WO2022193137A1 - 车辆控制方法及装置 - Google Patents

车辆控制方法及装置 Download PDF

Info

Publication number
WO2022193137A1
WO2022193137A1 PCT/CN2021/081106 CN2021081106W WO2022193137A1 WO 2022193137 A1 WO2022193137 A1 WO 2022193137A1 CN 2021081106 W CN2021081106 W CN 2021081106W WO 2022193137 A1 WO2022193137 A1 WO 2022193137A1
Authority
WO
WIPO (PCT)
Prior art keywords
braking deceleration
vehicle
target
braking
information
Prior art date
Application number
PCT/CN2021/081106
Other languages
English (en)
French (fr)
Inventor
汪洁
邹文韬
李小凯
杜引
Original Assignee
华为技术有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 华为技术有限公司 filed Critical 华为技术有限公司
Priority to PCT/CN2021/081106 priority Critical patent/WO2022193137A1/zh
Priority to CN202180000616.7A priority patent/CN113165615A/zh
Publication of WO2022193137A1 publication Critical patent/WO2022193137A1/zh

Links

Images

Classifications

    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60T—VEHICLE BRAKE CONTROL SYSTEMS OR PARTS THEREOF; BRAKE CONTROL SYSTEMS OR PARTS THEREOF, IN GENERAL; ARRANGEMENT OF BRAKING ELEMENTS ON VEHICLES IN GENERAL; PORTABLE DEVICES FOR PREVENTING UNWANTED MOVEMENT OF VEHICLES; VEHICLE MODIFICATIONS TO FACILITATE COOLING OF BRAKES
    • B60T8/00—Arrangements for adjusting wheel-braking force to meet varying vehicular or ground-surface conditions, e.g. limiting or varying distribution of braking force
    • B60T8/17—Using electrical or electronic regulation means to control braking
    • B60T8/172—Determining control parameters used in the regulation, e.g. by calculations involving measured or detected parameters
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60T—VEHICLE BRAKE CONTROL SYSTEMS OR PARTS THEREOF; BRAKE CONTROL SYSTEMS OR PARTS THEREOF, IN GENERAL; ARRANGEMENT OF BRAKING ELEMENTS ON VEHICLES IN GENERAL; PORTABLE DEVICES FOR PREVENTING UNWANTED MOVEMENT OF VEHICLES; VEHICLE MODIFICATIONS TO FACILITATE COOLING OF BRAKES
    • B60T17/00—Component parts, details, or accessories of power brake systems not covered by groups B60T8/00, B60T13/00 or B60T15/00, or presenting other characteristic features
    • B60T17/18—Safety devices; Monitoring
    • B60T17/22—Devices for monitoring or checking brake systems; Signal devices

Definitions

  • the present application relates to the field of vehicle control, and in particular, to a vehicle control method and device.
  • the emergency brake assist (EBA) system on the vehicle can apply emergency braking to the vehicle when the current driving state is in a dangerous state.
  • the Emergency Brake Assist system actively boosts the pressure after recognizing an emergency braking situation. In this way, the pressure can be decompressed faster, the braking distance of the vehicle can be greatly reduced, and the collision of the vehicle can be avoided as much as possible.
  • the emergency braking assistance system on the vehicle does not consider the driver's braking demand when performing emergency braking, but outputs a preset braking force for braking, resulting in poor user experience and even potential safety hazards.
  • the emergency braking assist system may misjudge the situation as an emergency braking condition, and then trigger the emergency braking by mistake.
  • the brake assist function provides unnecessary deceleration for the vehicle.
  • the emergency brake assist system usually directly outputs the maximum braking force after judging that the current working condition is an emergency braking condition, such as the output of the anti-lock braking system (
  • an emergency braking condition such as the output of the anti-lock braking system
  • Unnecessary deceleration or excessive deceleration are not in line with the driver's subjective wishes, resulting in degraded user experience, and there may even be safety hazards such as being rear-ended by a rear car.
  • the present application provides a vehicle control method and device, which can provide suitable braking deceleration, more conform to the driver's subjective wishes, and improve user experience during vehicle braking.
  • a vehicle control method comprising: acquiring information of a target vehicle, where the information of the target vehicle includes motion information of the target vehicle and pressure information of a brake master cylinder of the target vehicle; sending an indication of target braking deceleration information, the instruction information of the target braking deceleration is used to instruct the target vehicle to perform brake boosting on the master cylinder, and the target braking deceleration is predicted based on the information of the target vehicle.
  • the information of the target vehicle before active supercharging is obtained by the driver during the natural driving process, which can reflect the driver's subjective will.
  • the driver's braking intention can be more accurately quantified, so that the braking process of the vehicle conforms to the driver's subjective wishes, and the user experience and driving safety are improved. sex.
  • the target braking deceleration can be more in line with the driver's braking intention, and the accuracy of the prediction can be further improved.
  • the driving process is more in line with the driver's subjective wishes, which further improves the user experience and driving safety.
  • the solutions of the embodiments of the present application do not rely on hardware devices such as pedal position sensors, pedal simulators, or brake-by-wire systems, which saves hardware costs.
  • the indication information of the target braking deceleration may include the target braking deceleration itself, or information that can be used to obtain the target braking deceleration, for example, the indication information of the target braking deceleration may be The difference between the target braking deceleration and the current braking deceleration is not specifically limited in this application.
  • the motion information of the vehicle refers to information related to the motion state of the vehicle.
  • the motion information of the target vehicle includes at least one of the following: the speed of the target vehicle or the acceleration of the target vehicle.
  • the pressure information of the master cylinder refers to information related to the pressure of the master cylinder.
  • the pressure information of the master cylinder includes at least one of the following: a pressure gradient of the master cylinder or the pressure of the master cylinder.
  • Braking deceleration refers to the ratio of the amount of speed change after braking to the time it takes for the speed change to occur.
  • the target braking deceleration is determined according to the first braking deceleration, and the first braking deceleration is determined by the braking deceleration prediction model for the target vehicle. information is processed.
  • the braking deceleration prediction model is used to predict the first braking deceleration according to the information in the input model. For example, the braking deceleration prediction model predicts the first braking deceleration according to the input information of the target vehicle.
  • the first braking deceleration is the braking deceleration requested by the driver.
  • the braking deceleration prediction model may be a neural network model, for example, a recurrent neural network (RNN) model.
  • RNN recurrent neural network
  • the target braking deceleration is the first braking deceleration.
  • the neural network model can be used as the braking deceleration prediction model, the braking deceleration model can be trained based on the data collected in the natural driving process, and the trained braking deceleration model can be used to predict the driver's braking deceleration model.
  • the powerful feature expression ability of the neural network model can improve the prediction accuracy of the braking deceleration requested by the driver.
  • the braking deceleration prediction model is obtained by training based on at least one training sample, and the training sample includes the information of the training vehicle and the sample label of the training sample, and the information of the training vehicle.
  • the motion information of the training vehicle and the pressure information of the brake master cylinder of the training vehicle are included, and the sample label of the training sample is used to indicate the braking deceleration requested by the driver of the training vehicle.
  • the at least one training sample is obtained from natural driving test data.
  • Natural driving test data are braking data obtained during a braking operation performed by the driver without active boosting of systems such as emergency brake assist.
  • the method further includes: acquiring environmental perception information of the target vehicle; wherein the target braking deceleration is predicted and obtained according to the information of the target vehicle and the environmental perception information of the target vehicle of.
  • the first braking deceleration is obtained by processing the information of the target vehicle and the environmental perception information of the target vehicle through the braking deceleration prediction model.
  • the training samples may include information of the training vehicle, environment perception information of the training vehicle, and sample labels of the training samples.
  • the environment perception information of the training vehicle is used for model training, so that the model can judge whether the driver needs emergency braking based on the actual collision risk, thereby improving the accuracy of the prediction model.
  • the environmental perception information of the target vehicle is also used as the input of the model, so that the braking result can better satisfy the driver's subjective wishes, and improve the user experience and safety.
  • the pressure information of the master brake cylinder of the target vehicle includes the pressure slope of the master brake cylinder of the target vehicle, and before sending the indication information of the target braking deceleration, The pressure gradient of the master brake cylinder of the target vehicle is greater than or equal to the first threshold.
  • the motion information of the target vehicle includes the speed of the target vehicle, and the first threshold is determined according to the speed of the target vehicle.
  • the target braking deceleration is determined according to a second braking deceleration, and the second braking deceleration is a reduction of the first braking deceleration by a target gain coefficient.
  • the target gain coefficient is a mapping relationship between the target gain coefficient and the danger level of the current driving scene.
  • the target gain coefficient is determined through the mapping relationship between the multiple gain coefficients and the danger levels of the multiple driving scenarios and the danger level of the current driving scenario.
  • the target gain coefficient is one of a plurality of gain coefficients.
  • the danger level can also be understood as a safety level.
  • the danger level of the driving scene is determined according to the information of the vehicle and the environmental perception information of the vehicle.
  • the risk discrimination index can be calculated according to the motion information of the vehicle and the environmental perception information of the vehicle, and then the risk level is determined according to the risk discrimination index.
  • the target braking deceleration is the second braking deceleration.
  • the first braking deceleration is processed correspondingly according to the gain coefficient corresponding to the danger level of the current driving scene, so that graded braking can be realized based on different danger levels, and the safety of vehicle driving is improved.
  • the gain coefficient corresponding to the danger level is greater than 1.
  • the first braking deceleration is amplified when the danger level is greater than or equal to the first level threshold.
  • the gain coefficients corresponding to different risk levels can be preset.
  • the mapping relationship between the multiple gain coefficients and the multiple risk levels may be preset.
  • the first braking deceleration is amplified, which is beneficial to further improve the safety of driving.
  • the danger level of the current driving scene is greater than or equal to the second level threshold.
  • the target braking deceleration is determined according to the larger absolute value of the second braking deceleration and the safe braking deceleration, and the safe braking deceleration Used to represent the braking deceleration required for the target vehicle to avoid a collision.
  • the safe braking deceleration is determined according to the motion information of the target vehicle and the environmental perception information of the target vehicle and is required to avoid a collision.
  • the target braking deceleration is the larger absolute value of the second braking deceleration and the safe braking deceleration.
  • the target braking deceleration is the smaller value between the larger absolute value and the braking deceleration threshold.
  • the braking deceleration threshold is determined by the ABS.
  • the safe braking deceleration is determined by the motion information of the target vehicle and the environmental perception information of the target vehicle, and the target braking is determined according to the one of the safe braking deceleration and the second braking deceleration, which has a larger absolute value. Deceleration can effectively avoid collision risks and further improve driving safety on the premise of satisfying the driver's subjective wishes as much as possible.
  • a vehicle control device comprising: an acquisition unit for acquiring information of a target vehicle, where the information of the target vehicle includes motion information of the target vehicle and pressure information of a brake master cylinder of the target vehicle; a sending unit, It is used to send the instruction information of the target braking deceleration.
  • the instruction information of the target braking deceleration is used to instruct the target vehicle to perform brake boosting on the brake master cylinder.
  • the target braking deceleration is predicted according to the information of the target vehicle. .
  • the information of the target vehicle before active supercharging is obtained by the driver during the natural driving process, which can reflect the driver's subjective will.
  • the driver's braking intention can be more accurately quantified, so that the braking process of the vehicle conforms to the driver's subjective wishes, and the user experience and driving safety are improved. sex.
  • the target braking deceleration can be more in line with the driver's braking intention, and the accuracy of the prediction can be further improved.
  • the driving process is more in line with the driver's subjective wishes, which further improves the user experience and driving safety.
  • the solutions of the embodiments of the present application do not rely on hardware devices such as pedal position sensors, pedal simulators, or brake-by-wire systems, which saves hardware costs.
  • the target braking deceleration is determined according to a first braking deceleration, and the first braking deceleration is a prediction of the target vehicle through a braking deceleration prediction model. information is processed.
  • the braking deceleration prediction model is obtained by training based on at least one training sample, and the training sample includes the information of the training vehicle and the sample label of the training sample, and the information of the training vehicle.
  • the motion information of the training vehicle and the pressure information of the brake master cylinder of the training vehicle are included, and the sample label of the training sample is used to indicate the braking deceleration requested by the driver of the training vehicle.
  • the pressure information of the master brake cylinder of the target vehicle includes the pressure slope of the master brake cylinder of the target vehicle, and before sending the indication information of the target braking deceleration, The pressure gradient of the master brake cylinder of the target vehicle is greater than or equal to the first threshold.
  • the motion information of the target vehicle includes the speed of the target vehicle
  • the first threshold is determined according to the speed of the target vehicle
  • the target braking deceleration is determined according to a second braking deceleration
  • the second braking deceleration is a reduction of the first braking deceleration by a target gain coefficient.
  • the target braking deceleration is determined according to the larger absolute value of the second braking deceleration and the safe braking deceleration, and the safe braking deceleration Used to represent the braking deceleration required for the target vehicle to avoid a collision.
  • a third aspect provides a chip, the chip includes at least one processor and an interface circuit, the at least one processor obtains instructions stored in a memory through the interface circuit, and executes any one of the implementation manners of the first aspect above method in .
  • the chip may further include a memory, in which instructions are stored, the processor is configured to execute the instructions stored in the memory, and when the instructions are executed, the The processor is configured to execute the method in any one of the implementation manners of the first aspect.
  • a computer-readable medium stores program code for execution by a device, the program code comprising a method for performing any one of the implementations of the first aspect.
  • a computer program product comprising instructions, when the computer program product is run on a computer, the computer program product causes the computer to execute the method in any one of the implementation manners of the first aspect above.
  • a terminal in a sixth aspect, includes the apparatus of any one of the implementation manners of the second aspect.
  • the terminal further includes a brake master cylinder.
  • the terminal may be a vehicle, and the apparatus related to the second aspect above is used to control the vehicle.
  • FIG. 1 is a schematic structural diagram of an autonomous vehicle provided by an embodiment of the present application.
  • FIG. 2 is a schematic structural diagram of a vehicle control device provided by an embodiment of the present application.
  • FIG. 3 is a schematic flowchart of a vehicle control method provided by an embodiment of the present application.
  • FIG. 4 is a schematic diagram of the relationship between the pressure slope of the master cylinder and braking deceleration provided by an embodiment of the present application;
  • FIG. 5 is a schematic diagram of a prediction process of a first braking deceleration provided by an embodiment of the present application
  • FIG. 6 is a schematic flowchart of a graded braking processing process provided by an embodiment of the present application.
  • FIG. 7 is a schematic diagram of a graded auxiliary braking effect provided by an embodiment of the present application.
  • FIG. 8 is a schematic flowchart of an arbitration process for target braking deceleration provided by an embodiment of the present application.
  • FIG. 9 is a schematic diagram of braking effects in different scenarios provided by an embodiment of the present application.
  • FIG. 10 is a schematic diagram of a method for determining a mapping relationship between a first threshold and a speed of a vehicle provided by an embodiment of the present application;
  • FIG. 11 is a schematic diagram of the distribution of the pressure slope of a brake master cylinder provided by an embodiment of the present application.
  • FIG. 12 is a schematic flowchart of a method for identifying a driver's braking intention provided by an embodiment of the present application
  • FIG. 13 is a schematic diagram of a vehicle control device provided by an embodiment of the present application.
  • FIG. 14 is a schematic diagram of another vehicle control device provided by an embodiment of the present application.
  • the solutions of the embodiments of the present application can be applied to a braking system of a vehicle, for example, an emergency braking assist system, to provide a suitable braking deceleration for the vehicle.
  • FIG. 1 is a functional block diagram of a vehicle 100 provided by an embodiment of the present application.
  • the vehicle 100 is configured in a fully or partially autonomous driving mode.
  • the vehicle 100 may control a target vehicle while in an autonomous driving mode, and may determine the current state of the vehicle and its surrounding environment through human manipulation, determine the likely behavior of at least one other vehicle in the surrounding environment, and A confidence level corresponding to the likelihood that other vehicles will perform the possible behavior is determined, and the vehicle 100 is controlled based on the determined information.
  • the vehicle 100 may be placed to operate without human interaction.
  • Vehicle 100 may include various subsystems, such as travel system 110 , sensing system 120 , control system 130 , one or more peripherals 140 and power supply 160 , computer system 150 , and user interface 170 .
  • vehicle 100 may include more or fewer subsystems, and each subsystem may include multiple elements. Additionally, each of the subsystems and elements of the vehicle 100 may be interconnected by wire or wirelessly.
  • the travel system 110 may include components for providing powered motion to the vehicle 100 .
  • the traveling system may be used to drive the vehicle to perform corresponding motion behaviors, such as forward, backward, and steering, during the obstacle avoidance process.
  • the travel system 110 includes an engine 111 , a transmission 112 , an energy source 113 and wheels 114 .
  • the sensing system 120 may include several sensors that sense information about the environment surrounding the vehicle 100 .
  • the sensing system may be used to acquire environmental information and road structure information, so as to perform subsequent control based on the acquired information.
  • the sensing system 120 may include a positioning system 121 (eg, a global positioning system (GPS), BeiDou system, or other positioning system), an inertial measurement unit (IMU) 122, a radar 123, a laser Distance meter 124 , camera 125 and vehicle speed sensor 126 .
  • the sensing system 120 may also include sensors that monitor the internal systems of the vehicle 100 (eg, an in-vehicle air quality monitor, a fuel gauge, an oil temperature gauge, etc.). Sensor data from one or more of these sensors can be used to detect objects and their corresponding characteristics (position, shape, orientation, velocity, etc.). This detection and identification is a critical function for the safe operation of the autonomous vehicle 100 .
  • the positioning system 121 may be used to estimate the geographic location of the vehicle 100 .
  • the IMU 122 may be used to sense position and orientation changes of the vehicle 100 based on inertial acceleration.
  • IMU 122 may be a combination of an accelerometer and a gyroscope.
  • the radar 123 may utilize radio signals to sense objects within the surrounding environment of the vehicle 100 .
  • radar 123 may be used to sense the speed and/or heading of objects.
  • the laser rangefinder 124 may utilize laser light to sense objects in the environment in which the vehicle 100 is located.
  • the laser rangefinder 124 may include one or more laser sources, laser scanners, and one or more detectors, among other system components.
  • camera 125 may be used to capture multiple images of the surrounding environment of vehicle 100 .
  • camera 125 may be a still camera or a video camera.
  • the vehicle speed sensor 126 may be used to measure the speed of the vehicle 100 .
  • real-time speed measurement of the vehicle can be performed.
  • the measured vehicle speed may be communicated to the control system 130 to effect control of the vehicle.
  • Control system 130 controls the operation of the vehicle 100 and its components.
  • Control system 130 may include various elements, such as may include steering system 131 , throttle 132 , braking unit 133 , computer vision system 134 , route control system 135 , and obstacle avoidance system 136 .
  • the steering system 131 may operate to adjust the heading of the vehicle 100 .
  • it may be a steering wheel system.
  • the throttle 132 may be used to control the operating speed of the engine 111 and thus the speed of the vehicle 100 .
  • the braking unit 133 may be used to control the deceleration of the vehicle 100 ; the braking unit 133 may use friction to slow the wheels 114 . In other embodiments, the braking unit 133 may convert the kinetic energy of the wheels 114 into electrical current. The braking unit 133 may also take other forms to slow the wheels 114 to control the speed of the vehicle 100 .
  • computer vision system 134 is operable to process and analyze images captured by camera 125 in order to identify objects and/or features in the environment surrounding vehicle 100 .
  • Such objects and/or features may include traffic signals, road boundaries and obstacles.
  • Computer vision system 134 may use object recognition algorithms, structure from motion (SFM) algorithms, video tracking, and other computer vision techniques.
  • the computer vision system 134 may be used to map the environment, track objects, estimate the speed of objects, and the like.
  • the route control system 135 may be used to determine the route of travel of the vehicle 100 .
  • the obstacle avoidance system 136 may be used to identify, evaluate, and avoid or otherwise traverse potential obstacles in the environment of the vehicle 100 .
  • control system 130 may additionally or alternatively include components in addition to those shown and described. Alternatively, some of the components shown above may be reduced.
  • vehicle 100 may interact with external sensors, other vehicles, other computer systems, or users through peripheral devices 140 .
  • peripherals 140 may provide a means for vehicle 100 to interact with user interface 170 .
  • Wireless communication system 141 may communicate wirelessly with one or more devices, either directly or via a communication network.
  • Power supply 160 may provide power to various components of vehicle 100 .
  • Computer system 150 may include at least one processor 151 that executes instructions 153 stored in a non-transitory computer-readable medium such as memory 152 .
  • Computer system 150 may also be multiple computing devices that control individual components or subsystems of vehicle 100 in a distributed fashion.
  • processor 151 may be any conventional processor, such as a commercially available central processing unit (CPU).
  • CPU central processing unit
  • the processor may be a dedicated device such as an application specific integrated circuit (ASIC) or other hardware-based processor.
  • FIG. 1 functionally illustrates a processor, memory, and other elements of the computer in the same block, one of ordinary skill in the art will understand that the processor, computer, or memory may actually include storage that may or may not be Multiple processors, computers or memories within the same physical enclosure.
  • the memory may be a hard drive or other storage medium located within an enclosure other than a computer.
  • reference to a processor or computer will be understood to include reference to a collection of processors or computers or memories that may or may not operate in parallel.
  • some components such as the steering and deceleration components may each have their own processor that only performs computations related to component-specific functions .
  • a processor may be located remotely from the vehicle and in wireless communication with the vehicle. In other aspects, some of the processes described herein are performed on a processor disposed within the vehicle while others are performed by a remote processor, including taking steps necessary to perform a single maneuver.
  • memory 152 may contain instructions 153 (eg, program logic) that may be used by processor 151 to perform various functions of vehicle 100 , including those described above.
  • Memory 152 may also include additional instructions, such as including sending data to, receiving data from, interacting with, and/or performing data processing on one or more of travel system 110 , sensing system 120 , control system 130 , and peripherals 140 control commands.
  • memory 152 may store data such as road maps, route information, vehicle location, direction, speed, and other such vehicle data, among other information. Such information may be used by the vehicle 100 and the computer system 150 during operation of the vehicle 100 in autonomous, semi-autonomous and/or manual modes.
  • User interface 170 may be used to provide information to or receive information from a user of vehicle 100 .
  • user interface 170 may include one or more input/output devices within the set of peripheral devices 140, such as wireless communication system 141, vehicle computer 142, microphone 143, and speaker 144.
  • computer system 150 may control functions of vehicle 100 based on input received from various subsystems (eg, travel system 110 , sensing system 120 , and control system 130 ) and from user interface 170 .
  • computer system 150 may utilize input from control system 130 to control braking unit 133 to avoid obstacles detected by sensing system 120 and obstacle avoidance system 136 .
  • computer system 150 is operable to provide control of various aspects of vehicle 100 and its subsystems.
  • one or more of these components described above may be installed or associated with the vehicle 100 separately.
  • memory 152 may exist partially or completely separate from vehicle 100 .
  • the above-described components may be communicatively coupled together in a wired and/or wireless manner.
  • FIG. 1 should not be construed as a limitation on the embodiments of the present application.
  • the autonomous vehicle vehicle 100 or computing devices associated with the autonomous vehicle 100 may be based on the characteristics of the identified objects and the state of the surrounding environment (eg, , traffic, rain, ice on the road, etc.) to predict the behavior of the identified objects.
  • each identified object is dependent on the behavior of the other, so it is also possible to predict the behavior of a single identified object by considering all identified objects together.
  • the vehicle 100 can adjust its speed based on the predicted behavior of the identified object.
  • the self-driving car can determine what steady state the vehicle will need to adjust to (eg, accelerate, decelerate, or stop) based on the predicted behavior of the object.
  • other factors may also be considered to determine the speed of the vehicle 100, such as the lateral position of the vehicle 100 in the road being traveled, the curvature of the road, the proximity of static and dynamic objects, and the like.
  • the above-mentioned vehicle 100 may be a traditional vehicle, a new energy vehicle, a smart vehicle, etc.
  • the so-called traditional vehicle refers to a vehicle that uses automobiles, diesel, etc. to provide energy
  • a new energy vehicle refers to a newly emerged vehicle that uses new energy such as electric energy, gas, etc. to provide energy
  • a smart car refers to a car loaded with smart devices such as an intelligent control unit.
  • the vehicle type of the above-mentioned vehicle 100 may include, for example, a car, a truck, a passenger car, an engineering vehicle, a bus, etc., which is not particularly limited in the embodiments of the present application.
  • various types of automobiles driving on the road are mainly used as examples for introduction.
  • the emergency braking assistance system on the vehicle can perform emergency braking on the vehicle when the current driving state is in a dangerous state.
  • the emergency braking assistance system on the vehicle does not consider the driver's braking demand when performing emergency braking, but brakes according to the preset braking force, resulting in poor user experience and even potential safety hazards.
  • the automatic emergency braking (AEB) system senses the surrounding environment through sensors, and brakes according to the preset braking force when the current driving state is dangerous.
  • this braking process does not take into account the driver's braking demand, and sudden braking can lead to poor user experience.
  • the emergency braking assist system may misjudge a non-emergency braking condition as an emergency braking condition, and then trigger the emergency braking assist function by mistake, providing unnecessary deceleration for the vehicle, and the emergency braking assist After judging that the current working condition is an emergency braking condition, the system usually directly outputs the maximum braking force. Unnecessary deceleration or excessive deceleration are not in line with the driver's subjective wishes, resulting in a degraded user experience, and there may even be potential safety hazards such as being rear-ended by a rear car.
  • the embodiments of the present application provide a vehicle control method, which provides suitable braking deceleration, which is more in line with the driver's subjective wishes, and can improve the user experience in the braking process of the vehicle.
  • a vehicle control device 200 provided by the embodiment of the present application will be described below with reference to FIG. 2 .
  • the apparatus 200 may use the method in the embodiment of the present application to perform braking control on the vehicle.
  • FIG. 2 shows a vehicle control device provided by an embodiment of the present application.
  • the apparatus 200 in FIG. 2 includes an emergency braking intention recognition module 210 , a driver requested deceleration prediction module 220 , a graded braking module 230 and a braking deceleration decision module 240 .
  • the emergency braking intention identification module 210 is used to identify the emergency braking intention of the driver, that is, to determine whether the driver needs emergency braking at present, or, in other words, to identify whether the current emergency braking condition is present.
  • the emergency braking intention identification module 210 is an optional module.
  • the emergency braking intention recognition module 210 is integrated in the apparatus 200 , or may be provided independently of the apparatus 200 .
  • the emergency braking intention recognition module 210 is an optional module.
  • the emergency braking intention identification module 210 may not be provided in the system.
  • the driver requested deceleration prediction module 220 when the current operating condition is an emergency braking condition, the driver requested deceleration prediction module 220 , the graded braking module 230 or the braking deceleration decision module 240 are activated.
  • the emergency braking intention identification module 210 may identify the driver's emergency braking intention according to the information of the target vehicle.
  • the information of the target vehicle includes pressure information of the master cylinder of the target vehicle and motion information of the target vehicle.
  • the driver requested deceleration prediction module 220 is used to predict the deceleration requested by the driver.
  • the driver-requested deceleration prediction module 220 may predict the braking deceleration requested by the driver, ie, the first braking deceleration, according to the information of the target vehicle. Further, the driver requested deceleration prediction module 220 may predict the braking deceleration requested by the driver according to the information of the target vehicle and the environment perception information.
  • the graded braking module 230 is configured to process the braking deceleration requested by the driver according to the danger level of the current driving scene to obtain the second braking deceleration.
  • the output result of the driver's request deceleration prediction module 220 is input into the grading braking module 230, and the grading braking module 230, according to the gain coefficient corresponding to the danger level of the current driving scene, that is, the target gain coefficient, determines the driver's value.
  • the requested braking deceleration is processed and the second braking deceleration is output.
  • graded braking module 230 is an optional module.
  • the braking deceleration decision module 240 is configured to determine the target braking deceleration, and the target braking deceleration is the braking deceleration output by the device 200 .
  • the driver requested deceleration prediction module 220 may input the first braking deceleration to the braking deceleration decision module 240 .
  • the braking deceleration decision module 240 may use the safety braking deceleration and the first braking deceleration with a larger absolute value as the target braking deceleration.
  • the safe braking deceleration is used to represent the braking deceleration required by the target vehicle to avoid a collision.
  • the graded braking module 230 may output the second braking deceleration to the braking deceleration decision module 240 .
  • the braking deceleration decision module 240 may use the safety deceleration and the second braking deceleration output by the graded braking module 230 with a larger absolute value as the target braking deceleration.
  • the braking deceleration decision module 240 is an optional module.
  • the target braking deceleration may be the second braking deceleration output by the graded braking module 230 .
  • the target braking deceleration may be the first braking deceleration output by the driver requested deceleration prediction module 220 .
  • FIG. 3 shows a schematic flowchart of a vehicle control method 300 provided by an embodiment of the present application.
  • the method 300 includes steps S310 to S320. Steps S310 to S320 will be described below.
  • S310 Acquire information of the target vehicle, where the information of the target vehicle includes motion information of the target vehicle and pressure information of a master brake cylinder of the target vehicle.
  • the motion information of the vehicle refers to information related to the motion state of the vehicle.
  • the motion information of the target vehicle includes at least one of the following: the speed of the target vehicle or the acceleration of the target vehicle.
  • the motion information of the target vehicle may be acquired by the sensing system 120 in FIG. 1 .
  • the speed of the target vehicle is obtained through the vehicle speed sensor 126 .
  • the acceleration of the target vehicle is obtained through the inertial measurement unit 122 .
  • the pressure information of the master cylinder refers to information related to the pressure of the master cylinder.
  • the pressure information of the master cylinder includes at least one of the following: a pressure gradient of the master cylinder or the pressure of the master cylinder.
  • the pressure slope of the master cylinder can be understood as the rate of change of the pressure of the master cylinder.
  • the pressure gradient of the master cylinder may also be referred to as the pressure rise rate of the master cylinder.
  • the pressure slope of the master cylinder may be determined by periodically acquired values of the pressure of the master cylinder.
  • the pressure information of the brake master cylinder may be acquired by the sensing system 120 in FIG. 1 .
  • the pressure information of the brake master cylinder is obtained through the sensor of the internal system.
  • S320 Send instruction information of the target braking deceleration, where the instruction information of the target braking deceleration is used to instruct the target vehicle to perform active boosting of the master cylinder, and the target braking deceleration is predicted according to the information of the target vehicle.
  • the function of this step is to control the vehicle to perform active boosting of the master cylinder.
  • sending the instruction information of the target braking deceleration to the actuator of the target vehicle can instruct or trigger the target vehicle to perform active pressurization on the master cylinder, so that the target vehicle performs braking according to the target braking deceleration.
  • the indication information of the target braking deceleration may include the target braking deceleration itself, or information that can be used to obtain the target braking deceleration, for example, the indication information of the target braking deceleration may be:
  • the difference between the target braking deceleration and the current braking deceleration is not specifically limited in this application.
  • Braking deceleration refers to the ratio of the amount of speed change after braking to the time it takes for the speed change to occur. Braking deceleration can also be understood as acceleration.
  • Active boosting refers to boosting that is performed autonomously by the vehicle, rather than boosting performed by the driver via the brake pedal, eg, active boosting performed by an emergency brake assist system on the vehicle.
  • the information of the target vehicle is the information of the target vehicle at the time of starting the active supercharging or the information of the target vehicle before the time of the active supercharging.
  • the pedal force and the pressure of the brake master cylinder are coupled, and the solution of calculating the braking deceleration requested by the driver in real time through the pedal opening, the pedal opening change rate or the cylinder pressure information is not applicable.
  • the pedal opening and the rate of change of the pedal opening will be affected by the coupled brake cylinder pressure, and the real intention of the driver cannot be accurately quantified through real-time pedal force and other parameters.
  • the information of the target vehicle before active supercharging is obtained by the driver during the natural driving process, which can reflect the driver's subjective will.
  • the driver's braking intention can be more accurately quantified, so that the braking process of the vehicle conforms to the driver's subjective wishes, and the user experience and driving safety are improved. sex.
  • the braking intention of the driver reflected by the cylinder pressure information of the same master cylinder may also be different.
  • the braking deceleration requested by the driver may be different even if the cylinder pressure slope of the master cylinder is the same.
  • the vehicle speed is low, the braking deceleration requested by the driver is small, and when the vehicle speed is high, the braking deceleration requested by the driver is large.
  • the embodiment of the present application predicts the target braking deceleration by using the motion information of the target vehicle and the pressure information of the brake master cylinder, so that the target braking deceleration can be more in line with the driver's braking intention, and the accuracy of the prediction is further improved, so that the vehicle The braking process is more in line with the driver's subjective wishes, which further improves the user experience and driving safety.
  • the method 300 may be executed by the EBA system.
  • the target braking deceleration is the braking deceleration that needs to be executed by the EBA system, or in other words, the target braking deceleration is According to the braking deceleration output by the EBA system, the actuator controls the target vehicle to perform active boosting to the brake master cylinder according to the target braking deceleration.
  • the EBA system can provide the emergency braking assistance function based on the target braking deceleration to realize the auxiliary braking, instead of directly outputting the maximum braking force, which is more in line with the driver's subjective wishes and improves the User experience and driving safety.
  • the method 300 may be executed by the AEB system, in this case, the target braking deceleration is the braking deceleration that the AEB system needs to execute, or in other words, the target braking deceleration is For the braking deceleration output by the AEB system, the actuator controls the target vehicle to perform active boosting to the brake master cylinder according to the target braking deceleration.
  • the AEB system can provide the emergency braking function based on the target braking deceleration to realize emergency braking, instead of directly outputting the preset braking force, which is more in line with the driver's subjective wishes and improves the User experience and driving safety.
  • the target braking deceleration is determined from the first braking deceleration.
  • the first braking deceleration is obtained by processing the information of the target vehicle through the braking deceleration prediction model.
  • the braking deceleration prediction model is used to predict the first braking deceleration according to the information in the input model. For example, the braking deceleration prediction model predicts the first braking deceleration according to the input information of the target vehicle.
  • the braking deceleration prediction model is obtained by training based on at least one training sample, the training sample includes the information of the training vehicle and the sample label of the training sample, and the information of the training vehicle includes the motion information of the training vehicle and the pressure of the brake master cylinder. information.
  • the sample labels of the training samples are used to indicate the braking deceleration requested by the driver of the training vehicle.
  • the first braking deceleration is the braking deceleration requested by the driver.
  • the motion information of the target vehicle and the pressure information of the brake master cylinder are used as the input of the brake deceleration prediction model, and the feature extraction is performed by the brake deceleration prediction model, and the output of the model is obtained according to the extracted features.
  • the output result of the braking deceleration model is the first braking deceleration.
  • the braking deceleration prediction model may be a neural network model, for example, a recurrent neural network (RNN) model.
  • RNN recurrent neural network
  • the at least one training sample is obtained from natural driving test data.
  • Natural driving test data is the braking data obtained during a braking operation performed by the driver without active boosting of systems such as emergency brake assist.
  • a training sample may be determined according to the data of a braking process in the process of driving the training vehicle naturally, that is, the motion information of the training vehicle and the pressure information of the master cylinder of the training vehicle are the braking process of this time. data in .
  • the braking deceleration requested by the driver of the training vehicle can be understood as the braking deceleration finally requested by the driver during the braking process.
  • the braking deceleration finally requested by the driver may be the value of the stable braking deceleration finally achieved by the training vehicle during this braking process.
  • the final braking deceleration requested by the driver may be the maximum braking deceleration achieved by the training vehicle during this braking process.
  • the magnitude of the braking deceleration in the embodiments of the present application refers to the magnitude of the absolute value of the braking deceleration.
  • obtaining the braking deceleration prediction model based on the training samples may include: taking the motion information of the training vehicle and the pressure information of the master cylinder of the training vehicle as the input of the braking deceleration prediction model, so as to train the driver of the vehicle to The requested braking deceleration is used as the target output of the braking deceleration prediction model to train the model, and the trained braking deceleration prediction model is obtained.
  • the training process may be completed offline.
  • the driver's operation is a sequential process, but under a certain braking intention, the driver's operation law is basically the same.
  • the driver's operation law can be reflected by parameters such as the pressure information of the vehicle's brake master cylinder and the vehicle's motion information during the braking process.
  • the change trend of the pressure gradient of the master cylinder of the vehicle during a braking process of natural driving basically corresponds to the change trend of the braking deceleration.
  • the braking force provided for the vehicle also increases accordingly, and accordingly, the absolute value of the braking deceleration of the vehicle also increases accordingly.
  • the braking deceleration with the largest absolute value in FIG. 4 is regarded as the braking deceleration finally requested by the driver.
  • the final braking deceleration requested by the driver can be predicted, that is, Fig. 4 prediction point in .
  • the motion information of the training vehicle in the training sample may include motion information corresponding to the moment when the pressure gradient of the master brake cylinder of the training vehicle is the largest.
  • the pressure information of the master brake cylinder of the training vehicle includes the pressure information of the master brake cylinder corresponding to the moment when the pressure gradient of the master brake cylinder of the training vehicle is the largest.
  • the sample label of the training sample includes the final requested braking deceleration of the driver of the training vehicle.
  • the motion information of the training vehicle and the pressure information of the brake master cylinder collected at the calculation point are used as the input of the braking deceleration prediction model, and the braking deceleration collected at the prediction point is used as the input of the braking deceleration prediction model.
  • the target output is used to train the model to obtain a trained predictive deceleration model.
  • the motion information of the training vehicle in a training sample may include the motion information of the training vehicle at time t2, and the pressure information of the master cylinder of the training vehicle may include the training vehicle at time t2. pressure information of the brake master cylinder.
  • the sample label of the training sample that is, the braking deceleration requested by the driver, may be the braking deceleration at time t3 in FIG. 4 .
  • the motion information of the training vehicle at time t2 and the pressure information of the brake master cylinder of the training vehicle can be used as the input of the braking deceleration prediction model, and the braking deceleration at time t3 can be used as the sample label for the braking deceleration prediction model.
  • Speed model for training can be used as the input of the braking deceleration prediction model, and the braking deceleration at time t3 can be used as the sample label for the braking deceleration prediction model.
  • the time after the first period of time after the pressure gradient of the master cylinder of the target vehicle reaches the first threshold value can be regarded as the time when the pressure gradient of the master cylinder of the target vehicle is the largest.
  • the first time period may be preset, for example, the first time period may be determined in advance through statistical laws of natural driving test data.
  • the first threshold may be determined according to the speed of the target vehicle. There is a mapping relationship between the first threshold and the speed of the target vehicle, and the specific description can refer to the method 1000 in the following.
  • the motion information of the target vehicle may include motion information corresponding to the moment when the time is away from the first time period after the moment when the pressure gradient of the master brake cylinder of the target vehicle reaches the first threshold.
  • the pressure information of the master brake cylinder of the target vehicle includes the pressure information of the master brake cylinder corresponding to the time when the time is away from the first time period after the time when the pressure slope of the master brake cylinder of the target vehicle reaches the first threshold value.
  • the information of the target vehicle collected after the moment when the pressure slope of the brake master cylinder of the target vehicle reaches the first threshold value and the moment of the first time interval between this moment and the moment can be used as the input of the braking deceleration model, and the The first braking deceleration is obtained after the braking deceleration model is processed.
  • the training process may be completed offline.
  • the prediction process can be done online. That is, the braking deceleration model can be a pre-trained offline model.
  • FIG. 4 is only an example of the variation trend of relevant parameters in a braking process, and the pressure gradient and braking deceleration values of the master brake cylinder in FIG. 4 do not limit the solutions in the embodiments of the present application.
  • the above training samples and the parameters used to input the braking deceleration model are only examples, and the information of the training vehicle at other times or periods collected during the braking process can also be used as the braking deceleration during the training process.
  • the input of the prediction model is used to train the braking deceleration prediction model, and the information of the target vehicle at other times or periods collected in the braking process is used as the input of the braking deceleration model in the inference process, and the first braking deceleration model is obtained. speed.
  • the embodiment of the present application does not limit the specific form of the parameters of the input braking deceleration model.
  • the target vehicle may perform step S320 after the first time period elapses after the pressure gradient of the master brake cylinder of the target vehicle reaches the first threshold, ie, perform active boosting of the master brake cylinder.
  • the EBA system on the target vehicle starts to perform the emergency braking assist operation after the first time period elapses after the pressure slope of the master brake cylinder reaches the first threshold, that is, outputs the target braking deceleration to perform active boosting of the brake master cylinder.
  • the first braking deceleration is predicted by the information before the active supercharging, which can reflect the driver's real braking intention, which is beneficial to improve the prediction accuracy of the braking deceleration requested by the driver.
  • the neural network model is used as the braking deceleration prediction model, the braking deceleration model is trained based on the data collected during the natural driving process, and the braking deceleration requested by the driver is predicted by the trained braking deceleration model.
  • Speed the powerful feature expression ability of the neural network model can improve the prediction accuracy of the braking deceleration requested by the driver.
  • step S310 further includes acquiring environmental perception information of the target vehicle.
  • the target braking deceleration is predicted based on the information of the target vehicle and the environmental perception information of the target vehicle.
  • the environment perception information of the vehicle refers to information related to the environment around the vehicle.
  • the environmental perception information of the target vehicle includes at least one of the following: the speed of the obstacle, the acceleration of the obstacle, or the relative position between the obstacle and the target vehicle, and the like.
  • the obstacles may include other vehicles or pedestrians and the like.
  • the environmental perception information may be acquired by the sensing system 120 in FIG. 1 .
  • the target braking deceleration may be determined from the first braking deceleration.
  • the first braking deceleration may be obtained by processing the target vehicle information and the environmental perception information of the target vehicle through a braking deceleration prediction model.
  • the motion information of the target vehicle, the pressure information of the brake master cylinder and the environmental perception information of the target vehicle are used as the input of the braking deceleration prediction model, and the feature extraction is carried out by the braking deceleration prediction model.
  • Features get the output of the model.
  • the output result of the braking deceleration model is the first braking deceleration.
  • the collection time of the environmental perception information of the target vehicle and the collection time of the information of the target vehicle may be the same.
  • the training samples may include information of the training vehicle, environment perception information of the training vehicle, and sample labels of the training samples.
  • a training sample may be determined according to data during a braking process in the process of driving the training vehicle naturally, that is, the motion information of the training vehicle, the pressure information of the master cylinder of the training vehicle, and the environmental perception of the training vehicle.
  • the information is the data during the braking process.
  • the collection moment of the environment perception information of the training vehicle may be the same as the collection moment of the information of the training vehicle.
  • Obtaining the braking deceleration prediction model based on the training samples may include: taking the motion information of the training vehicle, the pressure information of the brake master cylinder of the training vehicle and the environmental perception information of the training vehicle as the input of the braking deceleration prediction model, so as to train the vehicle
  • the braking deceleration requested by the driver is used as the target output of the braking deceleration prediction model to train the model, and the trained braking deceleration prediction model is obtained.
  • FIG. 5 shows a schematic diagram of the training and inference process of a braking deceleration prediction model.
  • the braking deceleration prediction model is trained based on natural driving data, and the training process can be done offline.
  • natural driving data is used to obtain training samples.
  • the training samples include motion information of the training vehicle, pressure information of the brake master cylinder of the training vehicle, environmental perception information of the training vehicle, and sample labels of the training samples.
  • the motion information of the target vehicle, the pressure information of the brake master cylinder and the environmental perception information of the target vehicle are input into the trained braking deceleration prediction model to obtain the first braking deceleration. This prediction process can be done online.
  • the environment perception information of the training vehicle is used for model training, so that the model can judge whether the driver needs emergency braking based on the actual collision risk, thereby improving the accuracy of the prediction model.
  • the environmental perception information of the target vehicle is also used as the input of the model, so that the braking result can better meet the driver's subjective wishes, and the user experience and safety are improved.
  • the target braking deceleration is determined according to the first braking deceleration, including: the target braking deceleration is the first braking deceleration.
  • the target braking deceleration is determined according to the first braking deceleration, including: the target braking deceleration is determined according to the second braking deceleration, and the second braking deceleration is determined by the target gain coefficient pair. Obtained by processing the first braking deceleration, there is a mapping relationship between the target gain coefficient and the danger level of the current driving scene.
  • the target gain coefficient is determined through the mapping relationship between the gain coefficient and the danger level of the driving scene.
  • the target gain coefficient is determined through the mapping relationship between the multiple gain coefficients and the danger levels of the multiple driving scenarios and the danger level of the current driving scenario.
  • the target gain coefficient is one of a plurality of gain coefficients.
  • the gain coefficient corresponding to the danger level of the current driving scene that is, the target gain coefficient
  • the first braking deceleration can be performed according to the target gain coefficient. processing to obtain the second braking deceleration.
  • the danger level can also be understood as a safety level.
  • the method 300 is only described in the following by taking this manner as an example, and does not constitute a limitation on the solutions of the embodiments of the present application.
  • the first braking deceleration is processed correspondingly according to the gain coefficient corresponding to the danger level of the current driving scene, so that graded braking can be implemented based on different danger levels, which improves the safety of vehicle driving.
  • Processing the first braking deceleration may include any of the following: amplifying the first braking deceleration, reducing the first braking deceleration, or using the first braking deceleration as the second braking deceleration. speed.
  • the result of the processing of the first braking deceleration may be different for different gain coefficients.
  • the second braking deceleration is obtained by multiplying the first braking deceleration by the target gain coefficient. In this case, if the target gain coefficient is greater than 1, the processing of the first braking deceleration is substantially the amplification processing of the first braking deceleration, and the amplified first braking deceleration is used as the second braking deceleration.
  • the target gain coefficient is 1, the first braking deceleration is processed essentially without processing the first braking deceleration, and the first braking deceleration is regarded as the second braking deceleration; the target gain If the coefficient is less than 1, the processing of the first braking deceleration is essentially the reduction processing of the first braking deceleration, and the reduced first braking deceleration is used as the second braking deceleration.
  • the multiple gain coefficients are greater than or equal to 1. That is, the target gain coefficient is greater than or equal to 1.
  • the processing of the first braking deceleration includes amplifying the first braking deceleration or using the first braking deceleration as the second braking deceleration.
  • the gain coefficient corresponding to the danger level is greater than 1. That is, the first braking deceleration is amplified when the danger level is greater than or equal to the first level threshold.
  • the gain coefficient corresponding to the danger level is equal to 1. That is, when the danger level is smaller than the first level threshold, the first braking deceleration is used as the second braking deceleration.
  • the first level threshold may be one.
  • the braking deceleration requested by ordinary drivers may not be enough to avoid obstacles due to lack of experience, insufficient pedaling force, or slow response.
  • the first braking deceleration is amplified, which is beneficial to further improve the safety of driving.
  • the danger level is low, the first braking deceleration is directly used as the second braking deceleration, which is more in line with the driver's subjective wishes and improves the user experience.
  • the gain coefficients corresponding to different risk levels can be preset.
  • the mapping relationship between the multiple gain coefficients and the multiple risk levels may be preset.
  • the gain coefficients corresponding to different risk levels may be determined according to the braking deceleration requested by the professional driver.
  • the professional driver calibrates the braking deceleration requested by the driver under different risk levels, and obtains the gain coefficients under different risk levels.
  • the danger level of the driving scene is determined according to the information of the vehicle and the environmental perception information of the vehicle.
  • the risk discrimination index can be calculated according to the motion information of the vehicle and the environmental perception information of the vehicle, and then the risk level is determined according to the risk discrimination index.
  • the risk judgment index is compared with a calibrated threshold, and the risk level is determined according to the comparison result.
  • the risk discrimination index may include at least one of the following: time to collision (TTC), time to brake (TTB), or time headway (THW).
  • TTC time to collision
  • TTB time to brake
  • TW time headway
  • hazard discrimination index and the method for dividing the hazard level are only illustrative, and the hazard discriminating index and the method for dividing the hazard level may be determined in other ways, which are not limited in the embodiments of the present application.
  • FIG. 6 shows a schematic flowchart of a graded braking process provided by an embodiment of the present application. Step S320 will be described below with reference to FIG. 6 . The solution in FIG. 6 can be regarded as a specific implementation of step S320.
  • FIG. 6 may be performed by the staged braking module 230 of FIG. 2 .
  • the scheme in FIG. 6 includes steps S610 to S640.
  • S610 Calculate the risk discrimination index according to the motion information and the environment perception information of the target vehicle.
  • the risk discrimination index includes at least one of the following: TTC, TTB, or THW.
  • S620 Determine the risk level of the current driving scene according to the risk discrimination index.
  • the danger discrimination index is compared with a calibrated threshold, and the danger level of the current driving scene is determined according to the comparison result.
  • the danger level of the driving scene may include multiple levels such as 0, 1, 2, and 3, and the danger level of the current driving scene is one of the danger levels.
  • S630 Determine a target gain coefficient corresponding to the risk level of the current driving scene according to the mapping relationship between the risk level and the gain coefficient.
  • the danger levels of the driving scene include four levels of 0, 1, 2, and 3, and the corresponding gain coefficients are k0, k1, k2, and k3, respectively.
  • S640 Process the first braking deceleration according to the target gain coefficient to obtain the second braking deceleration.
  • the target braking deceleration is determined according to the second braking deceleration, including: the target braking deceleration is the second braking deceleration.
  • the second braking deceleration is obtained by calibrating the first braking deceleration by a professional driver, which conforms to the driver's subjective wishes and improves driving safety at the same time.
  • the danger level of the current driving scene is greater than or equal to the second level threshold.
  • step S320 is not executed.
  • the second level threshold and the first level threshold may be the same or different.
  • the second level threshold is 1, and when the danger level of the current driving scene is 0, step S320 is not executed.
  • the vehicle may not perform active boosting, but perform boosting through driver pedal braking.
  • the solutions of the embodiments of the present application can be applied to an EBA system to provide an emergency braking assist function.
  • the emergency braking assist function may not be triggered. In this way, the accidental triggering of the emergency braking assistance function is further avoided by identifying the risk of collision by the danger level.
  • FIG. 7 shows the variation of the braking deceleration of the vehicle under different danger levels.
  • the target braking deceleration in the scheme of FIG. 7 is the second braking deceleration.
  • the target gain coefficient is 1, the first braking deceleration is not processed, and the EBA system may not provide the emergency braking assist function.
  • the curve reflects the braking of ordinary drivers. Changes in braking deceleration during operation. As the danger level increases, the gain coefficient increases gradually, and the second braking deceleration also increases.
  • the second braking deceleration obtained when the danger level is 3 in Fig. 7 is the maximum braking deceleration that the vehicle can output. deceleration. As shown in Figure 7, as the danger level increases, the second braking deceleration also increases.
  • the pressure can be built up faster, so that the vehicle can reach the required braking deceleration as soon as possible. Speed, or reach the second braking deceleration as soon as possible, to achieve graded auxiliary braking that is more in line with the driver's subjective wishes, and to ensure the safety of the vehicle at different levels of danger.
  • the calibration results of professional drivers cannot completely avoid collisions.
  • the safety of driving is further improved through the safe braking deceleration.
  • the target braking deceleration is determined according to the second braking deceleration, including: the target braking deceleration is based on the larger absolute value of the second braking deceleration and the safe braking deceleration definite.
  • Safe braking deceleration is used to represent the braking deceleration required for the target vehicle to avoid a collision.
  • the safe braking deceleration is determined according to the motion information of the target vehicle and the environmental perception information of the target vehicle and is required to avoid a collision.
  • the second braking deceleration and the safe braking deceleration are compared and arbitrated, and the target braking deceleration is determined according to the one with the larger absolute value.
  • the target braking deceleration is determined according to the larger absolute value of the second braking deceleration and the safe braking deceleration, including: the target braking deceleration is the second braking deceleration and the The item with the larger absolute value of the safe braking deceleration.
  • the target braking deceleration is determined by the second braking deceleration and the safe braking deceleration with a larger absolute value, including: the target braking deceleration is an item with a larger absolute value and the braking deceleration. The smaller value between the dynamic deceleration thresholds.
  • the braking deceleration threshold is determined by the ABS.
  • the safe braking deceleration is determined by the motion information of the target vehicle and the environmental perception information of the target vehicle, and the target braking is determined according to the one of the safe braking deceleration and the second braking deceleration, which has a larger absolute value. Deceleration can effectively avoid collision risks and further improve driving safety on the premise of satisfying the driver's subjective wishes as much as possible.
  • the target braking deceleration is determined according to the first braking deceleration, including that the target braking deceleration is determined according to the larger absolute value of the first braking deceleration and the safe braking deceleration.
  • the first braking deceleration and the safe braking deceleration are compared and arbitrated, and the target braking deceleration is determined according to the one with the larger absolute value.
  • the target braking deceleration may be determined based on the first braking deceleration and the safe braking deceleration.
  • the target braking deceleration is determined according to the larger one of the first braking deceleration and the safe absolute value, including: the target braking deceleration is one of the first braking deceleration and the safe braking deceleration.
  • the item with the larger absolute value is one of the first braking deceleration and the safe braking deceleration.
  • the target braking deceleration is determined by the first braking deceleration and the safe braking deceleration with a larger absolute value, including: the target braking deceleration is the larger absolute value and the The one with the smaller absolute value between the braking deceleration thresholds.
  • the braking deceleration threshold is determined by the ABS.
  • FIG. 8 shows a schematic flowchart of a method for determining a target braking deceleration provided by an embodiment of the present application.
  • the solution in FIG. 8 can be regarded as a specific implementation of step S320.
  • FIG. 8 may be executed by the brake deceleration decision module 240 in FIG. 2 .
  • the solution shown in FIG. 8 includes steps S710 to S730, and steps S710 to S730 will be described below.
  • S710 Determine safe braking deceleration according to the motion information and environment perception information of the target vehicle.
  • the larger of the safe braking deceleration and the first braking deceleration is determined.
  • step S730 determine the item with the larger absolute value in step S720 and the item with the smaller absolute value in the braking deceleration threshold determined by the ABS.
  • the smaller absolute value of the two is used as the target braking deceleration.
  • the target braking deceleration can be used as the braking deceleration value required by the emergency braking assistance system, or the braking deceleration value output by the emergency braking assistance system, and the target braking deceleration can be reached as soon as possible through active boosting. speed.
  • Fig. 9 shows the variation of braking deceleration in different scenarios.
  • Fig. 9(a) shows the change of braking deceleration in different scenarios when the second braking deceleration is greater than the safe braking deceleration, and
  • Fig. 9(b) shows the second braking deceleration Changes of braking deceleration in different scenarios when it is less than the safe braking deceleration.
  • the braking deceleration requested by the professional driver in the emergency condition is greater than the safe braking deceleration, which can realize safe obstacle avoidance.
  • professional drivers are usually better than ordinary drivers in terms of reaction speed and other aspects.
  • the rising rate of the braking deceleration curve corresponding to professional drivers is significantly higher, that is to say , the required braking deceleration can be achieved faster when a professional driver is driving the vehicle.
  • the second braking deceleration in the embodiment of the present application may be obtained by a professional driver calibrating the first braking deceleration, and the braking deceleration requested by the professional driver in FIG. 9 can also be understood as being implemented in this application.
  • Example of the second braking deceleration When the second braking deceleration is greater than the safe braking deceleration, the EBA system uses the second braking deceleration as the target braking deceleration.
  • the EBA system provides the emergency braking assist function based on the target braking deceleration. As shown in (a) of Figure 9, the curve of the braking deceleration corresponding to the EBA system has a higher rate of rise than the braking deceleration corresponding to the professional driver. That is to say, when the target braking deceleration is the same, the EBA system can provide the emergency braking assist function to achieve active pressure build-up, so that the vehicle can reach the target braking deceleration faster and improve driving safety. .
  • the braking deceleration requested by the professional driver in this emergency condition is less than the safe braking deceleration, and safe obstacle avoidance cannot be achieved.
  • the second braking deceleration in the embodiment of the present application may be obtained by a professional driver calibrating the first braking deceleration, and the braking deceleration requested by the professional driver in FIG. 9 can also be understood as being implemented in this application.
  • Example of the second braking deceleration When the second braking deceleration is smaller than the safe braking deceleration, the EBA system takes the safe braking deceleration as the target braking deceleration.
  • the EBA system provides an emergency braking assist function based on the target braking deceleration to achieve active pressure build-up, enabling the vehicle to reach the target braking deceleration faster and improving driving safety.
  • step S320 is executed, that is, instruction information of the target braking deceleration is sent.
  • the identification process of the emergency braking condition in the embodiment of the present application may also be understood as the identification process of the driver's emergency braking intention.
  • the emergency braking assist function can be triggered, that is, an indication of the target braking deceleration is sent message, instructing the target vehicle to perform active boosting of the master cylinder.
  • the pressure information of the master brake cylinder of the target vehicle satisfies at least one of the following conditions: the pressure slope of the master brake cylinder of the target vehicle is greater than or equal to the first threshold or the target vehicle.
  • the pressure of the vehicle's master brake cylinder is greater than or equal to a second threshold, the first threshold being determined based on the speed of the target vehicle.
  • the second threshold is determined according to the speed of the target vehicle.
  • first threshold and the second threshold please refer to the method 1000 hereinafter.
  • the EBA system can identify the driver's emergency braking intention according to the speed of the target vehicle and the pressure information of the brake master cylinder of the target vehicle.
  • the pressure information of the master brake cylinder of the target vehicle satisfies at least one of the above items, it is determined that the driver has an emergency braking intention, and the emergency braking assist function is triggered.
  • the threshold in the embodiment of the present application is not a fixed value, but is determined according to the speed of the target vehicle. By comparing the pressure information of the brake master cylinder with the threshold determined according to the vehicle speed, it is judged whether the driver has an emergency braking intention. Improves the accuracy of the driver's emergency braking intent.
  • This embodiment of the present application provides a method 900 for identifying a driver's emergency braking intention.
  • the method may be performed by the emergency braking intent recognition module 210 in FIG. 2 .
  • the driver's intention of emergency braking can be used as one of the triggering conditions of step S320. That is, the result of the identification method of the driver's emergency braking intention may be used to trigger step S320.
  • the method for identifying the driver's emergency braking intention includes steps S910 to S920, and the method is described below.
  • the information of the target vehicle includes motion information of the target vehicle and pressure information of the master cylinder of the target vehicle.
  • the motion information of the target vehicle includes the speed of the target vehicle.
  • the pressure information of the master brake cylinder of the target vehicle includes at least one of the following: a pressure gradient of the master brake cylinder of the target vehicle or a pressure of the master brake cylinder of the target vehicle.
  • the pressure information of the master cylinder of the target vehicle may be acquired periodically.
  • the pressure of the master brake cylinder is obtained in each cycle, and the pressure gradient of the master brake cylinder of the target vehicle can be determined according to the change value of the cylinder pressure of the target vehicle in the cycle.
  • the first threshold is determined according to the speed of the target vehicle.
  • the second threshold is determined based on the speed of the target vehicle.
  • the above determination result may be used as one of the triggering conditions of the aforementioned step S320, or, in other words, as one of the triggering conditions of the emergency braking assist function. That is, when the pressure information of the master cylinder of the target vehicle satisfies the condition in step S302, it is determined that the driver has an emergency braking intention. The driver has the intention of emergency braking before sending the indication information of the target braking deceleration.
  • the pressure information of the master brake cylinder of the target vehicle satisfies the following condition: the pressure slope of the master brake cylinder of the target vehicle is greater than or equal to a first threshold.
  • step S320 is not performed.
  • the pressure information of the master brake cylinder of the target vehicle satisfies the following condition: the pressure of the master brake cylinder of the target vehicle is greater than or equal to the second threshold.
  • step S320 is not executed.
  • the pressure information of the master brake cylinder of the target vehicle satisfies the following conditions: the pressure slope of the master brake cylinder of the target vehicle is greater than or equal to the first threshold, and the target vehicle The pressure of the master brake cylinder is greater than or equal to the second threshold.
  • Step S320 is not executed when the pressure gradient of the master brake cylinder of the target vehicle is less than the first threshold or the pressure of the master brake cylinder of the target vehicle is less than the second threshold.
  • the identification result of the emergency braking intention may be combined with the aforementioned determination result of the danger level as the triggering condition of step S320, or in other words, as the triggering condition of the emergency braking assist function.
  • the danger level of the current driving scene is greater than or equal to the second level threshold, or the driver has an emergency braking intention.
  • the indication information of the target braking deceleration is sent.
  • This can further improve driving safety and avoid the risk of collision caused by driver error in judgment.
  • the indication information of the target braking deceleration is sent.
  • step S320 may include: in the case that the danger level of the current driving scene is greater than or equal to the second level threshold, and the pressure slope of the master brake cylinder of the target vehicle is greater than or equal to the first threshold, sending the target braking deceleration Instructions.
  • step S320 is not executed.
  • the first threshold is determined according to the speed of the target vehicle.
  • mapping relationship between the first threshold and the speed of the vehicle.
  • the mapping relationship may be reflected as a functional expression, that is, the first threshold may be expressed as a function of the speed of the vehicle.
  • FIG. 10 shows a method 1000 for determining the mapping relationship between the first threshold and the speed of the vehicle.
  • the method 1000 includes steps S1010 to S1020, and steps S1010 to S1020 are described below.
  • S1010 Acquire the pressure gradient of the largest master brake cylinder in each set of braking data in the multiple sets of braking data.
  • the multiple sets of braking data are braking data collected during natural driving.
  • the maximum pressure gradient of the master cylinder in each group of braking data is extracted from the plurality of sets of braking data, that is, the maximum pressure gradient of the master cylinder in each braking process.
  • S1020 Fit the relationship between the first threshold and the speed of the vehicle according to the distribution of the pressure gradient of the maximum master cylinder under the emergency braking condition and the non-emergency braking condition in the multiple sets of braking data relation.
  • the multiple sets of braking data include braking data collected under emergency braking conditions and braking data collected under non-emergency braking conditions.
  • a professional driver may determine that a set of braking data belongs to braking data collected under emergency braking conditions or braking data collected under non-emergency braking conditions.
  • v represents the speed of the vehicle
  • p_thr' represents the first threshold
  • g() represents the function
  • FIG. 11 shows the distribution of the maximum brake master cylinder pressure slope under the emergency braking condition and the non-emergency braking condition when the vehicle is at the same speed.
  • the straight line in FIG. 11 is the first threshold value corresponding to the speed.
  • the pressure slopes of the master cylinder under emergency braking conditions are all in the upper part of Fig. 11, and the pressure gradients of the master cylinder under non-emergency braking conditions are all in the upper part of Fig. 11.
  • the threshold is obtained by fitting, and the pressure slope of the master cylinder under emergency braking conditions and non-emergency braking conditions is distinguished, and the threshold is the first threshold corresponding to the speed. .
  • the second threshold is determined based on the speed of the target vehicle.
  • mapping relationship between the second threshold and the speed of the vehicle.
  • the mapping relationship may be reflected as a functional expression, that is, the second threshold may be expressed as a function of the speed of the vehicle.
  • mapping relationship between the second threshold and the speed of the vehicle reference may be made to the method in FIG. 10 .
  • the mapping relationship between the second threshold and the speed of the vehicle may be determined through the following steps.
  • the multiple sets of braking data are braking data collected during natural driving.
  • the maximum brake master cylinder pressure in each group of brake data is extracted from the multiple sets of brake data, that is, the maximum brake master cylinder pressure in each braking process.
  • the multiple sets of braking data include braking data collected under emergency braking conditions and braking data collected under non-emergency braking conditions.
  • a professional driver may determine that a set of braking data belongs to braking data collected under emergency braking conditions or braking data collected under non-emergency braking conditions.
  • FIG. 12 shows a method 1100 for identifying a driver's braking intention provided by an embodiment of the present application.
  • the method 1100 in FIG. 12 may be regarded as a specific implementation of the method 900 , and for a specific description, refer to the aforementioned method 900 .
  • FIG. 12 may be performed by the emergency braking intent recognition module 210 in FIG. 2 .
  • the method 1100 includes steps S1110 to S1140, and steps S1110 to S1140 are described below.
  • the pressure of the master cylinder is acquired periodically.
  • S1140 Calculate the first threshold and the second threshold according to the speed of the target vehicle.
  • S1150 Determine whether the pressure gradient of the master brake cylinder of the target vehicle is greater than or equal to a first threshold and whether the pressure of the master brake cylinder of the target vehicle is greater than or equal to a second threshold.
  • the current scene is regarded as the emergency braking condition; otherwise, The current scenario is used as a non-emergency braking condition.
  • step S1140 may also calculate the first threshold value according to the speed of the target vehicle.
  • step S1150 may also be to determine whether the pressure gradient of the master brake cylinder of the target vehicle is greater than or equal to the first threshold.
  • the pressure gradient of the master brake cylinder of the target vehicle is greater than or equal to the first threshold, the current scene is regarded as the emergency braking condition; when the pressure gradient of the master brake cylinder of the target vehicle is less than the first threshold, Treat the current scenario as a non-emergency condition.
  • the method 1100 may not include S1120, and correspondingly, step S1140 may be calculating the second threshold according to the speed of the target vehicle.
  • Step S1150 may also be judging whether the pressure of the master brake cylinder of the target vehicle is greater than or equal to a second threshold.
  • the pressure of the master brake cylinder of the target vehicle is greater than or equal to the second threshold, the current scene is regarded as the emergency braking condition; when the pressure of the master brake cylinder of the target vehicle is less than the second threshold, the current scene Scenarios as non-emergency conditions.
  • FIG. 13 is a schematic diagram of a vehicle control device according to an embodiment of the present application.
  • the apparatus 2000 includes an obtaining unit 2001 and a sending unit 2002 .
  • the apparatus 2000 can be used to execute each step of the vehicle control method of the embodiment of the present application.
  • the acquiring unit 2001 may be configured to perform step S310 in the method shown in FIG. 3
  • the sending unit 2002 may be configured to perform step S320 in the method shown in FIG. 3 .
  • an obtaining unit 2001 is configured to obtain information of a target vehicle, where the information of the target vehicle includes motion information of the target vehicle and pressure information of a master brake cylinder of the target vehicle.
  • the sending unit 2002 is used to send the instruction information of the target braking deceleration, the instruction information of the target braking deceleration is used to instruct the target vehicle to perform brake boosting on the brake master cylinder, and the target braking deceleration is based on the target vehicle. information is predicted.
  • the target braking deceleration is determined according to a first braking deceleration, and the first braking deceleration is obtained by processing information of the target vehicle through a braking deceleration prediction model.
  • the braking deceleration prediction model is obtained by training based on at least one training sample, the training sample includes information of the training vehicle and the sample label of the training sample, and the information of the training vehicle includes motion information and The pressure information of the brake master cylinder of the training vehicle, and the sample label of the training sample is used to indicate the braking deceleration requested by the driver of the training vehicle.
  • the pressure information of the master brake cylinder of the target vehicle includes the pressure slope of the master brake cylinder of the target vehicle, and before sending the instruction information of the target braking deceleration, the master brake cylinder of the target vehicle The pressure slope of is greater than or equal to the first threshold.
  • the motion information of the target vehicle includes the speed of the target vehicle, and the first threshold is determined according to the speed of the target vehicle.
  • the target braking deceleration is determined according to the second braking deceleration, the second braking deceleration is obtained by processing the first braking deceleration by the target gain coefficient, and the target gain There is a mapping relationship between the coefficient and the danger level of the current driving scene.
  • the target braking deceleration is determined according to the larger absolute value of the second braking deceleration and the safe braking deceleration, and the safe braking deceleration is used to indicate that the target vehicle avoids a collision.
  • Required braking deceleration is used to indicate that the target vehicle avoids a collision.
  • FIG. 14 is a schematic diagram of a control device according to an embodiment of the present application.
  • the apparatus 3000 may include at least one processor 3002 and a communication interface 3003 .
  • the apparatus 3000 may further include at least one of a memory 3001 and a bus 3004 .
  • a memory 3001 and a bus 3004 .
  • any two or all three of the memory 3001 , the processor 3002 and the communication interface 3003 can be connected to each other through the bus 3004 for communication.
  • the memory 3001 may be a read only memory (ROM), a static storage device, a dynamic storage device, or a random access memory (RAM).
  • the memory 3001 can store a program.
  • the processor 3002 and the communication interface 3003 are used to execute various steps of the vehicle control method of the embodiment of the present application. That is to say, the processor 3002 may acquire the stored instructions from the memory 3001 through the communication interface 3003, so as to execute various steps of the vehicle control method of the embodiment of the present application.
  • the memory 3001 may have the function of the memory 152 shown in FIG. 1 to realize the above-mentioned function of storing programs.
  • the processor 3002 may adopt a general-purpose CPU, a microprocessor, an ASIC, a graphics processing unit (graphic processing unit, GPU), or one or more integrated circuits, for executing related programs, so as to implement the functions of the embodiments of the present application. The functions that need to be performed by the units in the control device, or each step of the control method in the embodiment of the present application is performed.
  • the processor 3002 may have the function of the processor 151 shown in FIG. 1 to realize the above-mentioned function of executing the related program.
  • the processor 3002 may also be an integrated circuit chip with signal processing capability.
  • each step of the control method of the embodiment of the present application may be completed by an integrated logic circuit of hardware in a processor or an instruction in the form of software.
  • the above-mentioned processor 3002 may also be a general-purpose processor, a digital signal processor (digital signal processing, DSP), an application specific integrated circuit (ASIC), an off-the-shelf programmable gate array (field programmable gate array, FPGA) or other Programming logic devices, discrete gate or transistor logic devices, discrete hardware components.
  • DSP digital signal processing
  • ASIC application specific integrated circuit
  • FPGA field programmable gate array
  • Programming logic devices discrete gate or transistor logic devices, discrete hardware components.
  • a general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.
  • the steps of the methods disclosed in conjunction with the embodiments of the present application may be directly embodied as executed by a hardware decoding processor, or executed by a combination of hardware and software modules in the decoding processor.
  • the software module may be located in random access memory, flash memory, read-only memory, programmable read-only memory or electrically erasable programmable memory, registers and other storage media mature in the art.
  • the storage medium is located in the memory, and the processor reads the information in the memory and, in combination with its hardware, completes the functions required to be performed by the units included in the vehicle control device of the embodiments of the present application, or executes each of the vehicle control methods of the embodiments of the present application. step.
  • the communication interface 3003 may use a transceiver device such as, but not limited to, a transceiver to implement communication between the device and other devices or a communication network.
  • the communication interface 3003 may also be, for example, an interface circuit.
  • the bus 3004 may include pathways for transferring information between various components of the device (eg, memory, processor, communication interface).
  • the embodiments of the present application further provide a computer program product including instructions, and when the instructions are executed by a computer, the instructions cause the computer to implement the methods in the foregoing method embodiments.
  • An embodiment of the present application further provides a terminal, where the terminal includes any one of the above control devices, for example, the control device shown in FIG. 13 or FIG. 14 .
  • the terminal may be a vehicle.
  • the terminal may also be a terminal for remotely controlling the vehicle.
  • the above-mentioned control device may be installed on the target vehicle, or may be independent of the target vehicle, for example, the target vehicle may be controlled by a drone, other vehicles, robots, or the like.
  • Computer readable media may include, but are not limited to, magnetic storage devices (eg, hard disks, floppy disks, or magnetic tapes, etc.), optical disks (eg, compact discs (CDs), digital versatile discs (DVDs), etc. ), smart cards and flash memory devices (eg, erasable programmable read-only memory (EPROM), cards, stick or key drives, etc.).
  • magnetic storage devices eg, hard disks, floppy disks, or magnetic tapes, etc.
  • optical disks eg, compact discs (CDs), digital versatile discs (DVDs), etc.
  • smart cards and flash memory devices eg, erasable programmable read-only memory (EPROM), cards, stick or key drives, etc.
  • the various storage media described herein may represent one or more devices and/or other machine-readable media for storing information.
  • the term "machine-readable medium” may include, but is not limited to, wireless channels and various other media capable of storing, containing, and/or carrying instructions and/or data.
  • the processor is a general-purpose processor, DSP, ASIC, FPGA or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components
  • the memory storage module
  • the disclosed apparatus and method may be implemented in other manners.
  • the apparatus embodiments described above are only illustrative.
  • the division of the units is only a logical function division. In actual implementation, there may be other division methods.
  • multiple units or components may be combined or Can be integrated into another system, or some features can be ignored, or not implemented.
  • the shown or discussed mutual coupling or direct coupling or communication connection may be through some interfaces, indirect coupling or communication connection of devices or units, which may be in electrical, mechanical or other forms.
  • the units described as separate components may or may not be physically separated, and components displayed as units may or may not be physical units, that is, may be located in one place, or may be distributed to multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution in this embodiment.
  • each functional unit in each embodiment of the present application may be integrated into one unit, or each unit may exist physically alone, or two or more units may be integrated into one unit.
  • the functions, if implemented in the form of software functional units and sold or used as independent products, may be stored in a computer-readable storage medium.
  • the technical solution of the present application, or the part that contributes to the prior art, or the part of the technical solution can be embodied in the form of a computer software product, and the computer software product is stored in a storage
  • the computer software product includes several instructions, the instructions are used to cause a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present application.
  • the aforementioned storage medium may include, but is not limited to, various media that can store program codes, such as a U disk, a removable hard disk, a ROM, a RAM, a magnetic disk, or an optical disk.

Landscapes

  • Engineering & Computer Science (AREA)
  • Transportation (AREA)
  • Mechanical Engineering (AREA)
  • Regulating Braking Force (AREA)

Abstract

本申请提供了一种车辆控制方法及装置，属于自动驾驶或者智能驾驶领域，适用于传统汽车、新能源汽车、智能汽车等各类车辆，该方法包括：获取目标车辆的信息，目标车辆的信息包括目标车辆的运动信息和目标车辆的制动主缸的压力信息；发送目标制动减速度的指示信息，目标制动减速度的指示信息用于指示目标车辆对制动主缸执行制动增压，目标制动减速度是根据目标车辆的信息预测得到的。本申请的方法能够提供合适的制动减速度，更符合驾驶员的主观意愿，提高车辆制动过程中的用户体验。

Description

车辆控制方法及装置 技术领域
本申请涉及车辆控制领域，尤其涉及一种车辆控制方法及装置。
背景技术
在紧急制动工况下，若驾驶员存在驾驶经验不足、反映不够迅速、踏板力不足或对危险判断不准确等问题，则会导致车辆的制动距离过长，增加了车辆碰撞的可能性。为了避免发生碰撞，车辆上的紧急制动辅助(emergency brake assist，EBA)系统能够在当前行驶状态处于危险状态时，对车辆进行紧急制动。紧急制动辅助系统在识别出紧急制动工况后主动增压。这样可以更快减压，大大减小车辆的制动滑行距离，尽可能避免车辆发生碰撞。
然而，通常车辆上的紧急制动辅助系统在进行紧急制动时不会考虑驾驶员的制动需求，而是输出预设的制动力以进行制动，导致用户体验较差，甚至存在安全隐患。例如，在路口或停车场等非紧急制动场景中，若驾驶员突然较大力度地踩踏刹车踏板，紧急制动辅助系统可能会将该情况误判为紧急制动工况，进而误触发紧急制动辅助功能，为车辆提供不必要的减速度，而且，紧急制动辅助系统在判断当前工况为紧急制动工况后，通常直接输出最大制动力，比如输出防抱死制动系统(antilock brake system，ABS)的阈值，然而当目标车辆的车速较低时无需输出最大制动力即可实现安全避障。不必要的减速度或过大的减速度均不符合驾驶员的主观意愿，导致用户体验下降，甚至可能存在被后车追尾等安全隐患。
因此，如何提高车辆制动过程中的用户体验成为一个亟待解决的问题。
发明内容
本申请提供一种车辆控制方法及装置，能够提供合适的制动减速度，更符合驾驶员的主观意愿，提高车辆制动过程中的用户体验。
第一方面，提供了一种车辆控制方法，包括：获取目标车辆的信息，目标车辆的信息包括目标车辆的运动信息和目标车辆的制动主缸的压力信息；发送目标制动减速度的指示信息，目标制动减速度的指示信息用于指示目标车辆对制动主缸执行制动增压，目标制动减速度是根据目标车辆的信息预测得到的。
根据本申请实施例的方案，主动增压前的目标车辆的信息是由驾驶员在自然驾驶过程中得到的，能够反映驾驶员的主观意愿。通过主动增压前的目标车辆的信息预测目标制动减速度，能够较准确地量化驾驶员的制动意图，使得车辆的制动过程符合驾驶员的主观意愿，提高了用户体验和驾驶的安全性。而且，通过目标车辆的运动信息和制动主缸的压力信息预测目标制动减速度，能够使得目标制动减速度更符合驾驶员的制动意图，进一步提高预测的准确性，使得车辆的制动过程更符合驾驶员的主观意愿，进一步提高用户体验和 驾驶的安全性。此外，本申请实施例的方案不依赖于踏板位置传感器、踏板模拟器或线控制动系统等硬件设备，节约了硬件成本。
示例性地，目标制动减速度的指示信息可以包含所述目标制动减速度本身，或者能够用于获取所述目标制动减速度的信息，例如，目标制动减速度的指示信息可以为目标制动减速度与当前的制动减速度的差值，本申请不做具体限定。
其中，车辆的运动信息指的是与车辆的运动状态相关的信息。例如，目标车辆的运动信息包括以下至少一项：目标车辆的速度或目标车辆的加速度等。
制动主缸的压力信息指的是与制动主缸的压力相关的信息。例如，制动主缸的压力信息包括以下至少一项：制动主缸的压力斜率或制动主缸的压力等。
制动减速度指的是制动后速度变化量与发生该速度变化所用的时间的比值。
结合第一方面，在第一方面的某些实现方式中，目标制动减速度是根据第一制动减速度确定的，第一制动减速度是通过制动减速度预测模型对目标车辆的信息进行处理得到的。
制动减速度预测模型用于根据输入模型中的信息预测得到第一制动减速度。例如，制动减速度预测模型根据输入的目标车辆的信息预测得到第一制动减速度。
第一制动减速度即为驾驶员所请求的制动减速度。
示例性地，制动减速度预测模型可以为神经网络模型，例如，循环神经网络(recurrent neural network，RNN)模型。
示例性地，目标制动减速度为第一制动减速度。
在本申请实施例的方案中，可以以神经网络模型作为制动减速度预测模型，基于自然驾驶过程中采集的数据训练制动减速度模型，通过训练好的制动减速度模型预测驾驶员所请求的制动减速度，神经网络模型强大的特征表达能力能够提高驾驶员所请求的制动减速度的预测准确率。
结合第一方面，在第一方面的某些实现方式中，制动减速度预测模型是基于至少一个训练样本训练得到的，训练样本包括训练车辆的信息以及训练样本的样本标签，训练车辆的信息包括训练车辆的运动信息和训练车辆的制动主缸的压力信息，训练样本的样本标签用于指示训练车辆的驾驶员所请求的制动减速度。
该至少一个训练样本是根据自然驾驶测试数据得到的。
自然驾驶测试数据是在没有诸如紧急制动辅助系统等系统主动增压的情况下获得的驾驶员执行的制动操作过程中的制动数据。
结合第一方面，在第一方面的某些实现方式中，方法还包括：获取目标车辆的环境感知信息；其中，目标制动减速度是根据目标车辆的信息和目标车辆的环境感知信息预测得到的。
进一步地，第一制动减速度是通过制动减速度预测模型对目标车辆的信息和目标车辆的环境感知信息进行处理得到的。
在该情况下，训练样本可以包括训练车辆的信息、训练车辆的环境感知信息以及训练样本的样本标签。
本申请实施例中将训练车辆的环境感知信息用于模型的训练，使得模型能够基于实际的碰撞风险判断驾驶员是否需要紧急制动，提高预测模型的准确率。相应地，在推理过程 中，将目标车辆的环境感知信息也作为模型的输入，使得制动结果更能满足驾驶员的主观意愿，提高用户体验以及安全性。
结合第一方面，在第一方面的某些实现方式中，目标车辆的制动主缸的压力信息包括目标车辆的制动主缸的压力斜率，在发送目标制动减速度的指示信息之前，目标车辆的制动主缸的压力斜率大于或等于第一阈值。
结合第一方面，在第一方面的某些实现方式中，目标车辆的运动信息包括目标车辆的速度，第一阈值是根据目标车辆的速度确定的。
结合第一方面，在第一方面的某些实现方式中，目标制动减速度是根据第二制动减速度确定的，第二制动减速度是通过目标增益系数对第一制动减速度进行处理得到的，目标增益系数与当前驾驶场景的危险等级之间具有映射关系。
示例性地，目标增益系数是通过多个增益系数与多个驾驶场景的危险等级之间的映射关系以及当前驾驶场景的危险等级确定的。目标增益系数为多个增益系数中的一个。
在一种实现方式中，危险等级越高，车辆发生碰撞的概率越小，相应的增益系数越小。在该情况下，危险等级也可以理解为安全等级。
在另一种实现方式中，危险等级越高，车辆发生碰撞的概率越大，相应的增益系数越大。
驾驶场景的危险等级是根据车辆的信息和车辆的环境感知信息确定的。
具体地，可以根据车辆的运动信息和车辆的环境感知信息计算危险判别指标，进而根据危险判别指标确定危险等级。
示例性地，目标制动减速度为第二制动减速度。
根据本申请实施例的方案，根据当前驾驶场景的危险等级对应的增益系数对第一制动减速进行相应的处理，能够基于不同的危险等级实现分级制动，提高了车辆行驶的安全性。
结合第一方面，在第一方面的某些实现方式中，在危险等级大于或等于第一等级阈值的情况下，该危险等级对应的增益系数大于1。
也就是说，在危险等级大于或等于第一等级阈值的情况下对第一制动减速度进行放大处理。
不同危险等级对应的增益系数可以是预先设定的。或者说，多个增益系数与多个危险等级之间的映射关系可以是预先设定的。
通过本申请实施例的方案，在危险等级较高的情况下，对第一制动减速度进行放大处理，有利于进一步提高驾驶的安全性。
结合第一方面，在第一方面的某些实现方式中，在发送目标制动减速度的指示信息之前，当前驾驶场景的危险等级大于或等于第二等级阈值。
结合第一方面，在第一方面的某些实现方式中，目标制动减速度是根据第二制动减速度和安全制动减速度中绝对值较大一项确定的，安全制动减速度用于表示目标车辆避免碰撞所需的制动减速度。
具体地，安全制动减速度是根据目标车辆的运动信息和目标车辆的环境感知信息确定的、避免发生碰撞所需的制动减速度。
可选地，目标制动减速度为第二制动减速度和安全制动减速度中的绝对值较大的一项。
可替换地，目标制动减速度为绝对值较大的一项与制动减速度阈值之间的较小值。
示例性地，制动减速度阈值时由ABS确定的。
本申请实施例通过目标车辆的运动信息和目标车辆的环境感知信息确定安全制动减速度，并根据安全制动减速度和第二制动减速度中绝对值较大的一项确定目标制动减速度，能够在尽量满足驾驶员主观意愿的前提下，有效规避碰撞风险，进一步提高驾驶的安全性。
第二方面，提供了一种车辆控制装置，包括：获取单元，用于获取目标车辆的信息，目标车辆的信息包括目标车辆的运动信息和目标车辆的制动主缸的压力信息；发送单元，用于发送目标制动减速度的指示信息，目标制动减速度的指示信息用于指示目标车辆对制动主缸执行制动增压，目标制动减速度是根据目标车辆的信息预测得到的。
根据本申请实施例的方案，主动增压前的目标车辆的信息是由驾驶员在自然驾驶过程中得到的，能够反映驾驶员的主观意愿。通过主动增压前的目标车辆的信息预测目标制动减速度，能够较准确地量化驾驶员的制动意图，使得车辆的制动过程符合驾驶员的主观意愿，提高了用户体验和驾驶的安全性。而且，通过目标车辆的运动信息和制动主缸的压力信息预测目标制动减速度，能够使得目标制动减速度更符合驾驶员的制动意图，进一步提高预测的准确性，使得车辆的制动过程更符合驾驶员的主观意愿，进一步提高用户体验和驾驶的安全性。此外，本申请实施例的方案不依赖于踏板位置传感器、踏板模拟器或线控制动系统等硬件设备，节约了硬件成本。
结合第二方面，在第二方面的某些实现方式中，目标制动减速度是根据第一制动减速度确定的，第一制动减速度是通过制动减速度预测模型对目标车辆的信息进行处理得到的。
结合第二方面，在第二方面的某些实现方式中，制动减速度预测模型是基于至少一个训练样本训练得到的，训练样本包括训练车辆的信息以及训练样本的样本标签，训练车辆的信息包括训练车辆的运动信息和训练车辆的制动主缸的压力信息，训练样本的样本标签用于指示训练车辆的驾驶员所请求的制动减速度。
结合第二方面，在第二方面的某些实现方式中，目标车辆的制动主缸的压力信息包括目标车辆的制动主缸的压力斜率，在发送目标制动减速度的指示信息之前，目标车辆的制动主缸的压力斜率大于或等于第一阈值。
结合第二方面，在第二方面的某些实现方式中，目标车辆的运动信息包括目标车辆的速度，第一阈值是根据目标车辆的速度确定的。
结合第二方面，在第二方面的某些实现方式中，目标制动减速度是根据第二制动减速度确定的，第二制动减速度是通过目标增益系数对第一制动减速度进行处理得到的，目标增益系数与当前驾驶场景的危险等级之间具有映射关系。
结合第二方面，在第二方面的某些实现方式中，目标制动减速度是根据第二制动减速度和安全制动减速度中绝对值较大一项确定的，安全制动减速度用于表示目标车辆避免碰撞所需的制动减速度。
第三方面，提供一种芯片，所述芯片包括至少一个处理器与接口电路，所述至少一个处理器通过所述接口电路获取存储器上存储的指令，执行上述第一方面的任意一种实现方式中的方法。
可选地，作为一种实现方式，所述芯片还可以包括存储器，所述存储器中存储有指令，所述处理器用于执行所述存储器上存储的指令，当所述指令被执行时，所述处理器用于执行第一方面的任意一种实现方式中的方法。
第四方面，提供一种计算机可读介质，该计算机可读介质存储用于设备执行的程序代码，该程序代码包括用于执行第一方面的任意一种实现方式中的方法。
第五方面，提供一种包含指令的计算机程序产品，当该计算机程序产品在计算机上运行时，使得计算机执行上述第一方面的任意一种实现方式中的方法。
第六方面，提供一种终端，该终端包括第二方面的任意一种实现方式的装置。
可选地，该终端还包括制动主缸。
示例性地，该终端可以为车辆，上述第二方面涉及的装置用于控制车辆。
附图说明
图1是本申请实施例提供的一种自动驾驶汽车的结构示意图；
图2是本申请实施例提供的一种车辆控制装置的结构示意图；
图3是本申请实施例提供的一种车辆控制方法的示意性流程图；
图4是本申请实施例提供的制动主缸的压力斜率和制动减速度之间的关系的示意图；
图5是本申请实施例提供的一种第一制动减速度的预测过程的示意图；
图6是本申请实施例提供的一种分级制动处理过程的示意性流程图；
图7是本申请实施例提供的一种分级辅助制动效果的示意图；
图8是本申请实施例提供的一种目标制动减速度的仲裁过程的示意性流程图；
图9是本申请实施例提供的不同场景下的制动效果的示意图；
图10是本申请实施例提供的第一阈值与车辆的速度之间的映射关系的确定方法的示意图；
图11是本申请实施例提供的一种制动主缸的压力斜率的分布情况的示意图；
图12是本申请实施例提供的一种驾驶员制动意图识别方法的示意性流程图；
图13是本申请实施例提供的一种车辆控制装置的示意图；
图14是本申请实施例提供的另一种车辆控制装置的示意图。
具体实施方式
下面将结合附图，对本申请中的技术方案进行描述。
本申请实施例的方案能够应用于车辆的制动系统中，例如，紧急制动辅助系统，为车辆提供合适的制动减速度。
图1是本申请实施例提供的车辆100的功能框图。在一个实施例中，将车辆100配置为完全或部分地自动驾驶模式。
在一个示例中，车辆100可以在处于自动驾驶模式中的同时控制目标车辆，并且可通过人为操作来确定车辆及其周边环境的当前状态，确定周边环境中的至少一个其他车辆的可能行为，并确定其他车辆执行可能行为的可能性相对应的置信水平，基于所确定的信息来控制车辆100。在车辆100处于自动驾驶模式中时，可以将车辆100置为在没有和人交互的情况下操作。
车辆100可包括各种子系统，例如，行进系统110、传感系统120、控制系统130、一个或多个外围设备140以及电源160、计算机系统150和用户接口170。可选地，车辆100可包括更多或更少的子系统，并且每个子系统可包括多个元件。另外，车辆100的每个子系统和元件可以通过有线或者无线互连。
示例性地，行进系统110可以包括用于向车辆100提供动力运动的组件。在本申请实施例中，行进系统可以用于在避障过程中，驱动车辆执行相应的运动行为，例如前进、后退、转向等等。行进系统110包括引擎111、传动装置112、能量源113和车轮114。
传感系统120可以包括感测关于车辆100周边的环境的信息的若干个传感器。在本申请实施例中，传感系统可以用于获取环境信息和道路结构信息，从而基于这些获取的信息，执行后续的控制。
例如，传感系统120可以包括定位系统121(例如，全球定位系统(global positioning system,GPS)、北斗系统或者其他定位系统)、惯性测量单元(inertial measurement unit，IMU)122、雷达123、激光测距仪124、相机125以及车速传感器126。传感系统120还可以包括被监视车辆100的内部系统的传感器(例如，车内空气质量监测器、燃油量表、机油温度表等)。来自这些传感器中的一个或多个的传感器数据可用于检测对象及其相应特性(位置、形状、方向、速度等)。这种检测和识别是自主车辆100的安全操作的关键功能。
其中，定位系统121可以用于估计车辆100的地理位置。IMU 122可以用于基于惯性加速度来感测车辆100的位置和朝向变化。在一个实施例中，IMU 122可以是加速度计和陀螺仪的组合。
示例性地，雷达123可以利用无线电信号来感测车辆100的周边环境内的物体。在一些实施例中，除了感测物体以外，雷达123还可用于感测物体的速度和/或前进方向。
示例性地，激光测距仪124可以利用激光来感测车辆100所位于的环境中的物体。在一些实施例中，激光测距仪124可以包括一个或多个激光源、激光扫描器以及一个或多个检测器，以及其他系统组件。
示例性地，相机125可以用于捕捉车辆100的周边环境的多个图像。例如，相机125可以是静态相机或视频相机。
示例性地，车速传感器126可以用于测量车辆100的速度。例如，可以对车辆进行实时测速。测得的车速可以传送给控制系统130以实现对车辆的控制。
控制系统130为控制车辆100及其组件的操作。控制系统130可以包括各种元件，比如可以包括转向系统131、油门132、制动单元133、计算机视觉系统134、路线控制系统135以及障碍规避系统136。
示例性地，转向系统131可以操作来调整车辆100的前进方向。例如，在一个实施例中可以为方向盘系统。油门132可以用于控制引擎111的操作速度并进而控制车辆100的速度。
示例性地，制动单元133可以用于控制车辆100减速；制动单元133可以使用摩擦力来减慢车轮114。在其他实施例中，制动单元133可以将车轮114的动能转换为电流。制动单元133也可以采取其他形式来减慢车轮114转速从而控制车辆100的速度。
如图1所示，计算机视觉系统134可以操作来处理和分析由相机125捕捉的图像以便 识别车辆100周边环境中的物体和/或特征。上述物体和/或特征可以包括交通信号、道路边界和障碍物。计算机视觉系统134可以使用物体识别算法、运动中恢复结构(structure from motion，SFM)算法、视频跟踪和其他计算机视觉技术。在一些实施例中，计算机视觉系统134可以用于为环境绘制地图、跟踪物体、估计物体的速度等等。
示例性地，路线控制系统135可以用于确定车辆100的行驶路线。障碍规避系统136可以用于识别、评估和避免或者以其他方式越过车辆100的环境中的潜在障碍物。
在一个实例中，控制系统130可以增加或替换地包括除了所示出和描述的那些以外的组件。或者也可以减少一部分上述示出的组件。
如图1所示，车辆100可以通过外围设备140与外部传感器、其他车辆、其他计算机系统或用户之间进行交互。
在一些实施例中，外围设备140可以提供车辆100与用户接口170交互的手段。无线通信系统141可以直接地或者经由通信网络来与一个或多个设备无线通信。
电源160可以向车辆100的各种组件提供电力。
车辆100的部分或所有功能可以受计算机系统150控制，其中，计算机系统150可以包括至少一个处理器151，处理器151执行存储在例如存储器152中的非暂态计算机可读介质中的指令153。计算机系统150还可以是采用分布式方式控制车辆100的个体组件或子系统的多个计算设备。
例如，处理器151可以是任何常规的处理器，诸如商业可获得的中央处理器(central processing unit，CPU)。
可选地，该处理器可以是诸如专用集成电路(application specific integrated circuit，ASIC)或其它基于硬件的处理器的专用设备。尽管图1功能性地图示了处理器、存储器、和在相同块中的计算机的其它元件，但是本领域的普通技术人员应该理解该处理器、计算机、或存储器实际上可以包括可以或者可以不存储在相同的物理外壳内的多个处理器、计算机或存储器。例如，存储器可以是硬盘驱动器或位于不同于计算机的外壳内的其它存储介质。因此，对处理器或计算机的引用将被理解为包括对可以或者可以不并行操作的处理器或计算机或存储器的集合的引用。不同于使用单一的处理器来执行此处所描述的步骤，诸如转向组件和减速组件的一些组件每个都可以具有其自己的处理器，所述处理器只执行与特定于组件的功能相关的计算。
在此处所描述的各个方面中，处理器可以位于远离该车辆并且与该车辆进行无线通信。在其它方面中，此处所描述的过程中的一些在布置于车辆内的处理器上执行而其它则由远程处理器执行，包括采取执行单一操纵的必要步骤。
在一些实施例中，存储器152可包含指令153(例如，程序逻辑)，指令153可以被处理器151来执行车辆100的各种功能，包括以上描述的那些功能。存储器152也可包括额外的指令，比如包括向行进系统110、传感系统120、控制系统130和外围设备140中的一个或多个发送数据、从其接收数据、与其交互和/或对其进行控制的指令。
示例性地，除了指令153以外，存储器152还可存储数据，例如，道路地图、路线信息，车辆的位置、方向、速度以及其它这样的车辆数据，以及其他信息。这种信息可在车辆100在自主、半自主和/或手动模式中操作期间被车辆100和计算机系统150使用。
用户接口170可以用于向车辆100的用户提供信息或从其接收信息。可选地，用户接 口170可以包括在外围设备140的集合内的一个或多个输入/输出设备，例如，无线通信系统141、车载电脑142、麦克风143和扬声器144。
在本申请的实施例中，计算机系统150可以基于从各种子系统(例如，行进系统110、传感系统120和控制系统130)以及从用户接口170接收的输入来控制车辆100的功能。例如，计算机系统150可以利用来自控制系统130的输入以便控制制动单元133来避免由传感系统120和障碍规避系统136检测到的障碍物。在一些实施例中，计算机系统150可操作来对车辆100及其子系统的许多方面提供控制。
可选地，上述这些组件中的一个或多个可与车辆100分开安装或关联。例如，存储器152可以部分或完全地与车辆100分开存在。上述组件可以按有线和/或无线方式来通信地耦合在一起。
可选地，上述组件只是一个示例，实际应用中，上述各个模块中的组件有可能根据实际需要增添或者删除，图1不应理解为对本申请实施例的限制。
自动驾驶汽车车辆100或者与自动驾驶车辆100相关联的计算设备(如图1的计算机系统112、计算机视觉系统140、数据存储装置114)可以基于所识别的物体的特性和周围环境的状态(例如，交通、雨、道路上的冰、等等)来预测所述识别的物体的行为。可选地，每一个所识别的物体都依赖于彼此的行为，因此还可以将所识别的所有物体全部一起考虑来预测单个识别的物体的行为。车辆100能够基于预测的所述识别的物体的行为来调整它的速度。换句话说，自动驾驶汽车能够基于所预测的物体的行为来确定车辆将需要调整到(例如，加速、减速、或者停止)什么稳定状态。在这个过程中，也可以考虑其它因素来确定车辆100的速度，诸如，车辆100在行驶的道路中的横向位置、道路的曲率、静态和动态物体的接近度等等。
上述车辆100可以为传统汽车、新能源车、智能汽车等，所谓传统汽车是指利用汽车、柴油等提供能源的汽车，新能源车则指最新出现的利用电能、燃气等新能源提供能源的车辆，智能汽车则是指装载有智能控制单元等智能设备的车，上述车辆100的车辆类型例如可以包括轿车、卡车、客车、工程车、公交车等，本申请实施例不做特别的限定。在本申请实施例中，主要以道路上行驶的各类汽车为例进行介绍。
为了提高在紧急制动工况下车辆的安全性，车辆上的紧急制动辅助系统能够在当前行驶状态处于危险状态时，对车辆进行紧急制动。
通常车辆上的紧急制动辅助系统在进行紧急制动时不会考虑驾驶员的制动需求，而是根据预设的制动力进行制动，导致用户体验较差，甚至存在安全隐患。例如，自动紧急制动(autonomous emergency braking，AEB)系统通过传感器对周围环境进行感知，并在当前行驶状态为危险状态时，根据预设的制动力进行制动。然而，该制动过程没有考虑驾驶员的制动需求，突然的制动会导致用户体验较差。再如，紧急制动辅助系统可能会将非紧急制动工况误判为紧急制动工况，进而误触发紧急制动辅助功能，为车辆提供不必要的减速度，而且，紧急制动辅助系统在判断当前工况为紧急制动工况后，通常直接输出最大的制动力。不必要的减速度或过大的减速度均不符合驾驶员的主观意愿，导致用户体验下降，甚至可能存在被后车追尾等安全隐患。
本申请实施例提供一种车辆控制方法，提供合适的制动减速度，更符合驾驶员的主观意愿，能够提升车辆制动过程中的用户体验。
为了更好的描述本申请实施例的方法，下面结合图2对本申请实施例提供的一种车辆控制装置200进行说明。装置200可以采用本申请实施例中的方法对车辆进行制动控制。
图2示出了本申请实施例提供的一种车辆控制装置。图2中的装置200包括紧急制动意图识别模块210、驾驶员请求减速度预测模块220、分级制动模块230以及制动减速度决策模块240。
紧急制动意图识别模块210用于识别驾驶员的紧急制动意图，即判断驾驶员当前是否需要紧急制动，或者说，识别当前是否为紧急制动工况。
需要说明的是，紧急制动意图识别模块210为可选模块。示例性地，若装置200应用于EBA系统中，则紧急制动意图识别模块210集成于装置200中，也可以独立于装置200设置。可替换地，若装置200不是应用于EBA系统中，则紧急制动意图识别模块210为可省模块。例如，当装置200应用于AEB系统中，则系统中可以不设置紧急制动意图识别模块210。
示例性地，在当前工况为紧急制动工况的情况下，激活驾驶员请求减速度预测模块220、分级制动模块230或制动减速度决策模块240。
紧急制动意图识别模块210可以根据目标车辆的信息识别驾驶员的紧急制动意图。
目标车辆的信息包括目标车辆的制动主缸的压力信息和目标车辆的运动信息。
驾驶员请求减速度预测模块220用于预测驾驶员所请求的减速度。
具体地，驾驶员请求减速度预测模块220可以根据目标车辆的信息预测驾驶员所请求的制动减速度，即第一制动减速度。进一步地，驾驶员请求减速度预测模块220可以根据目标车辆的信息和环境感知信息预测驾驶员所请求的制动减速度。
分级制动模块230用于根据当前驾驶场景的危险等级对驾驶员所请求的制动减速度处理，得到第二制动减速度。
也就是将驾驶员请求减速度预测模块220的输出结果输入至分级制动模块230中，由分级制动模块230根据当前驾驶场景的危险等级对应的增益系数，即目标增益系数，对驾驶员所请求的制动减速度进行处理，输出第二制动减速度。
需要说明的是，分级制动模块230为可选模块。
制动减速度决策模块240用于确定目标制动减速度，该目标制动减速度即为装置200输出的制动减速度。
示例性地，在装置200不包括分级制动模块230的情况下，驾驶员请求减速度预测模块220可以将第一制动减速度输入至制动减速度决策模块240。制动减速度决策模块240可以将安全制动减速度和第一制动减速度中绝对值较大的值作为目标制动减速度。
其中，安全制动减速度用于表示目标车辆避免碰撞所需的制动减速度。
可替换地，在装置200包括分级制动模块230的情况下，分级制动模块230可以将第二制动减速度输出至制动减速度决策模块240。制动减速度决策模块240可以将安全减速度和分级制动模块230输出的第二制动减速度中绝对值较大的值作为目标制动减速度。
需要说明的是，制动减速度决策模块240为可选模块。
示例性地，在装置200不包括减速度制动决策模块240的情况下，目标制动减速度可以为分级制动模块230输出的第二制动减速度。
进一步地，在装置200不包括减速度制动决策模块240和分级制动模块230的情况下， 目标制动减速度可以为驾驶员请求减速度预测模块220输出的第一制动减速度。
图3示出了本申请实施例提供的一种车辆控制方法300的示意性流程图。方法300包括步骤S310至步骤S320。下面对步骤S310至步骤S320进行说明。
S310，获取目标车辆的信息，目标车辆的信息包括目标车辆的运动信息和目标车辆的制动主缸的压力信息。
其中，车辆的运动信息指的是与车辆的运动状态相关的信息。例如，目标车辆的运动信息包括以下至少一项：目标车辆的速度或目标车辆的加速度等。
示例性地，目标车辆的运动信息可以通过图1中的传感系统120获取。例如，通过车速传感器126得到目标车辆的速度。再如，通过惯性测量单元122得到目标车辆的加速度。
制动主缸的压力信息指的是与制动主缸的压力相关的信息。例如，制动主缸的压力信息包括以下至少一项：制动主缸的压力斜率或制动主缸的压力等。
制动主缸的压力斜率可以理解为制动主缸的压力的变化速率。例如，制动主缸的压力增加的过程中，制动主缸的压力斜率也可以称为制动主缸的压力上升速率。
示例性地，制动主缸的压力斜率可以通过周期性获取的制动主缸的压力的值确定。
示例性地，制动主缸的压力信息可以通过图1中的传感系统120获取。例如，通过内部系统的传感器获得制动主缸的压力信息。
S320，发送目标制动减速度的指示信息，目标制动减速度的指示信息用于指示目标车辆对制动主缸执行主动增压，目标制动减速度是根据目标车辆的信息预测得到的。该步骤的功能是控制车辆对制动主缸执行主动增压。
具体的，向目标车辆的执行器发送目标制动减速度的指示信息，能够指示或者触发目标车辆对制动主缸执行主动增压，使目标车辆根据所述目标制动减速度执行制动。
可选的，目标制动减速度的指示信息可以包含所述目标制动减速度本身，或者能够用于获取所述目标制动减速度的信息，例如，目标制动减速度的指示信息可以为目标制动减速度与当前的制动减速度的差值，本申请不做具体限定。
制动减速度(deceleration)指的是制动后速度变化量与发生该速度变化所用的时间的比值。制动减速度也可以理解为加速度。
主动增压指的是车辆自主执行的增压，而非驾驶员通过制动踏板所执行的增压，例如，车辆上的紧急制动辅助系统执行的主动增压。
目标车辆的信息均为主动增压起始时刻或主动增压时刻之前的目标车辆的信息。
传统的非线控制动系统中，踏板力与制动主缸的压力是耦合的，通过踏板开度、踏板开度变化率或缸压信息实时计算驾驶员请求的制动减速度的方案不适用于车辆主动增压的场景。紧急制动辅助系统在进行主动增压时，踏板开度以及踏板开度的变化率均会受到耦合的制动缸压的影响，通过实时的踏板力等参数无法准确量化驾驶员的真实意图。
在本申请实施例的方案中，主动增压前的目标车辆的信息是由驾驶员在自然驾驶过程中得到的，能够反映驾驶员的主观意愿。通过主动增压前的目标车辆的信息预测目标制动减速度，能够较准确地量化驾驶员的制动意图，使得车辆的制动过程符合驾驶员的主观意愿，提高了用户体验和驾驶的安全性。
在车辆的运动信息不同的情况下，相同的制动主缸的缸压信息所反映的驾驶员的制动意图也可能是不同的。例如，在车速不同的情况下，即使制动主缸的缸压斜率相同，驾驶 员所请求的制动减速度也可能是不同的。在车速较低时，驾驶员所请求的制动减速度较小，在车速较高时，驾驶员所请求的制动减速度较大。
本申请实施例通过目标车辆的运动信息和制动主缸的压力信息预测目标制动减速度，能够使得目标制动减速度更符合驾驶员的制动意图，进一步提高预测的准确性，使得车辆的制动过程更符合驾驶员的主观意愿，进一步提高用户体验和驾驶的安全性。
此外，本申请实施例的方案不依赖于踏板位置传感器、踏板模拟器或线控制动系统等硬件设备，节约了硬件成本。
在一种可能的实现方式中，方法300可以由EBA系统执行，在该情况下，目标制动减速度即为EBA系统所需要执行的制动减速度，或者说，目标制动减速度即为EBA系统输出的制动减速度，执行器根据目标制动减速度控制目标车辆对制动主缸执行主动增压。
这样，在紧急制动工况中，EBA系统可以基于目标制动减速度提供紧急制动辅助功能以实现辅助制动，而不是直接输出最大的制动力，更符合驾驶员的主观意愿，提高了用户体验和驾驶的安全性。
在另一种可能的实现方式中，方法300可以由AEB系统执行，在该情况下，目标制动减速度即为AEB系统所需要执行的制动减速度，或者说，目标制动减速度即为AEB系统输出的制动减速度，执行器根据目标制动减速度控制目标车辆对制动主缸执行主动增压。
这样，在紧急制动工况中，AEB系统可以基于目标制动减速度提供紧急制动功能以实现紧急制动，而不是直接输出预设的制动力，更符合驾驶员的主观意愿，提高了用户体验和驾驶的安全性。
应理解，以上两种应用场景仅为示意，本申请实施例中的方法300还可以应用于其他制动系统中，本申请实施例对此不做限定。为了便于描述和说明，后文中以方法300应用于EBA系统为例进行说明，不对本申请实施例的应用场景构成限定。
可选地，目标制动减速度是根据第一制动减速度确定的。第一制动减速度是通过制动减速度预测模型对目标车辆的信息进行处理得到的。
制动减速度预测模型用于根据输入模型中的信息预测得到第一制动减速度。例如，制动减速度预测模型根据输入的目标车辆的信息预测得到第一制动减速度。
进一步地，制动减速度预测模型是基于至少一个训练样本训练得到的，训练样本包括训练车辆的信息以及训练样本的样本标签，训练车辆的信息包括训练车辆的运动信息和制动主缸的压力信息。训练样本的样本标签用于指示训练车辆的驾驶员所请求的制动减速度。
第一制动减速度即为驾驶员所请求的制动减速度。
也就是说将目标车辆的运动信息和制动主缸的压力信息作为制动减速度预测模型的输入，由制动减速度预测模型进行特征提取，并根据提取到的特征得到模型的输出。制动减速度模型的输出结果即为第一制动减速度。
其中，制动减速度预测模型可以为神经网络模型，例如，循环神经网络(recurrent neural network，RNN)模型。
该至少一个训练样本是根据自然驾驶测试数据得到的。
自然驾驶测试数据是在没有诸如紧急制动辅助系统等系统主动增压的情况下获得的 驾驶员执行的制动操作过程中的制动数据。
一个训练样本可以是根据自然驾驶训练车辆的过程中的一次制动过程中的数据确定的，也就是说，训练车辆的运动信息和训练车辆的制动主缸的压力信息是该次制动过程中的数据。该训练车辆的驾驶员所请求的制动减速度可以理解为在该次制动过程中驾驶员最终所请求的制动减速度。示例性地，驾驶员最终所请求的制动减速度可以为在该次制动过程中训练车辆最终达到的稳定的制动减速度的值。或者，驾驶员最终所请求的制动减速度可以为在该次制动过程中，训练车辆达到的最大的制动减速度。应理解，本申请实施例中的制动减速度的大小指的是制动减速度的绝对值的大小。
具体地，基于训练样本得到制动减速度预测模型可以包括：以训练车辆的运动信息和训练车辆的制动主缸的压力信息作为制动减速度预测模型的输入，以训练车辆的驾驶员所请求的制动减速度作为制动减速度预测模型的目标输出对该模型进行训练，得到训练好的制动减速度预测模型。
其中，该训练过程可以是离线(offline)完成的。
在自然驾驶的制动过程中，驾驶员的操作是一个时序过程，但在一定的制动意图下，驾驶员的操作规律基本保持一致。驾驶员的操作规律可以通过制动过程中车辆的制动主缸的压力信息以及车辆的运动信息等参数体现。如图4所示，自然驾驶的一次制动过程中车辆的制动主缸的压力斜率的变化趋势与制动减速度的变化趋势基本是对应的。随着车辆的制动主缸的压力斜率的增大，为车辆提供的制动力也随之增大，相应地，车辆的制动减速度的绝对值也随之增大。例如，将图4中的绝对值最大的制动减速度作为驾驶员最终所请求的制动减速度。通过制动主缸的压力斜率最大的时刻对应的车辆的运动信息和制动主缸的压力信息，即图4中的计算点，可以预测驾驶员最终所请求的制动减速度，即图4中的预测点。
可选地，训练样本中的训练车辆的运动信息可以包括训练车辆的制动主缸的压力斜率最大的时刻对应的运动信息。训练车辆的制动主缸的压力信息包括训练车辆的制动主缸的压力斜率最大的时刻对应的制动主缸的压力信息。训练样本的样本标签包括该训练车辆的驾驶员最终所请求的制动减速度。
即以计算点时刻采集到的训练车辆的运动信息和制动主缸的压力信息作为制动减速度预测模型的输入，以预测点时刻采集到的制动减速度作为制动减速度预测模型的目标输出对该模型进行训练，得到训练好的预测减速度模型。
以图4所示的制动过程为例，一个训练样本中的训练车辆的运动信息可以包括t2时刻的训练车辆的运动信息，训练车辆的制动主缸的压力信息可以包括t2时刻的训练车辆的制动主缸的压力信息。该训练样本的样本标签，即驾驶员所请求的制动减速度，可以为图4中的t3时刻的制动减速度。也就是说，可以将t2时刻的训练车辆的运动信息和训练车辆的制动主缸的压力信息作为制动减速度预测模型的输入，将t3时刻的制动减速度作为样本标签对制动减速度模型进行训练。
如图4所示，在自然驾驶的制动过程中，当制动主缸的压力斜率达到第一阈值的时刻(如图4中的t1时刻)之后经过一段时间(例如，图4中的Δt)后会达到最大斜率。
也就是说，可以将目标车辆的制动主缸的压力斜率达到第一阈值之后经过第一时间段之后的时刻视为目标车辆的制动主缸的压力斜率最大的时刻。
第一时间段可以预先设置的，例如第一时间段可以是预先通过自然驾驶测试数据的统计规律确定的。
第一阈值可以是根据目标车辆的速度确定的。第一阈值和目标车辆的速度之间具有映射关系，具体描述可以参见后文中的方法1000。
可选地，目标车辆的运动信息可以包括目标车辆的制动主缸的压力斜率达到第一阈值的时刻之后与该时刻距离第一时间段的时刻对应的运动信息。目标车辆的制动主缸的压力信息包括目标车辆的制动主缸的压力斜率达到第一阈值的时刻之后与该时刻距离第一时间段的时刻对应的制动主缸的压力信息。
也就是说，可以将目标车辆的制动主缸的压力斜率达到第一阈值的时刻之后与该时刻间隔第一时间段的时刻采集到的目标车辆的信息作为制动减速度模型的输入，通过制动减速度模型处理后得到第一制动减速度。
其中，该训练过程可以是离线(offline)完成的。预测过程可以是在线(online)完成的。即制动减速度模型可以是预先离线训练好的模型。
应理解，图4仅为一次制动过程中的相关参数的变化趋势的示例，图4中的制动主缸的压力斜率和制动减速度的数值对本申请实施例中的方案不构成限定。
需要说明的是，上述训练样本以及用于输入制动减速度模型的参数仅为示例，也可以将制动过程中采集到的其他时刻或时段的训练车辆的信息作为训练过程中制动减速度预测模型的输入，对制动减速度预测模型进行训练，将制动过程中采集到的其他时刻或时段的目标车辆的信息作为推理过程中制动减速度模型的输入，得到第一制动减速度。本申请实施例对输入制动减速度模型的参数的具体形式不做限定。
目标车辆可以在目标车辆的制动主缸的压力斜率达到第一阈值后经过第一时间段之后执行步骤S320，即对制动主缸执行主动增压。当方法300应用于EBA系统中时，目标车辆上的EBA系统在制动主缸的压力斜率达到第一阈值后经过第一时间段之后开始执行紧急制动辅助操作，即输出目标制动减速度以对制动主缸执行主动增压。
这样，通过主动增压前的信息预测第一制动减速度，能够反映驾驶员的真实制动意图，有利于提高驾驶员所请求的制动减速度的预测准确率。
本申请实施例中以神经网络模型作为制动减速度预测模型，基于自然驾驶过程中采集的数据训练制动减速度模型，通过训练好的制动减速度模型预测驾驶员所请求的制动减速度，神经网络模型强大的特征表达能力能够提高驾驶员所请求的制动减速度的预测准确率。
进一步地，步骤S310还包括获取目标车辆的环境感知信息。在该情况下，目标制动减速度是根据目标车辆的信息和目标车辆的环境感知信息预测得到的。
车辆的环境感知信息指的是与车辆周围的环境相关的信息。例如，目标车辆的环境感知信息包括以下至少一项：障碍物的速度、障碍物的加速度或障碍物与目标车辆之间的相对位置等。示例性地，障碍物可以包括他车或行人等。
示例性地，环境感知信息可以通过图1中的传感系统120获取。
如前所述，目标制动减速度可以是根据第一制动减速度确定的。第一制动减速度可以是通过制动减速度预测模型对目标车辆信息和目标车辆的环境感知信息进行处理得到的。
也就是说将目标车辆的运动信息、制动主缸的压力信息以及目标车辆的环境感知信息 作为制动减速度预测模型的输入，由制动减速度预测模型进行特征提取，并根据提取到的特征得到模型的输出。制动减速度模型的输出结果即为第一制动减速度。
目标车辆的环境感知信息的采集时刻和目标车辆的信息的采集时刻可以是相同的。
在该情况下，训练样本可以包括训练车辆的信息、训练车辆的环境感知信息以及训练样本的样本标签。
一个训练样本可以是根据自然驾驶训练车辆的过程中的一次制动过程中的数据确定的，也就是说，训练车辆的运动信息、训练车辆的制动主缸的压力信息以及训练车辆的环境感知信息均是该次制动过程中的数据。训练车辆的环境感知信息的采集时刻与训练车辆的信息的采集时刻可以是相同的。
基于训练样本得到制动减速度预测模型可以包括：以训练车辆的运动信息、训练车辆的制动主缸的压力信息和训练车辆的环境感知信息作为制动减速度预测模型的输入，以训练车辆的驾驶员所请求的制动减速度作为制动减速度预测模型的目标输出对该模型进行训练，得到训练好的制动减速度预测模型。
图5示出了一种制动减速度预测模型的训练及推理过程的示意图。如图5所示，基于自然驾驶数据训练制动减速度预测模型，该训练过程可以是离线完成的。其中，自然驾驶数据用于得到训练样本。训练样本包括训练车辆的运动信息、训练车辆的制动主缸的压力信息和训练车辆的环境感知信息以及训练样本的样本标签。将目标车辆的运动信息、制动主缸的压力信息以及目标车辆的环境感知信息输入至训练好的制动减速度预测模型中，得到第一制动减速度。该预测过程可以是在线完成的。
在紧急制动工况和非紧急制动工况中，即使车辆的运动信息和车辆的制动主缸的压力信息相同，驾驶员实际所请求的制动减速度也可能是不同的。本申请实施例中将训练车辆的环境感知信息用于模型的训练，使得模型能够基于实际的碰撞风险判断驾驶员是否需要紧急制动，提高预测模型的准确率。相应地，在推理过程中，将目标车辆的环境感知信息也作为模型的输入，使得制动结果更能满足驾驶员的主观意愿，提高用户体验以及安全性。当方法300应用于紧急制动辅助系统中时，有利于避免在非紧急制动工况中紧急制动功能被误触发。
可选地，目标制动减速度是根据第一制动减速度确定的，包括：目标制动减速度为第一制动减速度。
将第一制动减速度作为目标制动减速度，能够更好地体现驾驶员的制动意图。
可选地，目标制动减速度是根据第一制动减速度确定的，包括：目标制动减速度是据第二制动减速度确定的，第二制动减速度是通过目标增益系数对第一制动减速度进行处理得到的，目标增益系数与当前驾驶场景的危险等级之间具有映射关系。
或者说，目标增益系数是通过增益系数与驾驶场景的危险等级之间的映射关系确定的。
示例性地，目标增益系数是通过多个增益系数与多个驾驶场景的危险等级之间的映射关系以及当前驾驶场景的危险等级确定的。目标增益系数为多个增益系数中的一个。
也就是说，根据驾驶场景的危险等级与增益系数之间的映射关系可以确定当前驾驶场景的危险等级对应的增益系数，即目标增益系数，进而可以根据目标增益系数对第一制动减速度进行处理，得到第二制动减速度。
在一种实现方式中，危险等级越高，车辆发生碰撞的概率越小，相应的增益系数越小。在该情况下，危险等级也可以理解为安全等级。
在另一种实现方式中，危险等级越高，车辆发生碰撞的概率越大，相应的增益系数越大。为了便于描述和理解，后文中仅以该方式为例对方法300进行说明，不对本申请实施例的方案构成限定。
本申请实施例中根据当前驾驶场景的危险等级对应的增益系数对第一制动减速进行相应的处理，能够基于不同的危险等级实现分级制动，提高了车辆行驶的安全性。
对第一制动减速进行处理可以包括以下任一项：对第一制动减速度进行放大处理、对第一制动减速度进行缩小处理或将第一制动减速度作为第二制动减速度。
针对不同的增益系数，对第一制动减速度的处理的结果可以是不同的。在一种实现方式中，第二制动减速度是通过将第一制动减速度和目标增益系数相乘得到的。在该情况下，目标增益系数大于1，则对第一制动减速度进行处理实质上为对第一制动减速度进行放大处理，将放大后的第一制动减速度作为第二制动减速度；目标增益系数为1，则对第一制动减速度进行处理实质上为对第一制动减速度不进行处理，将第一制动减速度作为第二制动减速度；目标增益系数小于1，则对第一制动减速度进行处理实质上为对第一制动减速度进行缩小处理，将到缩小后的第一制动减速度作为第二制动减速度。
进一步地，该多个增益系数大于或等于1。也就是说目标增益系数大于或等于1。
在该情况下，对第一制动减速度的处理包括对第一制动减速度进行放大处理或将第一制动减速度作为第二制动减速度。
可选地，在危险等级大于或等于第一等级阈值的情况下，该危险等级对应的增益系数大于1。也就是说，在危险等级大于或等于第一等级阈值的情况下对第一制动减速度进行放大处理。
进一步地，在危险等级小于第一等级阈值的情况下，该危险等级对应的增益系数等于1。也就是说，在危险等级小于第一等级阈值的情况下，将第一制动减速度作为第二制动减速度。
例如，第一等级阈值可以为1。
在面对紧急制动工况时，由于经验不足、踩踏力不足或反映不迅速等，普通驾驶员所请求的制动减速度可能不足以实现避障。通过本申请实施例的方案，在危险等级较高的情况下，对第一制动减速度进行放大处理，有利于进一步提高驾驶的安全性。而在危险等级较低的情况下，直接将第一制动减速度作为第二制动减速度，更符合驾驶员的主观意愿，提高用户体验。
不同危险等级对应的增益系数可以是预先设定的。或者说，多个增益系数与多个危险等级之间的映射关系可以是预先设定的。
示例性地，不同危险等级对应的增益系数可以是根据专业驾驶员所请求的制动减速度确定的。
具体地，由专业驾驶员对不同的危险等级下的驾驶员所请求的制动减速度进行标定，得到不同危险等级下的增益系数。
例如，在自然驾驶的过程中，将一个危险等级的场景下专业驾驶员所请求的制动减速度除以普通驾驶员所请求的制动减速度，得到的结果作为该危险等级对应的增益系数。
相较于普通驾驶员，专业驾驶员对紧急制动工况的判断更准确，通过专业驾驶员标定的增益系数对普通驾驶员所请求的制动减速度进行增益处理，能够在尽量满足普通驾驶员的主观意愿的前提下，提高驾驶的安全性。
驾驶场景的危险等级是根据车辆的信息和车辆的环境感知信息确定的。
具体地，可以根据车辆的运动信息和车辆的环境感知信息计算危险判别指标，进而根据危险判别指标确定危险等级。
示例性地，将危险判断指标与标定的阈值进行比较，根据比较结果确定危险等级。
例如，危险判别指标可以包括以下至少一项：距离碰撞剩余时间(time to collision，TTC)、距离制动剩余时间(time to brake，TTB)或车间时距(time head way，THW)。
应理解，上述危险判别指标以及危险等级的划分方法仅为示意，危险判别指标以及危险等级的划分方法可以通过其他方式确定，本申请实施例对此不做限定。
图6中示出了本申请实施例提供的一种分级制动处理的示意性流程图。下面结合图6对步骤S320进行说明。图6中的方案可以视为步骤S320的一种具体实现方式。
示例性地，图6可以由图2中的分级制动模块230执行。
图6中的方案包括步骤S610至步骤S640。
S610，根据目标车辆的运动信息和环境感知信息计算危险判别指标。
例如，危险判别指标包括以下至少一项：TTC、TTB或THW。
S620，根据危险判别指标确定当前驾驶场景的危险等级。
示例性地，将危险判别指标与标定的阈值进行比较，根据比较结果确定当前驾驶场景的危险等级。
例如，驾驶场景的危险等级可以包括0,1,2,3等多个等级，当前驾驶场景的危险等级即为其中一个危险等级。
S630，根据危险等级与增益系数之间的映射关系确定当前驾驶场景的危险等级对应的目标增益系数。
例如，驾驶场景的危险等级包括0,1,2,3这四个等级，对应的增益系数分别为k0，k1，k2和k3。
S640，根据目标增益系数对第一制动减速度进行处理，得到第二制动减速度。
可选的，目标制动减速度是根据第二制动减速度确定的，包括：目标制动减速度为第二制动减速度。
第二制动减速度是通过专业驾驶员对第一制动减速度进行标定得到的，符合驾驶员的主观意愿，同时提高了驾驶的安全性。
进一步地，在发送目标制动减速度的指示信息之前，当前驾驶场景的危险等级大于或等于第二等级阈值。
或者可以理解为，当前驾驶场景的危险等级大于或等于第二等级阈值的条件为发送目标制动减速度的指示信息的触发条件之一。在当前驾驶场景的危险等级小于第二等级阈值的情况下，不执行步骤S320。
第二等级阈值与第一等级阈值可以相同，也可以不同。
例如，第二等级阈值为1，在当前驾驶场景的危险等级为0时，不执行步骤S320。
也就是说，在危险等级较低时，车辆可以不执行主动增压，而是通过驾驶员踏板制动 执行增压。
如前所示，本申请实施例的方案可以应用于EBA系统中，用于提供紧急制动辅助功能。当方法300应用于EBA系统中，在当前驾驶场景的危险等级小于第二等级阈值的情况下，可以不触发紧急制动辅助功能。这样，通过危险等级的识别碰撞风险，进一步避免了紧急制动辅助功能的误触发情况。
图7示出了不同危险等级下的车辆的制动减速度的变化情况。图7的方案中的目标制动减速度即为第二制动减速度。
如图7所示，在危险等级为0时，目标增益系数为1，不对第一制动减速度进行处理，EBA系统可以不提供紧急制动辅助功能，该曲线反映了普通驾驶员进行制动操作时的制动减速度变化情况。随着危险等级的增加，增益系数逐渐增大，第二制动减速度也随之增大，图7中危险等级为3时得到的第二制动减速度即为车辆能够输出的最大制动减速度。如图7所示，随着危险等级的增加，第二制动减速度也随之增大，在EBA系统的辅助下，能够更快建压，以使车辆能够尽快达到所需的制动减速度，或者说尽快达到第二制动减速度，实现更符合驾驶员主观意愿的分级辅助制动，保证在车辆在不同危险等级下的安全性。
然而专业驾驶员的标定结果不能完全避免发生碰撞。本申请实施例中通过安全制动减速度进一步提高驾驶的安全性。
可选地，目标制动减速度是根据第二制动减速度确定的，包括：目标制动减速度是根据第二制动减速度和安全制动减速度中的绝对值较大的一项确定的。
安全制动减速度用于表示目标车辆避免碰撞所需的制动减速度。
具体地，安全制动减速度是根据目标车辆的运动信息和目标车辆的环境感知信息确定的、避免发生碰撞所需的制动减速度。
将第二制动减速度和安全制动减速度进行比较仲裁，根据其中绝对值较大的一项确定目标制动减速度。
可选地，目标制动减速度是根据第二制动减速度和安全制动减速度中的绝对值较大的一项确定的，包括：目标制动减速度为第二制动减速度和安全制动减速度中的绝对值较大的一项。
可选地，目标制动减速度是第二制动减速度和安全制动减速度中绝对值较大的一项确定的，包括：目标制动减速度为绝对值较大的一项与制动减速度阈值之间的较小值。
示例性地，制动减速度阈值时由ABS确定的。
本申请实施例通过目标车辆的运动信息和目标车辆的环境感知信息确定安全制动减速度，并根据安全制动减速度和第二制动减速度中绝对值较大的一项确定目标制动减速度，能够在尽量满足驾驶员主观意愿的前提下，有效规避碰撞风险，进一步提高驾驶的安全性。
可选地，目标制动减速度是根据第一制动减速度确定的，包括目标制动减速度是根据第一制动减速度和安全制动减速中绝对值较大的一项确定的。
将第一制动减速度和安全制动减速度进行比较仲裁，根据其中绝对值较大的一项确定目标制动减速度。
也就是说，若方法300不包括对第一制动减速度进行处理，则可以根据第一制动减速度和安全制动减速度确定目标制动减速度。
可选地，目标制动减速度是根据第一制动减速度和安全绝对值较大的一项确定的，包括：目标制动减速度为第一制动减速度和安全制动减速度中绝对值较大的一项。
可选地，目标制动减速度是第一制动减速度和安全制动减速度中绝对值较大的一项确定的，包括：目标制动减速度为该绝对值较大的一项与制动减速度阈值之间的绝对值较小的一项。
示例性地，制动减速度阈值时由ABS确定的。
图8示出了本申请实施例提供的一种确定目标制动减速度的方法的示意性流程图。图8中的方案可以视为步骤S320的一种具体实现方式。
示例性地，图8可以由图2中的制动减速度决策模块240执行。
图8所示的方案包括步骤S710至步骤S730，下面对步骤S710至步骤S730进行说明。
S710，根据目标车辆的运动信息和环境感知信息确定安全制动减速度。
S720，在对第一制动减速度进行处理的情况下，确定安全制动减速度和第二制动减速度中绝对值较大的一项。
在对第一制动减速度没有进行处理的情况下，确定安全制动减速度和第一制动减速度中的较大值。
S730，确定步骤S720中绝对值较大的一项与ABS决定的制动减速度阈值中绝对值较小的一项。
将两者中绝对值较小的一项作为目标制动减速度。
目标制动减速度可以作为紧急制动辅助系统所需要的执行的制动减速度值，或者说紧急制动辅助系统输出的制动减速度值，通过主动增压以尽快达到该目标制动减速度。
本申请实施例的方案可以应用于EBA系统中，用于提供紧急制动辅助功能。图9示出了不同场景下的制动减速度的变化情况。图9的(a)示出了第二制动减速度大于安全制动减速度的情况下不同场景的制动减速度的变化情况，图9的(b)示出了第二制动减速度小于安全制动减速度的情况下不同场景的制动减速度的变化情况。
如图9所示，普通驾驶员在紧急制动工况中，由于存在判断不准确等问题，驾驶员所请求的制动减速度(即第一制动减速度)难以实现安全避障。
如图9的(a)所示，专业驾驶员在该紧急工况中所请求的制动减速度大于安全制动减速度，能够实现安全避障。同时，专业驾驶员通常反应速度等方面优于普通驾驶员，如图9所示，相较于普通驾驶员，专业驾驶员对应的制动减速度的曲线的上升速率明显更高，也就是说，专业驾驶员驾驶车辆的情况下能够更快达到所需的制动减速度。本申请实施例中的第二制动减速度可以是由专业驾驶员对第一制动减速度进行标定得到的，图9中专业驾驶员所请求的制动减速度也可以理解为本申请实施例中的第二制动减速度。在第二制动减速度大于安全制动减速度的情况下，EBA系统将第二制动减速度作为目标制动减速度。EBA系统基于目标制动减速度提供紧急制动辅助功能，如图9的(a)所示，EBA系统所对应的制动减速度的曲线的上升速率高于专业驾驶员对应的制动减速度的曲线，也就是说，在目标制动减速度相同的情况下，EBA系统能够提供紧急制动辅助功能以实现主动建压，使车辆更快达到目标制动减速度，提高了驾驶的安全性。
如图9的(b)所示，如图9的(b)所示，专业驾驶员在该紧急工况中所请求的制动减速度小于安全制动减速度，无法实现安全避障。本申请实施例中的第二制动减速度可以 是由专业驾驶员对第一制动减速度进行标定得到的，图9中专业驾驶员所请求的制动减速度也可以理解为本申请实施例中的第二制动减速度。在第二制动减速度小于安全制动减速度的情况下，EBA系统将安全制动减速度作为目标制动减速度。EBA系统基于目标制动减速度提供紧急制动辅助功能以实现主动建压，使车辆更快达到目标制动减速度，提高了驾驶的安全性。
此外，从图9中可以看出，其他紧急制动辅助系统在紧急制动工况的情况下，直接输出ABS系统的阈值，即最大制动减速度，不考虑驾驶员的主观意愿以及安全制动减速度，影响用户体验，甚至存在安全隐患。
如前所述，方法300可以应用于紧急制动工况中。示例性地，在紧急制动工况的情况下，执行步骤S320，即发送目标制动减速度的指示信息。
本申请实施例中紧急制动工况的识别过程也可以理解为驾驶员紧急制动意图的识别过程。
若方法300应用于EBA系统中，在将当前场景认定为紧急制动工况或者说识别出驾驶员的紧急制动意图之后，可以触发紧急制动辅助功能，即发送目标制动减速度的指示信息，指示目标车辆对制动主缸执行主动增压。
可选地，在发送目标制动减速度的指示信息之前，目标车辆的制动主缸的压力信息满足以下至少一个条件：目标车辆的制动主缸的压力斜率大于或等于第一阈值或者目标车辆的制动主缸的压力大于或等于第二阈值，第一阈值是根据目标车辆的速度确定的。第二阈值时根据目标车辆的速度确定的。
第一阈值和第二阈值的具体描述详见后文中的方法1000。
也就是说EBA系统可以根据目标车辆的速度和目标车辆的制动主缸的压力信息识别驾驶员的紧急制动意图。示例性地，在目标车辆的制动主缸的压力信息满足上述至少一项时，认定驾驶员具有紧急制动意图，触发紧急制动辅助功能。
现有的紧急制动辅助系统通常利用踏板信号或车速等信息与设定的阈值进行比较，根据比较结果判断当前场景是否为紧急制动工况，在识别出紧急制动工况后，提供紧急制动辅助功能。然而，上述判别方式的准确性较低，导致紧急制动辅助功能的误触发率较高，可能为驾驶员提供不必要的制动减速度，降低了用户体验，同时存在安全隐患。
本申请实施例中的阈值不是一个固定值，而是根据目标车辆的速度确定的，通过制动主缸的压力信息与根据车速确定的阈值比较来判断驾驶员是否具有紧急制动意图，这样能够提高驾驶员紧急制动意图的准确性。
本申请实施例提供了一种驾驶员紧急制动意图的识别方法900。该方法可以由图2中的紧急制动意图识别模块210执行。驾驶员具有紧急制动意图可以作为步骤S320的触发条件之一。也就是说，驾驶员紧急制动意图的识别方法的结果可以用于触发步骤S320。
驾驶员紧急制动意图的识别方法包括步骤S910至步骤S920，下面对该方法进行说明。
S910，获取目标车辆的信息。
目标车辆的信息包括目标车辆的运动信息和目标车辆的制动主缸的压力信息。
目标车辆的运动信息包括目标车辆的速度。目标车辆的制动主缸的压力信息包括以下至少一项：目标车辆的制动主缸的压力斜率或目标车辆的制动主缸的压力。
示例性地，目标车辆的制动主缸的压力信息可以是周期性获取的。例如，每个周期获 取制动主缸的压力，根据周期内目标车辆的缸压变化值即可确定目标车辆的制动主缸的压力斜率。
应理解，以上仅为示意，目标车辆的制动主缸的压力信息也可以按照其他频率获取，本申请实施例对此不做限定。
S920，在目标车辆的制动主缸的压力信息满足以下至少一个条件时，判定驾驶员具有紧急制动意图：目标车辆的制动主缸的压力斜率大于或等于第一阈值，或者，目标车辆的制动主缸的压力大于或等于第二阈值。
其中，第一阈值是根据目标车辆的速度确定的。第二阈值是根据目标车辆的速度确定的。
上述判别结果可以作为前述步骤S320的触发条件之一，或者说，作为紧急制动辅助功能的触发条件之一。也就是说，在目标车辆的制动主缸的压力信息满足步骤S302中的条件时，判断驾驶员具有紧急制动意图。在发送目标制动减速度的指示信息之前，驾驶员具有紧急制动意图。
示例性地，在发送目标制动减速度的指示信息之前，目标车辆的制动主缸的压力信息满足以下条件：目标车辆的制动主缸的压力斜率大于或等于第一阈值。
即在目标车辆的制动主缸的压力斜率大于或等于第一阈值的情况下，有可能触发发送目标制动减速度的指示信息。在目标车辆的制动主缸的压力斜率小于第一阈值的情况下，不执行步骤S320。
可替换地，在发送目标制动减速度的指示信息之前，目标车辆的制动主缸的压力信息满足以下条件：目标车辆的制动主缸的压力大于或等于第二阈值。
即在目标车辆的制动主缸的压力大于或等于第二阈值的情况下，有可能触发发送目标制动减速度的指示信息。在目标车辆的制动主缸的压力小于第二阈值的情况下，不执行步骤S320。
可替换地，在发送目标制动减速度的指示信息之前，目标车辆的制动主缸的压力信息满足以下条件：目标车辆的制动主缸的压力斜率大于或等于第一阈值，且目标车辆的制动主缸的压力大于或等于第二阈值。
即在目标车辆的制动主缸的压力斜率大于或等于第一阈值，且目标车辆的制动主缸的压力大于或等于第二阈值的情况下，有可能触发发送目标制动减速度的指示信息。在目标车辆的制动主缸的压力斜率小于第一阈值或者目标车辆的制动主缸的压力小于第二阈值的情况下，不执行步骤S320。
进一步地，紧急制动意图的识别结果可以和前述危险等级的判别结果结合，作为步骤S320的触发条件，或者说，作为紧急制动辅助功能的触发条件。
可选地，在发送目标制动减速度的指示信息之前，满足以下至少一个条件：当前驾驶场景的危险等级大于或等于第二等级阈值，或者，驾驶员具有紧急制动意图。
示例性地，在当前驾驶场景的危险等级大于或等于第二等级阈值或者驾驶员具有紧急制动意图的情况下，发送目标制动减速度的指示信息。
这样可以进一步提高驾驶的安全性，避免驾驶员判断失误导致的碰撞风险。
可替换地，在当前驾驶场景的危险等级大于或等于第二等级阈值，且驾驶员具有紧急制动意图的情况下，发送目标制动减速度的指示信息。
例如，步骤S320可以包括：在当前驾驶场景的危险等级大于或等于第二等级阈值，且目标车辆的制动主缸的压力斜率大于或等于第一阈值的情况下，发送目标制动减速度的指示信息。
在当前驾驶场景的危险等级小于第二等级阈值，或目标车辆的制动主缸的压力斜率小于第一阈值的情况下，不执行步骤S320。
这样可以进一步提高紧急制动辅助功能触发的准确性，避免发生误触发的情况，提高用户体验。
如前所述，第一阈值是根据目标车辆的速度确定的。
第一阈值与车辆的速度之间具有映射关系。示例性地，该映射关系可以反映为函数表达式，即第一阈值可以表示为车辆的速度的函数。
图10中示出了一种第一阈值与车辆的速度之间的映射关系的确定方法1000。方法1000包括步骤S1010至步骤S1020，下面对步骤S1010至步骤S1020进行说明。
S1010，获取多组制动数据中每组制动数据中最大的制动主缸的压力斜率。
该多组制动数据为自然驾驶过程中采集的制动数据。从该多组中制动数据中分别提取每组制动数据中的最大的制动主缸的压力斜率，即每次制动过程中最大的制动主缸的压力斜率。
S1020，根据该多组制动数据中的紧急制动工况和非紧急制动工况下的最大的制动主缸的压力斜率的分布情况，拟合第一阈值与车辆的速度之间的关系。
该多组制动数据包括紧急制动工况下采集得到的制动数据和非紧急制动工况下采集到的制动数据。示例性地，可以由专业驾驶员判断一组制动数据属于紧急制动工况下采集到的制动数据或非紧急制动工况下采集到的制动数据。
第一阈值与车辆的速度之间的关系可以表示为：p_thr'＝g(v)。
其中，v表示车辆的速度，p_thr'表示第一阈值，g()表示函数。
图11示出了在车辆处于相同速度的情况下，紧急制动工况和非紧急制动工况下的最大的制动主缸的压力斜率的分布情况。图11中的直线即为该速度对应的第一阈值。如图11所示，在该速度下，紧急制动工况下的制动主缸的压力斜率均处于图11中的上方，非紧急制动工况下的制动主缸的压力斜率均处于图11中的下方，由此通过拟合得到阈值，将紧急制动工况和非紧急制动工况下的制动主缸的压力斜率区分开，该阈值即为该速度对应的第一阈值。
如前所述，第二阈值是根据目标车辆的速度确定的。
第二阈值与车辆的速度之间具有映射关系。示例性地，该映射关系可以反映为函数表达式，即第二阈值可以表示为车辆的速度的函数。
示例性的，第二阈值与车辆的速度之间的映射关系的确定方法可以参考图10中的方法。具体地，可以通过以下步骤确定第二阈值与车辆的速度之间的映射关系。
S1，获取多组制动数据中每组制动数据中最大的制动主缸的压力。
该多组制动数据为自然驾驶过程中采集的制动数据。从该多组中制动数据中分别提取每组制动数据中的最大的制动主缸的压力，即每次制动过程中最大的制动主缸的压力。
S2，根据该多组制动数据中的紧急制动工况和非紧急制动工况下的最大的制动主缸压力的分布情况，拟合第二阈值与车辆的速度之间的关系。
该多组制动数据包括紧急制动工况下采集得到的制动数据和非紧急制动工况下采集到的制动数据。示例性地，可以由专业驾驶员判断一组制动数据属于紧急制动工况下采集到的制动数据或非紧急制动工况下采集到的制动数据。
具体的拟合方式可以参照图11中的方式，此处不再赘述。
图12示出了本申请实施例提供的一种驾驶员制动意图识别方法1100，图12中的方法1100可以视为方法900的一种具体实现方式，具体描述可以参见前述方法900。
示例性地，图12可以由图2中的紧急制动意图识别模块210执行。
方法1100包括步骤S1110至步骤S1140，下面对步骤S1110至步骤S1140进行说明。
S1110，获取目标车辆的制动主缸的压力。
示例性地，周期性地获取制动主缸的压力。
S1120，计算制动主缸的压力斜率。
S1130，获取目标车辆的速度。
S1140，根据目标车辆的速度计算第一阈值和第二阈值。
S1150，判断目标车辆的制动主缸的压力斜率是否大于或等于第一阈值以及目标车辆的制动主缸的压力是否大于或等于第二阈值。
在目标车辆的制动主缸的压力斜率大于或等于第一阈值，且目标车辆的制动主缸的压力大于或等于第二阈值的情况下，将当前场景作为紧急制动工况；否则，当前场景作为非紧急制动工况。
应理解，方法1100中的步骤仅为示例，不对本申请实施例构成限定。例如，步骤S1140也可以为根据目标车辆的速度计算第一阈值。相应地，步骤S1150也可为，判断目标车辆的制动主缸的压力斜率是否大于或等于第一阈值。在目标车辆的制动主缸的压力斜率大于或等于第一阈值的情况下，将当前场景作为紧急制动工况；在目标车辆的制动主缸的压力斜率小于第一阈值的情况下，将当前场景作为非紧急工况。再如，方法1100可以不包括S1120，相应地，步骤S1140可以为根据目标车辆的速度计算第二阈值。步骤S1150也可为，判断目标车辆的制动主缸的压力是否大于或等于第二阈值。在目标车辆的制动主缸的压力大于或等于第二阈值的情况下，将当前场景作为紧急制动工况；在目标车辆的制动主缸的压力小于第二阈值的情况下，将当前场景作为非紧急工况。
在本申请实施例中，通过制动主缸的压力信息与根据目标车辆的速度确定的阈值比较来判断驾驶员是否具有紧急制动意图，这样能够提高驾驶员紧急制动意图的准确性。
下面结合图13至图14对本申请实施例的装置进行说明。应理解，下面描述的装置能够执行前述本申请实施例的方法，为了避免不必要的重复，下面在介绍本申请实施例的装置时适当省略重复的描述。
图13是本申请实施例的车辆控制装置的示意图。该装置2000包括获取单元2001和发送单元2002。该装置2000可以用于执行本申请实施例的车辆控制方法的各步骤。例如，获取单元2001可以用于执行图3所示方法中的步骤S310，发送单元2002可以用于执行图3所示方法中的步骤S320。
具体地，获取单元2001，用于获取目标车辆的信息，目标车辆的信息包括所述目标车辆的运动信息和所述目标车辆的制动主缸的压力信息。发送单元2002，用于发送目标制动减速度的指示信息，目标制动减速度的指示信息用于指示目标车辆对制动主缸执行制 动增压，目标制动减速度是根据目标车辆的信息预测得到的。
可选地，作为一个实施例，目标制动减速度是根据第一制动减速度确定的，第一制动减速度是通过制动减速度预测模型对目标车辆的信息进行处理得到的。
可选地，作为一个实施例，制动减速度预测模型是基于至少一个训练样本训练得到的，训练样本包括训练车辆的信息以及训练样本的样本标签，训练车辆的信息包括训练车辆的运动信息和训练车辆的制动主缸的压力信息，训练样本的样本标签用于指示训练车辆的驾驶员所请求的制动减速度。
可选地，作为一个实施例，目标车辆的制动主缸的压力信息包括目标车辆的制动主缸的压力斜率，在发送目标制动减速度的指示信息之前，目标车辆的制动主缸的压力斜率大于或等于第一阈值。
可选地，作为一个实施例，目标车辆的运动信息包括目标车辆的速度，第一阈值是根据目标车辆的速度确定的。
可选地，作为一个实施例，目标制动减速度是根据第二制动减速度确定的，第二制动减速度是通过目标增益系数对第一制动减速度进行处理得到的，目标增益系数与当前驾驶场景的危险等级之间具有映射关系。
可选地，作为一个实施例，目标制动减速度是根据第二制动减速度和安全制动减速度中绝对值较大一项确定的，安全制动减速度用于表示目标车辆避免碰撞所需的制动减速度。
图14是本申请实施例的控制装置的示意图。该装置3000可以包括至少一个处理器3002和通信接口3003。
可选地，该装置3000还可以包括存储器3001和总线3004中的至少一项。其中，存储器3001、处理器3002和通信接口3003中的任意两项之间或全部三项之间均可以通过总线3004实现彼此之间的通信连接。
可选地，存储器3001可以是只读存储器(read only memory，ROM)，静态存储设备，动态存储设备或者随机存取存储器(random access memory，RAM)。存储器3001可以存储程序，当存储器3001中存储的程序被处理器3002执行时，处理器3002和通信接口3003用于执行本申请实施例的车辆的控制方法的各个步骤。也就是说，处理器3002可以通过通信接口3003从存储器3001获取存储的指令，以执行本申请实施例的车辆控制方法的各个步骤。
可选地，存储器3001可以具有图1所示存储器152的功能，以实现上述存储程序的功能。可选地，处理器3002可以采用通用的CPU，微处理器，ASIC，图形处理器(graphic processing unit，GPU)或者一个或多个集成电路，用于执行相关程序，以实现本申请实施例的控制装置中的单元所需执行的功能，或者执行本申请实施例的控制方法的各个步骤。
可选地，处理器3002可以具有图1所示处理器151的功能，以实现上述执行相关程序的功能。
可选地，处理器3002还可以是一种集成电路芯片，具有信号的处理能力。在实现过程中，本申请实施例的控制方法的各个步骤可以通过处理器中的硬件的集成逻辑电路或者软件形式的指令完成。
可选地，上述处理器3002还可以是通用处理器、数字信号处理器(digital signal  processing，DSP)、专用集成电路(ASIC)、现成可编程门阵列(field programmable gate array，FPGA)或者其他可编程逻辑器件、分立门或者晶体管逻辑器件、分立硬件组件。可以实现或者执行本申请实施例中的公开的各方法、步骤及逻辑框图。通用处理器可以是微处理器或者该处理器也可以是任何常规的处理器等。结合本申请实施例所公开的方法的步骤可以直接体现为硬件译码处理器执行完成，或者用译码处理器中的硬件及软件模块组合执行完成。软件模块可以位于随机存储器，闪存、只读存储器，可编程只读存储器或者电可擦写可编程存储器、寄存器等本领域成熟的存储介质中。该存储介质位于存储器，处理器读取存储器中的信息，结合其硬件完成本申请实施例的车辆的控制装置中包括的单元所需执行的功能，或者执行本申请实施例的车辆控制方法的各个步骤。
可选地，通信接口3003可以使用例如但不限于收发器一类的收发装置，来实现装置与其他设备或通信网络之间的通信。该通信接口3003例如还可以是接口电路。
总线3004可包括在装置各个部件(例如，存储器、处理器、通信接口)之间传送信息的通路。
本申请实施例还提供一种包含指令的计算机程序产品，该指令被计算机执行时使得该计算机实现上述方法实施例中的方法。
本申请实施例还提供一种终端，该终端包括上述任意一种控制装置，例如图13或图14所示控制装置等。
示例性地，该终端可以为车辆。或者，该终端还可以是对车辆进行远程控制的终端。
上述控制装置既可以是安装在目标车辆上的，又可以是独立于目标车辆的，例如可以是利用无人机、其他车辆、机器人等来控制该目标车辆。
除非另有定义，本申请所使用的所有的技术和科学术语与属于本申请的技术领域的技术人员通常理解的含义相同。本申请中在本申请的说明书中所使用的术语只是为了描述具体的实施例的目的，不是旨在于限制本申请。
本申请的各个方面或特征可以实现成方法、装置或使用标准编程和/或工程技术的制品。本申请中使用的术语“制品”可以涵盖可从任何计算机可读器件、载体或介质访问的计算机程序。例如，计算机可读介质可以包括但不限于：磁存储器件(例如，硬盘、软盘或磁带等)，光盘(例如，压缩盘(compact disc，CD)、数字通用盘(digital versatile disc，DVD)等)，智能卡和闪存器件(例如，可擦写可编程只读存储器(erasable programmable read-only memory，EPROM)、卡、棒或钥匙驱动器等)。
本申请描述的各种存储介质可代表用于存储信息的一个或多个设备和/或其它机器可读介质。术语“机器可读介质”可以包括但不限于：无线信道和能够存储、包含和/或承载指令和/或数据的各种其它介质。
需要说明的是，当处理器为通用处理器、DSP、ASIC、FPGA或者其他可编程逻辑器件、分立门或者晶体管逻辑器件、分立硬件组件时，存储器(存储模块)可以集成在处理器中。
还需要说明的是，本申请描述的存储器旨在包括但不限于这些和任意其它适合类型的存储器。
本领域普通技术人员可以意识到，结合本申请中所公开的实施例描述的各示例的单元及步骤，能够以电子硬件、或者计算机软件和电子硬件的结合来实现。这些功能究竟以硬 件还是软件方式来执行，取决于技术方案的特定应用和设计约束条件。专业技术人员可以对每个特定的应用来使用不同方法来实现所描述的功能，但是这种实现不应认为超出本申请的保护范围。
所属领域的技术人员可以清楚地了解到，为描述的方便和简洁，上述描述的装置和单元的具体工作过程，可以参考前述方法实施例中的对应过程，在此不再赘述。
在本申请所提供的几个实施例中，应该理解到，所揭露的装置和方法，可以通过其它的方式实现。例如，以上所描述的装置实施例仅仅是示意性的，例如，所述单元的划分，仅仅为一种逻辑功能划分，实际实现时可以有另外的划分方式，例如多个单元或组件可以结合或者可以集成到另一个系统，或一些特征可以忽略，或不执行。此外，所显示或讨论的相互之间的耦合或直接耦合或通信连接可以是通过一些接口，装置或单元的间接耦合或通信连接，可以是电性，机械或其它的形式。
所述作为分离部件说明的单元可以是或者也可以不是物理上分开的，作为单元显示的部件可以是或者也可以不是物理单元，即可以位于一个地方，或者也可以分布到多个网络单元上。可以根据实际的需要选择其中的部分或者全部单元来实现本实施例方案的目的。
另外，在本申请各个实施例中的各功能单元可以集成在一个单元中，也可以是各个单元单独物理存在，也可以两个或两个以上单元集成在一个单元中。
所述功能如果以软件功能单元的形式实现并作为独立的产品销售或使用时，可以存储在一个计算机可读取存储介质中。基于这样的理解，本申请的技术方案本质上，或者说对现有技术做出贡献的部分，或者该技术方案的部分，可以以计算机软件产品的形式体现出来，该计算机软件产品存储在一个存储介质中，该计算机软件产品包括若干指令，该指令用以使得一台计算机设备(可以是个人计算机，服务器，或者网络设备等)执行本申请各个实施例所述方法的全部或部分步骤。前述的存储介质可以包括但不限于：U盘、移动硬盘、ROM、RAM、磁碟或者光盘等各种可以存储程序代码的介质。
以上所述，仅为本申请的具体实施方式，但本申请的保护范围并不局限于此，任何熟悉本技术领域的技术人员在本申请揭露的技术范围内，可轻易想到变化或替换，都应涵盖在本申请的保护范围之内。因此，本申请的保护范围应以所述权利要求的保护范围为准。

Claims (19)

  1. 一种车辆控制方法，其特征在于，包括：
    获取目标车辆的信息，所述目标车辆的信息包括所述目标车辆的运动信息和所述目标车辆的制动主缸的压力信息；
    发送目标制动减速度的指示信息，所述目标制动减速度的指示信息用于指示所述目标车辆对制动主缸执行制动增压，所述目标制动减速度是根据所述目标车辆的信息预测得到的。
  2. 根据权利要求1所述的方法，其特征在于，所述目标制动减速度是根据第一制动减速度确定的，所述第一制动减速度是通过制动减速度预测模型对所述目标车辆的信息进行处理得到的。
  3. 根据权利要求2所述的方法，其特征在于，所述制动减速度预测模型是基于至少一个训练样本训练得到的，所述训练样本包括训练车辆的信息以及所述训练样本的样本标签，所述训练车辆的信息包括所述训练车辆的运动信息和所述训练车辆的制动主缸的压力信息，所述训练样本的样本标签用于指示所述训练车辆的驾驶员所请求的制动减速度。
  4. 根据权利要求1至3中任一项所述的方法，其特征在于，所述方法还包括：
    获取所述目标车辆的环境感知信息；
    其中，所述目标制动减速度是根据所述目标车辆的信息和所述目标车辆的环境感知信息预测得到的。
  5. 根据权利要求1至4中任一项所述的方法，其特征在于，所述目标车辆的制动主缸的压力信息包括所述目标车辆的制动主缸的压力斜率，在发送目标制动减速度的指示信息之前，所述目标车辆的制动主缸的压力斜率大于或等于第一阈值。
  6. 根据权利要求5所述的方法，其特征在于，所述目标车辆的运动信息包括所述目标车辆的速度，所述第一阈值是根据所述目标车辆的速度确定的。
  7. 根据权利要求2至6中任一项所述的方法，其特征在于，所述目标制动减速度是根据第二制动减速度确定的，所述第二制动减速度是通过目标增益系数对所述第一制动减速度进行处理得到的，所述目标增益系数与当前驾驶场景的危险等级之间具有映射关系。
  8. 根据权利要求7所述的方法，其特征在于，所述目标制动减速度是根据所述第二制动减速度和安全制动减速度中绝对值较大一项确定的，所述安全制动减速度用于表示所述目标车辆避免碰撞所需的制动减速度。
  9. 一种车辆控制装置，其特征在于，包括：
    获取单元，用于获取目标车辆的信息，所述目标车辆的信息包括所述目标车辆的运动信息和所述目标车辆的制动主缸的压力信息；
    发送单元，用于发送目标制动减速度的指示信息，所述目标制动减速度的指示信息用于指示所述目标车辆对制动主缸执行制动增压，所述目标制动减速度是根据所述目标车辆的信息预测得到的。
  10. 根据权利要求9所述的装置，其特征在于，所述目标制动减速度是根据第一制动减速度确定的，所述第一制动减速度是通过制动减速度预测模型对所述目标车辆的信息进 行处理得到的。
  11. 根据权利要求10所述的装置，其特征在于，所述制动减速度预测模型是基于至少一个训练样本训练得到的，所述训练样本包括训练车辆的信息以及所述训练样本的样本标签，所述训练车辆的信息包括所述训练车辆的运动信息和所述训练车辆的制动主缸的压力信息，所述训练样本的样本标签用于指示所述训练车辆的驾驶员所请求的制动减速度。
  12. 根据权利要求9至11中任一项所述的装置，其特征在于，所述目标车辆的制动主缸的压力信息包括所述目标车辆的制动主缸的压力斜率，在发送所述目标制动减速度的指示信息之前，所述目标车辆的制动主缸的压力斜率大于或等于第一阈值。
  13. 根据权利要求12所述的装置，其特征在于，所述目标车辆的运动信息包括所述目标车辆的速度，所述第一阈值是根据所述目标车辆的速度确定的。
  14. 根据权利要求10至13中任一项所述的装置，其特征在于，所述目标制动减速度是根据第二制动减速度确定的，所述第二制动减速度是通过目标增益系数对所述第一制动减速度进行处理得到的，所述目标增益系数与当前驾驶场景的危险等级之间具有映射关系。
  15. 根据权利要求14所述的装置，其特征在于，所述目标制动减速度是根据所述第二制动减速度和安全制动减速度中绝对值较大一项确定的，所述安全制动减速度用于表示所述目标车辆避免碰撞所需的制动减速度。
  16. 一种芯片，其特征在于，所述芯片包括至少一个处理器与接口电路，所述至少一个处理器通过所述接口电路获取存储器上存储的指令，以执行如权利要求1至8中任一项所述的方法。
  17. 一种计算机可读存储介质，其特征在于，所述计算机可读介质存储用于设备执行的程序代码，该程序代码包括用于执行如权利要求1至8中任一项所述的方法的指令。
  18. 一种终端，其特征在于，所述终端包括如权利要求9至15中任一项所述装置。
  19. 根据权利要求18所述的终端，其特征在于，所述终端还包括制动主缸。
PCT/CN2021/081106 2021-03-16 2021-03-16 车辆控制方法及装置 WO2022193137A1 (zh)

Priority Applications (2)

Application Number Priority Date Filing Date Title
PCT/CN2021/081106 WO2022193137A1 (zh) 2021-03-16 2021-03-16 车辆控制方法及装置
CN202180000616.7A CN113165615A (zh) 2021-03-16 2021-03-16 车辆控制方法及装置

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
PCT/CN2021/081106 WO2022193137A1 (zh) 2021-03-16 2021-03-16 车辆控制方法及装置

Publications (1)

Publication Number Publication Date
WO2022193137A1 true WO2022193137A1 (zh) 2022-09-22

Family

ID=76876017

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2021/081106 WO2022193137A1 (zh) 2021-03-16 2021-03-16 车辆控制方法及装置

Country Status (2)

Country Link
CN (1) CN113165615A (zh)
WO (1) WO2022193137A1 (zh)

Families Citing this family (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2022193137A1 (zh) * 2021-03-16 2022-09-22 华为技术有限公司 车辆控制方法及装置
CN115359440B (zh) * 2022-08-26 2024-01-12 武汉铁路职业技术学院 一种基于物联网的铁路机车智能安全运行及系统
WO2024047601A1 (en) * 2022-09-01 2024-03-07 Faiveley Transport Italia S.P.A. Method for predicting an expected deceleration of at least one vehicle, and corresponding system

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110329249A (zh) * 2019-07-02 2019-10-15 武汉理工大学 一种循环神经网络的汽车前向碰撞预警控制系统及方法
US20200079348A1 (en) * 2018-09-11 2020-03-12 Hyundai Motor Company Method for controlling deceleration of vehicle using front driving environment information
CN112298173A (zh) * 2020-11-06 2021-02-02 吉林大学 一种面向智能驾驶的车辆安全行驶控制系统及控制方法
CN112356789A (zh) * 2020-11-13 2021-02-12 上汽通用五菱汽车股份有限公司 制动减速度的自适应标定方法、车辆及可读存储介质
CN113165615A (zh) * 2021-03-16 2021-07-23 华为技术有限公司 车辆控制方法及装置

Family Cites Families (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP5796547B2 (ja) * 2012-06-13 2015-10-21 株式会社アドヴィックス 車両の走行支援装置
JP2014024409A (ja) * 2012-07-25 2014-02-06 Denso Corp 車両用ブレーキ制御装置
CN109591811B (zh) * 2017-09-28 2020-08-14 华为技术有限公司 车辆制动方法、装置及存储介质
CN109801511B (zh) * 2017-11-16 2021-01-05 华为技术有限公司 一种碰撞预警方法及装置
CN109017729A (zh) * 2018-07-31 2018-12-18 南京越博动力系统股份有限公司 一种车辆制动辅助系统及其控制方法
CN111114540B (zh) * 2018-10-30 2021-06-18 长城汽车股份有限公司 车辆及其安全驾驶方法、装置
CN109927720B (zh) * 2019-03-25 2021-01-19 浙江吉利汽车研究院有限公司 一种动态制动辅助控制方法、装置及系统

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20200079348A1 (en) * 2018-09-11 2020-03-12 Hyundai Motor Company Method for controlling deceleration of vehicle using front driving environment information
CN110329249A (zh) * 2019-07-02 2019-10-15 武汉理工大学 一种循环神经网络的汽车前向碰撞预警控制系统及方法
CN112298173A (zh) * 2020-11-06 2021-02-02 吉林大学 一种面向智能驾驶的车辆安全行驶控制系统及控制方法
CN112356789A (zh) * 2020-11-13 2021-02-12 上汽通用五菱汽车股份有限公司 制动减速度的自适应标定方法、车辆及可读存储介质
CN113165615A (zh) * 2021-03-16 2021-07-23 华为技术有限公司 车辆控制方法及装置

Also Published As

Publication number Publication date
CN113165615A (zh) 2021-07-23

Similar Documents

Publication Publication Date Title
WO2022193137A1 (zh) 车辆控制方法及装置
JP6962316B2 (ja) 情報処理装置、情報処理方法、プログラム、およびシステム
US11756353B2 (en) Downloading system memory data in response to event detection
US20190308620A1 (en) Feature-based prediction
CN108099918B (zh) 用于确定自主车辆的命令延迟的方法
US9454150B2 (en) Interactive automated driving system
CN110550029A (zh) 障碍物避让方法及装置
US9499141B1 (en) Sensor-triggering of friction and regenerative braking
US11254311B2 (en) Lateral adaptive cruise control
WO2019006743A1 (zh) 一种用于控制车辆行驶的方法与设备
WO2019030219A1 (en) METHOD AND SYSTEM FOR DRIVING A VEHICLE
CN112638738B (zh) 车辆测速装置的故障诊断方法和故障诊断装置
CN113022578B (zh) 基于车辆运动信息乘客提醒方法、系统、车辆及存储介质
WO2021121247A1 (zh) 一种确定目标对象跟踪门限的方法、装置
US20230222914A1 (en) Vehicle reminding method and system, and related device
CN111047047A (zh) 驾驶模型的训练方法和装置、电子设备、计算机存储介质
CN112977376A (zh) 车辆制动控制方法、装置、设备和存储介质
US20220258727A1 (en) Automated valet parking system, control method of automated valet parking system, and autonomous driving vehicle
JP6816379B2 (ja) 衝突回避システム、情報処理装置、衝突回避プログラム及び情報処理プログラム
CN113335311B (zh) 一种车辆碰撞检测方法、装置、车辆及存储介质
WO2022126349A1 (zh) 控制方法和控制装置
JP2024032849A (ja) 情報処理装置、情報処理システム、情報処理方法及びプログラム
CN115782911A (zh) 行车场景中对方向盘脱手事件的数据处理方法及相关装置
US11878705B2 (en) Method and apparatus for generating test case for dynamic verification of autonomous driving system
Lavanya et al. An adaptive throttle and brake control system for automatic cruise control in disability support vehicle

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 21930733

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 21930733

Country of ref document: EP

Kind code of ref document: A1