles behave differently compared to internal combustion engine (ICE) vehicles. For example, unlike ICE vehicles, EVs do not need to keep the engine speed within a limited range. Therefore, EVs do not have the sawtooth torque-speed curve of ICE vehicles. Also, although the driver of an EV may enjoy the quietness and rapid acceleration of the electric motor, the driver may lose the pleasure of hearing the sound of the fuel engine and feeling the vibration generated when the fuel engine roars. Therefore, there are different driving experiences for the drivers of EVs and ICE vehicles, and these differences may cause the drivers of more traditional vehicles to give up purchasing EVs. The methods and systems disclosed in the present invention are aimed at solving one or more of the above-mentioned problems and other problems. Summary of the Invention

[0003] One aspect of the present disclosure provides a simulation method for an electric vehicle (EV). The method may include: creating a simulation model that associates multiple target behaviors of a target vehicle with the EV; obtaining multiple vehicle parameters of the EV to generate a set of EV control parameters; obtaining multiple configuration parameters of the target vehicle; based on the set of EV control parameters and the multiple configuration parameters of the target vehicle, using the simulation model to provide a set of simulated target vehicle controls, where the simulation model is a neural network trained to reflect the relationship between the set of EV control parameters and the set of simulated target vehicle controls; and outputting the set of simulated target vehicle controls to the EV such that the EV is controlled based on the set of simulated target vehicle controls to achieve the multiple target behaviors of the target vehicle.

[0004] Another aspect of the present disclosure provides a simulation system for an electric vehicle (EV). The simulation system may include multiple input devices that provide multiple vehicle parameters, a memory containing program instructions, and a processor coupled to the memory and the multiple input devices. When the program instructions are executed, the processor is configured to: create a simulation model that associates multiple target behaviors of a target vehicle with the EV; obtain multiple vehicle parameters of the EV to generate a set of EV control parameters; obtain multiple configuration parameters of the target vehicle; based on the set of EV control parameters and the multiple configuration parameters of the target vehicle, using the simulation model to provide a set of simulated target vehicle controls, where the simulation model is a neural network trained to reflect the relationship between the set of EV control parameters and the set of simulated target vehicle controls; and output the set of simulated target vehicle controls to the EV such that the EV is controlled based on the set of simulated target vehicle controls to achieve the multiple target behaviors of the target vehicle.

[0005] Another aspect of the present disclosure provides an electric vehicle (EV). The EV may include: a battery pack for supplying power to the EV; a set of wheels; at least one electric motor coupled to the battery pack for supplying driving power to the set of wheels to drive the EV; and an on-vehicle computer system for performing the following operations: creating a simulation model that associates multiple target behaviors of a target vehicle with the EV; obtaining multiple vehicle parameters of the EV to generate a set of EV control parameters; obtaining multiple configuration parameters of the target vehicle; based on the set of EV control parameters and the multiple configuration parameters of the target vehicle, using the simulation model to provide a set of simulated target vehicle controls, where the simulation model is a neural network trained to reflect the relationship between the set of EV control parameters and the set of simulated target vehicle controls; and outputting the set of simulated target vehicle controls to the EV such that the EV is controlled based on the set of simulated target vehicle controls to achieve the multiple target behaviors of the target vehicle.

[0006] Those skilled in the art can understand other aspects of the present disclosure according to the description, claims, and drawings of the present disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0007] To more clearly illustrate the technical solutions in the embodiments of the present disclosure, the drawings used in the description of the disclosed embodiments will be briefly described below. Those of ordinary skill in the art can obtain other drawings from these drawings without creative efforts, so these other drawings are also included in the present disclosure.

[0008] Figure 1 An exemplary operating environment incorporating certain embodiments of the present disclosure is shown;

[0009] Figure 2 A block diagram of an exemplary electric vehicle (EV) according to an embodiment of the present disclosure is shown;

[0010] Figure 3A A block diagram of an exemplary on-vehicle computer system according to an embodiment of the present disclosure is shown;

[0011] Figure 3B A block diagram of an exemplary computer system according to an embodiment of the present disclosure is shown;

[0012] Figure 4 A block diagram of an exemplary simulation system for an EV according to an embodiment of the present disclosure is shown;

[0013] Figure 5A A block diagram of an exemplary simulator model according to an embodiment of the present disclosure is shown;

[0014] Figure 5BA block diagram showing an exemplary target feature according to an embodiment of the present disclosure;

[0015] Figure 5C A block diagram showing an exemplary driver feature according to an embodiment of the present disclosure;

[0016] Figure 6 A flowchart showing an exemplary simulation method for an EV according to an embodiment of the present disclosure;

[0017] Figure 7 A flowchart showing an exemplary method for training a simulation model according to an embodiment of the present disclosure;

[0018] Figure 8 A flowchart showing another exemplary method for training a simulation model according to an embodiment of the present disclosure;

[0019] Figure 9A Showing an exemplary simulator model trained according to an embodiment of the present disclosure;

[0020] Figure 9B Showing the calculation of the forward cycle consistency loss according to an embodiment of the present disclosure;

[0021] Figure 9C Showing the calculation of the backward cycle consistency loss according to an embodiment of the present disclosure;

[0022] Figure 10 A flowchart showing an exemplary method for mining trip data of a training data set according to an embodiment of the present disclosure;

[0023] Figure 11 Showing an exemplary heat map according to an embodiment of the present disclosure; and

[0024] Figure 12 A flowchart showing the discovery of a new data domain according to an embodiment of the present disclosure. DETAILED DESCRIPTION

[0025] The technical solutions of the present disclosure will be described below with reference to the accompanying drawings. It should be understood that these embodiments are provided to enable a more thorough understanding of the present disclosure and to fully convey the scope of the present disclosure to those skilled in the art. The present disclosure can be implemented in various forms and should not be limited by the embodiments set forth herein.

[0026] In an embodiment of the present disclosure, a statement such as "A and B are connected" may include the case where A and B are connected to each other and in contact with each other, or may include the case where A and B are connected by another component and not in direct contact with each other. In addition, terms such as "first" and "second" are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence.

[0027] For most consumers, an electric vehicle (EV) generally provides a new driving experience for the driver of the EV. Some drivers may find the EV driving experience interesting and exciting, while some other drivers may miss the driving experience of more traditional vehicles, especially those high-performance internal combustion engine (ICE) vehicles, such as Mercedes-AMG series vehicles. Thus, for an EV with sufficient capabilities, an on-vehicle simulation method can be provided for the EV to simulate certain ICE vehicle characteristics to enhance the driving experience of the EV. That is, according to the present disclosure, an electric vehicle (EV) can be provided with an on-vehicle simulation system for simulating certain characteristics of a target vehicle. Figure 1 An exemplary operating environment incorporating certain embodiments of the present disclosure is shown.

[0028] As Figure 1 shown, the operating environment 100 can include an EV 110, a driver / user 120, a user terminal 130, a cloud server 140, and a communication network 150. Any number of EVs, users, user terminals, servers, and / or communication networks can be included, and other components can also be included. The EV 110 can include any vehicle operating on battery power, such as a pure electric or hybrid electric vehicle, including cars, aerial vehicles, or water vehicles, etc. For example, the EV 110 can include a battery pack for supplying power to the EV 110, a set of wheels, at least one electric motor coupled to the battery pack to provide driving power to the set of wheels to drive the EV 110, a wireless communication device for connecting to the cloud server and / or a mobile device carried by the driver of the EV 110, and an on-vehicle computer system for performing simulation of the target vehicle on the EV 110. The wireless communication device also provides a wireless connection to the Internet for synchronizing features and reporting errors and logs. The driver 120 may be driving the EV 110, which may be owned by the driver 120, or may be owned by someone else and only driven by the driver 120. The user terminal 130 can include any portable user device, such as a smart phone, a personal digital assistant (PDA), a laptop computer, a notebook computer, or a combination of vehicle equipment and user devices, such as Apple Car Play, etc. Any portable device can be included as the user terminal 130. In addition, the user terminal 130 can be carried or owned by the driver 120, or can be placed in the EV 110 or be part of the EV.

[0029] In addition, the communication network 150 can include any type of communication network, such as a wired and / or wireless network, to connect the EV 110 and / or the user terminal 130 to the Internet or the cloud server 140. The cloud server 140 can be provided by a commercial entity for managing, monitoring, maintaining, or servicing the EV 110, such as a dealer or a vehicle manufacturer, or a service provider for EV-related services. The cloud server 140 can store certain data required for simulation and can perform calculations transferred from the EV 110.

[0030] Figure 2 A block diagram of an exemplary electric vehicle (EV) according to an embodiment of the present disclosure is shown. As Figure 2 shown, the electric vehicle 110 can include various subsystems or components. Specifically, the EV 110 can include a plurality of wheels 240, an electric motor 222, an accelerator pedal 208, a brake pedal 206, a differential 238, a battery pack 216, an on-vehicle computer system 230, a motor controller 218, a steering wheel 228, a driver's seat 226, a dashboard 232, a sound system 234, and an actuator 236. The EV 110 can also include a charger 202, a converter 214, a 12V battery 204, sensors 210, a wireless transceiver 212, an antenna 242, a transmission 224, and an inverter 220, etc. Any number of these subsystems or components can be included, certain components can be removed, and other components can be included.

[0031] The on-vehicle computer system 230 can control various components of the EV 110. The charger 202 can charge the battery pack 216 through the converter 214 to convert an alternating current (AC) or direct current (DC) input into an appropriate charging power source. The charger 202 can be an on-vehicle charger of the EV 110. The on-vehicle charger can be a level 1 charger that receives a 120VAC output from a wall socket. The EV 110 / battery pack 216 can also be charged by an external level 2 or level 3 charger, which can use a high-voltage AC power source to charge the battery pack 216 faster than the on-vehicle charger.

[0032] In some embodiments, the battery pack 216 can include a battery thermal management system to heat the battery pack 216 when the temperature of the battery pack 216 is below a predefined low-temperature threshold, or to cool the battery pack 216 when the temperature of the battery pack 216 is above a predefined high-temperature threshold. The battery pack 216 operates more efficiently when the temperature of the battery pack 216 is within a range between the predefined low-temperature threshold and the predefined high-temperature threshold.

[0033] The output of the battery pack 216 can be fed to the motor controller 218 to control the electric motor 222. The output of the battery pack 216 can pass through the inverter 220. The inverter 220 can regulate the voltage of the battery pack 216 to a voltage suitable for driving the electric motor 222. The output of the electric motor 222 can pass through the transmission 224 and the differential 238 to drive the wheels 240.

[0034] In addition, the electric motor 222 can include a stator and a rotor ( Figure 2 not shown in the figure). The stator is the stationary housing of the electric motor 222 that is mounted to the chassis of the EV 110. The rotor is the rotating element and feeds torque to the transmission 224 of the EV 110. The transmission 224 of the EV 110 regulates the rotational speed of the rotor before using the torque of the rotor to drive the differential 238 of the EV 110. The differential 238 of the EV 110 distributes the torque to the wheels 240 according to a specific ratio suitable for the driving condition.

[0035] The EV 110 can include more than one electric motor 222. For example, the EV 110 can include two electric motors 222. One electric motor 222 drives the two front wheels 240 and the other electric motor 222 drives the two rear wheels 240. In another example, the EV 110 can include four electric motors 222. The four electric motors 222 respectively drive each of the four wheels 240. When each wheel 240 is directly driven by one electric motor 222, the differential 238 can be removed. Tires (not shown) can be mounted on each wheel 240.

[0036] In addition, an accelerator pedal 208 and a brake pedal 206 can be provided and arranged to accelerate and decelerate the EV 110. Sensors 210 and actuators 236 can be provided to facilitate acceleration and deceleration. For example, the sensors 210 can detect the positions of the accelerator pedal 208 and the brake pedal 206 and make their positions available to the on-vehicle computer system 230. The on-vehicle computer system 230 controls the electric motor 222 based on the positions of the accelerator pedal 208 and the brake pedal 206 through the motor controller 218 and the inverter 220. The actuators 236 can be controlled by the on-vehicle computer system 230 to dynamically adjust the suspension of the EV 110 based on the condition of the EV 110. In some embodiments, the actuators 236 can be controlled by the on-vehicle computer system 230 to adjust the stiffness of the accelerator pedal 208 and the brake pedal 206.

[0037] The EV 110 can also use the sound system 234 and the dashboard 232 to provide certain vehicle interactions to the driver 120. For example, in addition to playing music and radio channels, the sound system 234 can be controlled by the on-vehicle computer system 230 to simulate engine sounds. The dashboard 232 can be controlled by the on-vehicle computer system 230 to display certain information to the driver 120, including an image of the dashboard of another vehicle.

[0038] The 12V battery 204 can be used to provide auxiliary power to various components of the EV 110, such as the on-vehicle computer system 230, the dashboard 232, the sound system 234, the sensors 210, the actuators 236, the wireless transceiver 212, and other control circuits.

[0039] The wireless transceiver 212 can be connected to the antenna 242. The wireless transceiver 212 can facilitate Figure 1 the communication between the on-vehicle computer system 230 shown and the cloud server 140 and the user terminal 130. The wireless transceiver 212 can include a cellular communication transceiver that supports 3G / 4G / 5G cellular communication to communicate with the cloud server 140, and include a Bluetooth / Wi-Fi transceiver to communicate with the user terminal 130. Other wireless communication formats can also be used.

[0040] The EV 110 can provide a steering wheel 228 and a driver's seat 226 to an individual (e.g., the driver 120 or another passenger in the EV) for driving the EV 110. For example, the driver 120 of the EV 110 sits in the driver's seat 226 and uses the steering wheel 228 to maneuver the driving direction of the EV 110. In one embodiment, speakers (not shown) can be placed under the driver's seat 226 to play simulated engine sounds to the individual, or play low-frequency sounds to simulate the vibration caused by a gasoline engine. The EV 110 can also include a Global Positioning System (GPS) device (not shown) to detect the current position of the EV 110.

[0041] The current position can be used to determine local traffic / safety rules and regulations. The local traffic / safety rules and regulations are used to perform a safety check on controlling the EV 110.

[0042] In operation, the on-vehicle computer system 230 can obtain multiple configuration parameters from one or more of the memory storage device of the on-vehicle computer system, the cloud server, and the mobile device carried by the driver of the EV 110. The on-vehicle computer system 230 can perform various control functions for the EV 110, and can also perform a simulation process to simulate certain vehicle behaviors of another vehicle. When performing the simulation process, the on-vehicle computer system can transfer some or all of the simulation process to the cloud server to limit the energy consumption at the EV 110. Figure 3AA block diagram of an exemplary in-vehicle computer system according to an embodiment of the present disclosure is shown. As Figure 3A shown, the computer system 300 / in-vehicle computer system 230 may include a processor 304, a memory 302, a display screen 306, a microphone / speaker 308, an interface 310, sensors 312, actuators 314, a camera 316, etc. The computer system 300 may be Figure 2 the in-vehicle computer system 230 shown. Certain devices may be omitted and other devices may be included.

[0043] The memory 302 may store program instructions. The program instructions, when executed by the processor 304, perform an in-vehicle simulation method for the EV 110. In some embodiments, the memory 302 may include dynamic random access memory (DRAM), embedded multimedia controller (e.MMC), low-power DRAM (LPDRAM), NOR flash memory, single-level cell (SLC) NAND flash memory, solid-state drive (SSD), universal flash storage (UFS) device, or a combination thereof.

[0044] In some embodiments, the processor 304 may be one or more hardware processors, microprocessors, and microcontrollers distributed across various parts of the EV. For example, the processor 304 may include a vehicle network processor dedicated to in-vehicle networks, a vision processor dedicated to vision processing, a radar processor dedicated to radar processing, a processor for engine control, a graphics processing unit (GPU) for dashboard rendering, an audio digital signal processor (DSP) for audio processing, a communication processor for supporting wireless communications such as 5G mobile, an artificial intelligence processor for implementing neural networks, or a combination thereof. In some embodiments, some of the above computing tasks may be transferred to a cloud server to maintain the computing power available for EV operation. Therefore, the cloud server will return the result to the EV when the computing task transferred from the EV 100 is completed.

[0045] The computer system 300 may also include a display screen 306 and a microphone / speaker 308 to interact with the user 120 of the computer system 300. The display screen 306 is part of a human-machine interface (HMI) to facilitate the interaction between the driver 120 and the computer system 300. The HMI may include an infotainment system and an instrument cluster. The display screen 306 may include any suitable type of computer display device or electronic device display. For example, the display screen 306 may include an LCD display device, an OLED display device, or a combination thereof. The display screen 306 may be a touch display screen. The display screen 306 may include a gesture sensor for gestures of the hands of individuals (e.g., the driver 120, the passenger) in front of the display screen 306. The display screen 306 may also include a tactile driver to provide tactile feedback. The display screen 306 may also include a head-up display (HUD) to provide information to the driver 120 at eye level. The display screen 306 may include a transparent window display that projects an image onto a transparent film sandwiched or laminated in the window of the EV 110 using a projector mounted inside the EV 110. The microphone / speaker 308 allows individuals to interact with the computer system 300 using voice commands. The microphone / speaker 308 may include an active noise cancellation function. The computer system 300 may also include other peripheral devices for interacting with individuals.

[0046] The computer system 300 may use an interface 310 to connect various accessories, such as sensors 312, actuators 314, and cameras 316. The interface 310 may include a vehicle interface processor (VIP). The sensors 312 and actuators 314 may be Figure 2 the sensors 210 and actuators 236 shown in. The computer system 300 may include an internal bus to connect the memory 302, the processor 304, the display screen 306, the microphone / speaker 308, and the interface 310 together. The interface 310 may be connected to the sensors 312, the actuators 314, and the cameras 316 via the internal bus. For example, the internal bus may be a controller area network (CAN) bus, a FlexRay bus, a media-oriented system transport (MOST) bus, an automotive Ethernet bus, a local interconnect network (LIN) bus, or a combination thereof. The internal bus may also be used to connect Figure 3A other accessories not shown in.

[0047] Return Figure 1 , in operation, the user terminal 130 and / or the cloud server 140 may interact with the EV 110 or the in-vehicle computer system 230 via the communication network 150 to perform certain user or server processes. Figure 3B A block diagram of an exemplary computer system according to an embodiment of the present disclosure is shown. The computer system 350 may be Figure 1 the cloud server 140 shown in.

[0048] As shown Figure 3B in FIG. 350, a computer system 350 may include a memory 352, a processor 354, a communication interface 358, input / output devices 360, a data storage device 362, etc. Other devices may also be included. The processor 354 may include any suitable one or more hardware processors. In addition, the processor 354 may include multiple cores for multi-threading or parallel processing, and may include graphics capabilities for processing of a human-machine interface (HMI) (i.e., an example of the input / output device 360). The memory 352 may include any suitable memory modules, such as ROM, RAM, flash memory modules, and erasable and rewritable memories, as well as mass storage, such as CD-ROMs, DVDs, USB flash drives, and hard disks, etc. The memory 352 may store computer program instructions or program modules for implementing various processes, which, when executed by the processor 354, are used to perform the interaction with the in-vehicle computer system 230 on the EV 110.

[0049] In addition, the computer system 350 may further include a display. The display may be any suitable display technology suitable for displaying images or videos. For example, the display may include a liquid crystal display (LCD) screen, an organic light-emitting diode (OLED) screen, etc., and may be a touch screen. The communication interface 358 may include certain network interface devices for establishing connections through a communication network. The input / output devices 360 may include any suitable input devices for inputting information to the processor 354 and / or output devices for outputting information from the processor 354, such as keypads, keyboards, and mouse devices, cameras, microphones, and other sensors, etc. In addition, the data storage device 362 may include one or more data storage devices for storing certain data and for performing certain operations on the stored data, such as database searches, model training, etc. Due to the limited memory size of the in-vehicle computer system 230, the data required for simulation may be stored in the data storage device 362. When needed, the data for simulation may be downloaded by the in-vehicle computer system 230 from the data storage device 362. In addition, local regulations and / or rules may prevent data from leaving the EV 110 without certain restrictions. The data may be tokenized, encrypted, and sanitized before being sent to the cloud server 140. Personal identifiable information needs to be protected whether it is stored in the in-vehicle computer system 230 or sent to the cloud server 140. In any case, data handling needs to be consistent with the driver's consent or the service agreement signed by the driver. In some embodiments, local regulations and / or rules may limit the data collected by the EV and the data leaving the EV. The data collected by the EV and the data leaving the EV may be tokenized, encrypted, and sanitized to ensure proper handling of personally identifiable information (PII) data. The data collected by the EV and the data leaving the EV are handled, used, and stored according to the driver's consent and preferences.

[0050] Return Figure 1 In operation, the EV 110 can be driven by the driver 120. After the driver 120 enters the EV 110, the driver 120 can interact with the in-vehicle computer system 230 of the EV 110 to provide inputs to the in-vehicle computer system 230, such that the in-vehicle computer system 230 can execute a simulation process to simulate certain vehicle behaviors, actions, and / or characteristics of a target vehicle on the EV 110. The inputs can include user information and / or configuration information. As used herein, the term "simulation" can refer to the process of obtaining static and / or dynamic parameters of the EV 110 to achieve certain vehicle behaviors, actions, and / or characteristics of a target vehicle on the EV 110 and safely controlling the EV 110 to achieve certain vehicle behaviors, actions, and / or characteristics of the target vehicle.

[0051] For example, the target behaviors of a target vehicle can include vehicle handling characteristics, gear shifting, dynamic engine sounds and vibrations transmitted to the driver's seat, a simulated instrument panel of the target vehicle, and combinations thereof. Vehicle handling characteristics can reflect how a vehicle responds and reacts to driver inputs of the vehicle and at least include the weight distribution of the vehicle and the cornering stiffness of the vehicle tires. The weight distribution of the vehicle can include the height of the center of mass, the center of mass, roll moment of inertia, and yaw and pitch moment of inertia. Other factors contributing to vehicle handling characteristics include the stiffness of the vehicle frame, electronic stability control, steering accuracy, power transfer to the wheels, braking effect, vehicle body aerodynamics, and spring stiffness of the vehicle suspension, etc.

[0052] In an internal combustion engine (ICE) vehicle, gasoline is burned to cause mechanical movement to move the ICE vehicle, and gear shifting is used to adapt the vehicle transmission to various vehicle speeds. Gear shifting in an ICE vehicle causes a sudden change in torque. Different from an ICE vehicle, an EV uses one or more electric motors to drive the wheels of the EV. The one or more electric motors can be electronically controlled to drive the wheels of the EV at various vehicle speeds without the need for gear shifting. Reconstructing the gear shifting that results in a sudden change in torque is one aspect of the behavior simulation of a target vehicle.

[0053] In addition, in operation, the fuel engine of an ICE vehicle generates a large noise and causes the ICE vehicle to vibrate. On the other hand, the one or more electric motors of an EV do not generate a large noise and do not cause the EV to vibrate. To simulate the behavior of a target vehicle, the EV may need to reconstruct the dynamic engine sounds and vibrations, which may be limited to the space around the driver's seat.

[0054] The target vehicle is not necessarily an ICE vehicle. Different EVs or other types of vehicles can also be the target vehicles to be simulated on the EV 110. On the other hand, different vehicles typically include different dashboards. The simulation of the behavior of the target vehicle can include reconstructing the dashboard of the target vehicle. When the EV can include one or more display screens at a location on the dashboard, the EV controls the one or more display screens to present the dashboard of the target vehicle. For example, when the target vehicle is another EV, the dashboard of the simulator of the other EV can be displayed at the EV, so that the driver 120 can have the feeling of the other EV when looking at the dashboard. In some embodiments, it is necessary to show key information specific to the EV (i.e., remaining battery charge). When the simulation is in operation, the key information can be shown in the original format of the EV or in a different format. Additionally, dashboard customization can be facilitated so that the driver can display certain information (i.e., navigation information) that may not have been on the display of the target vehicle.

[0055] Various other behaviors, actions, and / or characteristics of the target vehicle can be simulated on the EV 110. The simulation process can be implemented as simulation software running on the in-vehicle computer system 230, or a combination of software and hardware implemented by the in-vehicle computer system 230 or running on both the in-vehicle computer system 230 and the cloud server 140, or a combination of software and hardware implemented by the in-vehicle computer system 230 and / or the cloud server 140. That is, the in-vehicle computer system 230 and / or the cloud server 140 can implement a simulation system on the EV 110 to perform the simulation process based on the request of the driver 120. Figure 4 A block diagram of an exemplary simulation system for an EV according to an embodiment of the present disclosure is shown.

[0056] As Figure 4 shown, the simulation system 400 can include a simulator 402, a plurality of input modules 410, a plurality of output modules 420, a plurality of action modules 430, etc. Other modules can also be included. The simulator 402 can include any suitable mathematical model or algorithm to generate certain simulation output parameters based on input parameters. Figure 5A A block diagram of an exemplary simulator model according to an embodiment of the present disclosure is shown.

[0057] As Figure 5AAs shown, the simulator 402 may include a neural network model 500. In this specification, the neural network model 500 is also referred to as a vehicle simulator model. The vehicle simulator model is trained to reflect the relationship between a plurality of vehicle parameters and a plurality of configuration parameters as inputs and one or more control parameters as outputs. Other types of artificial intelligence / machine learning models may also be used. The neural network model 500 may be a deep learning network model or a combination of multiple machine learning models, and may include an input layer 504, intermediate layers 506, 508 (hidden layers), and an output layer 510, etc. When including a convolutional neural network, the hidden layer may further include convolutional layers. In addition, the neural network model 500 may further include a generative adversarial network for desired performance improvement. In addition, an input 502 may be provided to the input layer 504, and an output 512 may be provided by the output layer 510. Each layer may include one or more neural network nodes. The number of neural network layers is for illustrative purposes, and any number of neural network layers may be used. The parameters of the neural network model 500 may be obtained by the in-vehicle computer system 230 and may also be stored / transmitted from the cloud server 140.

[0058] The neural network model 500 may first be trained, for example, by the cloud server 140 to establish the simulator 402. For example, the cloud server 140 may obtain historical data of a target vehicle (e.g., a vehicle of the same type as the target vehicle) and the EV 110 as the values of the input 502 and the output 512 to train the neural network model 500. The cloud server 140 may also obtain vehicle data during operation and data of the driver 120 to train the neural network model 500. For example, the vehicle data may include usage statistics such as simulation duration, location, and activation frequency, and error logs such as cases where the simulator 402 fails to initialize or is deactivated by the safety module shown during operation. Figure 4 In some embodiments, the cloud server 140 may extract only a part of the vehicle data that can be used to train the vehicle simulator model. In this way, the amount of data collected can be reduced to conserve energy at the EV and minimize the use of the communication network. In some embodiments, since local regulations and rules may restrict which data are allowed to leave the EV, the data extraction performed by the cloud server 140 may be restricted or may require prior consent from a person with EV permissions (e.g., the owner).

[0059] For example, in some embodiments, the input 502 may include multiple vehicle parameters of the EV, including the operating time parameter of the EV. The operating time parameter of the EV may be a parameter that describes or affects the operating time behavior of the vehicle, where the operating time behavior may refer to the vehicle being driven. For example, the operating time parameter of the EV at least includes steering wheel position, vehicle weight distribution, road surface condition, impact distribution, braking position, torque vector, and battery availability; and the output 512 may include one or more control parameters, including target turning angle, target steering ratio, target weight distribution, and target wheelbase. The input 502 may also include the driving condition of the EV. For example, the driving condition of the EV at least includes position, data from rain / fog sensors, and camera feeds for understanding the terrain. The input 502 may also include local regulations and rules.

[0060] In another embodiment, the input 502 may include multiple vehicle parameters of the EV, including accelerator pedal position, steering wheel position, road surface condition, observed traction, available power, motor temperature, battery temperature, gyroscope measurements, accelerator measurements, suspension position, throttle position, braking position, and regeneration settings; and the output 512 may include one or more control parameters, including target acceleration or deceleration, target drive wheels, target traction settings, and target handling characteristics.

[0061] In another embodiment, the input 502 may include multiple vehicle parameters of the EV, including accelerator pedal position and window position; and the output 512 may include one or more control parameters, including the target engine sound at least on the driver side of the EV 110. All appropriate input parameters and output parameters may be used.

[0062] After training the neural network model 500, the neural network model 500 may be loaded into the in-vehicle computer system 230 of the EV 110, for example, by retrieving it from the cloud server 140 via the communication network 150 or by locally storing the model data on the EV 110.

[0063] Return Figure 4 , the multiple input modules 410 may include several modules configured to provide input parameters based on specific types of input parameters. Specifically, the multiple input modules 410 may include a vehicle input module 412, a configuration module 414, and a safety module 416. Other modules may also be included.

[0064] The vehicle input module 412 may provide input parameters related to the vehicle itself (i.e., the EV 110 or the host vehicle). That is, the vehicle input module 412 may provide the values of multiple vehicle parameters of the EV 110. The multiple vehicle parameters may include torque parameters, weight distribution, steering parameters, acceleration and deceleration parameters, and suspension parameters.

[0065] Torque (pound - feet or Newton - meters) is the amount of traction power generated by the electric motor 222 when the driver 120 of the EV 110 depresses the accelerator pedal 208. Horsepower refers to the power generated by the electric motor 222. Weight distribution is the amount of the total vehicle weight applied to the ground at an axle, a set of axles, or an individual wheel. Weight distribution affects how quickly the vehicle accelerates and decelerates and how the vehicle maneuvers when turning. This is because of the weight transfer that occurs when the vehicle is moving, which affects the level of tire grip.

[0066] Steering parameters include steering wheel position, brake pedal position, impact position, vehicle weight distribution, torque vector, road surface condition, battery availability, or a combination thereof. Acceleration and deceleration parameters include steering position, road surface condition, observed traction, available power, motor temperature, battery pack temperature, gyroscopic measurements, accelerator measurements, suspension position, throttle position, brake pedal position, regeneration settings, or a combination thereof. Some parameters may appear in more than one of the steering parameters, acceleration and deceleration parameters, and suspension parameters. Other parameters may also be included. Additionally, the vehicle input module 412 may provide vehicle parameters in real - time during operation. Alternatively, the vehicle input module 412 may provide stored vehicle parameters. Some vehicle parameters change dynamically and can be obtained from sensors of the EV 110. Some other vehicle parameters are static and can be obtained from the EV data storage device at the cloud server. Thus, the in - vehicle computer system 230 can obtain multiple vehicle parameters of the EV 110 locally and / or remotely from the cloud server.

[0067] Furthermore, the configuration module 414 may provide input parameters related to the simulated configuration (i.e., the behavior of the target vehicle). That is, the configuration module 414 may provide values of multiple target vehicle parameters and / or information about the driver, i.e., configuration parameters. The multiple configuration parameters at least include information about the target vehicle and the settings of the target vehicle for the driver. For example, the configuration module 414 may obtain the target characteristics of the target vehicle and / or the driver characteristics of the driver of the EV 110 and determine the configuration parameters for the simulation. Other information may also be included.

[0068] The target characteristics may include information for configuring the simulation. Figure 5B A block diagram of exemplary target characteristics according to an embodiment of the present disclosure is shown. As Figure 5B shown, the target characteristics 550 may include vehicle make 552, vehicle model 554, vehicle behavior list 556, primary vehicle requirements 558, simulator information 560, driver information 562, and other information 564. Certain information items may be omitted, and other information items may be added.

[0069] The vehicle brand 552 can indicate the brand of the target vehicle, and the vehicle model 554 can indicate the model of the target vehicle. The vehicle behavior list 556 can indicate one or more vehicle behaviors or parameters to be simulated. For example, the target characteristics of the target vehicle can include the horsepower / torque curve, suspension stiffness / type / programming, steering ratio, wheelbase, vehicle type, speed-fuel consumption curve, dashboard data, control weight for steering, accelerator pedal feel, and brake pedal feel, braking map, or a combination thereof.

[0070] For an ICE vehicle, torque is equal to horsepower multiplied by a constant (e.g., 5,252) divided by the rotational speed (revolutions per minute or (RPM)). Due to gear shifting, the torque curve over time for an ICE vehicle looks like a sawtooth curve. As the driver of the ICE vehicle presses the accelerator pedal of the ICE vehicle, the torque increases over time and then drops sharply when a gear shift occurs. Different from an ICE vehicle, an EV does not need to shift gears but has a torque curve over time that initially rises and remains rising as long as the driver 120 of the EV continues to press the accelerator pedal 208. The EV and the ICE vehicle behave significantly differently in response to the driver's pressing of the accelerator pedal or throttle pedal. The gear shifting behavior of the ICE vehicle is simulated by the on-vehicle computer system 230 of the EV 110 so that the driver 120 of the EV 110 can feel the gear shifting behavior of the ICE vehicle.

[0071] The suspension can include controlling the vertical movement of the wheels of the target vehicle relative to the chassis of the target vehicle or the target body, or a passive suspension provided by a large spring where the vertical movement is entirely determined by the road surface. The active suspension can change the hardness of the shock absorber to match changing road or dynamic conditions, or can use actuators to independently raise and lower the chassis at each wheel. The suspension can be a spring-type suspension, and the suspension stiffness can be referred to as the spring stiffness. The spring stiffness is a component that sets the ride height of the vehicle. When the spring is compressed or stretched, the force it exerts is proportional to its change in length. The spring stiffness is the change in the force it exerts divided by the change in the deflection of the spring. The spring stiffness can be programmed to adapt to the weight of the vehicle. Therefore, it is necessary to simulate the behavior of the suspension of the target vehicle on the EV 110.

[0072] The steering ratio refers to the ratio between the rotation of the steering wheel (in degrees) and the rotation of the wheel (in degrees). A higher steering ratio means that the steering wheel has to rotate more to make the wheel rotate, but it will be easier to turn the steering wheel. A lower steering ratio means that the steering wheel has to rotate less to make the wheel rotate, but it will be more difficult to turn the steering wheel. Therefore, it is necessary to simulate the behavior of the steering wheel of the target vehicle on the EV 110.

[0073] The wheelbase is the horizontal distance between the centers of the front and rear wheels. When the vehicle accelerates, depending on the suspension, the rear of the vehicle typically drops while the front of the vehicle rises. When the vehicle decelerates, depending on the suspension, the rear of the vehicle typically rises while the front of the vehicle drops. The relative rise and fall of the front and rear of the vehicle and the wheelbase together affect the vehicle's weight distribution and the feel of driving the vehicle. Therefore, it is necessary to simulate the behavior of the wheelbase of the target vehicle on the EV 110.

[0074] Vehicle types can include sedan type, GT type, and sport utility vehicle (SUV) type. Vehicle type affects the feel of driving the vehicle and plays a role in simulating the behavior of the target vehicle on the EV 110. A speed - fuel consumption curve is used to estimate the fuel consumption of the target vehicle. When the driver 120 drives the EV 110 operating in simulation mode, the estimated fuel consumption of the target vehicle can be displayed on the dashboard.

[0075] Dashboard data is the data that appears on the dashboard of the target vehicle. Some of the dashboard data of the target vehicle may no longer be applicable to the EV 110 but will still be estimated and presented to the driver 120 on the dashboard of the EV 110 so that the driver 120 of the EV110 feels like driving the target vehicle. The control weight for steering is used in four - wheel steering to improve the agility and stability of turning at various vehicle speeds. When the driver 120 turns the steering wheel at low speed, the front wheels turn in the direction of travel while the rear wheels turn in the opposite direction, effectively reducing the turning radius of the vehicle and making low - speed maneuvering faster and easier. Steering at higher speeds causes both the front and rear wheels to turn in the same direction to increase high - speed stability. This steering behavior of the target vehicle can be simulated on the EV 110. For some ICE characteristics, the four - wheel steering behavior at higher speeds can be disabled. For example, when the speed of the EV exceeds a predetermined speed threshold, the four - wheel steering can be disabled for safety reasons.

[0076] The feel of the accelerator pedal and the feel of the brake pedal vary from vehicle to vehicle. The driver 120 generally remembers the feel of the accelerator pedal and the feel of the brake pedal of the target vehicle. It is necessary to simulate the feel of the accelerator pedal and the feel of the brake pedal of the target vehicle on the EV 110. The braking graph includes the braking distance or the stopping distance. The braking distance is the distance that the vehicle will travel from the point where the brake pedal is fully depressed to the point where the vehicle comes to a complete stop. The braking distance is mainly affected by the vehicle speed and the coefficient of friction between the tires and the road surface. It is necessary to simulate the braking graph of the target vehicle on the EV 110. In addition, for safety reasons, the maximum braking capacity of the EV is always provided in an emergency. Emergencies can include but are not limited to tire blowout, headlight failure, throttle / accelerator stuck, engine stall, impending collision, wildlife on the road, and driving off the road.

[0077] In addition, as Figure 5BAs shown, the host vehicle requirements 558 can indicate one or more requirements of the host vehicle for performing a simulation, such as horsepower, powertrain configuration, etc. The simulator information 560 can indicate specific information about the simulator for simulating the target vehicle, and the driver information 562 can be used to locate target features when the driver identifies features that can be used for searching and locating. The other information 564 can be used for other user or vehicle-specific information.

[0078] In addition, the driver characteristics can include information specific to the driver 120 to facilitate the simulation process. Figure 5C A block diagram of exemplary driver characteristics according to an embodiment of the present disclosure is shown. As Figure 5C shown, the driver characteristics 580 can include driver identification 582, driver personal information 584, driver vehicle information 586, driver account information 588, driver social media information 590, target feature list 592, and other information 594. Certain information items can be omitted and other information items can be added.

[0079] The driver identification 582 can indicate the identification of the driver 120 that can be used to search a database. The driver personal information 584 can include personal information about the driver 120, such as weight, gender, age, address, location, and occupation, etc. The driver vehicle information 586 can include vehicle-specific information of the driver, such as vehicle registration, vehicle garage information, and vehicle usage information, etc. The driver account information 588 can include login information for accessing the cloud server 140, and the driver social media information 590 can include information about the driver's social network presence, such as driver social media access information for sharing the recorded trip data. The recorded trip data can include simulation data, including information about the selected ICE features. The simulation data in the recorded trip data shared by the driver on social media can be used as a training dataset to train the simulation model. The target feature list 592 can include one or more target features that the driver can use or select to perform a simulation, and each target feature can be individually selected by the driver 120 for simulating the behavior of the target vehicle on the EV 110. The other information 594 can contain other application-specific information.

[0080] Return Figure 4, the input module 410 may further include a security module 416. The security module 416 may provide information for performing security checks during the simulation process to ensure that the simulation is secure and compliant with certain rules and regulations. For example, the security module 416 may include range information of configuration parameters, such that the range information can be used to perform security checks on the configuration parameters to ensure that the values of the configuration parameters are within a safe range. The security module 416 may also include range information of output parameters and / or action parameters, such that the range information can be used to perform security checks on the output parameters and / or action parameters to ensure that the values of the output parameters and / or action parameters are within a safe range.

[0081] In addition, the security module 416 may further include regulatory information, such that the regulatory information can be used to perform security checks on the output parameters and / or action parameters to ensure that the values of the output parameters and / or action parameters are compliant with regulations with or without location information. The security module 416 may also include certain system patch or update information, such that the system patch or update information can be used to update or repair the simulator 402 and other modules. The security module 416 may also include main vehicle requirements, such as engine fault codes, overdue maintenance, and low tire pressure. The security module 416 may also include various requirements or other information, such as road terrain, local regulations and / or rules, and weather conditions.

[0082] Furthermore, as Figure 4 shown, the plurality of output modules 420 may include a perception module 422, a target dynamics module 424, a data module 426, etc. Other modules may also be included. The perception module 422 may receive the output parameters of the simulator 402, which are static and / or related to the appearance and feel of the target vehicle, such as dashboard display, lighting display, and the position and posture of the driver's seat and steering wheel, etc. That is, all the data is related to the appearance and feel of the target vehicle, i.e., what the vehicle should sound like, what the vehicle should look like, and what the display should be.

[0083] The target dynamics module 424 may receive the output parameters of the simulator 402, which are dynamic and require certain continuous actions to be performed on the EV 110 to change the driving characteristics of the EV 110. That is, all the data is related to the behavior of the vehicle during operation (such as acceleration or deceleration, etc.). When actions are required to achieve the target behavior, the target dynamics module 424 may provide information to the replay module 432 to cause a change in the vehicle behavior to meet the target characteristics of the driver 120.

[0084] In addition, the data module 426 can record the simulation data from the simulator 402 and store or upload the data to the cloud server 140 to further train the simulation model in the simulator 402. For example, the data module 426 can also record trip data and share the trip data via social media or other networks in a simulated scenario. That is, the driver 120 can use the data module 426 to share the driving data of the virtual vehicle (i.e., the simulated target vehicle) on social media. In some embodiments, heat maps can be introduced to analyze the trip data from the EV to identify / remove noise. After identifying / removing the noise from the trip data from the EV, the trip data can be clustered into one or more domains. Based on one or more domains of the trip data from the EV, patterns and anomalies may be discovered. For example, vehicle simulation models can be created and trained corresponding to certain patterns and anomalies. Thus, additional revenue can be earned by providing pattern-specific and / or anomaly-specific simulation services to customers.

[0085] In addition, as Figure 4 shown, the multiple action modules 430 can include a replay module 432, a vehicle control, display, and sound module 434, a vehicle powertrain module 436, and a vehicle data analysis system 438, etc. Other modules may also be included. The replay module 432 can be provided to perform the actions required to achieve the target behavior of the target vehicle. That is, the replay module 432 can receive information from the target dynamics module 424 to determine one or more actions required to achieve the target behavior, and can further instruct the corresponding modules to perform the relevant actions.

[0086] For example, the vehicle control, display, and sound module 434 can perform actions belonging to the control, display, and sound categories; the vehicle powertrain module 436 can perform actions related to the powertrain; and the vehicle data analysis 438 can collect all action data and can further anonymize the collected data so that the anonymized driving data can be uploaded to the cloud server 140 for analysis and / or simulation model training. For example, the collected data can include usage statistics such as simulation duration, location, and activation frequency, and error logs such as cases where the simulator 402 fails to initialize or is deactivated by the security module 416 during operation.

[0087] In operation, the simulation system 400 or the in-vehicle computer system 230 interacts with the driver 120 to perform various simulation processes provided by the simulation system 400. Figure 6 A flowchart of an exemplary simulation method for an EV according to an embodiment of the present disclosure is shown. The EV can be Figure 1 and Figure 2 the EV 110 shown. The processor 304 of the in-vehicle computer system 230 can execute the program instructions stored in the memory 302 to implement the simulation method.

[0088] At S602, a simulation model is created that associates multiple target behaviors of a target vehicle with an EV.

[0089] Reconstructing or replaying the experience of driving the target vehicle for a driver driving an EV brings a sense of nostalgia to the driver. The EV can be operated in a normal mode or a simulation mode. When the EV is operated in the normal mode, the EV exhibits the behavior of an EV. When the EV is operated in the simulation mode, the EV exhibits multiple target behaviors of the target vehicle. In other words, in order to replay multiple target behaviors of the target vehicle on the EV, the driver of the EV needs to operate the EV in the simulation mode.

[0090] When the EV is operated by a driver in the normal mode, the driver of the EV controls the EV through multiple input devices of the EV to generate multiple vehicle parameters of the EV. The on-vehicle computer system of the EV obtains the multiple vehicle parameters of the EV to generate the set of EV control parameters and controls the EV based on the set of EV control parameters.

[0091] When the EV is operated by a driver in the simulation mode, the driver of the EV controls the EV through multiple input devices of the EV to generate multiple vehicle parameters of the EV. The on-vehicle computer system of the EV obtains the multiple vehicle parameters of the EV to generate the set of EV control parameters. However, the on-vehicle computer system does not directly control the EV based on the set of EV control parameters. Instead, the on-vehicle computer system uses the simulation model to convert the set of EV control parameters into a set of simulated target vehicle controls and controls the EV based on the set of simulated target vehicle controls. The simulated target vehicle controls can be output settings or other output parameters for controlling the operation of the EV. Examples of the simulated target vehicle controls include one or more of a target turning angle, a target acceleration or deceleration, a target drive wheel, a target traction setting, a target handling characteristic, and a target engine sound.

[0092] Both the set of EV control parameters and the set of simulated target vehicle controls are used to control the EV. The set of EV control parameters is used to control the EV when the EV is operated in the normal mode. The set of simulated target vehicle controls is used to control the EV when the EV is operated in the simulation mode. When the EV is operated in the simulation mode, the EV exhibits the target behavior of the target vehicle. Converting the set of EV control parameters into the set of simulated target vehicle controls through the simulation model helps to operate the EV in the simulation mode.

[0093] In some embodiments, the goal of converting the set of EV control parameters into the set of simulated target vehicle controls is to reconstruct multiple target behaviors of the target vehicle on the EV. However, due to the differences between the EV and the target vehicle, the accurate conversion of the set of EV control parameters to the set of simulated target vehicle controls is not determined by the optimization of individual parameters, but by the combined effect of all parameters. In other words, the accurate conversion is not only an objective engineering issue, but also a subjective look and feel issue. In addition, the accurate conversion focuses on the subjective look and feel perceived by the EV driver. In the present disclosure, the perceptions of other passengers in the EV are irrelevant.

[0094] In some embodiments, because the accurate conversion is about the look and feel perceived by the EV driver, it is difficult to obtain a mathematical function of the simulation model to reflect the relationship between the set of EV control parameters and the set of simulated target vehicle controls. Explore machine learning-based methods to obtain the simulation model. In this case, the simulation model is created and trained on a high-performance computer system separate from the EV. After training the simulation model with a training data set to achieve certain performance goals, the simulation model can be loaded into the in-vehicle computer system of the EV. The simulation model is capable of converting the set of EV control parameters into the set of simulated target vehicle controls in real time, such that the driver of the EV feels like driving the target vehicle.

[0095] In some embodiments, the simulation model can be loaded into a cloud server, and the simulation process is also executed at the cloud server. In this case, the data required for the simulation process can be exchanged between the EV and the cloud server. Therefore, battery power can be conserved for driving the EV.

[0096] In some embodiments, the simulation model is a neural network. The set of EV control parameters is input into the neural network to obtain the set of simulated target vehicle controls.

[0097] Reference Figure 6 , at S604, multiple vehicle parameters of the EV are obtained to generate a set of EV control parameters. The multiple vehicle parameters of the EV at least include the running time parameter of the EV and the driving condition of the EV.

[0098] To simulate multiple target behaviors of the target vehicle on the EV, the in-vehicle computer system needs to obtain information about both the EV and the target vehicle. The multiple vehicle parameters of the EV are real-time data collected by various sensors and input devices of the EV. Based on the multiple vehicle parameters of the EV, the in-vehicle computer system generates the set of EV control parameters. In the normal mode, the set of EV control parameters can be used to directly control the EV. In the simulation mode, the set of EV control parameters is input into the simulation model to obtain the set of simulated target vehicle controls. The set of simulated target vehicle controls is used to control the EV to simulate multiple target behaviors of the target vehicle.

[0099] For example, the plurality of vehicle parameters may include steering parameters, acceleration and deceleration parameters, and suspension parameters. The steering parameters may include steering wheel position, brake pedal position, impact position, vehicle weight distribution, torque vectoring, road surface condition, battery availability, or a combination thereof. The acceleration and deceleration parameters may include steering position, road surface condition, observed traction, available power, motor temperature, battery pack temperature, gyroscope readings, accelerator readings, suspension position, throttle position, brake pedal position, regeneration settings, or a combination thereof. Some parameters may appear in more than one of the steering parameters, acceleration and deceleration parameters, and suspension parameters. The on-vehicle computer system 230 may obtain the plurality of vehicle parameters of the EV 110 from various subsystems or components of the EV 110 in real time.

[0100] Return reference Figure 6 , at S606, a plurality of configuration parameters of the target vehicle are obtained. The configuration parameters of the target vehicle may be settings or other parameters that affect the way the vehicle operates. In one embodiment, the plurality of configuration parameters at least include information about the target vehicle and settings of the target vehicle for the driver. For example, after the on-vehicle computer system 230 receives an emulation request from the driver 120, the on-vehicle computer system 230 may enter an emulation mode to start various emulation processes. Then, the on-vehicle computer system 230 may obtain the configuration parameters for the emulation process. Specifically, the on-vehicle computer system 230 may obtain driver-related information as well as target behavior and target vehicle information. Additionally or optionally, safety information associated with the emulation process may also be obtained by the on-vehicle computer system 230 locally or remotely from the cloud server 140. For example, the safety information may include health information of the EV, local traffic / safety rules and regulations, and surrounding information from the driver assistance system.

[0101] Driver characteristics may be obtained for the driver-related information, and target characteristics may also be obtained for the target behavior and target vehicle information. The target characteristics may indicate the target behavior to be emulated and / or the target vehicle to be emulated. The target characteristics may include various types of information, such as horsepower / torque curve, weight distribution, suspension stiffness / type / programming, steering ratio, wheelbase, vehicle type, fuel consumption curve, dashboard data, control weight for steering, acceleration pedal feel, and brake pedal feel, brake map, or a combination thereof. The target behavior is not initially configured on the EV 110.

[0102] In some embodiments, the target features may be included in the driver features. Thus, the vehicle computer system 230 may obtain the target vehicle from the driver features of the driver 120. In some cases, obtaining the target features of the target vehicle may include using an interior camera to obtain the identity of the driver of the EV, and retrieving driver features and / or target features associated with the identity of the driver of the EV. In some embodiments, the driver 120 may also input the target vehicle into the vehicle computer system 230 through an input interface of the vehicle computer system 230.

[0103] Optionally or additionally, after obtaining the configuration parameters and based on the safety information, the vehicle computer system 230 may determine whether it is safe to activate the simulation before activating the simulation. For example, the vehicle computer system 230 may evaluate the health status of the EV based on the presence of engine fault codes, overdue maintenance, and low tire pressure. After activating the simulation, the vehicle computer system 230 may perform a safety check to determine whether it is safe to continue the simulation. Specifically, the vehicle computer system 230 may perform a first safety check on the configuration parameters to determine whether the configuration parameters are within the safety range of the EV 110. If some of the configuration parameters are outside the safety range, the vehicle computer system 230 may prompt an error message and may exit the simulation mode. If the first safety check passes, the vehicle computer system 230 may enter the simulation mode to continue the simulation process.

[0104] In some embodiments, before the EV begins to operate in the simulation mode, the vehicle computer system 230 may obtain a request from the driver of the EV to simulate the target behavior of the target vehicle. For example, the driver 120 may interact with the vehicle computer system 230 to input a simulation request into the vehicle computer system 230, and may also provide driver features to the vehicle computer system 230. The interaction between the driver 120 and the vehicle computer system 230 may take various forms. In one embodiment, the driver 120 may manually input the request and / or driver features through the human-machine interface (HMI) of the vehicle computer system 230. In some other embodiments, the driver 120 may input the request and / or driver features through other devices.

[0105] For example, the driver 120 may carry the user terminal 130. The driver 120 may request the simulation and manage the in-vehicle computer system 230 and the simulation through the user terminal 130. The driver 120 may configure the driver characteristics on the user terminal 130 and load the driver characteristics into the in-vehicle computer system 230. The driver characteristics may include information about the target vehicle in the target feature list, as well as other driver-specific information items. The driver 120 may also manage the connection between the EV 110 and the cloud server 140. For example, the driver 120 may use a mobile application on the user terminal 130 to configure the in-vehicle computer system 230 of the EV 110 to establish a connection to the cloud server 140.

[0106] In some embodiments, after the driver 120 enters the EV 110, the in-vehicle computer system 230 may identify the driver 120 through the camera of the EV 110 and may issue a simulation request through the camera. In some other embodiments, the in-vehicle computer system 230 may identify the driver 120 through the user terminal 130 wirelessly connected to the in-vehicle computer system 230. For example, the wireless connection is a Bluetooth connection. After identifying the driver 120, the in-vehicle computer system 230 retrieves the driver characteristics associated with the driver 120. The in-vehicle computer system 230 may retrieve the driver characteristics from the memory device of the in-vehicle computer system 230, from the user terminal 130 wirelessly connected to the driver 120, or from the cloud server 140.

[0107] Return reference Figure 6 , at S608, the simulation model is used to provide a set of simulated target vehicle controls based on the set of EV control parameters and the multiple configuration parameters of the target vehicle. More specifically, the set of EV control parameters and the multiple configuration parameters of the target vehicle may be provided as input parameters to the simulator 402, such that the simulator 402 may generate the set of simulated target vehicle controls that reflect the target behavior of the target vehicle. In some embodiments, in order to save the battery power of the EV 110, the in-vehicle computer system 230 may transfer the execution of the target vehicle simulation process to the cloud server 140. After completing the target vehicle simulation process, the cloud server 140 returns multiple output parameters to the in-vehicle computer system 230. In this case, the data exchange that occurs between the in-vehicle computer system 230 and the cloud server 140 through wireless communication may cause a slight delay.

[0108] In some embodiments, in order to accurately reflect the relationship between the set of EV control parameters and the set of simulated target vehicle controls, it is necessary to train the simulation model with a training data set and test the simulation model with a test data set. The training data set and the test data set generally include a sample set of EV control parameters and a corresponding set of simulated target vehicle controls. However, the training data set and the test data set are not easily obtained.

[0109] In the process of designing an EV or a target vehicle, a designer typically creates an engineering model of the EV or the target vehicle. For example, the engineering model of the EV can be used to generate multiple sets of EV control parameters, and the engineering model of the target vehicle can be used to generate multiple sets of target vehicle controls. In another example, one manufacturer of an EV may be able to collect multiple sets of EV control parameters, and another manufacturer of a target vehicle may be able to collect multiple sets of target vehicle controls. In another example, a driver of an EV may be able to collect multiple sets of EV control parameters of the EV driven by the driver, and a driver of a target vehicle may be able to collect multiple sets of target vehicle controls of the target vehicle driven by the driver.

[0110] In some embodiments, the target vehicle is a vehicle different from the EV, the EV is configured with an adjustable seat, and the behavior of the target vehicle includes at least a seat profile such that the enhanced lumbar support and seat depth of the adjustable seat of the EV are adjusted to simulate the seat depth of the seat of the target vehicle.

[0111] In some embodiments, after a pre-configured time expires, the adjustable seat of the EV is controlled by the driver of the EV to gradually return to the initial settings.

[0112] In some embodiments, the target vehicle is an ICE vehicle, the EV is configured with a massage actuator in the driver's seat, and the behavior of the target vehicle includes controlling the massage actuator in the driver's seat to simulate the vibration of the ICE engine.

[0113] In some embodiments, the target vehicle is a vehicle different from the EV, the EV is equipped with an olfactory fragrance dispenser, and the behavior of the target vehicle includes a fragrance characteristic such that the olfactory fragrance dispenser is controlled to release a fragrance to simulate the fragrance found in the target vehicle, which is the fragrance of genuine leather or artificial leather.

[0114] Figure 7 A flowchart of an exemplary method of training a simulation model according to an embodiment of the present disclosure is shown. As Figure 7 shown, at S702, multiple sets of EV control parameters are collected, and at S704, multiple sets of target vehicle controls are collected. Regardless of the method of collecting multiple sets of EV control parameters and multiple sets of target vehicle controls, the multiple sets of EV control parameters and multiple sets of target vehicle controls can be used as a training data set and a test data set, respectively, to train and test the simulation model. As Figure 7 shown, at S706, a neural network is trained with multiple sets of EV control parameters and multiple sets of target vehicle controls to obtain a simulation model corresponding to the target vehicle.

[0115] Because the training dataset does not include multiple sets of simulated target vehicle controls, the neural network of the simulation model needs to have a structure that can utilize the readily available training dataset. In some embodiments, the neural network is a Cycle Generative Adversarial Network (CycleGAN). CycleGAN includes a first GAN and a second GAN. The first GAN includes a first generator model and a first discriminator. The second GAN includes a second generator model and a second discriminator.

[0116] CycleGAN technology was initially developed for unpaired image-to-image translation. In the present disclosure, multiple sets of EV control parameters and multiple sets of simulated target vehicle controls are not image data. However, similar to the image data transformed by CycleGAN, the multiple sets of EV control parameters and the multiple sets of simulated target vehicle controls are unpaired. Unpaired training datasets from two different domains (e.g., the EV domain and the target vehicle domain) can be used to train CycleGAN. In the embodiments of the present disclosure, the unpaired training dataset is multiple sets of EV control parameters and multiple sets of target vehicle controls. Therefore, a simulation model with a CycleGAN structure can be trained to accurately convert the set of EV control parameters into a corresponding set of simulated target vehicle controls that provide the real appearance and feel of multiple target behaviors of the target vehicle to the driver of the EV.

[0117] The following describes how to use the training dataset to train CycleGAN. Figure 8 A flowchart showing another exemplary method for training a simulation model according to an embodiment of the present disclosure is shown. As Figure 8 shown, the method of training the simulation model includes the following processes.

[0118] At S802, multiple sets of EV control parameters are input into the first generator model to generate multiple sets of simulated target vehicle controls.

[0119] In this case, a set of EV control parameters is the runtime EV control parameters as a result of the driver's operation of the EV, and a set of simulated target vehicle controls is the runtime EV control parameters for simulating the target vehicle. The goal of the simulation model is to convert the set of EV control parameters into a corresponding set of simulated target vehicle controls. If multiple sets of EV control parameters and the corresponding multiple sets of simulated target vehicle controls are readily available, the first generator model can be trained alone to accurately convert from the set of EV control parameters to the corresponding set of simulated target vehicle controls. However, such paired training datasets are not readily available. Instead, only multiple EV control parameters and multiple sets of target vehicle controls can be collected as the training dataset. Here, a set of target vehicle controls is the runtime target vehicle control parameters as a result of the driver's operation of the target vehicle.

[0120] The CycleGAN technique is used to overcome the problem of the lack of paired training datasets.

[0121] At S804, multiple sets of target vehicle controls and multiple sets of simulated target vehicle controls are input into the first discriminator to calculate the likelihood of the multiple sets of simulated target vehicle controls as the multiple sets of target vehicle controls, thereby updating the first generator model in each training iteration.

[0122] The first discriminator is used to make the multiple sets of simulated target vehicle controls (EV control parameters) generated by the first generator model look like the multiple sets of target vehicle controls (target vehicle control parameters). However, because the training datasets (i.e., the multiple sets of EV control parameters and the multiple sets of target vehicle controls) are not paired, even if the multiple sets of simulated target vehicle controls (EV control parameters) look like the multiple sets of target vehicle controls, the multiple sets of simulated target vehicle controls are not an accurate transformation of the multiple EV control parameters. For example, a set of simulated target vehicle controls can generally simulate the gear shifting of a target vehicle, but may not accurately reflect the gear shifting specific to the accelerator pedal position of the target vehicle. The accelerator pedal position is indirectly captured in this set of EV control parameters. This problem will be solved by the cycle consistency loss function described below.

[0123] At S806, multiple sets of target vehicle controls are input into the second generator model to generate multiple sets of simulated EV control parameters.

[0124] To form the CycleGAN structure, the second GAN performs the inverse transformation of the first GAN. In this case, this set of target vehicle controls is the runtime target vehicle control parameters as a result of the driver's operation of the target vehicle, and this set of simulated EV control parameters is the runtime target vehicle control parameters for simulating the EV. Since the simulation model is only intended to simulate the target vehicle on the EV, this set of simulated EV control parameters has no practical use, but is necessary for CycleGAN training purposes.

[0125] At S808, multiple sets of EV control parameters and multiple sets of simulated EV control parameters are input into the second discriminator to calculate the likelihood of the multiple sets of simulated EV control parameters as the multiple sets of EV control parameters, thereby updating the second generator model in each training iteration.

[0126] Similarly, the second discriminator improves the performance of the second generator model.

[0127] Figure 9A Shows a training exemplary simulator model according to an embodiment of the present disclosure. In some embodiments, as Figure 9AAs shown, training the neural network includes: inputting multiple sets of EV control parameters generated by the EV engineering model 902 into the first generator model 912 to generate multiple sets of simulated target vehicle controls; inputting the multiple sets of target vehicle controls and the multiple sets of simulated target vehicle controls into the first discriminator 922 to calculate the likelihood of the multiple sets of simulated target vehicle controls as the multiple sets of target vehicle controls, thereby updating the first generator model 912 in each training iteration; inputting the multiple sets of target vehicle controls generated by the target vehicle engineering model 904 into the second generator model 914 to generate multiple sets of simulated EV control parameters; inputting the multiple sets of EV control parameters and the multiple sets of simulated EV control parameters into the second discriminator 924 to calculate the likelihood of the multiple sets of simulated EV control parameters as the multiple sets of EV control parameters, thereby updating the second generator model 914 in each training iteration; and calculating a cycle consistency loss to update the first generator model 912 and the second generator model 914 in each training iteration.

[0128] Training the simulation model includes two aspects. One aspect is to maximize the likelihood through any discriminator. The other aspect is to minimize the cycle consistency loss. As Figure 8 shown, at S810, the cycle consistency loss is calculated to update the first generator model and the second generator model in each training iteration.

[0129] There are two ways to calculate the cycle consistency loss and use it to update the first generator model and the second generator model in each training iteration. The cycle consistency loss can be calculated as a forward cycle consistency loss or a backward cycle consistency loss, and both are described below.

[0130] Figure 9B illustrates calculating the forward cycle consistency loss according to an embodiment of the present disclosure. In some embodiments, as Figure 9B shown, calculating the cycle consistency loss includes: inputting multiple sets of EV control parameters generated by the EV engineering model 902 into the first generator model 912 to generate multiple sets of simulated target vehicle controls; inputting the multiple sets of simulated target vehicle controls generated by the first generator model 912 into the second generator model 914 to generate multiple sets of simulated EV control parameters; and comparing the multiple sets of EV control parameters with the multiple sets of simulated EV control parameters generated by the second generator model 914.

[0131] Figure 9C illustrates calculating the backward cycle consistency loss according to an embodiment of the present disclosure. In some embodiments, as Figure 9CAs shown, calculating the cyclic consistency loss includes: inputting multiple sets of target vehicle control inputs generated by the target vehicle engineering model 904 into the second generator model 914 to generate multiple sets of simulated EV control parameters; inputting the multiple sets of simulated EV control parameters generated by the second generator model 914 into the first generator model 912 to generate multiple sets of simulated target vehicle controls; and comparing the multiple sets of target vehicle controls with the multiple sets of simulated target vehicle controls generated by the first generator model 912.

[0132] Reference Figure 6 , at S610, output the set of simulated target vehicle controls to the EV such that the EV is controlled based on the set of simulated target vehicle controls to achieve multiple target behaviors of the target vehicle.

[0133] In some embodiments, the simulation model is trained with an easily obtainable dataset. The simulation model accurately converts the set of EV control parameters into the set of simulated target vehicle controls. The set of simulated target vehicle controls is used to control the EV to provide the driver of the EV with the true appearance and feel of multiple target behaviors of the target vehicle.

[0134] In some embodiments, a safety check is performed on the set of simulated target vehicle controls before outputting the set of simulated target vehicle controls to the EV. If the set of simulated target vehicle controls is used to control the EV, the safety check ensures that the EV operates safely.

[0135] In some embodiments, creating the simulation model includes obtaining the simulation model from a cloud server that includes multiple simulation models pre-trained respectively for multiple target vehicles. Multiple simulation models can be trained respectively for multiple target vehicles. Different target vehicles correspond to different simulation models. The EV obtains the simulation model corresponding to the target vehicle selected by the driver of the EV.

[0136] In some embodiments, the multiple target behaviors of the target vehicle include vehicle handling characteristics, gear shifting, dynamic engine sounds and vibrations transmitted to the driver's seat, the simulated instrument panel of the target vehicle, or combinations thereof. The multiple target behaviors of the target vehicle are not initially configured on the EV.

[0137] In some embodiments, the multiple vehicle parameters of the EV include steering wheel position, vehicle weight distribution, road surface conditions, impact distribution, brake position, torque vector, battery availability, accelerator pedal position, steering wheel position, observed traction, available power, motor temperature, battery temperature, gyroscope measurements, accelerator measurements, suspension position, throttle position, brake position, regeneration settings, window position, or combinations thereof.

[0138] In some embodiments, each set of simulated target vehicle controls includes a target turning angle, a target steering ratio, a target weight distribution, a target wheelbase, a target acceleration or deceleration, a target drive wheel, a target traction setting, a target handling characteristic, a target engine sound at least on the driver's side of the EV, or a combination thereof.

[0139] In some embodiments, the target vehicle includes an internal combustion engine (ICE) vehicle or another electric vehicle.

[0140] In some embodiments, the on-vehicle computer system 230 can obtain output parameters (i.e., the set of simulated target vehicle controls) from the simulator 402 for achieving the target behavior of the target vehicle. After obtaining the output parameters and based on the safety information, the on-vehicle computer system 230 can perform a second safety check on the parameters to determine whether certain parameters are within the safety range of the EV 110. If any parameter exceeds the safety range, the on-vehicle computer system 230 can generate an error message and can stop using the out-of-range parameter in any further process or action.

[0141] In some embodiments, the output parameters from the simulator 402 can be fed into another machine learning process to determine safety risks. The another machine learning process can include a reinforcement learning algorithm. The reinforcement learning algorithm not only identifies immediate safety risks and avoids operating the EV in the presence of immediate safety risks, but also identifies future safety risks and avoids operating the EV in the presence of future safety risks.

[0142] In some embodiments, the reinforcement learning algorithm is used to dynamically adjust the safety range of the second safety check to minimize safety risks.

[0143] In addition, the on-vehicle computer system 230 can perform one or more actions based on the output parameters to achieve the target behavior of the target. For example, the on-vehicle computer system 230 can generate control parameters for relevant subsystems or components of the EV 110 to control the subsystems / components to achieve the simulated target behavior of the target vehicle. For example, one or more control parameters can include steering control, powertrain control, suspension control, dashboard display, engine sound, haptic control, driver seat control, or a combination thereof. The simulated behavior of the target vehicle can include vehicle handling characteristics, gear shifting, dynamic engine sound and vibration transmitted to the driver seat, the simulated dashboard of the target vehicle, and a combination thereof.

[0144] Certain actions may be performed statically by the in-vehicle computer system 230, such as display and sound-related actions, while certain other actions may be performed dynamically during the operation of the EV 110, such as powertrain and driving-related actions. For example, the in-vehicle computer system 230 may render different dashboard displays as the target dashboard for the target vehicle on the EV. In some embodiments, the in-vehicle computer system 230 may perform automatic dashboard adjustment as the target dashboard for the target vehicle on the EV 110. For example, the in-vehicle computer system 230 may divide the electrical dashboard of the EV 110 into multiple regions, measure the brightness of the ambient light in each region through one or more light sensors, and adjust the contrast, brightness, and content of each region based on the brightness of the ambient light in each region.

[0145] In one embodiment, based on the output parameters, the in-vehicle computer system 230 may adjust certain subsystems to simulate the target turning angle, target steering ratio, target weight distribution, and target wheelbase. In another embodiment, based on the output parameters, the in-vehicle computer system 230 may adjust certain subsystems to simulate the target acceleration or deceleration, target drive wheels, target traction settings, and target handling characteristics. In another embodiment, based on the output parameters, the in-vehicle computer system 230 may adjust the in-vehicle speaker subsystem to simulate the target engine sound. In another embodiment, based on the output parameters, the in-vehicle computer system 230 may perform driver seat transformation, including tightening the tether, changing the hardness, changing the lumbar support, or a combination thereof within a preconfigured time, and restoring the driver seat settings after the expiration of the preconfigured time.

[0146] In addition, the in-vehicle computer system 230 may perform one or more data operations based on the simulated target vehicle on the EV. That is, based on the virtual vehicle, i.e., the simulated target vehicle, certain vehicle-related data can be processed and / or analyzed in various ways. For example, the in-vehicle computer system 230 may obtain the position of the EV 110 and may perform further actions based on that position, such as determining the local driving rules corresponding to that position and applying the limitations of the local driving rules to the control parameters of the EV 110. In one embodiment, the in-vehicle computer system 230 may collect the data of the simulation process and the vehicle data of the simulated target vehicle, and anonymize and upload the collected data to the cloud server 140 for training the vehicle simulator model. In another embodiment, the in-vehicle computer system 230 may collect the simulated trip data of the driver 120 and upload the trip data to the social media website identified by the driver 120. Other data operations may also be performed.

[0147] Accordingly, embodiments of the present disclosure provide a method and system for an EV to simulate the behavior of a target vehicle on an EV. When driving the EV, a driver may request to simulate the behavior of the target vehicle, thereby appreciating the appearance and feel of the target vehicle and enjoying the pleasure of driving the target vehicle. The in-vehicle simulation system also allows the driver to share trip data collected when the EV is operating in the simulation mode to social media. When the EV is operating in the simulation mode, vehicle data generated by the in-vehicle simulation system may also be collected and uploaded to a server as training data for training a new simulator model or retraining and updating a current simulator model.

[0148] The present disclosure also provides a method for mining trip data to obtain a training data set. When the EV is operating in the simulation mode, various parameters of the EV may be collected in real time. After the EV completes a trip, if the driver agrees to collect the trip data, the trip data will be uploaded to a cloud server. The trip data may be mined to discover data domains. The data domains may be used to classify the trip data into data clusters. The data clusters may be used as a training data set to train a simulation model.

[0149] Figure 10 A flowchart of an exemplary method for mining trip data for a training data set according to an embodiment of the present disclosure is shown. As Figure 10 shown, the method for mining trip data includes the following steps.

[0150] At S1002, trip data is obtained from the EV.

[0151] When the EV is operating in the simulation mode, trip data is collected in real time. The trip data may be stored in an in-vehicle computer system of the EV. After the EV completes a trip, the trip data may be uploaded to a cloud server. The trip data may be retrieved directly from a storage device of the in-vehicle computer system of the EV.

[0152] At S1004, the trip data is preprocessed to identify data irrelevant to simulation model training.

[0153] Since the trip data is collected for training a simulation model, data irrelevant to simulation model training may be identified.

[0154] At S1006, a heat map is created to classify the preprocessed data into multiple data clusters corresponding to multiple data domains.

[0155] For example, Figure 11The heatmap shown helps reduce noise in a large amount of trip data from each of multiple data domains. The multiple data domains can be used to classify the trip data into multiple data clusters. The heatmap helps classify and / or generalize the trip data such that the trip data can be further purified to identify noise in the trip data. The purified trip data can then be used as a training data set to improve the performance of a simulation model.

[0156] At S1008, multiple data clusters are output as a training data set for training a simulation model.

[0157] Figure 12 A flowchart for discovering new data domains according to an embodiment of the present disclosure is shown. Data that cannot be classified into multiple data clusters can be processed to discover new data domains.

[0158] At S1202, preprocessed trip data that does not belong to any data cluster is obtained. For example, preprocessed trip data that does not belong to any existing data cluster can be used to form a new data cluster that identifies new correlations. The new data cluster can be used to extract valuable insights.

[0159] At S1204, a pattern recognition process is performed to determine a new data domain.

[0160] The pattern recognition process can include a random forest algorithm to obtain more valuable insights from the preprocessed trip data that does not belong to any data cluster. The pattern recognition process can be used to extract a training data set to train a simulation model for a specific / extreme scenario.

[0161] At S1206, the new data domain is output for use in processing trip data to obtain a training data set for training a simulation model.

[0162] For example, trip data based on weather and road terrain may be noise for a particular data domain, such as a driver frequently braking in a congested geographical area (such as India or China). However, for another data domain such as acceleration / torque during rain / snow, the frequent braking data can be used to improve the simulation model. In some embodiments, the frequent braking data can be used to determine the safety range for a second safety check.

[0163] In an embodiment of the present disclosure, trip data can be collected with the driver's consent to train a simulation model to improve simulation performance. The trip data can also be used to determine the safety range for a safety check.

[0164] The foregoing embodiments have described in detail the objectives, technical solutions, and beneficial effects of the present disclosure. The foregoing embodiments are only some of the embodiments of the present disclosure, rather than all of the embodiments of the present disclosure, and should not be used to limit the scope of the present disclosure. Other embodiments that can be obtained by those of ordinary skill in the art without creative efforts based on the foregoing embodiments shall fall within the scope of the present disclosure. In addition, without conflict, the embodiments and features in the embodiments can be combined with each other. Therefore, any changes, equivalent substitutions, and modifications made in accordance with the present disclosure still fall within the scope of the present disclosure.

Claims

1. A simulation method for an electric vehicle (EV), the simulation method comprising: Creating a simulation model that associates multiple target behaviors of a target vehicle with the EV, wherein the simulation model is a neural network trained to reflect the relationship between EV control parameters and simulated target vehicle controls, and the simulation model is created by the following steps: (a) Collecting multiple sets of EV control parameters; (b) Collecting multiple sets of simulated target vehicle controls; (c) Processing the multiple sets of EV control parameters and multiple sets of target vehicle controls using a heat map to identify noise through data clustering; And (d) After processing the multiple sets of EV control parameters and the multiple sets of target vehicle controls, training the neural network with the multiple sets of EV control parameters and the multiple sets of target vehicle controls to obtain the simulation model corresponding to the target vehicle; Obtaining multiple vehicle parameters of the EV to generate an additional set of EV control parameters, the multiple vehicle parameters of the EV including at least the running time parameter of the EV and the driving condition of the EV; Obtaining multiple configuration parameters of the target vehicle, the multiple configuration parameters including at least the information of the target vehicle and the settings of the target vehicle for the driver; Based on the additional set of EV control parameters and the multiple configuration parameters of the target vehicle, using the simulation model to provide a set of simulated target vehicle controls; And Outputting the set of simulated target vehicle controls to the EV such that the EV is controlled based on the set of simulated target vehicle controls to achieve the multiple target behaviors of the target vehicle.

2. The method according to claim 1, the method further comprising: Performing a safety check on the set of simulated target vehicle controls before outputting the set of simulated target vehicle controls to the EV.

3. The method according to claim 1, wherein creating the simulation model comprises: Obtaining the simulation model from a cloud server, the cloud server containing multiple simulation models pre-trained via neural networks for multiple target vehicles respectively.

4. An electric vehicle (EV), the electric vehicle (EV) comprising: A wireless communication device for connecting to a cloud server and / or a mobile device carried by the driver of the EV; And An in-vehicle computer system for performing: Creating a simulation model that associates multiple target behaviors of a target vehicle with the EV, wherein the simulation model is a neural network trained to reflect the relationship between EV control parameters and simulated target vehicle controls, and the simulation model is created by the following steps: (a) Collecting multiple sets of EV control parameters; (b) Collecting multiple sets of simulated target vehicle controls; (c) Processing the multiple sets of EV control parameters and multiple sets of target vehicle controls using a heat map to identify noise through data clustering; And (d) After processing the multiple sets of EV control parameters and the multiple sets of target vehicle controls, training the neural network with the multiple sets of EV control parameters and the multiple sets of target vehicle controls to obtain the simulation model corresponding to the target vehicle; Obtain a plurality of vehicle parameters of the EV to generate an additional set of EV control parameters, where the plurality of vehicle parameters of the EV at least include the running time parameter of the EV and the driving condition of the EV; Obtain a plurality of configuration parameters of the target vehicle, where the plurality of configuration parameters at least include the information of the target vehicle and the settings of the target vehicle for the driver; Based on the additional set of EV control parameters and the plurality of configuration parameters of the target vehicle, use the simulation model to provide a set of simulated target vehicle controls; And Output the set of simulated target vehicle controls to the EV, such that the EV is controlled based on the set of simulated target vehicle controls to achieve the plurality of target behaviors of the target vehicle.

5. The EV according to claim 4, wherein: The plurality of vehicle parameters of the EV include steering wheel position, vehicle weight distribution, road surface condition, impact distribution, brake position, torque vector, battery availability, accelerator pedal position, steering wheel position, observed traction, available power, motor temperature, battery temperature, gyroscope measurement, accelerator measurement, suspension position, throttle position, brake position, regeneration setting, window position, or a combination thereof.

6. The method according to claim 1, wherein collecting the multiple sets of EV control parameters includes: Collecting the multiple sets of EV control parameters generated by inputting the plurality of vehicle parameters of the EV into an EV simulator that simulates the behavior of the EV; Collecting the multiple sets of EV control parameters generated by a plurality of anonymous EVs; And / or collecting the multiple sets of EV control parameters generated by the EV.

7. The method according to claim 1, wherein collecting the multiple sets of target vehicle controls includes: Collecting the multiple sets of target vehicle controls generated by inputting the plurality of vehicle parameters of the EV into a target vehicle simulator that simulates the behavior of the target vehicle; Collecting the multiple sets of target vehicle controls generated by a plurality of anonymous target vehicles; And / or Collecting the multiple sets of target vehicle controls generated by the target vehicle.

8. The method according to claim 1, wherein: The neural network is a Cycle Generative Adversarial Network (CycleGAN) including a first generator model, a first discriminator, a second generator model, and a second discriminator; And Training the neural network includes: Inputting the multiple sets of EV control parameters into the first generator model to generate multiple sets of simulated target vehicle controls; Inputting the multiple sets of target vehicle controls and the multiple sets of simulated target vehicle controls into the first discriminator to calculate the likelihood of the multiple sets of simulated target vehicle controls as the multiple sets of target vehicle controls, thereby updating the first generator model in each training iteration; Inputting the multiple sets of target vehicle controls into the second generator model to generate multiple sets of simulated EV control parameters; Input the multiple sets of EV control parameters and the multiple sets of simulated EV control parameters into the second discriminator to calculate the likelihood of the multiple sets of simulated EV control parameters as the multiple sets of EV control parameters, thereby updating the second generator model in each training iteration; and Calculate the cycle consistency loss to update the first generator model and the second generator model in each training iteration.

9. The method according to claim 8, wherein calculating the cycle consistency loss includes:[[]] Input the multiple sets of EV control parameters into the first generator model to generate the multiple sets of simulated target vehicle controls; Input the multiple sets of simulated target vehicle controls generated by the first generator model into the second generator model to generate the multiple sets of simulated EV control parameters; And Compare the multiple sets of EV control parameters with the multiple sets of simulated EV control parameters generated by the second generator model.

10. The method according to claim 8, wherein calculating the cycle consistency loss includes:[[]] Input the multiple sets of target vehicle controls into the second generator model to generate the multiple sets of simulated EV control parameters; Input the multiple sets of simulated EV control parameters generated by the second generator model into the first generator model to generate the multiple sets of simulated target vehicle controls; and compare the multiple sets of target vehicle controls with the multiple sets of simulated target vehicle controls generated by the first generator model.

11. The method according to claim 1, wherein:[[]] The multiple target behaviors of the target vehicle include vehicle handling characteristics, gear shifting, dynamic engine sounds and vibrations transmitted to the driver's seat, the simulated instrument panel of the target vehicle, or a combination thereof; and the multiple target behaviors of the target vehicle are initially not configured on the EV.

12. The method according to claim 1, wherein:[[]] The multiple vehicle parameters of the EV include steering wheel position, vehicle weight distribution, road surface condition, shock distribution, brake position, torque vector, battery availability, accelerator pedal position, steering wheel position, observed traction, available power, motor temperature, battery temperature, gyroscope measurement, accelerator measurement, suspension position, throttle position, brake position, regeneration setting, window position, or a combination thereof.

13. The method according to claim 1, wherein:[[]] Each set of simulated target vehicle controls includes a target turning angle, a target steering ratio, a target weight distribution, a target wheelbase, a target acceleration or deceleration, a target drive wheel, a target traction setting, a target handling characteristic, a target engine sound at least on the driver's side of the EV, or a combination thereof.

14. The method according to claim 1, wherein the method further comprises: In response to receiving a request from the driver of the EV to perform a simulation of the target vehicle on the EV:[[]] Obtain safety information associated with the simulation; Before activating the simulation, determine whether it is safe to activate the simulation; and perform the simulation in response to determining that it is safe to activate the simulation; and After activating the simulation, perform a safety check to determine whether it is safe to continue the simulation; and deactivate the simulation in response to at least one of the following: (i) determining that it is unsafe to continue the simulation, or (ii) receiving a request from the driver to deactivate the simulation.

15. The method according to claim 14, wherein: the safety information includes health information of the EV, local traffic / safety rules and regulations, and surrounding information from a driver assistance system; and the safety check includes a first safety check performed on the plurality of configuration parameters to determine that the plurality of configuration parameters are within a first safety range, and a second safety check performed on one or more control parameters to determine that the one or more control parameters are within a second safety range.

16. The method according to claim 15, wherein: a reinforcement learning algorithm is used to dynamically adjust the second safety range of the second safety check to minimize safety risks.

17. A simulation system for an electric vehicle (EV), the simulation system comprising: a plurality of input devices that provide a plurality of vehicle parameters; a memory that contains program instructions; and a processor coupled to the memory and the plurality of input devices, and when the program instructions are executed, the processor is configured to: create a simulation model that associates a plurality of target behaviors of a target vehicle with the EV, wherein the simulation model is a neural network trained to reflect the relationship between EV control parameters and the control of the simulated target vehicle, and the simulation model is created by the following steps: (a) collecting multiple sets of EV control parameters; (b) collecting multiple sets of simulated target vehicle controls; (c) processing the multiple sets of EV control parameters and multiple sets of target vehicle controls using a heat map to identify noise through data clustering; and (d) after processing the multiple sets of EV control parameters and the multiple sets of target vehicle controls, training the neural network with the multiple sets of EV control parameters and the multiple sets of target vehicle controls to obtain a simulation model corresponding to the target vehicle; obtain the plurality of vehicle parameters of the EV to generate additional sets of EV control parameters, the plurality of vehicle parameters of the EV including at least the operating time parameter of the EV and the driving condition of the EV; obtain a plurality of configuration parameters of the target vehicle, the plurality of configuration parameters including at least information about the target vehicle and settings of the target vehicle for the driver; based on the additional sets of EV control parameters and the plurality of configuration parameters of the target vehicle, use the simulation model to provide a set of simulated target vehicle controls; and output the set of simulated target vehicle controls to the EV such that the EV is controlled based on the set of simulated target vehicle controls to achieve the plurality of target behaviors of the target vehicle.

18. The simulation system according to claim 17, wherein the processor is further configured to: Before outputting the set of simulated target vehicle controls to the EV, a safety check is performed on the set of simulated target vehicle controls.

19. The simulation system according to claim 17, wherein the processor is further configured to: Collect the multiple sets of EV control parameters generated by inputting the multiple vehicle parameters of the EV into an EV simulator that simulates the behavior of the EV; Collect the multiple sets of EV control parameters generated by multiple anonymous EVs; And / or collect the multiple sets of EV control parameters generated by the EV.

20. The EV according to claim 4, wherein: The multiple target behaviors of the target vehicle include vehicle handling characteristics, gear shifting, dynamic engine sounds and vibrations transmitted to the driver's seat, a simulated dashboard of the target vehicle, or a combination thereof; and The multiple target behaviors of the target vehicle are not initially configured on the EV.

Images