Control method, device and vehicle

Abstract

The application provides a control method and device and a vehicle, which can be applied to the field of intelligent vehicles. The method comprises the following steps: acquiring a state of the vehicle, the state being used to indicate that the vehicle is in a manual driving state or used to indicate that the vehicle is in an intelligent driving state; and controlling a first processing unit and a second processing unit according to the state of the vehicle, the first processing unit and the second processing unit being used for intelligent driving of the vehicle. The application can be applied to intelligent vehicles and electric vehicles, and can control multiple processing units in the vehicle based on the state of the vehicle, thereby helping to improve the endurance of the vehicle.

Description

Technical Field

[0001] This application relates to the field of intelligent driving, and more specifically, to a control method, device, and vehicle. Background Technology

[0002] With the development of vehicle intelligence, intelligent driving has become a hot research topic. To ensure vehicle safety during operation and to achieve redundant control, some vehicles are currently equipped with a main processing unit and a backup processing unit. Both the main and backup processing units can output vehicle control commands, thereby improving the safety of the vehicle in intelligent driving mode. However, the overall energy consumption of multiple processing units is high, which may affect the vehicle's range. Summary of the Invention

[0003] This application proposes a control method, apparatus, and vehicle that can control multiple processing units in a vehicle based on the vehicle's state, thereby helping to improve the vehicle's range.

[0004] In a first aspect, this application provides a control method, which includes: acquiring the state of a vehicle, the state indicating that the vehicle is in a manual driving state, or the state indicating that the vehicle is in an intelligent driving state; and controlling a first processing unit and a second processing unit according to the state of the vehicle, the first processing unit and the second processing unit being used for intelligent driving of the vehicle.

[0005] Based on the above technical solution, since the computing power requirements of the processing unit are low in the manual driving state and high in the intelligent driving state, the first and second processing units can be controlled according to the vehicle's state. This is beneficial for adjusting the computing power of the processing units according to different states, which helps to reduce the power consumption of the processing units and thus helps to improve the vehicle's range.

[0006] In some possible implementations, the vehicle's state is obtained, including: obtaining the vehicle's state based on the intelligent driving functions that are enabled on the vehicle.

[0007] In conjunction with the first aspect, in some implementations of the first aspect, controlling the first processing unit and the second processing unit according to the vehicle's state includes: when the state indicates that the vehicle is in an intelligent driving state, controlling the first processing unit and the second processing unit according to first information, wherein the first information includes one or more of the following: a first intelligent driving function activated by the vehicle, environmental information around the vehicle, or the vehicle's remaining battery power.

[0008] Based on the above technical solution, when the vehicle is in intelligent driving mode, the first processing unit and the second processing unit can be controlled based on one or more of the following: the first intelligent driving function activated by the vehicle, environmental information around the vehicle, or the remaining battery power of the vehicle. This further enhances the flexibility in controlling the first and second processing units, helps adjust the state of the processing units according to different judgment criteria, and in certain scenarios, helps reduce the power consumption of the processing units, thereby contributing to improving the vehicle's range.

[0009] In conjunction with the first aspect, in some implementations of the first aspect, controlling the first processing unit and the second processing unit according to the first information includes: when the first intelligent driving function is a preset intelligent driving function, controlling at least some functions in the first processing unit to be enabled and controlling the second processing unit to stop working; or, when the first intelligent driving function is not a preset intelligent driving function, controlling at least some functions in the first processing unit and the second processing unit to be enabled.

[0010] Based on the above technical solution, when the first intelligent driving function is the preset intelligent driving function, at least some functions of the first processing unit can be turned on and the second processing unit can be turned off. In this way, one processing unit can be used to control the vehicle. While ensuring that the computing power of one processing unit can support some intelligent driving functions or lower intelligent driving levels, it helps to reduce the power consumption of the processing unit, thereby helping to improve the vehicle's range.

[0011] In conjunction with the first aspect, in some implementations of the first aspect, the first information includes environmental information surrounding the vehicle. Based on the first information, controlling the first processing unit and the second processing unit includes: when the environmental information meets preset conditions, controlling at least some functions in the first processing unit to start and controlling the second processing unit to stop working; or, when the environmental information does not meet preset conditions, controlling at least some functions in the first processing unit and the second processing unit to start.

[0012] Based on the above technical solution, when the environmental information meets preset conditions, at least some functions of the first processing unit can be activated and the second processing unit can be deactivated. In this way, when the environmental information around the vehicle meets certain conditions, controlling the vehicle through a single processing unit can ensure vehicle safety. Simultaneously, it helps reduce the power consumption of the processing unit, thereby contributing to improved vehicle range.

[0013] In some possible implementations, the preset conditions include, but are not limited to: the light intensity at the vehicle's current location is greater than or equal to a preset light intensity, the weather condition at the vehicle's location indicates that it is currently sunny, and the vehicle is on a structured road.

[0014] In conjunction with the first aspect, in some implementations of the first aspect, the first information includes the vehicle's remaining battery power. Based on the first information, controlling the first processing unit and the second processing unit includes: when the remaining battery power is less than or equal to a preset remaining battery power, controlling at least some functions in the first processing unit to be enabled and controlling the second processing unit to stop working; or, when the remaining battery power is greater than the preset remaining battery power, controlling at least some functions in the first processing unit and the second processing unit to be enabled.

[0015] Based on the above technical solution, when the vehicle's remaining battery power is less than or equal to the preset battery power, a processing unit can be used to control the vehicle, which helps to reduce the power consumption of the processing unit, thereby helping to improve the vehicle's range and avoid the vehicle's power interruption due to low remaining battery power.

[0016] In conjunction with the first aspect, in some implementations of the first aspect, the first information includes a first intelligent driving function, environmental information, and remaining battery power. Controlling the first processing unit and the second processing unit based on the first information includes: if the first intelligent driving function is a preset intelligent driving function, controlling the second processing unit to stop working and controlling at least some functions in the first processing unit to be activated based on the environmental information and / or remaining battery power; or, if the first intelligent driving function is not a preset intelligent driving function, controlling at least some functions in the first processing unit and the second processing unit to be activated based on the environmental information and / or remaining battery power.

[0017] Based on the above technical solution, when the first intelligent driving function is a preset intelligent driving function, the second processing unit can be controlled to stop working, and at least some functions in the first processing unit can be activated based on environmental information and / or remaining battery power. Thus, when the first information includes multiple parameters, the operating states of the first and second processing units can be determined primarily based on the intelligent driving function. And based on environmental information and / or remaining battery power, the functions in the processing units can be controlled. This helps improve the flexibility in controlling the operating states of the first and second processing units and the functions within them, and in certain scenarios, it helps reduce the power consumption of the processing units, thus contributing to increased vehicle range.

[0018] In conjunction with the first aspect, in some implementations of the first aspect, the first processing unit and the second processing unit include a target detection function. The method further includes: according to second information, controlling one or more of the following: the state of multiple sub-functions in the target detection function, the sampling frame rate of the first processing unit and the second processing unit, and the inference frequency of the models corresponding to the multiple sub-functions. The second information includes the road type where the vehicle is located and / or the intelligent driving function activated by the vehicle.

[0019] Based on the above technical solution, multiple sub-functions within the target detection function can be controlled according to the road type and / or the intelligent driving functions activated by the vehicle. This helps to improve the flexibility of the target detection function in the control processing unit.

[0020] In some possible implementations, these multiple sub-functions are used to detect targets other than motor vehicles.

[0021] In conjunction with the first aspect, in some implementations of the first aspect, multiple sub-functions include at least two of the following: traffic light detection function, sign detection function, and non-motor vehicle detection function.

[0022] In conjunction with the first aspect, in some implementations of the first aspect, the second information includes the road type where the vehicle is located. Based on the second information, one or more of the following are controlled: the state of multiple sub-functions in the target detection function, the sampling frame rate of the first processing unit and the second processing unit, or the inference frequency of the model corresponding to the multiple sub-functions. This includes: when the road type indicates that the vehicle is on a highway, controlling multiple sub-functions to be turned off; or, performing at least one of the following: controlling the sampling frame rate to a first sampling frame rate; or, controlling the inference frequency of the model corresponding to the multiple sub-functions to a first inference frequency; or, when the road type indicates that the vehicle is on a non-highway, performing at least one of the following: controlling the sampling frame rate to a second sampling frame rate; or, controlling the inference frequency of the model corresponding to the multiple sub-functions to a second inference frequency; wherein the first sampling frame rate is less than the second sampling frame rate, and the first inference frequency is less than the second inference frequency.

[0023] Based on the above technical solution, when the vehicle is on a highway, multiple sub-functions can be shut down, the first and second processing units can use a lower sampling frame rate, or the models corresponding to multiple sub-functions can use a lower inference frequency. In this way, while ensuring the vehicle's safe operation on highways, the overhead of the processing units can be reduced, which helps to improve the vehicle's range.

[0024] In conjunction with the first aspect, in some implementations of the first aspect, the second information includes the vehicle's activated intelligent driving function. Based on the second information, one or more of the following are controlled: the state of multiple sub-functions in the target detection function, the sampling frame rate of the first processing unit and the second processing unit, or the inference frequency of the models corresponding to the multiple sub-functions. This includes: when the intelligent driving function is a highway cruise function, controlling multiple sub-functions to be disabled; or performing at least one of the following: controlling the sampling frame rate to a first sampling frame rate; or controlling the inference frequency of the models corresponding to the multiple sub-functions to a first inference frequency; or, when the intelligent driving function is an urban road cruise function, performing at least one of the following: controlling the sampling frame rate to a second sampling frame rate; or controlling the inference frequency of the models corresponding to the multiple sub-functions to a second inference frequency; wherein the first sampling frame rate is less than the second sampling frame rate, and the first inference frequency is less than the second inference frequency.

[0025] Based on the above technical solution, when the vehicle's highway cruise control function is activated, multiple sub-functions can be controlled to be turned off, a lower sampling frame rate can be used, or the models corresponding to multiple sub-functions can use a lower inference frequency. In this way, while ensuring the vehicle's safe operation on highways, the overhead of the processing unit when the vehicle is on a highway can be reduced, which helps to improve the vehicle's range.

[0026] In conjunction with the first aspect, in some implementations of the first aspect, the method further includes: controlling the working mode of the sensor according to the third information, wherein the first processing unit and the second processing unit are used to process the data collected by the sensor, and the third information includes one or more of the following: environmental information around the vehicle, intelligent driving functions activated by the vehicle, and road type in which the vehicle is located.

[0027] Based on the above technical solution, the operating mode of the sensors can be controlled based on one or more of the following: environmental information surrounding the vehicle, the vehicle's activated intelligent driving functions, and the road type the vehicle is on. This allows for flexible control of the sensors' operating modes.

[0028] In some possible implementations, the sensor can operate at different power levels in different operating modes.

[0029] In some possible implementations, the sampling frequency range of the sensor differs depending on the operating mode.

[0030] In conjunction with the first aspect, in some implementations of the first aspect, the third information includes the road type where the vehicle is located. Based on the third information, the operating mode of the control sensor is configured as follows: if the road type where the vehicle is located is a highway, the operating mode of the control sensor is configured as a first operating mode; or if the road type where the vehicle is located is a non-highway, the operating mode of the control sensor is configured as a second operating mode.

[0031] Based on the above technical solution, the sensors can be controlled to adopt different operating modes depending on the road conditions. For example, when the vehicle is on a highway, the sensor's operating mode corresponds to a higher sampling frequency, which can increase the frequency at which the vehicle detection model in the processing unit acquires data. This helps to increase the frequency at which the vehicle detection model outputs vehicle targets, improves the timeliness of the processing unit's output of vehicle control commands, and thus helps to improve the user's driving safety.

[0032] In conjunction with the first aspect, in some implementations of the first aspect, the third information includes environmental information around the vehicle. Based on the third information, the operating mode of the sensor is controlled, including: when the environmental information around the vehicle meets preset conditions, the operating mode of the sensor is controlled to be the third operating mode; or, when the environmental information around the vehicle does not meet preset conditions, the operating mode of the sensor is controlled to be the fourth operating mode.

[0033] Based on the above technical solution, the sensors can be controlled to adopt different operating modes depending on the environmental information around the vehicle. For example, when the environmental information around the vehicle does not meet the preset conditions, the sensor's operating mode corresponds to a higher sampling frequency, which can increase the frequency at which the target detection model in the processing unit acquires data. This helps to increase the frequency at which the target detection model outputs targets, improves the timeliness of the processing unit's output of vehicle control commands, and thus helps to improve the user's driving safety.

[0034] In conjunction with the first aspect, in some implementations of the first aspect, the third information includes the intelligent driving function activated by the vehicle. Based on the third information, the operating mode of the control sensor is controlled, including: when the intelligent driving function activated by the vehicle is highway cruise function, the operating mode of the control sensor is controlled to be the fifth operating mode; or, when the intelligent driving function activated by the vehicle is urban road cruise function, the operating mode of the control sensor is controlled to be the sixth operating mode.

[0035] Based on the above technical solution, the sensors can be controlled to adopt different operating modes when different intelligent driving functions are activated in the vehicle. For example, when the vehicle is using highway cruise control, the sensor's operating mode corresponds to a higher sampling frequency, which can increase the frequency at which the vehicle detection model in the processing unit acquires data. This helps to increase the frequency at which the vehicle detection model outputs vehicle targets, improves the timeliness of the processing unit's output of vehicle control commands, and thus helps to improve the user's driving safety.

[0036] In conjunction with the first aspect, in some implementations of the first aspect, controlling the first processing unit and the second processing unit according to the vehicle's state includes: when the state indicates that the vehicle is in a manual driving state, controlling some functions in the first processing unit to be activated and controlling the second processing unit to stop working.

[0037] In some possible implementations, this part of the functionality is a function within the first processing unit that is unrelated to artificial intelligence. For example, this part of the functionality could be an image rendering function or a data processing function.

[0038] In conjunction with the first aspect, in some implementations of the first aspect, controlling the activation of certain functions in the first processing unit includes: controlling the activation of certain functions in the first processing unit based on the remaining battery power of the vehicle.

[0039] Secondly, this application provides a control device that includes units or modules for performing any of the possible methods in the first aspect.

[0040] Thirdly, a control device is provided, comprising: a processor for executing a computer program stored in the memory, such that the device performs the method in any possible implementation of the first aspect described above.

[0041] In conjunction with the third aspect, in some implementations of the third aspect, the device also includes a memory.

[0042] Fourthly, a computer program product is provided, comprising: computer program code, which, when executed on a computer or processor, causes the computer or processor to perform the method in any possible implementation of the first aspect.

[0043] It should be noted that the above computer program code can be stored in whole or in part on a storage medium, which can be packaged together with the processor or packaged separately from the processor.

[0044] Fifthly, a computer-readable storage medium is provided, the computer-readable medium storing instructions that, when executed by a processor, cause the processor to implement the method in any possible implementation of the first aspect.

[0045] In a sixth aspect, a chip system is provided, the chip system including a processor for supporting the implementation of the functions involved in the first aspect above, such as transmitting or processing the data and / or information involved in the methods described above.

[0046] In some possible implementations, the chip system also includes a memory for storing program instructions and data necessary for vehicle or communication equipment. The chip system can consist of chips or include chips and other discrete components.

[0047] In a seventh aspect, a vehicle is provided that includes means as in any possible implementation of the second or third aspect, or the vehicle includes a computer-readable storage medium as described in the fifth aspect, or the vehicle includes a chip system as described in the sixth aspect, or the vehicle is loaded with a computer program product as described in the fourth aspect.

[0048] The beneficial effects not described in detail in the second to seventh aspects above can be referred to the description in the first aspect, and will not be repeated here. Attached Figure Description

[0049] Figure 1 This is a functional schematic diagram of a vehicle provided in an embodiment of this application.

[0050] Figure 2 This is a schematic block diagram of the intelligent driving system provided in the embodiments of this application.

[0051] Figure 3 This is a schematic flowchart of the control method provided in the embodiments of this application.

[0052] Figure 4 This is a schematic diagram of the system architecture provided in the embodiments of this application.

[0053] Figure 5 This describes the data transmission process between the sensor and the processing unit provided in the embodiments of this application.

[0054] Figure 6 This is a schematic diagram of power supply for the intelligent driving system provided in this application.

[0055] Figure 7 This is a schematic diagram of a control device provided in an embodiment of this application. Detailed Implementation

[0056] The technical solutions of the embodiments of this application will be described below with reference to the accompanying drawings. In the description of the embodiments of this application, unless otherwise stated, " / " means "or," for example, A / B can mean A or B; "and / or" in this document is merely a description of the association relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, and B existing alone. "At least one" refers to one or more. For example, "at least one of A and B," similar to "A and / or B," describes the association relationship between related objects, indicating that three relationships can exist. For example, at least one of A and B can represent: A existing alone, A and B existing simultaneously, and B existing alone.

[0057] The use of prefixes such as "first" and "second," or suffixes such as "#1" and "#2," in the embodiments of this application is solely for distinguishing different descriptive objects and does not limit the position, order, priority, quantity, or content of the described objects. The use of ordinal numbers and other prefixes used to distinguish descriptive objects in the embodiments of this application does not constitute a limitation on the described objects. The description of the described objects is found in the claims or the context of the embodiments, and should not constitute unnecessary limitations due to the use of such prefixes. Furthermore, in the description of this embodiment, unless otherwise stated, "multiple" means two or more.

[0058] The technical solutions in this application will now be described with reference to the accompanying drawings.

[0059] See Figure 1 As an example, Figure 1 This is a functional schematic diagram of a vehicle 100 provided in an embodiment of this application.

[0060] It is understood that vehicle 100 may include multiple subsystems; for example, vehicle 100 may include a perception system 110 and a computing platform 120. In some implementations, vehicle 100 may include more subsystems, or it may include fewer subsystems. Each subsystem may include one or more components. Furthermore, each subsystem and component of vehicle 100 may be interconnected via wired or wireless means.

[0061] As an example, the perception system 110 may include several types of sensors for sensing information about the environment surrounding the vehicle 100. For instance, the perception system 110 may include a positioning system, which may be a global positioning system (GPS), a BeiDou system, or another positioning system. As another example, the perception system 110 may also include one or more of the following devices: an inertial measurement unit (IMU), a camera device, a lidar, a millimeter-wave radar, and an ultrasonic radar.

[0062] As an example, some or all of the functions of vehicle 100 can be controlled by computing platform 120. Exemplarily, computing platform 120 may include processors 121 to 12n (n being a positive integer), where the processor can be a circuit with signal processing capabilities. In some implementations, the aforementioned processor can be a circuit with instruction read and execute capabilities, such as a central processing unit (CPU), a microprocessor unit (MPU), a graphics processing unit (GPU) (which can be understood as a type of microprocessor), or a digital signal processor (DSP). In other implementations, the processor can implement certain functions through the logical relationships of hardware circuits, where the logical relationships of the hardware circuits are fixed or reconfigurable. For example, the processor may be a hardware circuit implemented using an application-specific integrated circuit (ASIC) or a programmable logic device (PLD), such as a field-programmable gate array (FPGA). In reconfigurable hardware circuits, the process of the processor loading a configuration document to implement the hardware circuit configuration can be understood as the process of the processor loading instructions to implement related functions. In addition, the processor can also be a hardware circuit designed for artificial intelligence. For example, the aforementioned processor can be understood as an ASIC, such as a neural network processing unit (NPU), a tensor processing unit (TPU), a deep learning processing unit (DPU), etc.

[0063] For example, the computing platform 120 may also include a memory, wherein the memory may be used to store instructions, and some or all of the processors 121 to 12n may call the instructions in the memory to perform the corresponding functions.

[0064] It is understood that the computing platform 120 can control the functions of the vehicle 100 based on inputs received from various subsystems (e.g., the perception system 110). In some implementations, the computing platform 120 can be used to provide control over many aspects of the vehicle 100 and its subsystems.

[0065] In some embodiments, vehicle 100 may further include a human-machine interaction system 130. As an example, the human-machine interaction system 130 may include a device for receiving user instructions and a device for providing prompts to the user. The device for receiving user instructions may include at least one of the following: a sound receiving device for receiving user voice instructions, such as a microphone, transceiver, etc.; or a device for receiving instructions input by the user through a screen, such as a human-machine interface (HMI); or a camera device for receiving instructions such as user body posture. The prompting device may include at least one of the following: a sound-emitting device and a display device. More specifically, the sound-emitting device may include a speaker, audio radiator, or other device for playing audio. Taking a vehicle as an example, display devices are mainly divided into two categories: the first is an in-vehicle display screen; the second is a projection display screen, such as a head-up display (HUD). An in-vehicle display screen is a physical display screen and an important component of an in-vehicle infotainment system, including instrument panel screens, central control screens, passenger entertainment screens, rear entertainment screens, and panoramic sunroofs. It should be noted that in-vehicle display screens may include HMIs.

[0066] The method provided in this application can be applied to the field of intelligent driving. For example, the method provided in this application can be used in application scenarios where some or all functions of a vehicle are turned on or off. The vehicle 100 in this application can include: road vehicles, water vehicles, air vehicles, industrial equipment, agricultural equipment, or entertainment equipment, etc. For example, vehicle 100 can be a means of transportation (such as commercial vehicles, passenger cars, motorcycles, flying cars, trains, etc.), industrial vehicles (such as forklifts, trailers, tractors, etc.), engineering vehicles (such as excavators, bulldozers, cranes, etc.), agricultural equipment (such as lawnmowers, harvesters, etc.), amusement equipment, toy vehicles, etc.; or vehicle 100 includes a wheeled device, which can be: a robot, mobile medical equipment, or an experimental platform. This application does not specifically limit the type of vehicle.

[0067] As an example, the intelligent driving system of vehicle 100 may include an advanced driving assistant system (ADAS) and an autonomous driving system (ADS). The intelligent driving system utilizes various sensors on the vehicle (including but not limited to: lidar, millimeter-wave radar, cameras, ultrasonic sensors, GPS, and inertial measurement units) to acquire information from the vehicle's surroundings, and analyzes and processes this information to achieve functions such as obstacle perception, target recognition, vehicle localization, path planning, and driver alerts, thereby improving the safety, automation, and comfort of vehicle driving.

[0068] See Figure 2 As an example, Figure 2 A schematic block diagram of an intelligent driving system provided in an embodiment of this application is shown. The intelligent driving system may include three functional modules: a perception module 210, a planning module 220, and a control module 230. The perception module 210 perceives the environment surrounding the vehicle through sensors and outputs corresponding perception data to the planning module 220. The planning module 220 obtains information such as road topology based on the information acquired by the perception module 210. Based on the road topology and destination information, the planning module 220 can determine a planned trajectory over a period of time. The planning module 220 can send this planned trajectory to the control module 230. After receiving the planned trajectory from the planning module 220, the control module 230 can output control signals to control actuators to take corresponding actions, such as braking, starting, steering, accelerating, decelerating, and honking.

[0069] For example, the above-mentioned sensing module 210, planning module 220 and control module 230 can be located in the above-mentioned computing platform 120.

[0070] It should be noted that the intelligent driving mentioned above refers to a comprehensive system that enables vehicles to have environmental perception, decision-making and planning, and / or autonomous control capabilities through technologies such as artificial intelligence, sensor fusion processing, and network information collaboration. Its core goal is to ultimately achieve a gradual transformation from human driving to machine autonomous driving. For example, the functions implemented by intelligent driving mainly include, but are not limited to: adaptive cruise control (ACC), automatic emergency braking (AEB), automatic parking (AP), blind spot monitoring (BSM), front cross-traffic braking (FCTB), front cross-traffic alert (FCTA), rear crossing traffic braking (RCTB), rear crossing traffic alert (RCTA), forward collision warning (FCW), lane departure warning (LDW), lane keeping assist (LKA), rear collision warning (RCW), traffic sign recognition (TSR), traffic jam assist (TJA), and highway assist (HWA). It should be understood that the various functions described above may have their own specific requirements and content at different levels of autonomous driving (e.g., L0-L5). Here, "intelligent driving" focuses on driving technology and functions, while "autonomous driving" focuses on driving capabilities. For example, intelligent driving may include assisted driving, conditional autonomous driving, highly automated driving, and fully automated driving.

[0071] It should be noted that the above functions and autonomous driving levels are only examples. Actual functions and autonomous driving levels can be divided and designed according to requirements. This application does not impose any restrictions on the division and design of functions and autonomous driving levels.

[0072] As an example, the degree to which a vehicle-based driving automation system can perform dynamic driving tasks is determined based on the role allocation in performing these tasks and the presence or absence of an operational design domain (ODD), such as the external conditions applicable to its operation as defined during the system's design, including road, traffic, weather, and lighting limitations. Driving automation is categorized into levels 0 to 5 (or L0-L5). Among these six levels, levels 0-2 represent driving assistance, where the system assists humans in performing dynamic driving tasks, with the driver remaining the primary driver. Levels 3-5 represent autonomous driving, where the system performs dynamic driving tasks in place of the human under the designed operating conditions; when activated, the system becomes the primary driver. The names and definitions of each level are as follows: Level 0 driving automation (also known as emergency assistance) systems cannot continuously perform lateral or longitudinal motion control of the vehicle during dynamic driving tasks, but they possess the ability to continuously perform partial target and event detection and response during dynamic driving tasks. Level 1 driving automation (also known as partial driver assistance) systems continuously perform lateral or longitudinal motion control of the vehicle during dynamic driving tasks under their design operating conditions, and possess the ability to perform partial target and event detection and response adapted to the performed lateral or longitudinal motion control. Level 2 driving automation (also known as combined driver assistance) systems continuously perform lateral and longitudinal motion control of the vehicle during dynamic driving tasks under their design operating conditions, and possess the ability to perform partial target and event detection and response adapted to the performed lateral and longitudinal motion control. Level 3 driving automation (also known as conditionally automated driving) systems continuously perform all dynamic driving tasks under their design operating conditions. Level 4 driving automation (also known as highly automated driving) systems continuously perform all dynamic driving tasks under their design operating conditions and automatically execute minimum risk strategies. Level 5 driving automation (also known as fully automated driving) systems continuously execute all dynamic driving tasks and automatically implement minimum-risk strategies under any drivable conditions. As mentioned in the background section above, intelligent driving technology has become a hot research topic. When a vehicle is in a Level 2 to Level 5 driving automation state, it can achieve intelligent driving. In other words, in these scenarios, the main controller of the vehicle can be the vehicle's intelligent driving system. To achieve redundant control of the vehicle, some current vehicles are equipped with a main processing unit and a backup processing unit. In this way, both the main processing unit and the backup processing unit can output vehicle control commands, thereby improving the safety of the vehicle in intelligent driving mode. However, the overall energy consumption of multiple processing units is high, which may affect the vehicle's range. The current Levels 0-5 are only an exemplary presentation; with the evolution of intelligent driving standards, other levels or functional definitions may emerge. This application does not limit the specific levels or functions.

[0073] This application provides a control method, device, and vehicle that can control multiple processing units in the vehicle based on the vehicle's state, thereby helping to improve the vehicle's range.

[0074] For example, Figure 3This is a schematic flowchart of a control method 300 provided in an embodiment of this application. Exemplarily, Figure 3 This can be executed by the aforementioned vehicle 100; or by the aforementioned computing platform 120; or by the processor, circuitry, or chip within the aforementioned computing platform 120; or by the aforementioned intelligent driving system. For example... Figure 3 As shown, the control method 300 may include: S310, obtain the vehicle's status.

[0075] In some possible implementations, the vehicle's status can be used to indicate whether the vehicle is in a manual driving state or an intelligent driving state.

[0076] For example, manual driving can be understood as the vehicle's movement being primarily controlled by the driver. For instance, manual driving could be the Level 0 or Level 1 driving automation mentioned earlier.

[0077] For example, intelligent driving state can be understood as: the movement of the vehicle is mainly controlled by the aforementioned intelligent driving system. For instance, intelligent driving state can be the L2 to L5 level driving automation mentioned above.

[0078] S320 controls a first processing unit and a second processing unit based on the vehicle's status. The first processing unit and the second processing unit are used for intelligent driving of the vehicle.

[0079] In some possible implementations, the first processing unit and the second processing unit may respectively acquire data from the sensors and generate vehicle control commands based on the sensor data.

[0080] For example, the first processing unit can acquire data collected by multiple sensors in the first sensor set, and generate a first vehicle control command based on the data collected by the multiple sensors in the first sensor set.

[0081] For example, the second processing unit can acquire data collected by multiple sensors in the second sensor set, and generate a second vehicle control command based on the data collected by the multiple sensors in the second sensor set.

[0082] For example, the sensors in the first sensor set and the sensors in the second sensor set are the same.

[0083] For example, Figure 4The diagram illustrates a system architecture provided in an embodiment of this application. This system architecture includes sensors and an intelligent driving system. Exemplarily, the sensors include a first camera device, a second camera device, a third camera device, a fourth camera device, a lidar, a millimeter-wave radar, and automated driving integrated positioning (ADIP). Exemplarily, the first camera device includes one or more of a forward-looking long-range camera, a left front camera, and a right front camera; the second camera device includes a surround-view camera; the third camera includes an 8M resolution camera and / or a time-of-flight (TOF) camera; and the fourth camera device includes a left rear camera and / or a right rear camera.

[0084] The data collected by the sensor can be accessed through the middle layer interface to System of Chip (SOC) 1 and SOC 2.

[0085] For example, data acquired by a camera device can be input to SOC1 and SOC2 via a deserializer. Data acquired by a lidar device can be input to SOC1 and SOC2 via a Layer 2 switch (LSW). Data acquired by a millimeter-wave radar can be input to SOC1 and the microcontroller unit (MCU) via a controller area network (CAN) bus. Data from an ADIP (Advanced Device Interface) can be input to SOC2 and the MCU via the CAN bus. Data acquired by an IMU (Integrated Mutual Utility Unit) can be input to the MCU.

[0086] In some possible implementations, the data acquired by the millimeter-wave radar can also be input to SOC1, SOC2 and MCU via CAN bus.

[0087] Figure 4 The intelligent driving system shown adopts a dual SOC redundancy design. There is a bidirectional communication link between SOC1 and SOC2 to realize data sharing or state synchronization. SOC1 can output the first processing result to the MCU based on the input data, and SOC2 can output the second processing result to the MCU based on the input data. The MCU can obtain the third processing result based on the input data, the first processing result and the second processing result.

[0088] The first and second processing results mentioned above can include backup vehicle control commands, and the third processing result can include the primary vehicle control command. When the MCU is functioning normally, the intelligent driving system can control the vehicle based on the primary vehicle control command. In the event of an MCU failure, the intelligent driving system can control the vehicle based on backup vehicle control commands. For example, in the event of both an MCU failure and a SOC1 failure, the vehicle can be controlled based on the vehicle control command in the second processing result. Thus, in the event of a single point of failure (SOC1, SOC2, or MCU), the above system architecture can achieve vehicle control and support parallel parking.

[0089] For example, the first processing unit can be as described above. Figure 4 The second processing unit of the SOC1 shown can be the one described above. Figure 4 The SOC2 shown.

[0090] In some possible implementations, the first processing unit and the second processing unit may each have corresponding functions.

[0091] For example, the first processing unit may possess one or more of the following functions: data processing, image rendering, active safety, cruise control, or automatic parking. For instance, the data processing function can process data input from sensors, such as performing data sampling. The image rendering function can render the vehicle's surrounding environment based on sensor-collected data; for example, this image rendering function can be used to render a surrounding reality (SR) interface or an environment information display (EID) interface. For example, the rendered interface can be displayed on the vehicle's central control screen or instrument panel, allowing the user to view the vehicle's surroundings. Active safety functions may include lateral and longitudinal active safety functions; for example, lateral active safety functions include automatic emergency steering (AES), and longitudinal active safety functions include automatic emergency braking (AEB). The cruise control function enables the vehicle to cruise in urban areas or on highways. The automatic parking function enables the vehicle to park automatically.

[0092] Similarly, the second processing unit may possess one or more of the following functions: data processing, image rendering, active safety, cruise control, automatic parking, or advanced intelligent driving functions. For example, advanced intelligent driving functions can achieve Level 3 or higher level of driving automation.

[0093] In some embodiments, the functions of the first processing unit and the second processing unit may be exactly the same. For example, both the first processing unit and the second processing unit may have the following functions: perception information processing, image acquisition, active safety, cruise control, and parking.

[0094] In some embodiments, the functions of the first processing unit and the second processing unit may be partially the same. For example, compared to the first processing unit, the second processing unit additionally includes advanced intelligent driving functions.

[0095] In some embodiments, each function of the processing unit can correspond to an algorithm model. For example, the data processing function in the first processing unit can correspond to a data processing model. The image rendering function can correspond to an image rendering model. The active safety function can correspond to an active safety model. The cruise control function can correspond to a cruise control model. The automatic parking function can correspond to a parking model.

[0096] The cruise and parking functions in the above processing units can be functions related to artificial intelligence (AI). For example, the cruise function may include traffic light detection, lane line detection, sign detection, motor vehicle detection, and non-motor vehicle detection, while the parking function may include parking space line detection, motor vehicle detection, and non-motor vehicle detection.

[0097] The following describes possible implementations of the first and second processing units for vehicle state control, taking into account the different states of the vehicle.

[0098] Scenario 1: The vehicle is in manual driving mode.

[0099] In some embodiments, controlling the first processing unit and the second processing unit according to the vehicle's state includes: when the vehicle is in a manual driving state, controlling the first processing unit to operate and controlling the second processing unit to stop operating. This helps reduce the overhead of the processing units when the vehicle is in a manual driving state, thereby contributing to improving the vehicle's range.

[0100] In some embodiments, when the vehicle is in a manual driving state, the first processing unit can be controlled to operate and the second processing unit can be controlled to stop operating. This includes: when the vehicle is in a manual driving state, controlling some functions in the first processing unit to be activated and controlling the second processing unit to stop operating. This helps to further reduce the overhead of the first processing unit, thereby contributing to improving the vehicle's range.

[0101] For example, when the vehicle is in manual driving mode, the data processing and image rendering functions in the first processing unit can be turned on, and other functions other than data processing and image rendering can be turned off.

[0102] For example, when the vehicle is in manual driving mode, the data processing function, AEB function and image rendering function in the first processing unit can be turned on, and other functions other than data processing function, AEB function and image rendering function can be turned off.

[0103] In some embodiments, when the vehicle is in a manual driving state, controlling some functions in the first processing unit to be activated and controlling the second processing unit to be deactivated includes: when the vehicle is in a manual driving state, controlling some functions in the first processing unit to be activated and controlling the second processing unit to be deactivated based on the vehicle's battery level.

[0104] For example, when the vehicle's battery level is less than or equal to a first battery level threshold, the data processing function, active safety function, and image rendering function in the first processing unit can be enabled while other functions are disabled; or, when the vehicle's battery level is less than or equal to the first battery level threshold, the data processing function and image rendering function in the first processing unit can be enabled while other functions are disabled.

[0105] In some embodiments, when the vehicle is in a manual driving state, controlling some functions in the first processing unit to be activated and controlling the second processing unit to stop working based on the vehicle's battery level, includes: when the vehicle is in a manual driving state, controlling some functions in the first processing unit to be activated and controlling the second processing unit to stop working based on the vehicle's battery level and vehicle speed.

[0106] For example, when the vehicle's battery level is greater than or equal to a first battery level threshold and the vehicle's speed is greater than or equal to a first preset speed, the data processing function, active safety function, and image rendering function in the first processing unit can be enabled, while other functions can be disabled.

[0107] For example, when the vehicle's battery level is greater than or equal to a first battery level threshold and the vehicle's speed is less than a first preset speed, the data processing function, active safety function, image rendering function, and parking function in the first processing unit can be enabled, while other functions can be disabled.

[0108] For example, when the vehicle's battery level is less than a first battery level threshold and the vehicle's speed is less than a first preset speed, the data processing function and image rendering function in the first processing unit can be turned on while other functions are turned off. Alternatively, the data processing function, image rendering function, and active safety function in the first processing unit can be turned on while other functions are turned off.

[0109] Scenario 2: The vehicle is in intelligent driving mode.

[0110] In some embodiments, controlling the first processing unit and the second processing unit according to the state of the vehicle includes: when the vehicle is in an intelligent driving state, controlling at least some functions of the first processing unit to be turned on and controlling the second processing unit to stop working, or controlling at least some functions of the first processing unit to be turned on and controlling at least some functions of the second processing unit to be turned on.

[0111] In some embodiments, controlling the first processing unit and the second processing unit according to the state of the vehicle includes: when the vehicle is in an intelligent driving state, controlling the first processing unit and the second processing unit according to first information, wherein the first information includes one or more of the following: a first intelligent driving function activated by the vehicle, the environment in which the vehicle is located, or the remaining battery power of the vehicle.

[0112] For example, the first level of intelligent driving can be the driving automation level described above.

[0113] In some embodiments, the first information includes a first intelligent driving function. According to the first information, controlling the first processing unit and the second processing unit includes: when the first intelligent driving function is a preset intelligent driving function, controlling at least some functions in the first processing unit to be turned on and controlling the second processing unit to stop working; or, when the first intelligent driving function is not a preset intelligent driving function, controlling at least some functions in the first processing unit and the second processing unit to be turned on.

[0114] In some embodiments, the preset intelligent driving function includes one or more intelligent driving functions.

[0115] For example, when lane cruise control (LCC) is activated in the vehicle, the data processing function, image rendering function, active safety function and cruise function in the first processing unit can be activated, and the second processing unit can be stopped from working.

[0116] For example, when the vehicle has its highway cruise control function activated, the data processing function, image rendering function, active safety function, and cruise control function in the first processing unit can be activated, and the data processing function, image rendering function, active safety function, cruise control function, and advanced intelligent driving function in the second processing unit can also be activated.

[0117] In some embodiments, the first intelligent driving function corresponds to a first intelligent driving level. According to the first information, controlling the first processing unit and the second processing unit includes: when the first intelligent driving level is less than or equal to a preset intelligent driving level, controlling at least some functions in the first processing unit to be enabled and controlling the second processing unit to stop working; or, when the first intelligent driving level is greater than the preset intelligent driving level, controlling at least some functions in the first processing unit to be enabled and controlling at least some functions in the second processing unit to be enabled.

[0118] For example, the preset intelligent driving level can be the L2 level mentioned above.

[0119] For example, when the vehicle is in intelligent driving mode and the intelligent driving level of the vehicle is L2, at least some functions in the first processing unit can be controlled to be turned on and the second processing unit can be controlled to stop working; or, when the vehicle is in intelligent driving mode and the intelligent driving level of the vehicle is L3 or higher, at least some functions in the first processing unit and the second processing unit can be controlled to be turned on.

[0120] For example, when the LCC function is activated in the vehicle, it can be determined that the vehicle is currently at L2 level. At this time, the vehicle can control the data processing function, image rendering function, active safety function and cruise function in the first processing unit to be activated and control the second processing unit to stop working.

[0121] For example, when the vehicle has activated the Level 3 cruise assist function, it can be determined that the vehicle is currently at Level 3. At this time, the vehicle can control the data processing function, image rendering function, active safety function and cruise function in the first processing unit to be activated, and control the data processing function, image rendering function, active safety function, cruise function and advanced intelligent driving function in the second processing unit to be activated.

[0122] In some embodiments, the first information includes environmental information of the vehicle. Controlling the first processing unit and the second processing unit according to the first information includes: when the environmental information meets preset conditions, controlling at least some functions of the first processing unit to be turned on and controlling the second processing unit to be turned off; or, when the environmental information does not meet preset conditions, controlling at least some functions of the first processing unit and the second processing unit to be turned on.

[0123] In some embodiments, the environmental information of the vehicle includes one or more of the following: light intensity at the vehicle's location, weather at the vehicle's location, road type of the road the vehicle is on, or traffic congestion around the vehicle.

[0124] In some embodiments, the preset conditions include one or more of the following: the light intensity at the vehicle's location is greater than or equal to a preset light intensity; the weather at the vehicle's location is sunny; the road type of the road where the vehicle is located is a structured road; and the traffic congestion around the vehicle indicates that the vehicle is in a non-congested section of road.

[0125] For example, when the vehicle is in intelligent driving mode and the light intensity at the vehicle's location is greater than or equal to a preset light intensity, at least some functions in the first processing unit can be controlled to be turned on and the second processing unit can be controlled to stop working; or, when the vehicle is in intelligent driving mode and the light intensity at the vehicle's location is less than a preset light intensity, at least some functions in the first processing unit and the second processing unit can be controlled to be turned on.

[0126] For example, when the vehicle is in intelligent driving mode and the weather at the location of the vehicle is sunny, at least some functions in the first processing unit can be controlled to be turned on and the second processing unit can be controlled to stop working; or, when the vehicle is in intelligent driving mode and the weather at the location of the vehicle is foggy, rainy, snowy or dusty, at least some functions in the first processing unit and the second processing unit can be controlled to be turned on.

[0127] For example, when the vehicle is in intelligent driving mode and the road type where the vehicle is located is a structured road, at least some functions in the first processing unit can be controlled to be turned on and the second processing unit can be controlled to stop working; or, when the vehicle is in intelligent driving mode and the road type where the vehicle is located is an unstructured road, at least some functions in the first processing unit and the second processing unit can be controlled to be turned on.

[0128] The structured road mentioned above can refer to a road with clear lane lines and road markings. For example, the structured road can be an urban arterial road, a highway, or other similar road.

[0129] For example, when the vehicle is in intelligent driving mode and the traffic congestion around the vehicle indicates that the vehicle is in a non-congested road segment, at least some functions in the first processing unit can be controlled to be activated and the second processing unit can be controlled to stop operating. When the vehicle is in intelligent driving mode and the traffic congestion around the vehicle indicates that the vehicle is in a congested road segment, at least some functions in the first and second processing units can be controlled to be activated.

[0130] In some embodiments, the first information includes the vehicle's remaining battery power. Based on the first information, controlling the first processing unit and the second processing unit includes: when the vehicle's remaining battery power is less than or equal to a preset battery power, controlling at least some functions in the first processing unit to be enabled and controlling the second processing unit to be disabled; or, when the vehicle's remaining battery power is greater than the preset battery power, controlling at least some functions in the first processing unit and the second processing unit to be enabled.

[0131] For example, the preset battery level is 20%.

[0132] In some embodiments, the first information includes a first intelligent driving function, environmental information around the vehicle, and the remaining battery power of the vehicle. Controlling the first processing unit and the second processing unit based on the first information includes: if the first intelligent driving function is a preset intelligent driving function, controlling the second processing unit to stop operating and controlling at least some functions in the first processing unit to be activated based on the environmental information around the vehicle and / or the remaining battery power of the vehicle; or, if the first intelligent driving function is not a preset intelligent driving function, controlling at least some functions in the first processing unit and the second processing unit to be activated based on the environmental information around the vehicle and / or the remaining battery power of the vehicle.

[0133] For example, when the vehicle's intelligent driving function is LCC (Lane Control Center), the second processing unit can be controlled to shut down, and at least some functions in the first processing unit can be controlled to be activated based on environmental information around the vehicle and / or the vehicle's remaining battery power. For instance, if the vehicle's remaining battery power is less than or equal to a preset battery level, the parking function of the first processing unit can be kept in a deactivated state. As another example, if the vehicle's remaining battery power is greater than a preset battery level, the parking function of the first processing unit can be kept in a pending state.

[0134] The above parking function being in an inactive state can be understood as the parking function in the first processing unit being turned off regardless of the vehicle's speed.

[0135] The parking function being in a pending state can be understood as determining whether the parking function is activated based on the vehicle's speed. For example, if the vehicle's speed is less than a preset speed, the parking function in the first processing unit can be activated. Conversely, if the vehicle's speed is greater than or equal to a preset speed, the parking function in the first processing unit can be deactivated.

[0136] For example, when the vehicle's intelligent driving function is LCC (Lead Control), the second processing unit can be controlled to shut down, and at least some functions in the first processing unit can be controlled to activate based on environmental information surrounding the vehicle. For instance, active safety functions include RCW (Responsive Control Warning), FCW (Forward Collision Warning), AEB (Automatic Emergency Braking), and AES (Automatic Safety System). In sunny weather, the AEB and AES functions in the first processing unit can be activated. In rainy or snowy weather, the RCW, FCW, AEB, and AES functions in the first processing unit can be activated.

[0137] The activation of the RCW or FCW function can be understood as the activation of the RCW and FCW functions to provide a warning to the user when the risk of collision between the vehicle and an obstacle behind or in front of the vehicle is greater than or equal to the first risk threshold.

[0138] The activation of the AEB and AES functions can be understood as activating the AEB and AES functions when the risk of collision between the vehicle and an obstacle in front of the vehicle is greater than or equal to the second risk threshold, where the second risk threshold is greater than the first risk threshold.

[0139] For example, the risk of collision between a vehicle and an obstacle can be determined by the time to collision (TTC) between the vehicle and the obstacle.

[0140] In some embodiments, the first processing unit and the second processing unit include a target detection function. The method 300 further includes: according to second information, controlling one or more of the following: the state of multiple sub-functions in the target detection function, the sampling frame rate of the first processing unit and the second processing unit, and the inference frequency of the model corresponding to the multiple sub-functions. The multiple sub-functions correspond to different types of target detection functions. The second information includes the road type where the vehicle is located and / or the intelligent driving function activated by the vehicle. The multiple sub-functions are used to detect targets other than motor vehicles.

[0141] In the case where only the first processing unit is working in the first processing unit and the second processing unit, the sampling frame rate of the first processing unit can be controlled; or, in the case where both the first processing unit and the second processing unit are working, the sampling frame rate of the first processing unit and the second processing unit can be controlled.

[0142] For example, the road type in which the vehicle is located includes whether the vehicle is on a highway or a non-highway.

[0143] The above sampling frame rate can also be understood as the frame rate at which the processing unit samples data from the sensor.

[0144] For example, data sampling by the processing unit can refer to the process by which the processing unit extracts discrete data points from the raw data collected by the sensor at certain time intervals.

[0145] For example, the processing unit can extract discrete data points from continuous physical signals (such as electromagnetic waves and light signals) from sensors at certain time intervals.

[0146] In some embodiments, the road type where the vehicle is located can be obtained through the vehicle's location information and / or navigation information.

[0147] For example, the multiple sub-functions include at least two of the following: traffic light detection function, sign detection function, or non-motor vehicle detection function.

[0148] The above inference frequency can refer to the number of times the model performs inference per unit of time.

[0149] In some embodiments, the method 300 further includes: controlling the inference frequency of the model through software adjustment, and / or controlling the inference frequency of the model through hardware adjustment.

[0150] In some embodiments, controlling the inference frequency of the model through software adjustment includes adjusting the inference frequency of the model through one or more of frame skipping, model lightweighting, and dynamic exit.

[0151] For example, in the processing of video data by the model, the inference frequency of the model can be reduced by inferring once every n frames instead of inferring for every frame, where n is a positive integer.

[0152] For example, by pruning the model to remove certain neuron connections, the inference frequency of the model can be reduced.

[0153] For example, a model corresponding to a certain sub-function may include a large model and a small model. The small model can be obtained by distilling the large model. When it is necessary to reduce the inference frequency, the small model can be used for inference. When it is necessary to increase the inference frequency, the large model can be used for inference.

[0154] For example, an "exit" can be set in the middle layer of the model. If the results with high confidence can be obtained in the first few layers, the calculation can be stopped and the remaining layers can be stopped, thereby increasing the inference frequency.

[0155] In some embodiments, controlling the inference frequency of the model through hardware adjustment includes: adjusting the inference frequency of the model by changing the clock frequency of a chip, which can be a chip in a first processing unit or a second processing unit.

[0156] For example, the chip mentioned above can be one or more of a CPU, GPU, or NPU.

[0157] For example, if the total amount of computation required for model inference remains unchanged, reducing the chip's clock frequency can make the chip take longer to complete the same amount of convolution or attention mechanism operations, thereby increasing the time required for a single inference operation or reducing the number of inference tasks the model can complete per unit of time.

[0158] In some embodiments, according to the second information, controlling multiple sub-functions in the target detection function includes: when the road type of the vehicle indicates that the vehicle is on a highway, controlling at least some of the sub-functions to be turned off, or performing at least one of the following: controlling the sampling frame rate to a first sampling frame rate, or controlling the inference frequency to a first inference frequency; or when the road type of the vehicle indicates that the vehicle is on a non-highway, performing at least one of the following: controlling the sampling frame rate to a second sampling frame rate, or controlling the inference frequency to a second inference frequency, wherein the first sampling frame rate is less than the second sampling frame rate, and the first inference frequency is less than the second inference frequency.

[0159] For example, when the vehicle is on a highway, the traffic light detection function, sign detection function, or non-motorized vehicle detection function in the target detection function can be turned off; or, when the vehicle is on an urban road, the traffic light detection function, sign detection function, or non-motorized vehicle detection function can be turned on.

[0160] In some embodiments, according to the second information, controlling multiple sub-functions in the target detection function includes: when the intelligent driving function activated by the vehicle is highway cruise function, controlling at least some of the sub-functions to turn off, or performing at least one of the following: controlling the sampling frame rate to a first sampling frame rate, or controlling the inference frequency to a first inference frequency; or when the intelligent driving function activated by the vehicle is urban road cruise function, performing at least one of the following: controlling the sampling frame rate to a second sampling frame rate, or controlling the inference frequency to a second inference frequency, wherein the first sampling frame rate is less than the second sampling frame rate, and the first inference frequency is less than the second inference frequency.

[0161] In some embodiments, the method 300 further includes: controlling the operating mode of the sensor according to third information, the third information including one or more of the following: environmental information around the vehicle, intelligent driving functions activated by the vehicle, and the road type where the vehicle is located.

[0162] In some embodiments, the third information includes the road type where the vehicle is located. Based on the third information, the operating mode of the sensor is controlled, including: if the road type where the vehicle is located is a highway, the operating mode of the sensor is controlled to be a first operating mode; or if the road type where the vehicle is located is a non-highway, the operating mode of the sensor is controlled to be a second operating mode.

[0163] In this embodiment, when the vehicle is on a highway, the speed of surrounding targets is relatively high, and the vehicle has a high demand for monitoring the position changes of these targets. Therefore, the sensors can be controlled to use a higher sampling frequency to improve the processing unit's position update rate, thus ensuring vehicle safety. When the vehicle is not on a highway, the speed of surrounding targets is relatively slow, so the sensors can be controlled to use a lower sampling frequency. While ensuring safety, this reduces the overhead of the processing unit, thereby improving the vehicle's range.

[0164] In some embodiments, the sensor can operate at different power levels under different operating modes.

[0165] For example, in the first operating mode, the sensor operates in a first power range, and in the second operating mode, the sensor operates in a second power range.

[0166] For example, the minimum value of the first power range is greater than the maximum value of the second power range.

[0167] In some embodiments, different operating modes may correspond to different sampling frequencies, or different operating modes may correspond to different sampling frequency ranges.

[0168] For example, in the first operating mode, the sensor's sampling frequency is located in the first sampling frequency range, and in the second operating mode, the sensor's sampling frequency is located in the second sampling frequency range.

[0169] For example, the minimum value of the first sampling frequency interval is greater than or equal to the maximum value of the second sampling frequency interval. For instance, the first sampling frequency interval is [a, b], and the second sampling frequency interval is [c, d], where a is greater than or equal to d.

[0170] For example, the first operating mode can be a high-frequency mode, in which the camera's sampling frequency range is [50fps, 60fps]; the second operating mode can be a normal mode, in which the camera's sampling frequency is [30fps, 40fps]. In some embodiments, the third information includes environmental information around the vehicle. Controlling the sensor's operating mode according to the third information includes: controlling the sensor to operate in the third operating mode when the environmental information around the vehicle meets preset conditions; or controlling the sensor to operate in the fourth operating mode when the environmental information around the vehicle does not meet preset conditions.

[0171] In some embodiments, the third information includes environmental information around the vehicle. Based on the third information, the operating mode of the sensor is controlled, including: when the weather at the location of the vehicle is sunny, the operating mode of the sensor is controlled to be a third operating mode; or when the weather at the location of the vehicle is cloudy, rainy, snowy, or dusty, the operating mode of the sensor is controlled to be a fourth operating mode.

[0172] In this embodiment, when the weather is sunny at the vehicle's location, the sensor sampling frequency can be appropriately reduced due to the high accuracy of the data collected by the sensors. This reduces the overhead of the processing unit while ensuring vehicle safety, thereby helping to improve the vehicle's range. Conversely, when the weather is cloudy, rainy, snowy, or dusty at the vehicle's location, the sensor sampling frequency can be appropriately increased due to the relatively low accuracy of the data collected by the sensors, thus helping to ensure vehicle driving safety.

[0173] For example, in the third operating mode, the sensor's sampling frequency is in the third sampling frequency range, and in the fourth operating mode, the sensor's sampling frequency is in the fourth sampling frequency range.

[0174] For example, the minimum value of the third sampling frequency interval is greater than or equal to the maximum value of the fourth sampling frequency interval. For instance, the third sampling frequency interval is [a, b], and the fourth sampling frequency interval is [c, d], where a is greater than or equal to d.

[0175] In some embodiments, the third information includes the intelligent driving function activated by the vehicle. Based on the third information, the operating mode of the sensor is controlled, including: when the intelligent driving function activated by the vehicle is highway cruise, the operating mode of the sensor is controlled to be a fifth operating mode; or, when the intelligent driving function activated by the vehicle is urban road cruise, the operating mode of the sensor is controlled to be a sixth operating mode.

[0176] For example, in the fifth operating mode, the sensor's sampling frequency is in the fifth sampling frequency range, and in the sixth operating mode, the sensor's sampling frequency is in the sixth sampling frequency range.

[0177] For example, the minimum value of the fifth sampling frequency interval is greater than or equal to the maximum value of the sixth sampling frequency interval. For instance, the fifth sampling frequency interval is [a, b], and the sixth sampling frequency interval is [c, d], where a is greater than or equal to d.

[0178] Taking the target detection function in the processing unit as an example, Figure 5 The process of data transmission between the sensor and the processing unit provided in the embodiments of this application is illustrated. For example... Figure 5 As shown, the sensor can independently go into sleep mode and wake up.

[0179] For example, the sampling frequency of the sensor can be adjusted. For instance, the sampling frequency of the sensor can be controlled based on the third information mentioned above.

[0180] For example, the frequency at which the sensor sends data to the processing unit can be adjusted. For instance, the frequency at which the sensor sends data to the intelligent driving system can be controlled based on the aforementioned third information. If the vehicle is on a highway, the frequency at which the sensor sends data to the intelligent driving system can be controlled to a first frequency; if the vehicle is not on a highway, the frequency at which the sensor sends data to the intelligent driving control system can be controlled to a second frequency, where the first frequency is greater than the second frequency.

[0181] The processing unit includes a data sampling module, a target detection model, and a target filtering module. The data sampling module can sample data from the sensor. The specific data sampling process can be referred to the description in the above embodiments, and will not be repeated here.

[0182] For example, the frame rate at which the data sampling module samples data can be adjusted.

[0183] For example, the number of targets obtained after data sampling by the data sampling module can also be adjusted. For instance, the data sampling module can select targets with high confidence levels.

[0184] The target detection model can acquire data obtained after the data sampling module performs data sampling.

[0185] For example, the target detection model may include multiple sub-models, such as a traffic light detection model, a sign detection model, and a non-motorized vehicle detection model.

[0186] For example, the states of multiple sub-models in the object detection model can be adjusted. For instance, when vehicles are on a highway, the traffic light detection model, sign detection model, and non-motorized vehicle detection model can be turned off.

[0187] The target filtering module can filter the targets output by the target detection model.

[0188] For example, the target detection model also includes a motor vehicle detection model. The target filtering module can filter motor vehicles, which may include filtering by the type of motor vehicle or by the area where the motor vehicle is located.

[0189] For example, when a vehicle is on a highway, the vehicle detection model can filter the area around the vehicle where other vehicles are located. If the vehicle has LCC (Lane Control Center) enabled, the target filtering module can filter out vehicles that are in the same lane as the vehicle.

[0190] For example, the target filtering module can filter out targets with high confidence or high risk from the targets output by the target detection model.

[0191] The following is combined with Figure 6 This application provides a detailed illustration of the diagram illustrating the power supply for the intelligent driving system.

[0192] See Figure 6 The intelligent driving system 10 may include a first processing unit 11, a second processing unit 12, a first power supply 115, and a second power supply 125. The first processing unit 11 is connected to the output terminal of the first power supply 115, and the input terminal of the first power supply 115 is connected to the first output terminal 21 of the fast disconnection threshold 20. The second processing unit 12 is connected to the output terminal of the second power supply 125, and the input terminal of the second power supply 125 is connected to the second output terminal 22 of the fast disconnection threshold 20. The input terminal 23 of the fast disconnection threshold 20 is connected to a third power supply 30.

[0193] As an example, the first processing unit 11 and the second processing unit 12 can be used for intelligent driving of a vehicle. For instance, the first processing unit 11 and the second processing unit 12 can receive data from sensors and control the vehicle based on that data.

[0194] It is understandable that the functions of the first processing unit 11 and the second processing unit 12 can be exactly the same or partially the same.

[0195] As an example, the first power supply 115 and the second power supply 125 can serve as backup power supplies. For instance, when the circuit between the input terminal of the first power supply 115 and the third power supply 30 is open, the first power supply 115 can store electrical energy from the third power supply 30. When the circuit between the input terminal of the first power supply 115 and the third power supply 30 is closed, the first power supply 115 can provide electrical energy to the first processing unit 11, allowing the first processing unit 11 to continue operating for a certain period of time.

[0196] As an example, the fast disconnect threshold 20 can be used for circuit protection. Exemplarily, when the circuit between the input of the first power supply 115 and the third power supply 30 is open, the fast disconnect threshold 20 can be used to prevent damage to components due to excessive instantaneous voltage in the circuit. When the circuit between the input of the first power supply 115 and the third power supply 30 is closed, the fast disconnect threshold 20 can be used to prevent component reset due to insufficient instantaneous voltage in the circuit.

[0197] Continue reading Figure 6 The intelligent driving system 10 may also include a microcontroller unit 13 and a fourth power supply 135. The microcontroller unit 13 is connected to the output terminal of the fourth power supply 135, and the two input terminals of the fourth power supply 135 are respectively connected to the first output terminal 21 and the second output terminal 22 of the fast disconnection threshold 20.

[0198] As an example, the microcontroller unit 13 can also be used to control a vehicle. For instance, the first processing unit 11 and the second processing unit 12 can process the sensor data and send the processing results to the microcontroller unit 13, which can then control the vehicle based on the processing results. Alternatively, the microcontroller unit 13 can directly receive sensor data and control the vehicle based on that data.

[0199] As an example, the fourth power supply 135 can also serve as a backup power supply. The two input terminals of the fourth power supply 135 can be connected to the first output terminal 21 and the second output terminal 22 of the fast disconnection threshold 20, respectively. Providing two separate power supplies helps ensure a stable power supply to the microcontroller unit 13. If both circuits are disconnected, the fourth power supply 135 can still supply power to the microcontroller unit 13, allowing it to continue operating for a period of time.

[0200] In some embodiments, in the event of a failure of the microcontroller unit 13, either the first processing unit 11 or the second processing unit 12 can be configured as the vehicle's main controller. In other words, in the event of a failure of the microcontroller unit 13, either the first processing unit 11 or the second processing unit 12 can be configured to directly output vehicle control commands to control the vehicle, which helps to prevent the vehicle from losing control when the microcontroller unit 13 fails and improves vehicle safety.

[0201] This application also provides a control device, in which each unit implements the corresponding process of the above method embodiments. The device includes an acquisition unit and a processing unit. The acquisition unit can be used to implement corresponding data acquisition or transmission / reception functions, and the processing unit can be used to implement corresponding processing functions.

[0202] Optionally, the device further includes a storage unit, which can be used to store instructions and / or data, and the processing unit can read the instructions and / or data in the storage unit so that the device can perform the relevant actions in the foregoing method embodiments.

[0203] It should be understood that the specific process of each unit performing the above-mentioned corresponding steps has been described in detail in the above method embodiments, and will not be repeated here for the sake of brevity. It should also be understood that the device described here is embodied in the form of a functional unit. The terms "module" or "unit" here may refer to an ASIC, electronic circuitry, a processor (e.g., a shared processor, a proprietary processor, or a group processor, etc.) and memory for executing one or more software or firmware programs, integrated logic circuitry, and / or other suitable components that support the described functions.

[0204] The apparatuses described above have the function of implementing the corresponding steps in the methods described above. These functions can be implemented in hardware or by hardware executing corresponding software. The hardware or software includes one or more modules corresponding to the functions described above; for example, the acquisition unit can be replaced by a transceiver, and other units, such as the processing unit, can be replaced by a processor, used to execute the relevant processing operations in each method embodiment.

[0205] For example, the operations performed by the acquisition unit and the processing unit described above can be performed by a single processor, or they can be performed by different processors.

[0206] In the specific implementation process, the units in the above devices can be fully or partially integrated together, or they can be implemented independently. In one implementation, these units are integrated together and implemented in the form of a system-on-a-chip (SoC).

[0207] The following will combine Figure 7 The apparatus provided in the embodiments of this application is described in detail. It should be understood that the description of the apparatus embodiments corresponds to the description of the method embodiments. Therefore, for content not described in detail, please refer to the method embodiments above. For the sake of brevity, it will not be repeated here.

[0208] See Figure 7 As an example, Figure 7 This is a schematic diagram of a control device 700 provided in an embodiment of this application. The device 700 includes a memory 710, a processor 720, and a communication interface 730. The memory 710, processor 720, and communication interface 730 are connected via an internal connection path. The memory 710 stores instructions, and the processor 720 executes the instructions stored in the memory 710 to control the communication interface 730 to acquire information, thereby enabling the device 700 to implement the aforementioned control method. Optionally, the memory 710 can be coupled to the processor 720 via an interface, or it can be integrated with the processor 720.

[0209] It should be noted that the communication interface 730 described above uses a transceiver device, such as, but not limited to, a transceiver. The communication interface 730 may also include an input / output interface.

[0210] The processor 720 stores one or more computer programs, which include instructions. When the instructions are executed by the processor 720, the control device 700 performs the control methods described in the above embodiments.

[0211] In implementation, each step of the above method can be completed by the integrated logic circuitry of the hardware in the processor 720 or by instructions in software form. The method disclosed in the embodiments of this application can be directly implemented by the hardware processor, or by a combination of hardware and software modules in the processor. The software modules can reside in random access memory, flash memory, read-only memory, programmable read-only memory, electrically erasable programmable memory, registers, or other mature storage media in the art. This storage medium is located in memory 710, and the processor 720 reads the information in memory 710 and, in conjunction with its hardware, completes the steps of the above method. To avoid repetition, detailed descriptions are not provided here.

[0212] As one possible implementation, the control device 700 can be a physical device, such as including one or more of the following modules: central processing unit, microprocessor, application-specific integrated circuit, field-programmable gate array, complex programmable logic device (CPLD), coprocessor (assisting the central processing unit in completing corresponding processing and applications), microcontroller unit (MCU), domain controller (DC), vehicle domain controller (VDC), electronic control unit (ECU), cockpit domain controller (CDC), vehicle integration unit (VIU), vehicle control unit (VCU), motor control unit (MCU), etc. Furthermore, the control device 700 includes at least one processor integrated in the form of a System-on-Chip (SOC), commonly referred to by those skilled in the art as an SOC. This SOC may include at least one processor, and when the SOC includes multiple processors, the types of processors may be different.

[0213] Optionally, Figure 7 The communication interface 730 in the above embodiment can implement step S310. Figure 5 The processor 720 in the above embodiment can implement step S320.

[0214] Optionally, the device 700 can be located in Figure 1 Of the 100 vehicles in the list.

[0215] Optionally, the device 700 can be Figure 1 The computing platform 130 in the vehicle.

[0216] This application also provides a computer-readable storage medium storing program code that, when run on a computer, causes the computer to perform any of the methods described in the above embodiments.

[0217] This application also provides a computer program product, which includes a computer program that, when run, causes a computer to perform any of the methods described in the above embodiments.

[0218] This application also provides a chip, including: a circuit for performing any of the methods in the above embodiments.

[0219] This application embodiment also provides a vehicle, including as follows: Figure 7 The control device shown.

[0220] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0221] Those skilled in the art will understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0222] In the several embodiments provided in this application, it should be understood that the disclosed systems, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between apparatuses or units may be electrical, mechanical, or other forms.

[0223] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0224] In addition, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0225] If the aforementioned functions are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0226] It should be noted that the personal information and data processing (e.g., collection, storage, use, processing, transmission, provision and disclosure) involved in this application that are protected by the laws and regulations of the relevant countries and regions comply with the relevant laws and regulations of the relevant countries and regions.

[0227] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. A control method, characterized in that, include: The vehicle status is obtained, wherein the status indicates that the vehicle is in manual driving mode, or the status indicates that the vehicle is in intelligent driving mode. Based on the vehicle's state, a first processing unit and a second processing unit are controlled, which are used for intelligent driving of the vehicle.

2. The control method according to claim 1, characterized in that, The step of controlling the first processing unit and the second processing unit according to the state of the vehicle includes: When the state indicates that the vehicle is in intelligent driving mode, the first processing unit and the second processing unit are controlled according to the first information, wherein the first information includes one or more of the following: the first intelligent driving function activated by the vehicle, environmental information around the vehicle, or the remaining battery power of the vehicle.

3. The control method according to claim 2, characterized in that, The first information includes the first intelligent driving function, and the step of controlling the first processing unit and the second processing unit according to the first information includes: When the first intelligent driving function is a preset intelligent driving function, at least some functions in the first processing unit are activated and the second processing unit is deactivated; or... If the first intelligent driving function is not the preset intelligent driving function, at least some functions of the first processing unit and the second processing unit are activated.

4. The control method according to claim 2, characterized in that, The first information includes environmental information surrounding the vehicle. The step of controlling the first processing unit and the second processing unit based on the first information includes: When the environmental information meets preset conditions, at least some functions in the first processing unit are enabled, and the second processing unit is stopped; or... If the environmental information does not meet the preset conditions, at least some functions of the first processing unit and the second processing unit are enabled.

5. The control method according to claim 2, characterized in that, The first information includes the vehicle's remaining battery power. The step of controlling the first processing unit and the second processing unit based on the first information includes: If the remaining battery power is less than or equal to a preset remaining battery power, at least some functions in the first processing unit are activated and the second processing unit is stopped; or... When the remaining battery power is greater than the preset remaining battery power, at least some functions of the first processing unit and the second processing unit are activated.

6. The control method according to claim 2, characterized in that, The first information includes the first intelligent driving function, the environmental information, and the remaining battery power. The step of controlling the first processing unit and the second processing unit based on the first information includes: When the first intelligent driving function is a preset intelligent driving function, the second processing unit is controlled to stop working, and at least some functions in the first processing unit are controlled to be activated based on the environmental information and / or the remaining battery power; or... If the first intelligent driving function is not the preset intelligent driving function, at least some functions of the first processing unit and the second processing unit are activated based on the environmental information and / or the remaining battery power.

7. The control method according to any one of claims 1 to 6, characterized in that, The first processing unit and the second processing unit include target detection functionality, and the method further includes: Based on the second information, the state of multiple sub-functions in the target detection function, the sampling frame rate of the first processing unit and the second processing unit, and the inference frequency of the model corresponding to the multiple sub-functions are controlled, one or more of these factors. The second information includes the road type where the vehicle is located and / or the intelligent driving function activated by the vehicle. The multiple sub-functions are used to detect targets other than motor vehicles.

8. The control method according to claim 7, characterized in that, The multiple sub-functions include at least two of the following: traffic light detection function, sign detection function, and non-motor vehicle detection function.

9. The control method according to claim 7 or 8, characterized in that, The second information includes the road type where the vehicle is located. The step of controlling one or more of the following based on the second information: the state of multiple sub-functions in the target detection function, the sampling frame rate of the first processing unit and the second processing unit, and the inference frequency of the models corresponding to the multiple sub-functions: If the road type indicates that the vehicle is on a highway, control the multiple sub-functions to be disabled, or perform at least one of the following: control the sampling frame rate to a first sampling frame rate, or control the inference frequency to a first inference frequency; or... If the road type indicates that the vehicle is on a non-highway, perform at least one of the following: control the sampling frame rate to a second sampling frame rate, or control the inference frequency to a second inference frequency; Wherein, the first sampling frame rate is less than the second sampling frame rate, and the first inference frequency is less than the second inference frequency.

10. The control method according to claim 7 or 8, characterized in that, The second information includes the intelligent driving function activated by the vehicle. The step of controlling one or more of the following based on the second information: the state of multiple sub-functions in the target detection function, the sampling frame rate of the first processing unit and the second processing unit, and the inference frequency of the models corresponding to the multiple sub-functions: When the intelligent driving function is a highway cruise function, the plurality of sub-functions are turned off, or at least one of the following is performed: the sampling frame rate is controlled to be a first sampling frame rate, or the inference frequency is controlled to be a first inference frequency; or... When the intelligent driving function is urban road cruise function, at least one of the following is performed: controlling the sampling frame rate to a second sampling frame rate, or controlling the inference frequency to a second inference frequency; Wherein, the first sampling frame rate is less than the second sampling frame rate, and the first inference frequency is less than the second inference frequency.

11. The control method according to any one of claims 1 to 10, characterized in that, The method further includes: According to the third information, the operating mode of the control sensor is controlled. The first processing unit and the second processing unit are used to process the data collected by the sensor. The third information includes one or more of the following: environmental information around the vehicle, intelligent driving function activated by the vehicle, and road type where the vehicle is located.

12. The control method according to claim 11, characterized in that, The third information includes the road type where the vehicle is located, and controlling the sensor's operating mode based on the third information includes: If the vehicle is on a highway, the sensor is controlled to operate in the first operating mode; or... When the vehicle is on a non-highway road, the sensor is controlled to operate in the second operating mode.

13. The control method according to claim 11, characterized in that, The third information includes environmental information surrounding the vehicle, and controlling the sensor's operating mode based on the third information includes: If the environmental information around the vehicle meets preset conditions, the sensor's operating mode is controlled to the third operating mode; or... If the environmental information around the vehicle does not meet the preset conditions, the sensor is controlled to operate in the fourth operating mode.

14. The control method according to claim 11, characterized in that, The third information includes the intelligent driving function activated by the vehicle, and controlling the working mode of the sensor according to the third information includes: When the vehicle's intelligent driving function is set to highway cruise control, the sensor's operating mode is controlled to the fifth operating mode; or, When the intelligent driving function activated by the vehicle is the urban road cruise function, the operating mode of the sensor is controlled to be the sixth operating mode.

15. The control method according to any one of claims 1 to 14, characterized in that, The step of controlling the first processing unit and the second processing unit according to the state of the vehicle includes: When the status indicates that the vehicle is in the manual driving state, some functions in the first processing unit are activated and the second processing unit is stopped.

16. The control method according to claim 15, characterized in that, The control of enabling certain functions in the first processing unit includes: Based on the vehicle's remaining battery power, some functions in the first processing unit are activated.

17. A control device, characterized in that, Includes modules or units for performing the method according to any one of claims 1 to 16.

18. A control device, characterized in that, include: A processor for executing a computer program stored in memory to cause the apparatus to perform the method as described in any one of claims 1 to 16.

19. A computer-readable storage medium, characterized in that, It stores instructions that, when executed by a processor, implement the method as described in any one of claims 1 to 16.

20. A computer program product, characterized in that, The computer program product includes: computer program code, which, when executed by a processor, implements the method as described in any one of claims 1 to 16.

21. A vehicle, characterized in that, Includes the apparatus as described in claim 17 or 18, or the computer-readable storage medium as described in claim 19, or the vehicle is equipped with the computer program product as described in claim 20.

Images