WO2022188716A1 - 车辆控制方法、装置、设备及计算机存储介质 - Google Patents

车辆控制方法、装置、设备及计算机存储介质 Download PDF

Info

Publication number
WO2022188716A1
WO2022188716A1 PCT/CN2022/079377 CN2022079377W WO2022188716A1 WO 2022188716 A1 WO2022188716 A1 WO 2022188716A1 CN 2022079377 W CN2022079377 W CN 2022079377W WO 2022188716 A1 WO2022188716 A1 WO 2022188716A1
Authority
WO
WIPO (PCT)
Prior art keywords
acceleration
speed
target
accelerator
current
Prior art date
Application number
PCT/CN2022/079377
Other languages
English (en)
French (fr)
Inventor
许浩
黄河赞
Original Assignee
长沙智能驾驶研究院有限公司
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 长沙智能驾驶研究院有限公司 filed Critical 长沙智能驾驶研究院有限公司
Publication of WO2022188716A1 publication Critical patent/WO2022188716A1/zh

Links

Images

Classifications

    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
    • B60W60/00—Drive control systems specially adapted for autonomous road vehicles
    • B60W60/001—Planning or execution of driving tasks
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
    • B60W10/00—Conjoint control of vehicle sub-units of different type or different function
    • B60W10/04—Conjoint control of vehicle sub-units of different type or different function including control of propulsion units
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
    • B60W10/00—Conjoint control of vehicle sub-units of different type or different function
    • B60W10/18—Conjoint control of vehicle sub-units of different type or different function including control of braking systems
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
    • B60W30/00—Purposes of road vehicle drive control systems not related to the control of a particular sub-unit, e.g. of systems using conjoint control of vehicle sub-units
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
    • B60W50/00—Details of control systems for road vehicle drive control not related to the control of a particular sub-unit, e.g. process diagnostic or vehicle driver interfaces
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
    • B60W60/00—Drive control systems specially adapted for autonomous road vehicles
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
    • B60W50/00—Details of control systems for road vehicle drive control not related to the control of a particular sub-unit, e.g. process diagnostic or vehicle driver interfaces
    • B60W2050/0001—Details of the control system
    • B60W2050/0002—Automatic control, details of type of controller or control system architecture
    • B60W2050/0008—Feedback, closed loop systems or details of feedback error signal
    • B60W2050/0011—Proportional Integral Differential [PID] controller
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
    • B60W2520/00—Input parameters relating to overall vehicle dynamics
    • B60W2520/10—Longitudinal speed
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
    • B60W2520/00—Input parameters relating to overall vehicle dynamics
    • B60W2520/10—Longitudinal speed
    • B60W2520/105—Longitudinal acceleration
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
    • B60W2540/00—Input parameters relating to occupants
    • B60W2540/10—Accelerator pedal position
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
    • B60W2540/00—Input parameters relating to occupants
    • B60W2540/12—Brake pedal position

Definitions

  • the present application belongs to the technical field of automatic driving, and in particular, relates to a vehicle control method, apparatus, device, and computer storage medium.
  • the vehicle in the field of autonomous driving, the vehicle usually needs to drive according to the planned motion parameters.
  • the driving environment may bring uncertain disturbances to the driving of the vehicle, resulting in differences between the actual motion parameters of the vehicle and the planned motion parameters.
  • the vehicle usually compensates the control parameters of the vehicle directly according to the difference between the planned speed and the actual speed; however, when there are many uncertain disturbances, the compensated control parameters may not be reasonable enough. This results in poor control of the vehicle.
  • the embodiments of the present application provide a vehicle control method, device, device, and computer storage medium, so as to solve the problem that the compensated control parameters are not reasonable enough and the vehicle control effect is poor when the vehicle has many uncertain disturbances in the related art.
  • the problem is not reasonable enough and the vehicle control effect is poor when the vehicle has many uncertain disturbances in the related art. The problem.
  • an embodiment of the present application provides a vehicle control method, including:
  • the first acceleration is determined according to the current speed and the target speed; the second acceleration is determined according to the current speed, the current accelerator braking value and the predetermined target dynamic model; wherein, the target dynamic model records the difference between the speed, the acceleration and the accelerator braking value. Correspondence between;
  • the target accelerator braking value is determined, and the target accelerator braking value is used to control the actuator of the vehicle.
  • an embodiment of the present application provides a vehicle control device, including:
  • the first acquisition module is used to acquire the current speed, target speed, current acceleration and current accelerator braking value of the vehicle in one control cycle;
  • the first determination module is used to determine the first acceleration according to the current speed and the target speed; determine the second acceleration according to the current speed, the current accelerator brake value and the predetermined target dynamics model; wherein, the target dynamics model records the speed , acceleration and the corresponding relationship between the accelerator and brake values;
  • a second determination module configured to determine the target acceleration according to the first acceleration, the second acceleration and the current acceleration
  • the third determination module is used for determining the target accelerator braking value according to the target acceleration, the current speed and the target dynamic model, and the target accelerator braking value is used to control the actuator of the vehicle.
  • an embodiment of the present application provides an electronic device, where the device includes: a processor and a memory storing computer program instructions;
  • the above-described vehicle control method is implemented when the processor executes the computer program instructions.
  • an embodiment of the present application provides a computer storage medium, where computer program instructions are stored on the computer storage medium, and the computer program instructions are executed by a processor to implement the above-mentioned vehicle control method.
  • the current speed, target speed, current acceleration, and current accelerator braking value of the vehicle are obtained, the first acceleration is determined according to the current speed and the target speed, and the first acceleration is determined according to the current speed, the current
  • the accelerator braking value and the predetermined target dynamics model determine the second acceleration; determine the target acceleration according to the first acceleration, the second acceleration and the current acceleration; and further determine the target accelerator brake according to the target acceleration, the current speed and the target dynamics model value.
  • This embodiment can enable the vehicle to quickly adjust the speed to track the desired speed, and at the same time, considering the uncertain disturbance brought by the vehicle's driving environment, it is helpful to improve the rationality of the target accelerator and brake value and improve the control effect of the vehicle.
  • FIG. 1 is a schematic flowchart of a vehicle control method provided by an embodiment of the present application.
  • FIG. 3 is an example diagram of discrete data in the first kinetic model in the embodiment of the present application.
  • FIG. 5 is a schematic diagram of an internal mold structure controller in an embodiment of the present application.
  • FIG. 6 is a schematic diagram of an internal mold structure controller and a speed controller in an embodiment of the present application
  • Fig. 7 is an example diagram of the establishment process of the target kinetic model in the embodiment of the present application.
  • FIG. 8 is an example diagram of a vehicle control process in an embodiment of the present application.
  • FIG. 9 is a schematic structural diagram of a vehicle control device provided by an embodiment of the present application.
  • FIG. 10 is a schematic structural diagram of an electronic device provided by an embodiment of the present application.
  • the embodiments of the present application provide a vehicle control method, apparatus, device, and computer storage medium.
  • FIG. 1 shows a schematic flowchart of a vehicle control method provided by an embodiment of the present application. As shown in Figure 1, the vehicle control method includes:
  • Step 101 in a control cycle, obtain the current speed, target speed, current acceleration and current accelerator braking value of the vehicle;
  • Step 102 determine the first acceleration according to the current speed and the target speed; determine the second acceleration according to the current speed, the current accelerator braking value and the predetermined target dynamics model; wherein, the target dynamics model records speed, acceleration and accelerator Correspondence between brake values;
  • Step 103 determining the target acceleration according to the first acceleration, the second acceleration and the current acceleration
  • Step 104 according to the target acceleration, the current speed and the target dynamics model, determine the target accelerator braking value, and the target accelerator braking value is used to control the actuator of the vehicle.
  • the vehicle may be a vehicle with an automatic driving function. That is to say, the vehicle can plan motion parameters such as speed, and can automatically control the accelerator, brake and other actuators of the vehicle according to the planned motion parameters, so that the vehicle can travel in the desired way.
  • the vehicle can plan motion parameters such as speed, and can automatically control the accelerator, brake and other actuators of the vehicle according to the planned motion parameters, so that the vehicle can travel in the desired way.
  • the planning of the motion parameters of the vehicle and the control of the actuator can be carried out in different control cycles. It is easy to understand that in some closed-loop control application scenarios, the output of one control cycle can be used as the input of the next control cycle.
  • control process of the vehicle will be mainly described in a certain control cycle.
  • the vehicle may acquire the current speed, target speed, current acceleration and current accelerator/brake value of the vehicle.
  • the current speed and current acceleration of the vehicle can be collected by sensors installed on the vehicle, such as a speed sensor and an acceleration sensor.
  • the current speed and the current acceleration can also be obtained through the vehicle terminal.
  • the real-time position of the vehicle can be obtained through the high-precision map installed in the vehicle terminal, and obtained according to the position change. Parameters such as the current speed and current acceleration of the vehicle.
  • the target speed may refer to the speed planned in the control cycle, or the speed expected to be obtained by the vehicle in the control cycle.
  • the target speed may be the expected speed at a certain moment determined according to the vehicle performance or vehicle comfort; for another example, in the vehicle driving stage at a constant speed, the target speed may be the maximum speed limit of a certain road section, etc. .
  • the accelerator brake value can be used to indicate the action of the accelerator and brake to a certain extent. It is easy to understand that a vehicle usually includes accelerators, brakes, and corresponding pedals.
  • the accelerator brake value it can be divided into the accelerator value and the brake value; wherein, the accelerator value can refer to the opening degree of the accelerator, or the opening degree of the accelerator pedal, or the stroke of the accelerator pedal, etc.; correspondingly, the brake value can refer to The opening of the brake pedal, or the stroke of the brake pedal, etc.
  • the accelerator value may refer to the opening degree of the accelerator pedal, or the ratio of the stroke of the accelerator pedal to the total stroke; similarly, the braking value may refer to the opening degree of the brake pedal.
  • the accelerator and brake will not work at the same time, for example: when the accelerator value is 50%, the brake value is usually 0; and when the brake value is 50%, the accelerator value is usually 0.
  • the accelerator value and the brake value can be uniformly represented by the accelerator brake value.
  • the accelerator-brake value when the accelerator-brake value is 50%, it means that the accelerator value is 50%; when the accelerator-brake value is -50%, it means that the brake value is 50%; when the accelerator-brake value is 0, it means that neither the accelerator nor the brake work. That is to say, the positive and negative values of the accelerator and brake values can be used to indicate whether the accelerator is working or the braking is working.
  • the percent sign can be omitted when the value of the accelerator-brake value is given as an example below.
  • the accelerator-brake value is -35, which means the opening of the brake pedal is 35%.
  • the accelerator/brake value it can be collected by sensors such as pedal position sensor.
  • the accelerator/brake value can be used as a control quantity to control the accelerator or brake, and the control process is less affected by environmental factors; that is to say, the actual opening of the accelerator or brake may be different from the actual opening of the accelerator or brake.
  • the accelerator-brake value as the control variable is highly matched, therefore, in one control cycle, the obtained current accelerator-brake value may also be the accelerator-brake value output as the control variable in the previous control cycle.
  • step 102 the vehicle can obtain the first acceleration according to the current speed and the target speed; it is easy to understand that when the vehicle needs to adjust the speed, it usually needs to generate a corresponding acceleration; therefore, according to the current speed and the target speed, it is also possible to An acceleration is determined, which may be positive, negative, or zero.
  • a speed adjustment time may be preset, and the ratio of the difference between the current speed and the target speed and the speed adjustment time may be used as the first acceleration.
  • other preset speed controllers may also be used to obtain the first acceleration according to the current speed and the target speed.
  • the second acceleration can be determined according to the current speed, the current accelerator braking value and the predetermined target dynamic model.
  • the target dynamics model For the target dynamics model, the correspondence between speed, acceleration, and accelerator-brake values can be recorded.
  • the target dynamic model can be a data-driven dynamic model or an analytical dynamic model, etc., which can be selected according to actual needs.
  • a data-driven dynamic model it can be represented by a data table or the like; for example, the table records the corresponding accelerator and brake values at a specific speed and a specific acceleration. For example, when the speed is 4m/s and the acceleration is -2m/s 2 , the corresponding accelerator-brake value is -35.
  • the three parameters of speed, acceleration, and accelerator and brake values have a corresponding relationship; in practical applications, any two parameters can be used as known quantities to Query the third parameter.
  • the current speed and the current accelerator/brake value may be known, and the second acceleration may be obtained according to the data-driven dynamic model.
  • the analytical dynamic model it can be represented by a functional equation.
  • the acceleration can be used as the dependent variable, and the speed and the value of the accelerator and brake can be used as independent variables; then, according to the functional equation, the current speed and the current Throttle brake value, get the second acceleration.
  • the third parameter can also be obtained by calculation when any two parameters are known.
  • the vehicle may determine the target acceleration according to the first acceleration, the second acceleration and the current acceleration.
  • the first acceleration can be regarded as the adjustment amount required to directly eliminate the speed error.
  • the vehicle determines the target acceleration according to the first acceleration, the second acceleration and the current acceleration, which can simultaneously take into account the direct demand for vehicle motion parameter adjustment and the impact of environmental disturbances on vehicle motion.
  • the vehicle may determine a target accelerator/brake value according to the target acceleration, the current speed and the target dynamics model.
  • the target dynamics model can record the correspondence between the three parameters of speed, acceleration, and accelerator-brake value, and when two of the parameters are known, the third parameter can be obtained. Therefore, in step 104, when the vehicle obtains the target acceleration and the current speed, the target accelerator braking value can be obtained.
  • the target accelerator/brake value can be regarded as a control quantity generated in a control cycle to a certain extent, which can be used to control the accelerator or brake of the vehicle and other actuators, so as to realize the adjustment of the movement process of the vehicle.
  • the target dynamic model may be applied twice in the above steps 102 and 104, and to a certain extent, it can be considered that an internal model structure controller is used, and it can be estimated that due to the vehicle Uncertain disturbances brought by the driving environment.
  • the first acceleration is obtained according to the current speed and the target speed, which can be considered as using a speed controller, which helps the vehicle to quickly adjust the speed to track the desired speed (corresponding to the target speed).
  • the current speed, target speed, current acceleration, and current accelerator braking value of the vehicle are obtained, the first acceleration is determined according to the current speed and the target speed, and the first acceleration is determined according to the current speed, the current
  • the accelerator braking value and the predetermined target dynamics model determine the second acceleration; determine the target acceleration according to the first acceleration, the second acceleration and the current acceleration; and further determine the target accelerator brake according to the target acceleration, the current speed and the target dynamics model value.
  • the above speed and acceleration can be considered as the longitudinal speed and longitudinal acceleration of the vehicle.
  • the lateral speed and lateral acceleration may be small, and the speed and acceleration may also be the speed and acceleration of the entire vehicle.
  • the related parameters such as speed and acceleration can be considered as parameters in the longitudinal direction of the vehicle.
  • the vehicle control method in the above step 101, before acquiring the current speed, the target speed and the current accelerator and brake values, the vehicle control method may further include:
  • At least one step signal is determined, each step signal includes a first accelerator value, a first desired speed and a first braking value, the step signal is used to instruct the vehicle to accelerate from a standstill to a first accelerator value in a first movement phase a first desired speed, and decelerating from the first desired speed to rest with a first braking value in the second movement phase;
  • the corresponding relationship between the first motion parameter and the second motion parameter corresponding to each step signal is obtained respectively, and the first motion parameter corresponding relationship indicates the corresponding relationship between the speed and the acceleration of the vehicle in the first motion stage corresponding to any step information. ;
  • the corresponding relationship of the second motion parameter indicates the corresponding relationship between the speed and the acceleration of the vehicle in the second motion stage corresponding to any step information;
  • the target dynamic model is determined according to the corresponding relationship between the first motion parameter and the second motion parameter corresponding to the step signal.
  • the established target dynamic model may be the above-mentioned data-driven dynamic model.
  • the following describes the establishment process of the above target dynamics model in combination with a practical application scenario.
  • a data-driven longitudinal dynamics model can be established by measuring the step responses of the vehicle speed to the accelerator and braking, respectively, in a reference environment where the road is straight, the road is flat, and almost unaffected by wind speed.
  • the whole vehicle is regarded as a black box, the desired vehicle speed v x and the accelerator/brake value u are input, and the acceleration a obtained by the vehicle is used as the output for modeling; the modeling results are as follows:
  • step signal "90, 25, -50" For example, input the step signal "90, 25, -50", where "90” corresponds to the above-mentioned first throttle value, "25” corresponds to the above-mentioned first desired speed, and "-50” corresponds to the above-mentioned first throttle value A braking value.
  • the vehicle Under the instruction of the step signal "90,25,-50", the vehicle will accelerate to a desired speed of 25m/s at 90% of the accelerator value, and then brake at 50% of the braking value until the vehicle is stationary. Record key information such as speed, acceleration, accelerator opening and brake opening during this process.
  • the above acceleration process may correspond to the first movement stage of the vehicle; correspondingly, the braking process may correspond to the second movement stage of the vehicle.
  • step signal accelerator-brake-speed combinations can be input at certain intervals, and the acceleration and deceleration information (ie, corresponding acceleration) of the vehicle under the step signal can be collected.
  • FIG. 2 shows the corresponding relationship of the first motion parameters in the first motion stage corresponding to the step signal "90, 25, -50".
  • the abscissa in the figure can be the speed, the unit is m/s; the ordinate can be the acceleration, the unit is m/s 2 .
  • each speed corresponds to an acceleration, that is, there is a corresponding relationship between accelerator brake value-speed-acceleration.
  • there may be multiple accelerator-brake values for example, under a step signal, at least two accelerator-brake values can be generated. Because each accelerator and brake value has the corresponding relationship of motion parameters as shown in Figure 2. Based on the above-mentioned correspondence, the target dynamics model can be established.
  • the corresponding relationship between the motion parameters under each accelerator brake value is obtained based on the step signal, so that more accelerator brake value-speed-acceleration corresponding relationships can be easily obtained, and then can be established more efficiently. target dynamics model.
  • FIG. 2 there are two curves in FIG. 2 , one of which changes sharply and can be used to reflect the corresponding relationship between the acquired original speed and the original acceleration, and the curve can be recorded as the original data curve.
  • the raw data curve can be smoothed.
  • the above-mentioned determination of the target dynamics model according to the corresponding relationship between the first motion parameter and the second motion parameter corresponding to the step signal includes:
  • the target dynamic model is determined according to the processed correspondence between the first motion parameter and the second motion parameter.
  • the method of mean filtering and curve fitting may be used for processing, so as to obtain a relatively smooth curve in FIG. 2 , or denoted as the fitted data curve.
  • the method of smoothing the original data curve may also be an inertial filtering method, and when performing curve fitting, a quintic curve or other forms of curves may be used for fitting. That is to say, the processing method of the original data curve may not be specifically limited here.
  • the curve can represent the acceleration corresponding to the speed in the range of 0-25 m/s when the accelerator-brake value is 90.
  • the fitted data curve is discretized, and the corresponding relationship between other collected accelerator brake value-speed-acceleration is established in turn, as shown in Figure 3 Bold identification curve shown.
  • the X axis is the speed
  • the Y axis is the accelerator brake value
  • the Z axis is the acceleration.
  • the unbold curve indicated by the arrow in FIG. 3 can be obtained by using a linear approximation method.
  • the linearized data that is not directly collected in the range of -40 to -45 can be obtained.
  • FIG. 3 may show discrete data of the target dynamics model in a coordinate system, and in the following table, part of the discrete data in FIG. 3 may be shown.
  • the data in the header row is the speed
  • the data in the header column is the accelerator/brake value
  • the middle data is the acceleration.
  • the target dynamics model includes a first dynamics model and a second dynamics model
  • the speed and the accelerator brake are used as inputs, and the acceleration is used as the output;
  • the acceleration and speed are used as inputs, and the accelerator and brake values are used as outputs.
  • the target dynamics model can be made to further include the second dynamics model.
  • the data in the header row is the speed
  • the data in the header column corresponds to the acceleration
  • the middle data is the accelerator brake value.
  • the driving force F m can actually be divided into two parts, the driving force part F that eliminates the speed error r and the compensation disturbance part F d :
  • the environmental disturbance is represented by the difference between the actual output of the vehicle and the model output, and the disturbance force F d to be compensated is:
  • the driving force part Fr that eliminates the speed error can be simply obtained as follows:
  • m is the mass of the vehicle, the same mass of the vehicle itself has been reflected in the established model, and the mass is not introduced here.
  • the accelerator braking value u required for the vehicle to accelerate from v c to v d and overcome the environmental disturbance is:
  • a c is the current acceleration
  • a d is the expected acceleration of the vehicle
  • t can be understood as the expected time for eliminating the speed error, and the specific value can be preset
  • vc represents the current speed
  • u a is the current throttle-brake value.
  • FIG. 5 shows a schematic diagram of a typical internal mold structure controller.
  • the reference model in FIG. 5 can correspond to the above-mentioned speed controller, the internal model controller can correspond to the second dynamic model, the model output can correspond to the first dynamic model, and the controlled object can be the brake or the accelerator of the vehicle.
  • the following describes the vehicle control method provided by the embodiment of the present application on the basis of the internal model structure controller shown in FIG. 5 .
  • step 103 determining the target acceleration according to the first acceleration, the second acceleration and the current acceleration, includes:
  • a fourth acceleration is obtained by multiplying the third acceleration by a preset feedback coefficient
  • the target acceleration is determined according to the first acceleration and the compensation acceleration.
  • the internal model structure controller can be regarded as a closed-loop control to a certain extent; and in the process of determining the first acceleration, the speed controller is also applied, which can also be regarded as a closed-loop control.
  • the closed loop corresponding to the internal model structure controller can be abbreviated as the inner loop, and the closed loop corresponding to the speed controller can be abbreviated as the outer loop.
  • the second acceleration can be considered as the output of the above-mentioned first dynamic model, and correspondingly, the compensation acceleration can be obtained by multiplying the difference between the output of the first dynamic model and the actual acceleration of the vehicle by the feedback coefficient k, and then filtering by a filter.
  • the filter here can be called a feedback filter.
  • the feedback filter may be an inertial filter or a recursive filter, etc., which is not specifically limited here.
  • the first acceleration can be considered as the output of the above-mentioned outer loop, and the target acceleration can be obtained by adding the first acceleration and the compensation acceleration.
  • the acquisition of the compensating acceleration and the first acceleration can correspond to equations (4) and (5) respectively to a certain extent; and in this embodiment, the process of determining the compensating acceleration takes into account the preset feedback coefficient and the filtering process .
  • the above internal model structure controller and speed controller can be integrally used as an integral part of the vehicle controller.
  • By setting the feedback coefficient reasonably it is helpful to reduce the possibility of vehicle controller oscillation divergence and improve the stability of vehicle control; and filtering through the feedback filter can smooth the estimated disturbance and reduce the oscillation of the disturbance on the output of the control quantity;
  • the application of feedback filters and feedback coefficients can jointly ensure the stability of the inner loop.
  • the longitudinal parameterized inverse model corresponds to the above-mentioned second dynamic model
  • the parameterized reference model corresponds to the above-mentioned first dynamic model.
  • the fourth acceleration is filtered to obtain a compensated acceleration, comprising:
  • the fourth acceleration is filtered by the first inertial filter to obtain the compensation acceleration
  • the filter coefficient of the first inertial filter is inversely correlated with the speed error, and the speed error is the absolute value of the difference between the target speed and the current speed.
  • the first inertial filter it may be a first-order inertial filter, a second-order inertial filter, and the like.
  • the following description is mainly given by taking the first inertial filter as a first-order inertial filter as an example.
  • the first-order inertial filter G b (s) can generally be expressed by the following formula:
  • ⁇ is the filter coefficient of the first-order inertial filter
  • s is the Laplacian operator.
  • the value of ⁇ may be adjustable.
  • the filter coefficient ⁇ reflects the comfort and rapidity of the speed tracking control: if the coefficient ⁇ is small, the filter bandwidth is larger, the high-frequency disturbance signal can pass through the filter, and the rapidity of the speed tracking control is guaranteed. However, the comfort decreases; on the contrary, if the coefficient ⁇ is larger, the filter bandwidth becomes smaller, the high-frequency signal is filtered, the acceleration and deceleration of the vehicle are relatively slower, and the comfort of the speed tracking control is guaranteed, but the rapidity is sacrificed.
  • the filter coefficient ⁇ is adaptively adjusted according to the following logic: when the speed error is large, ⁇ takes a smaller value; when the speed error is small, ⁇ takes a larger value . That is, the filter coefficient of the first inertial filter may be inversely correlated with the absolute value of the difference between the target speed and the current speed.
  • determining the first acceleration according to the current speed and the target speed including:
  • the speed controller in the above-mentioned outer loop may be a PID controller.
  • the input of the outer loop speed PID controller can be the expected speed (ie target speed) of the vehicle from the upstream planning module and the actual speed (ie current speed) obtained by feedback, and the output is the PID control rate.
  • the time parameter t in equation (6) can be regarded as a proportional term parameter. That is to say, the PID controller here can be a high-level concept. In practical applications, it can be simple proportional control, proportional-integral control or proportional-integral-derivative control, etc., which can be selected according to needs.
  • the vehicle control method can use the controller of the outer loop PID control loop and the inner loop inner model structure control loop to achieve vehicle speed tracking, and the outer loop PID loop can quickly adjust to track the desired speed when the desired speed changes.
  • the inner loop inner model structure is used to evaluate the influence of model mismatch and environmental disturbance on the vehicle, and the smoothing of the feedback by the first-order inertial filter allows the vehicle to take into account both comfort and fastness when tracking the desired speed.
  • the vehicle control method further includes:
  • the target accelerator-brake value is filtered to obtain the accelerator-brake control command, and the accelerator-brake control command is used to control the accelerator or brake of the vehicle.
  • a filter may be used to filter the target accelerator/brake value.
  • the filter here may be called a feedforward filter.
  • the feedforward filter may be an inertial filter or a recursive filter, etc., which is not specifically limited here.
  • the accelerator/brake control command may carry corresponding control parameter values, so that the accelerator or brake can act in a desired manner; and these control parameter values may be obtained based on the above-mentioned target accelerator/brake values.
  • the target accelerator-brake value By filtering the target accelerator-brake value, the target accelerator-brake value can be smoothed and the damage to the actuator can be reduced.
  • the filtering process of the target accelerator/brake value may also be omitted.
  • an emergency braking command may be generated.
  • the filtering process of the target accelerator braking value can be omitted, so that the actuators such as brakes can respond quickly and improve the vehicle's braking performance. safety.
  • the target accelerator-brake value is filtered to obtain the accelerator-brake control command, including:
  • the second inertial filter is used to filter the target accelerator-brake value to obtain the accelerator-brake control command
  • the filter coefficient of the second inertial filter is inversely correlated with the speed error, and the speed error is the absolute value of the difference between the target speed and the current speed.
  • the second inertial filter may be a first-order inertial filter, a second-order inertial filter, etc., and may be selected according to actual needs.
  • the second inertial filter is denoted as G f (s), and the second inertial filter is a first-order inertial filter
  • the second inertial filter can be expressed by the following formula:
  • ⁇ is the filter coefficient of the first-order inertial filter
  • s is the Laplacian operator.
  • the value of ⁇ may be adjustable.
  • the adjustment of the feedforward coefficient ⁇ is similar to the feedback coefficient ⁇ .
  • ⁇ takes a small value to ensure rapidity; when the speed error is small, ⁇ takes a large value to ensure comfort.
  • the filter coefficient of the second inertial filter may be inversely correlated with the absolute value of the difference between the target speed and the current speed, thus helping to balance comfort and speed of vehicle control.
  • Filter the target accelerator-brake value to obtain the accelerator-brake control command which may also include:
  • the initial control amount is limited according to the preset value range to obtain the accelerator brake control command.
  • the preset value range can be [-95,95], which corresponds to the brake pedal opening not greater than 95% and the accelerator pedal opening not greater than 95%.
  • the initial control amount indicates that the required brake pedal opening is 99%
  • the initial control amount can be limited, so that the obtained accelerator-brake control instruction indicates that the brake pedal opening is adjusted to 95%.
  • the redundant protection function of the actuator can be played, and the damage of the actuator due to excessive adjustment can be effectively avoided.
  • Fig. 7 shows the establishment flow chart of the above-mentioned target kinetic model, including:
  • Step 701 vehicle step response data collection
  • Step 702 collect data and process
  • the collected data processing here may refer to the mean filtering and curve fitting processing, discretization processing and linear approximation of the original data curve mentioned in the above embodiment to obtain discrete data not obtained through direct collection, etc.;
  • Step 703 establishing a data-driven dynamic model
  • This step is equivalent to the step of establishing the first kinetic model above;
  • Step 704 establishing a data-driven dynamic inverse model
  • This step is equivalent to the step of establishing the second kinetic model above.
  • Fig. 8 shows the flow chart of vehicle control under the condition that the target dynamics model is established, including:
  • Step 801 find a matching trajectory point
  • the trajectory points here can be obtained from the upstream planning module.
  • the planning module may plan the path or speed of the vehicle; correspondingly, the output result of the planning module may include a speed planning curve, and the trajectory points may be points in the speed planning curve.
  • Step 802 coordinate conversion
  • the planned velocity vector of the trajectory point in the Cartesian coordinate system (such as the world coordinate system) can be converted into the frenet coordinate system, which can further help to decompose the planned velocity to obtain the longitudinal velocity and the lateral velocity;
  • the longitudinal velocity obtained by the above decomposition can be used as the desired velocity, or as the target velocity.
  • Step 803 calculating the longitudinal velocity error
  • Step 804 calculating the speed loop control amount
  • the speed loop is the closed loop corresponding to the speed controller in the above, and can also be called the outer loop; the control quantity output by the speed loop can be the above-mentioned first acceleration.
  • Step 805 internal model control quantity calculation
  • the internal model control quantity here may be acceleration; correspondingly, the calculation of the internal model control quantity may be considered as the calculation of determining the target acceleration according to the first acceleration and the compensation acceleration.
  • Step 806 parameterized dynamic inverse model interpolation
  • the parametric dynamic inverse model can correspond to the above-mentioned second dynamic model, the input is the speed and acceleration, and the output is the accelerator braking value;
  • the parametric dynamic inverse model interpolation may take the target acceleration and the current speed as inputs, perform interpolation calculation based on the parametric dynamic inverse model, and output the target accelerator braking value.
  • Step 807 filtering and limiting
  • the above-mentioned target accelerator/brake value may be filtered and limited.
  • the filtering here can correspond to the filtering process of the feedforward filter mentioned above, and the result obtained by filtering corresponds to the initial control amount; by limiting the initial control amount, the accelerator amount (such as the accelerator pedal opening) ) or the amount of braking (such as the opening of the brake pedal) is limited to a certain range, which acts as a redundant protection for the actuator.
  • the accelerator-brake control command may include control parameters that are finally acted on the actuator in one control cycle.
  • the accelerator-brake control command instructs to adjust the accelerator pedal opening degree to 60%
  • the accelerator pedal opening degree may be adjusted to 60% in the control cycle.
  • the vehicle control method provided by the embodiment of the present application proposes a method for estimating the disturbance by using the internal model structure for the uncertain disturbance caused by various driving environments (high-speed, park, mining area, etc.), and designs the method according to the method.
  • a dual closed-loop controller with PID control + inner model structure control is proposed; specifically, the outer loop can be a PID controller, and the inner loop can be an inner model structure controller, which is used to estimate the belt due to model deviation and driving environment. Uncertainty disturbances coming.
  • the combination of the above controllers has a relatively simple structure, has no special requirements for processor computing power, can adapt to a variety of environments, has better comfort, and has better accuracy and adaptability to a wide range of expected speeds and speed errors. sex.
  • an embodiment of the present application further provides a vehicle control device, which includes:
  • the first obtaining module 901 is used to obtain the current speed, target speed, current acceleration and current accelerator braking value of the vehicle in one control cycle;
  • the first determination module 902 is used to determine the first acceleration according to the current speed and the target speed; determine the second acceleration according to the current speed, the current accelerator brake value and the predetermined target dynamics model; wherein, the target dynamics model records Correspondence between speed, acceleration and accelerator brake value;
  • the second determination module 903 is configured to determine the target acceleration according to the first acceleration, the second acceleration and the current acceleration;
  • the third determination module 904 is used for determining the target accelerator braking value according to the target acceleration, the current speed and the target dynamic model, and the target accelerator braking value is used to control the actuator of the vehicle.
  • the above-mentioned second determining module 903 may include:
  • a first obtaining unit used for calculating the difference between the second acceleration and the current acceleration to obtain the third acceleration
  • a second obtaining unit configured to multiply the third acceleration by a preset feedback coefficient to obtain the fourth acceleration
  • a first filtering unit configured to filter the fourth acceleration to obtain a compensated acceleration
  • the first determination unit is configured to determine the target acceleration according to the first acceleration and the compensation acceleration.
  • the above-mentioned first filtering unit may be specifically used for:
  • the fourth acceleration is filtered by the first inertial filter to obtain the compensation acceleration
  • the filter coefficient of the first inertial filter is inversely correlated with the speed error, and the speed error is the absolute value of the difference between the target speed and the current speed.
  • the above-mentioned first determining module 902 may be specifically used for:
  • the vehicle control device may further include:
  • the filtering module is used to filter the target accelerator-brake value to obtain the accelerator-brake control command, and the accelerator-brake control command is used to control the accelerator or brake of the vehicle.
  • the filtering module can be specifically used for:
  • the second inertial filter is used to filter the target accelerator-brake value to obtain the accelerator-brake control command
  • the filter coefficient of the second inertial filter is inversely correlated with the speed error, and the speed error is the absolute value of the difference between the target speed and the current speed.
  • the above filtering module may include:
  • the second filtering unit is used for filtering the target accelerator braking value to obtain the initial control amount
  • the third obtaining unit is configured to limit the initial control quantity according to the preset value range to obtain the accelerator brake control command.
  • the above-mentioned vehicle control device may also include:
  • the fourth determination module is used to determine at least one step signal, each step signal includes a first accelerator value, a first expected speed and a first braking value, and the step signal is used to indicate that the vehicle is in the first motion stage with the first Accelerates from rest to a first desired speed at a throttle value, and decelerates from the first desired speed to rest at a first braking value in a second movement phase;
  • the second obtaining module is used to obtain the corresponding relationship between the first motion parameter and the second motion parameter corresponding to each step signal respectively, and the first motion parameter corresponding relationship indicates that the vehicle is in the first motion stage corresponding to any step information.
  • the corresponding relationship between the speed and the acceleration; the second motion parameter corresponding relationship indicates the corresponding relationship between the speed and the acceleration of the vehicle in the second motion stage corresponding to any step information;
  • the fifth determination module is configured to determine the target dynamics model according to the corresponding relationship of the first motion parameter and the corresponding relationship of the second motion parameter corresponding to the step signal.
  • the fifth determining module may include:
  • a processing unit configured to perform filtering and/or curve fitting processing on the correspondence between the first motion parameter and the second motion parameter corresponding to the step signal
  • the second determining unit is configured to determine the target dynamics model according to the processed correspondence between the first motion parameter and the second motion parameter.
  • the target dynamics model includes a first dynamics model and a second dynamics model
  • the speed and the accelerator brake are used as inputs, and the acceleration is used as the output;
  • the acceleration and speed are used as inputs, and the accelerator and brake values are used as outputs.
  • vehicle control device is a device corresponding to the above-mentioned vehicle control method, and all implementations in the above-mentioned method embodiments are applicable to the embodiments of the device, and the same technical effect can also be achieved.
  • FIG. 10 shows a schematic diagram of a hardware structure of an electronic device provided by an embodiment of the present application.
  • the electronic device may include a processor 1001 and a memory 1002 storing computer program instructions.
  • processor 1001 may include a central processing unit (CPU), or a specific integrated circuit (Application Specific Integrated Circuit, ASIC), or may be configured to implement one or more integrated circuits of the embodiments of the present application.
  • CPU central processing unit
  • ASIC Application Specific Integrated Circuit
  • Memory 1002 may include mass storage for data or instructions.
  • memory 1002 may include a Hard Disk Drive (HDD), a floppy disk drive, a flash memory, an optical disk, a magneto-optical disk, a magnetic tape, or a Universal Serial Bus (USB) drive or two or more A combination of more than one of the above.
  • Memory 1002 may include removable or non-removable (or fixed) media, where appropriate.
  • Storage 1002 may be internal or external to the integrated gateway disaster recovery device, where appropriate.
  • memory 1002 is non-volatile solid state memory.
  • Memory may include read only memory (ROM), random access memory (RAM), magnetic disk storage media devices, optical storage media devices, flash memory devices, electrical, optical or other physical/tangible memory storage devices.
  • ROM read only memory
  • RAM random access memory
  • magnetic disk storage media devices e.g., magnetic disks
  • optical storage media devices e.g., magnetic disks
  • flash memory devices e.g., electrical, optical or other physical/tangible memory storage devices.
  • a memory includes one or more tangible (non-transitory) computer-readable storage media (eg, memory devices) encoded with software including computer-executable instructions, and when the software is executed (eg, by a or multiple processors), it is operable to perform the operations described with reference to methods according to the present disclosure.
  • the processor 1001 reads and executes the computer program instructions stored in the memory 1002 to implement any one of the vehicle control methods in the foregoing embodiments.
  • the electronic device may also include a communication interface 1003 and a bus 1004 .
  • the processor 1001 , the memory 1002 , and the communication interface 1003 are connected through the bus 1004 and complete the mutual communication.
  • the communication interface 1003 is mainly used to implement communication between modules, apparatuses, units and/or devices in the embodiments of the present application.
  • the bus 1004 includes hardware, software, or both, coupling the components of the online data flow metering device to each other.
  • the bus may include Accelerated Graphics Port (AGP) or other graphics bus, Enhanced Industry Standard Architecture (EISA) bus, Front Side Bus (FSB), HyperTransport (HT) Interconnect, Industry Standard Architecture (ISA) Bus, Infiniband Interconnect, Low Pin Count (LPC) Bus, Memory Bus, Microchannel Architecture (MCA) Bus, Peripheral Component Interconnect (PCI) Bus, PCI-Express (PCI-X) Bus, Serial Advanced Technology Attachment (SATA) bus, Video Electronics Standards Association Local (VLB) bus or other suitable bus or a combination of two or more of the above.
  • Bus 1004 may include one or more buses, where appropriate. Although embodiments of this application describe and illustrate a particular bus, this application contemplates any suitable bus or interconnect.
  • the electronic device may be a mobile electronic device or a non-mobile electronic device.
  • the mobile electronic device may be a mobile phone, a tablet computer, a notebook computer, a palmtop computer or an in-vehicle electronic device, etc.
  • the non-mobile electronic device may be a server or the like.
  • the embodiment of the present application may provide a computer storage medium for implementation.
  • Computer program instructions are stored on the computer storage medium; when the computer program instructions are executed by the processor, any one of the vehicle control methods in the foregoing embodiments is implemented.
  • Examples of computer storage media include physical/tangible storage media such as electronic circuits, semiconductor memory devices, ROM, flash memory, erasable ROM (EROM), floppy disks, CD-ROMs, optical disks, hard disks, and the like.
  • Embodiments of the present application further provide a computer program product, which can be executed by a processor to implement the various processes of the above vehicle control method embodiments, and can achieve the same technical effect. To avoid repetition, details are not repeated here. .
  • An embodiment of the present application further provides a chip, the chip includes a processor and a communication interface, the communication interface and the processor are coupled, and the processor is used to run a program or an instruction to implement the various processes of the above vehicle control method embodiments, and can achieve the same The technical effect, in order to avoid repetition, will not be repeated here.
  • the chip mentioned in the embodiments of the present application may also be referred to as a system-on-chip, a system-on-chip, a system-on-a-chip, or a system-on-a-chip, or the like.
  • the functional blocks shown in the above-described structural block diagrams may be implemented as hardware, software, firmware, or a combination thereof.
  • it When implemented in hardware, it may be, for example, an electronic circuit, an application specific integrated circuit (ASIC), suitable firmware, a plug-in, a function card, or the like.
  • ASIC application specific integrated circuit
  • elements of the present application are programs or code segments used to perform the required tasks.
  • the program or code segments may be stored in a machine-readable medium or transmitted over a transmission medium or communication link by a data signal carried in a carrier wave.
  • a "machine-readable medium” may include any medium that can store or transmit information.
  • machine-readable media examples include electronic circuits, semiconductor memory devices, ROM, flash memory, erasable ROM (EROM), floppy disks, CD-ROMs, optical disks, hard disks, fiber optic media, radio frequency (RF) links, and the like.
  • the code segments may be downloaded via a computer network such as the Internet, an intranet, or the like.
  • processors may be, but are not limited to, general purpose processors, special purpose processors, application specific processors, or field programmable logic circuits. It will also be understood that each block of the block diagrams and/or flowchart illustrations, and combinations of blocks in the block diagrams and/or flowchart illustrations, can also be implemented by special purpose hardware for performing the specified functions or actions, or by special purpose hardware and/or A combination of computer instructions is implemented.

Landscapes

  • Engineering & Computer Science (AREA)
  • Transportation (AREA)
  • Mechanical Engineering (AREA)
  • Chemical & Material Sciences (AREA)
  • Combustion & Propulsion (AREA)
  • Automation & Control Theory (AREA)
  • Human Computer Interaction (AREA)
  • Control Of Driving Devices And Active Controlling Of Vehicle (AREA)
  • Feedback Control In General (AREA)

Abstract

一种车辆控制方法、装置、设备及计算机存储介质，其中车辆控制方法包括：在一个控制周期中，获取车辆的当前速度、目标速度、当前加速度以及当前油门刹车值；根据当前速度与目标速度，确定第一加速度；根据当前速度、当前油门刹车值以及预先确定的目标动力学模型，确定第二加速度；其中目标动力学模型记载有速度、加速度以及油门刹车值之间的对应关系；根据第一加速度、第二加速度以及当前加速度确定目标加速度；根据目标加速度、当前速度以及目标动力学模型，确定目标油门刹车值。

Description

车辆控制方法、装置、设备及计算机存储介质
相关申请的交叉引用
本申请要求享有于2021年03月08日提交的名称为“车辆控制方法、装置、设备及计算机存储介质”的中国专利申请202110251342.0的优先权，该申请的全部内容通过引用并入本文中。
技术领域
本申请属于自动驾驶技术领域，尤其涉及一种车辆控制方法、装置、设备及计算机存储介质。
背景技术
众所周知，在自动驾驶领域中，车辆通常需要按照规划的运动参数进行行驶。然而，一般来说，行驶环境可能对车辆的行驶带来不确定性扰动，导致车辆实际的运动参数与规划的运动参数存在差异。
相关技术中，车辆通常是直接根据规划速度与实际速度的差异，来对车辆的控制参数进行补偿；然而，在不确定性扰动较多的情况下，可能出现补偿的控制参数不够合理的情况，导致车辆的控制效果较差。
发明内容
本申请实施例提供一种在车辆控制方法、装置、设备及计算机存储介质，以解决相关技术中车辆在不确定性扰动较多的情况下，补偿的控制参数不够合理，车辆的控制效果较差的问题。
第一方面，本申请实施例提供一种车辆控制方法，包括：
在一个控制周期中，获取车辆的当前速度、目标速度、当前加速度以及当前油门刹车值；
根据当前速度与目标速度，确定第一加速度；根据当前速度、当前油 门刹车值以及预先确定的目标动力学模型，确定第二加速度；其中，目标动力学模型记载有速度、加速度以及油门刹车值之间的对应关系；
根据第一加速度、第二加速度以及当前加速度确定目标加速度；
根据目标加速度、当前速度以及目标动力学模型，确定目标油门刹车值，目标油门刹车值用于对车辆的执行机构进行控制。
第二方面，本申请实施例提供了一种车辆控制装置，包括：
第一获取模块，用于在一个控制周期中，获取车辆的当前速度、目标速度、当前加速度以及当前油门刹车值；
第一确定模块，用于根据当前速度与目标速度，确定第一加速度；根据当前速度、当前油门刹车值以及预先确定的目标动力学模型，确定第二加速度；其中，目标动力学模型记载有速度、加速度以及油门刹车值之间的对应关系；
第二确定模块，用于根据第一加速度、第二加速度以及当前加速度确定目标加速度；
第三确定模块，用于根据目标加速度、当前速度以及目标动力学模型，确定目标油门刹车值，目标油门刹车值用于对车辆的执行机构进行控制。
第三方面，本申请实施例提供了一种电子设备，设备包括：处理器以及存储有计算机程序指令的存储器；
处理器执行计算机程序指令时实现上述的车辆控制方法。
第四方面，本申请实施例提供了一种计算机存储介质，计算机存储介质上存储有计算机程序指令，计算机程序指令被处理器执行时实现上述的车辆控制方法。
本申请实施例提供的车辆控制方法，在一个控制周期中，获取车辆的当前速度、目标速度、当前加速度以及当前油门刹车值，根据当前速度与目标速度，确定第一加速度，根据当前速度、当前油门刹车值以及预先确定的目标动力学模型，确定第二加速度；根据第一加速度、第二加速度以及当前加速度确定目标加速度；并进一步根据目标加速度、当前速度以及目标动力学模型，确定目标油门刹车值。本实施例可以使得车辆能够迅速进行速度调整以跟踪期望速度，同时，考虑了车辆行驶环境带来的不确定 扰动，有助于提升目标油门刹车值的合理性，提高车辆的控制效果。
附图说明
为了更清楚地说明本申请实施例的技术方案，下面将对本申请实施例中所需要使用的附图作简单的介绍，对于本领域普通技术人员来讲，在不付出创造性劳动的前提下，还可以根据这些附图获得其他的附图。
图1是本申请实施例提供的车辆控制方法的流程示意图；
图2是本申请实施例中在一个油门刹车值下，速度与加速度的对应关系的示例图；
图3是本申请实施例中第一动力学模型中离散数据的示例图；
图4是本申请实施例中第二动力学模型中离散数据的示例图；
图5是本申请实施例中内模结构控制器的示意图；
图6是本申请实施例中内模结构控制器与速度控制器的示意图；
图7是本申请实施例中目标动力学模型的建立流程的示例图；
图8是本申请实施例中车辆控制过程的示例图；
图9是本申请实施例提供的车辆控制装置的结构示意图；
图10是本申请实施例提供的电子设备的结构示意图。
具体实施方式
下面将详细描述本申请的各个方面的特征和示例性实施例，为了使本申请的目的、技术方案及优点更加清楚明白，以下结合附图及具体实施例，对本申请进行进一步详细描述。应理解，此处所描述的具体实施例仅意在解释本申请，而不是限定本申请。对于本领域技术人员来说，本申请可以在不需要这些具体细节中的一些细节的情况下实施。下面对实施例的描述仅仅是为了通过示出本申请的示例来提供对本申请更好的理解。
需要说明的是，在本文中，诸如第一和第二等之类的关系术语仅仅用来将一个实体或者操作与另一个实体或操作区分开来，而不一定要求或者暗示这些实体或操作之间存在任何这种实际的关系或者顺序。而且，术语“包括”、“包含”或者其任何其他变体意在涵盖非排他性的包含，从而 使得包括一系列要素的过程、方法、物品或者设备不仅包括那些要素，而且还包括没有明确列出的其他要素，或者是还包括为这种过程、方法、物品或者设备所固有的要素。在没有更多限制的情况下，由语句“包括……”限定的要素，并不排除在包括要素的过程、方法、物品或者设备中还存在另外的相同要素。
为了解决相关技术中存在的问题，本申请实施例提供了一种车辆控制方法、装置、设备及计算机存储介质。下面首先对本申请实施例所提供的车辆控制方法进行介绍。
图1示出了本申请一个实施例提供的车辆控制方法的流程示意图。如图1所示，车辆控制方法，包括：
步骤101，在一个控制周期中，获取车辆的当前速度、目标速度、当前加速度以及当前油门刹车值；
步骤102，根据当前速度与目标速度，确定第一加速度；根据当前速度、当前油门刹车值以及预先确定的目标动力学模型，确定第二加速度；其中，目标动力学模型记载有速度、加速度以及油门刹车值之间的对应关系；
步骤103，根据第一加速度、第二加速度以及当前加速度确定目标加速度；
步骤104，根据目标加速度、当前速度以及目标动力学模型，确定目标油门刹车值，目标油门刹车值用于对车辆的执行机构进行控制。
本实施例中，车辆可以是具有自动驾驶功能的车辆。也就是说，车辆可以进行速度等运动参数的规划，并可以根据规划的运动参数，自动对车辆的油门、刹车等执行机构进行控制，以使得车辆能够按照期望的方式进行行驶。
此外，车辆对运动参数的规划以及对执行机构的控制，可以是分不同的控制周期进行的。容易理解的是，在一些闭环控制的应用场景下，一个控制周期的输出，可以作为下一个控制周期的输入。
本申请实施例中，将主要以某一个控制周期中对车辆的控制过程进行说明。
在步骤101中，车辆可以对车辆的当前速度、目标速度、当前加速度以及当前油门刹车值进行获取。
举例来说，车辆的当前速度与当前加速度可以通过安装在车辆上的传感器进行采集，例如通过速度传感器与加速度传感器等进行采集。当然，在另一些举例中，当前速度与当前加速度，也可以是通过车载终端进行获取的，例如，可以是通过车载终端中安装的高精地图来获取车辆的实时位置，并根据位置变化来获得车辆的当前速度与当前加速度等参数。
对于目标速度，可以是指在控制周期中规划的速度，或者说在该控制周期中期望车辆得到的速度。比如说，在车辆加速阶段，目标速度可以是根据车辆性能或车辆舒适度确定的某一时刻下的期望速度；再比如，在车辆匀速行驶阶段，目标速度可以是某一路段的最高限速等。
而油门刹车值，在一定程度上可以用于指示油门与刹车的动作情况。容易理解的是，车辆通常包括油门、刹车以及相应的踏板等。对于油门刹车值，可以分为油门值与刹车值；其中，油门值可以是指油门的开度，或者是油门踏板的开度，或者是油门踏板的行程等；相应地，刹车值可以是指刹车踏板的开度，或者是刹车踏板的行程等。
为便于说明，油门值可以是指油门踏板的开度，或者说油门踏板的行程与总行程的比值；类似地，刹车值可以是指刹车踏板的开度。
一般情况下，油门和刹车不会同时工作，例如：油门值为50％，刹车值通常为0；而刹车值为50％时，油门值通常为0。
在油门与刹车不会同时工作的假设下，可以将油门值与刹车值统一通过油门刹车值进行表示。例如：油门刹车值为50％时，表示油门值为50％；油门刹车值为-50％时，表示刹车值为50％；油门刹车值为0时，表示油门和刹车均不工作。也就是说，可以通过油门刹车值的正负，来表示具体是油门工作还是刹车工作。
另外，值得说明的是，以下在对油门刹车值的数值进行举例时，可以对百分号进行省略，比如，油门刹车值为-35，可以代表刹车踏板的开度为35％。
对于油门刹车值，可以是通过踏板位置传感器等类型的传感器进行采 集得到。当然，在一些应用场景下，油门刹车值可以作为控制量，对油门或者刹车进行控制，该控制过程受到环境因素的影响较少；也就是说，油门或者刹车的实际的开度，可能是与作为控制量的油门刹车值高度匹配的，因此，在一个控制周期中，获取的当前油门刹车值，也可以是上一个控制周期中作为控制量输出的油门刹车值。
在步骤102中，车辆根据当前速度与目标速度，可以得到第一加速度；容易理解的是，车辆需要进行速度调整时，通常会需要产生相应的加速度；因此，根据当前速度与目标速度，也可以确定出一加速度，该加速度可能是正值、负值或者是0。
举例来说，可以预设有一速度调整时间，将当前速度与目标速度的差值与该速度调整时间的比值作为第一加速度。当然，在另一些举例中，也可以是采用预先设置的其他类型的速度控制器，来根据当前速度与目标速度得到第一加速度。
而根据当前速度、当前油门刹车值以及预先确定的目标动力学模型，可以确定第二加速度。
对于目标动力学模型，可以记载有速度、加速度以及油门刹车值之间的对应关系。目标动力学模型可以是数据驱动型动力学模型或者解析动力学模型等，可以根据实际需要进行选择。
对于数据驱动型动力学模型，可以是通过数据表等方式进行表示；例如，在表格中记载有在特定速度与特定加速度下，对应的油门刹车值。例如，在速度为4m/s，加速度为-2m/s 2时，对应的油门刹车值为-35。
当然，容易理解的是，在数据驱动型动力学模型，由于速度、加速度以及油门刹车值这三个参数是具有对应关系的；在实际应用中，可以将任意两个参数作为已知量，来对第三个参数进行查询。比如，结合上文描述，可以已知当前速度与当前油门刹车值，根据数据驱动型动力学模型得到第二加速度。
对于解析动力学模型，可以是通过函数方程进行表示，例如，在一个函数方程中，可以将加速度作为应变量，将速度与油门刹车值作为自变量；进而可以根据该函数方程、当前速度以及当前油门刹车值，得到第二加速 度。
当然，与数据驱动型动力学模型类似地，在解析动力学模型中，基于函数方程，也可以在已知其中任两个参数的情况下，计算得到第三个参数。
在步骤103中，车辆根据第一加速度、第二加速度以及当前加速度，可以确定目标加速度。
具体来说，基于第二加速度与当前加速度，实际上可以表征环境扰动对车辆运动的影响。而第一加速度则可以认为是直接消除速度误差所需要的调节量。
换而言之，本实施例中，车辆根据第一加速度、第二加速度以及当前加速度，确定目标加速度，可以同时考虑到车辆运动参数调节的直接需求，以及环境扰动对车辆运动的影响。
在步骤104中，车辆可以根据目标加速度、当前速度以及目标动力学模型，确定目标油门刹车值。
如上文所示的，目标动力学模型可以记载有速度、加速度以及油门刹车值这三个参数之间的对应关系，在已知其中的两个参数的情况下，可以得到第三个参数。因此，在步骤104中，车辆在得到目标加速度与当前速度的情况下，可以得到目标油门刹车值。
目标油门刹车值在一定程度上可以认为是在一个控制周期中生成的控制量，可以用于对车辆的油门或者刹车等执行机构进行控制，以实现对车辆的运动过程的调整。
当然，在实际应用中，针对目标油门刹车值也可以进行进一步的处理，例如进行滤波或者限值等，以获得该控制周期中最终的控制量。
本实施例中，在一个控制周期内，可以在上述步骤102与步骤104中，对目标动力学模型进行了两次应用，在一定程度上可以认为使用了内模结构控制器，可以估计由于车辆行驶环境带来的不确定扰动。同时，在步骤102中，根据当前速度与目标速度，得到第一加速度，可以认为是采用了速度控制器，有助于使得车辆能够迅速进行速度调整以跟踪期望速度(对应目标速度)。
本申请实施例提供的车辆控制方法，在一个控制周期中，获取车辆的 当前速度、目标速度、当前加速度以及当前油门刹车值，根据当前速度与目标速度，确定第一加速度，根据当前速度、当前油门刹车值以及预先确定的目标动力学模型，确定第二加速度；根据第一加速度、第二加速度以及当前加速度确定目标加速度；并进一步根据目标加速度、当前速度以及目标动力学模型，确定目标油门刹车值。本实施例可以使得车辆能够迅速进行速度调整以跟踪期望速度，同时，考虑了车辆行驶环境带来的不确定扰动，有助于提升目标油门刹车值的合理性，提高车辆的控制效果。
在一个示例中，上述速度与加速度，可以认为是车辆的纵向速度与纵向加速度。当然，在一些场景下，横向速度与横向加速度可能较小，速度与加速度也可以是车辆整体的速度与加速度。为了简化说明，以下若无特别说明，涉及的速度、加速度等参数，可以认为是在车辆纵向上的参数。
在一个可能的实施例中，上述步骤101，在一个控制周期中，获取当前速度、目标速度以及当前油门刹车值之前，车辆控制方法还可以包括：
确定至少一个阶跃信号，每一阶跃信号均包括第一油门值、第一期望速度以及第一刹车值，阶跃信号用于指示车辆在第一运动阶段以第一油门值从静止加速至第一期望速度，并在第二运动阶段以第一刹车值从第一期望速度减速至静止；
分别获取每一阶跃信号对应的第一运动参数对应关系与第二运动参数对应关系，第一运动参数对应关系指示车辆在任一阶跃信息对应的第一运动阶段中，速度与加速度的对应关系；第二运动参数对应关系指示车辆在任一阶跃信息对应的第二运动阶段中，速度与加速度的对应关系；
根据阶跃信号对应的第一运动参数对应关系与第二运动参数对应关系，确定目标动力学模型。
在本实施例中，建立的目标动力学模型可以是上述的数据驱动型动力学模型。以下结合一个实际应用场景，来对上述目标动力学模型的建立过程进行说明。
该应用场景中，可以通过在道路笔直、路面平坦且几乎无风速影响的参考环境中，分别测量车速对油门和刹车的阶跃响应，建立基于数据驱动的纵向动力学模型。
假设不考虑车辆纵向动力学系统的内部结构，将整车当成黑箱，输入期望车速v x和油门/刹车值u，以车辆获得的加速度a为输出进行建模；建模结果如下：
a＝G(v x,u)       (1)
例如，输入阶跃信号“90,25,-50”，其中，“90”对应了上述的第一油门值，“25”对应了上述的第一期望速度，“-50”对应了上述的第一刹车值。
在阶跃信号“90,25,-50”的指示下，车辆将以90％的油门值起步加速至期望速度25m/s，随后以50％的刹车值刹车至车辆静止。记录此过程中的速度、加速度、油门开度以及刹车开度等关键信息。
容易理解的是，上述的加速过程，可以对应车辆的第一运动阶段；相应地，刹车过程，可以对应车辆的第二运动阶段。
此外，在其他阶跃信号下，可以重复上述过程，即可以以一定的间隔输入不同的阶跃信号油门-刹车-速度组合，采集车辆在阶跃信号下的加速减速信息(即对应加速度)。
参加图2，图2示出了在阶跃信号“90,25,-50”对应的第一运动阶段的第一运动参数对应关系。其中，图中的横坐标可以是速度，单位m/s；纵坐标可以是加速度，单位m/s 2。
从图2中可以看出，在油门刹车值为90的情况下，各个速度均对应有加速度，也就是存在油门刹车值-速度-加速度的对应关系。在实际应用中，油门刹车值可以存在多个，比如，在一个阶跃信号下，可以产生至少两个油门刹车值。由于每个油门刹车值下均具有如图2所示的运动参数对应关系。基于上述的对应关系，即可以建立目标动力学模型。
可见，本实施例中，基于阶跃信号来获取各个油门刹车值下的运动参数对应关系，可以比较方便地获取到较多的油门刹车值-速度-加速度的对应关系，进而可以比较高效地建立目标动力学模型。
继续参见图2，图2中存在两条曲线，其中一条曲线变化比较剧烈，可以用于反映采集的原始速度与原始加速度之间的对应关系，该曲线可以记为原始数据曲线。
然而，原始数据曲线中存在较大的毛刺，而且在加速换挡瞬间加速度会有较大回落，换挡完成后恢复正常。为了减少毛刺和换挡造成的突变对目标动力学模型的影响，可以针对原始数据曲线进行平滑处理。
具体来说，在一个可选的实施例中，上述根据阶跃信号对应的第一运动参数对应关系与第二运动参数对应关系，确定目标动力学模型，包括：
针对阶跃信号对应的第一运动参数对应关系与第二运动参数对应关系进行滤波和/或曲线拟合的处理；
根据处理后的第一运动参数对应关系与第二运动参数对应关系，确定目标动力学模型。
比如，针对图2中所示的原始数据曲线，可以采用均值滤波加曲线拟合的方式进行处理，进而得到图2中相对平滑的曲线，或者记为拟合数据曲线。
当然，对于原始数据曲线的平滑处理方式，也可以是采用的惯性滤波等方式，在进行曲线拟合时，可以采用五次曲线或者其他形式的曲线进行拟合。也就是说，针对原始数据曲线的处理方式，此处可以不作具体限定。
在一个示例中，结合图2中的拟合数据曲线，该曲线可以表征油门刹车值为90时，速度在0～25m/s范围内对应的加速度。类似地，以一定的速度间隔，例如按照0.4m/s的速度间隔，对拟合数据曲线进行离散化处理，依次建立其他已采集的油门刹车值-速度-加速度的对应关系，得到如图3所示的加粗的标识曲线。
其中，在图3中，X轴为速度，Y轴为油门刹车值，Z轴为加速度。
对于已采集油门刹车值的间隔区间内的数据，如图3中的箭头所指示的未加粗的曲线，可以是采用线性逼近的方法来得到。例如，通过线性逼近的方法，可以得到油门刹车值在-40到-45区间内未直接采集的线性化数据。
如此，可以建立比较完整的油门刹车值-速度-加速度一一对应关系，该对应关系可以通过上述a＝G(v x,u)进行表示。此时，在一般情况下，当输入速度和油门刹车值后，均可以得到一个对应的加速度。
此外，图3可以是在坐标系中对目标动力学模型的离散数据进行展示， 而在如下的表格中，可以对图3中的部分离散数据进行展示。在该表格中，表头行数据为速度，表头列数据为油门刹车值，中间数据为加速度。
Figure PCTCN2022079377-appb-000001
在一个示例中，目标动力学模型包括第一动力学模型与第二动力学模型；
其中，在第一动力学模型中，以速度与油门刹车值为输入，以加速度为输出；
在第二动力学模型中，以加速度与速度为输入，以油门刹车值为输出。
在上文中，a＝G(v x,u)可以对应的是第一动力学模型，即以速度和油门刹车值为输入，以加速度为输出。
而结合上述步骤104，还需要以加速度与速度为输入，以油门刹车值为输出。因此，本示例中，可以使得目标动力学模型进一步包括第二动力学模型。
结合一个具体应用场景，上述第二动力学模型，可以是a＝G(v x,u)的逆模型，可以记为：
u＝G -1(v x,a)          (2)
u＝G -1(v x,a)模型的建立和上述的a＝G(v x,u)模型的建立过程类似，图4示出了比较完整的逆模型离散数据，其中X轴为速度v x,，Y轴为加速度a，Z轴为油门刹车u。
此外，下表为图4中的部分离散数据，表头行数据为速度，表头列数据对应加速度，中间数据为油门刹车值。
Figure PCTCN2022079377-appb-000002
结合以上目标动力学模型的建立过程可见，本实施例中，通过阶跃信号的应用，可以较为方便地采集不同油门刹车值下，速度与加速度的对应关系，进而提高目标动力学模型的建立效率；而通过线性逼近的方式，可以实现离散数据的插值，通过较少的数据采集过程，可以获得较多的离散数据，从而有效提高目标动力学模型的运算性能。
为便于进一步理解本申请实施例中根据第一加速度、第二加速度以及当前加速度确定目标加速度，并基于目标加速度确定目标油门刹车值的过程，以下结合第一动力学模型a＝G(v x,u)与第二动力学模型u＝G -1(v x,a)，进行相关原理的说明。
一般导致车辆速度与期望速度(对应了目标速度)存在偏差的主要原因有两个：期望车速的变化和外界环境的扰动变化，当期望车速变大时，车辆需要补偿与车速方向相同的力F m以获得一定的加速度a使车速到达期望速度v d，同时为了保持在纵向方向上的受力平衡补偿环境扰动，驱动力F m实际上可以分为两部分，消除速度误差的驱动力部分F r和补偿扰动部分F d：
F m＝F r+F d                       (3)
根据牛顿第二定律以及建立的目标动力学模型，用车辆实际输出和模型输出的差表征环境扰动，则需补偿的扰动力F d：
F d＝m·G(u a,v c)-m·a c                   (4)
消除速度误差的驱动力部分F r，在一些应用场合下，可以简单地按照如下方式进行获取：
F d＝m·a d＝m·(v d–v c)/t                 (5)
m为车辆质量，同样的车辆自身质量在已建立的模型中已有体现，此处不引入质量。结合以上公式，车辆从v c加速到v d和克服环境干扰所需的油门刹车值为u：
u＝G -1((v d–v c)/t-m·a c+G(u a,v c),v c)      (6)
其中，在以上公式中，a c为当前加速度；a d为车辆期望加速度；t可理解为用于消除速度误差的期望时间，具体的数值可以是预设的；v c表示当前速度；u a为当前油门刹车值。
如上文所示的，在步骤102与步骤104中，对目标动力学模型进行了两次应用，一定程度上可以认为使用了内模结构控制器。图5示出了一种典型内模结构控制器的示意图。一般情况下，内模结构控制器为被控对象的冲击响应或者阶跃响应，而上文实施例中的第一动力学模型a＝G(v x,u)与第二动力学模型u＝G -1(v x,a)可以是基于车辆的阶跃响应建立的，可以满足内模结构控制器的此项要求。
图5中参考模型可以对应上述的速度控制器，内模控制器可以对应为第二动力学模型，模型输出可以对应第一动力学模型，被控对象可以是车辆的刹车或者油门。以下在图5所示的内模结构控制器的基础上，对本申请实施例提供的车辆控制方法进行说明。
在一个可选的实施例中，上述步骤103，根据第一加速度、第二加速度以及当前加速度确定目标加速度，包括：
针对第二加速度与当前加速度求差，得到第三加速度；
针对第三加速度与预设的反馈系数相乘，得到第四加速度；
针对第四加速度进行滤波，得到补偿加速度；
根据第一加速度与补偿加速度，确定目标加速度。
容易理解的是，内模结构控制器在一定程度可以认为是一种闭环控制；而在第一加速度确定过程中，也应用到了速度控制器，也可以认为是一种闭环控制。为了便于区分，可以将内模结构控制器对应的闭环简称为内环，将速度控制器对应的闭环简称为外环。
第二加速度可以认为是上述的第一动力学模型的输出，相应地，补偿加速度可以是第一动力学模型的输出和车辆实际加速度之差与反馈系数k 相乘，然后经过滤波器滤波得到。为了和其他可能采用到的滤波器进行区别，此处的滤波器可以称为反馈滤波器。在一些可能的实施方式中，反馈滤波器可以是惯性滤波器或者递归滤波器等，此处不做具体限定。
第一加速度可以是认为是上述外环的输出，第一加速度与补偿加速度相加可以得到目标加速度。
补偿加速度与第一加速度的获取，在一定程度上可以分别与式(4)与式(5)对应；而本实施例中，补偿加速度的确定过程，考虑了预设的反馈系数以及滤波的过程。
以上内模结构控制器与速度控制器可以整体作为车辆控制器的组成部分。通过合理地设置反馈系数，有助于减小车辆控制器振荡发散的可能，提高车辆控制的稳定性；而通过反馈滤波器进行滤波，可以平滑估计的扰动，减少扰动对控制量输出的振荡；反馈滤波器和反馈系数的应用可以共同保证内环的稳定性。
而为了更好地理解应用有反馈滤波器和反馈系数的内环，可以进一步参考图6。纵向参数化逆模型对应了上述的第二动力学模型，参数化参考模型对应了上述的第一动力学模型，第一动力学模型的输出与当前加速度求差后，可以乘以反馈系数，并进一步输入到反馈滤波器中，输出补偿加速度。
容易理解的是，在实际应用中，根据第一加速度、第二加速度以及当前加速度确定目标加速度的过程，除了可以是使用上文提及的方法，还可以是根据实际需要而作出的等效修改或替换，例如对反馈系数进行省略，或者是对为其中的一个或多个加速度参数增加计算权重等，此处不做一一列举。
在一个示例中，针对第四加速度进行滤波，得到补偿加速度，包括：
采用第一惯性滤波器对第四加速度进行滤波，得到补偿加速度；
其中，第一惯性滤波器的滤波器系数与速度误差反相关，速度误差为目标速度与当前速度之间差值的绝对值。
对于第一惯性滤波器，可以是一阶惯性滤波器，也可以是二阶惯性滤波器等等。为了简化描述，以下主要以第一惯性滤波器为一阶惯性滤波器 为例进行说明。
一阶惯性滤波器G b(s)一般可以通过下式进行表示：
Figure PCTCN2022079377-appb-000003
其中，α为一阶惯性滤波器的滤波器系数，s为拉普拉斯算子。本实施例中，α的值可以是可调的。
具体来说，滤波器系数α体现了速度跟踪控制的舒适性和快速性：如果系数α较小，滤波器带宽较大，高频扰动信号能够通过滤波器，速度跟踪控制的快速性得到保证，但是舒适性下降；反之，若系数α较大，滤波器带宽变小，高频信号被过滤，车辆的加、减速相对变慢，速度跟踪控制的舒适性得到保证，但是牺牲了快速性。
为了兼顾速度跟踪控制的快速性和舒适性，滤波器系数α根据以下逻辑自适应的调整：当速度误差较大时，α取较小的值；当速度误差较小时，α取较大的值。也就是说，第一惯性滤波器的滤波器系数可以是与目标速度与当前速度之间差值的绝对值反相关的。
可选地，上述步骤102，根据当前速度与目标速度，确定第一加速度，包括：
将当前速度与目标速度输入至PID控制器，输出第一加速度。
换而言之，本实施例中，上述的外环中的速度控制器，可以是PID控制器。
外环速度PID控制器输入可以上游规划模块的车辆期望速度(即目标速度)和反馈得到的实际速度(即当前速度)，输出为PID控制率。
若只考虑比例控制，式(6)中的时间参数t可以认为是比例项参数。也就是说，这里的PID控制器可以是一种上位的概念，在实际应用中，可以是简单的比例控制，也可以是比例积分控制或者比例积分微分控制等，具体可根据需要进行选择。
可见，本实施例中，车辆控制方法可以采用外环PID控制环加内环内模结构控制环的控制器实现车辆速度跟踪，外环PID环在期望速度变化时车辆能迅速调整以跟踪期望速度，内环内模结构用于评估模型失配和环境扰动对车辆的影响，同时一阶惯性滤波器对反馈的平滑让车辆在跟踪期望 速度时兼顾舒适性和快速性。
可选地，参见图6，上述步骤104，根据目标加速度、当前速度以及目标动力学模型，确定目标油门刹车值之后，车辆控制方法还包括：
针对目标油门刹车值进行滤波，得到油门刹车控制指令，油门刹车控制指令用于控制车辆的油门或刹车。
本实施例中，可以使用滤波器对目标油门刹车值进行滤波，为示区别，此处的滤波器可以称为前馈滤波器。在一些应用场景下，前馈滤波器可以是惯性滤波器或者递归滤波器等，此处不做具体限定。
容易理解的是，对于油门刹车控制指令，最终可以作用到例如油门或者刹车等类型的执行机构上。另外，油门刹车控制指令，可以携带有相应的控制参数值，以使得油门或者刹车能够按照期望的方式进行动作；而这些控制参数值，可以是基于上述的目标油门刹车值得到的。
通过对目标油门刹车值进行滤波，可以对目标油门刹车值进行平滑，减少对执行机构的损害。
当然，一些可行的实施方式中，在遇到紧急情况下，也可以省略对目标油门刹车值的滤波过程。例如，车辆在行驶过程中，需要紧急避让障碍物时，可能会产生紧急刹车指令，在这种情况下，可以省略目标油门刹车值的滤波过程，使得刹车等执行机构能够迅速响应，提高车辆的安全性。
在一个示例中，针对目标油门刹车值进行滤波，得到油门刹车控制指令，包括：
采用第二惯性滤波器对目标油门刹车值进行滤波，得到油门刹车控制指令；
其中，第二惯性滤波器的滤波器系数与速度误差反相关，速度误差为目标速度与当前速度之间差值的绝对值。
第二惯性滤波器与第一惯性滤波器类似，可以是一阶惯性滤波器，也可以是二阶惯性滤波器等等，可以根据实际需要进行选择。
设第二惯性滤波器记为G f(s)，且第二惯性滤波器为一阶惯性滤波器，则第二惯性滤波器可以通过下式进行表示：
Figure PCTCN2022079377-appb-000004
其中，β为一阶惯性滤波器的滤波器系数，s为拉普拉斯算子。本实施例中，β的值可以是可调的。
前馈系数β的调整和反馈系数α类似，当速度误差较大时，β取较小的值，以保证快速性；当速度误差较小时，β取较大的值，以保证舒适性。
换而言之，第二惯性滤波器的滤波器系数可以是与目标速度与当前速度之间差值的绝对值反相关的，如此，有助于平衡车辆控制的舒适性和快速性。
针对目标油门刹车值进行滤波，得到油门刹车控制指令，还可以包括：
针对目标油门刹车值进行滤波，得到初始控制量；
按照预设数值范围对初始控制量进行限幅，得到油门刹车控制指令。
距离来说，预设数值范围可以是[-95,95]，对应了刹车踏板开度不大于95％，油门踏板开度不大于95％。当初始控制量指示所需的刹车踏板开度为99％时，可以对初始控制量进行限幅，使得得到的油门刹车控制指令指示将刹车踏板开度调整为95％。
本实施例中，通过设置预设数值范围，可以起到对执行机构的冗余保护作用，有效避免执行机构因过度调整而产生损害。
当然，在一定应用场景下，比如在车辆正常行驶过程中，通过设置预设数值范围，可以减少因刹车或油门过度调整而导致的加速度突变，提高车辆的舒适性。
以下结合一些实际应用场景，对本申请实施例提供的车辆控制方法进行介绍：
参见图7，图7示出了上述目标动力学模型的建立流程图，包括：
步骤701，车辆阶跃响应数据采集；
即对应了在不同的阶跃信号的指导下，车辆的速度、加速度及其对应关系等数据的采集；
步骤702，采集数据处理；
这里的采集数据处理，可以是指上文实施例中提到的对原始数据曲线的均值滤波与曲线拟合处理、离散化处理以及线性逼近以得到未通过直接采集得到的离散数据等；
步骤703，建立数据驱动型动力学模型；
本步骤相当于上文建立第一动力学模型的步骤；
步骤704，建立数据驱动型动力学逆模型；
本步骤相当于上文建立第二动力学模型的步骤。
参见图8，图8示出了在目标动力学模型建立的情况下，车辆控制的流程图，包括：
步骤801，查找匹配的轨迹点；
这里的轨迹点，可以是从上游规划模块中获取的。
其中，规划模块可以针对车辆的路径或速度进行规划；相应地，规划模块的输出结果中，可以包括速度规划曲线，轨迹点可以是速度规划曲线中的点。
步骤802，坐标转换；
本步骤可以将轨迹点在笛卡尔坐标系(例如世界坐标系)的规划速度矢量，转换至frenet坐标系中，进而可以有助于进一步对规划速度分解得到纵向速度与横向速度；
一般情况下，可以使用上述分解得到的纵向速度作为期望速度，或者说作为目标速度。
步骤803，计算纵向速度误差；
即计算目标速度与当前速度之间的差值；
步骤804，速度环控制量计算；
速度环即上文中速度控制器对应的闭环，亦可以称为外环；速度环输出的控制量，可以是上述的第一加速度。
步骤805，内模控制量计算；
这里的内模控制量，可以是加速度；相应地，内模控制量的计算，可以认为是根据第一加速度与补偿加速度确定目标加速度的计算。
步骤806，参数化动力学逆模型插值；
参数化动力学逆模型可以对应上述的第二动力学模型，输入为速度和加速度，输出为油门刹车值；
具体在本步骤中，参数化动力学逆模型插值，可以是将目标加速度与 当前速度作为输入，基于参数化动力学逆模型进行插值计算，输出目标油门刹车值。
步骤807，滤波、限幅；
本步骤中，可以对上述的目标油门刹车值进行滤波与限幅。其中，此处的滤波可以对应上文中提到的前馈滤波器的滤波过程，滤波得到的结果对应为初始控制量；通过对初始控制量进行限幅，可以将油门量(比如油门踏板开度)或者刹车量(比如刹车踏板开度)限制在一定范围内，起到对执行机构的冗余保护作用。
在对初始控制量进行限幅处理后，可以得到上述的油门刹车控制指令。一般情况下，该油门刹车控制指令可以包括在一个控制周期中最终作用在执行机构上的控制参数。例如，该油门刹车控制指令指示将油门踏板开度调整为60％时，在该控制周期中，可以将油门踏板的开度调整为60％。
本申请实施例提供的车辆控制方法，针对多种行驶环境(高速、园区、矿区等)带来的不确定性扰动，提出了一种使用内模结构来估计扰动的方法，并根据该方法设计了一种PID控制+内模结构控制的双闭环控制器；具体来说，外环可以是一个PID控制器，内环可以是一个内模结构控制器，用来估计由于模型偏差和行驶环境带来的不确定性扰动。以上控制器的组合，结构比较简单，对处理器算力无特殊需求，能够适应多种环境、具有较好的舒适性、并对较大范围的期望速度和速度误差具有较好的精度和适应性。
如图9所示，本申请实施例还提供了一种车辆控制装置，该装置包括：
第一获取模块901，用于在一个控制周期中，获取车辆的当前速度、目标速度、当前加速度以及当前油门刹车值；
第一确定模块902，用于根据当前速度与目标速度，确定第一加速度；根据当前速度、当前油门刹车值以及预先确定的目标动力学模型，确定第二加速度；其中，目标动力学模型记载有速度、加速度以及油门刹车值之间的对应关系；
第二确定模块903，用于根据第一加速度、第二加速度以及当前加速度确定目标加速度；
第三确定模块904，用于根据目标加速度、当前速度以及目标动力学模型，确定目标油门刹车值，目标油门刹车值用于对车辆的执行机构进行控制。
可选地，上述第二确定模块903，可以包括：
第一获取单元，用于针对第二加速度与当前加速度求差，得到第三加速度；
第二获取单元，用于针对第三加速度与预设的反馈系数相乘，得到第四加速度；
第一滤波单元，用于针对第四加速度进行滤波，得到补偿加速度；
第一确定单元，用于根据第一加速度与补偿加速度，确定目标加速度。
可选地，上述第一滤波单元，可以具体用于：
采用第一惯性滤波器对第四加速度进行滤波，得到补偿加速度；
其中，第一惯性滤波器的滤波器系数与速度误差反相关，速度误差为目标速度与当前速度之间差值的绝对值。
可选地，上述第一确定模块902，可以具体用于：
将当前速度与目标速度输入至PID控制器，输出第一加速度。
可选地，车辆控制装置还可以包括：
滤波模块，用于针对目标油门刹车值进行滤波，得到油门刹车控制指令，油门刹车控制指令用于控制车辆的油门或刹车。
可选地，滤波模块可以具体用于：
采用第二惯性滤波器对目标油门刹车值进行滤波，得到油门刹车控制指令；
其中，第二惯性滤波器的滤波器系数与速度误差反相关，速度误差为目标速度与当前速度之间差值的绝对值。
可选地，上述滤波模块，可以包括：
第二滤波单元，用于针对目标油门刹车值进行滤波，得到初始控制量；
第三获取单元，用于按照预设数值范围对初始控制量进行限幅，得到油门刹车控制指令。
可选地，上述车辆控制装置，还可以包括：
第四确定模块，用于确定至少一个阶跃信号，每一阶跃信号均包括第一油门值、第一期望速度以及第一刹车值，阶跃信号用于指示车辆在第一运动阶段以第一油门值从静止加速至第一期望速度，并在第二运动阶段以第一刹车值从第一期望速度减速至静止；
第二获取模块，用于分别获取每一阶跃信号对应的第一运动参数对应关系与第二运动参数对应关系，第一运动参数对应关系指示车辆在任一阶跃信息对应的第一运动阶段中，速度与加速度的对应关系；第二运动参数对应关系指示车辆在任一阶跃信息对应的第二运动阶段中，速度与加速度的对应关系；
第五确定模块，用于根据阶跃信号对应的第一运动参数对应关系与第二运动参数对应关系，确定目标动力学模型。
可选地，第五确定模块，可以包括：
处理单元，用于针对阶跃信号对应的第一运动参数对应关系与第二运动参数对应关系进行滤波和/或曲线拟合的处理；
第二确定单元，用于根据处理后的第一运动参数对应关系与第二运动参数对应关系，确定目标动力学模型。
可选地，目标动力学模型包括第一动力学模型与第二动力学模型；
其中，在第一动力学模型中，以速度与油门刹车值为输入，以加速度为输出；
在第二动力学模型中，以加速度与速度为输入，以油门刹车值为输出。
需要说明的是，该车辆控制装置是与上述车辆控制方法对应的装置，上述方法实施例中所有实现方式均适用于该装置的实施例中，也能达到相同的技术效果。
图10示出了本申请实施例提供的电子设备的硬件结构示意图。
在电子设备可以包括处理器1001以及存储有计算机程序指令的存储器1002。
具体地，上述处理器1001可以包括中央处理器(CPU)，或者特定集成电路(Application Specific Integrated Circuit，ASIC)，或者可以被配置成实施本申请实施例的一个或多个集成电路。
存储器1002可以包括用于数据或指令的大容量存储器。举例来说而非限制，存储器1002可包括硬盘驱动器(Hard Disk Drive，HDD)、软盘驱动器、闪存、光盘、磁光盘、磁带或通用串行总线(Universal Serial Bus，USB)驱动器或者两个或更多个以上这些的组合。在合适的情况下，存储器1002可包括可移除或不可移除(或固定)的介质。在合适的情况下，存储器1002可在综合网关容灾设备的内部或外部。在特定实施例中，存储器1002是非易失性固态存储器。
存储器可包括只读存储器(ROM)，随机存取存储器(RAM)，磁盘存储介质设备，光存储介质设备，闪存设备，电气、光学或其他物理/有形的存储器存储设备。因此，通常，存储器包括一个或多个编码有包括计算机可执行指令的软件的有形(非暂态)计算机可读存储介质(例如，存储器设备)，并且当该软件被执行(例如，由一个或多个处理器)时，其可操作来执行参考根据本公开的方法所描述的操作。
处理器1001通过读取并执行存储器1002中存储的计算机程序指令，以实现上述实施例中的任意一种车辆控制方法。
在一个示例中，电子设备还可包括通信接口1003和总线1004。其中，如图10所示，处理器1001、存储器1002、通信接口1003通过总线1004连接并完成相互间的通信。
通信接口1003，主要用于实现本申请实施例中各模块、装置、单元和/或设备之间的通信。
总线1004包括硬件、软件或两者，将在线数据流量计费设备的部件彼此耦接在一起。举例来说而非限制，总线可包括加速图形端口(AGP)或其他图形总线、增强工业标准架构(EISA)总线、前端总线(FSB)、超传输(HT)互连、工业标准架构(ISA)总线、无限带宽互连、低引脚数(LPC)总线、存储器总线、微信道架构(MCA)总线、外围组件互连(PCI)总线、PCI-Express(PCI-X)总线、串行高级技术附件(SATA)总线、视频电子标准协会局部(VLB)总线或其他合适的总线或者两个或更多个以上这些的组合。在合适的情况下，总线1004可包括一个或多个总线。尽管本申请实施例描述和示出了特定的总线，但本申请考虑任何合适 的总线或互连。
根据本申请的实施例，电子设备可以是移动电子设备，也可以为非移动电子设备。示例性的，移动电子设备可以为手机、平板电脑、笔记本电脑、掌上电脑或者车载电子设备等，非移动电子设备可以为服务器等。
另外，结合上述实施例中的车辆控制方法，本申请实施例可提供一种计算机存储介质来实现。该计算机存储介质上存储有计算机程序指令；该计算机程序指令被处理器执行时实现上述实施例中的任意一种车辆控制方法。计算机存储介质的示例包括物理/有形的存储介质，如电子电路、半导体存储器设备、ROM、闪存、可擦除ROM(EROM)、软盘、CD-ROM、光盘、硬盘等。
本申请实施例还提供一种计算机程序产品，所述计算机程序产品可被处理器执行以实现上述车辆控制方法实施例的各个过程，且能达到相同的技术效果，为避免重复，这里不再赘述。
本申请实施例另提供了一种芯片，芯片包括处理器和通信接口，通信接口和处理器耦合，处理器用于运行程序或指令，实现上述车辆控制方法实施例的各个过程，且能达到相同的技术效果，为避免重复，这里不再赘述。
应理解，本申请实施例提到的芯片还可以称为系统级芯片、系统芯片、芯片系统或片上系统芯片等。
需要明确的是，本申请并不局限于上文所描述并在图中示出的特定配置和处理。为了简明起见，这里省略了对已知方法的详细描述。在上述实施例中，描述和示出了若干具体的步骤作为示例。但是，本申请的方法过程并不限于所描述和示出的具体步骤，本领域的技术人员可以在领会本申请的精神后，作出各种改变、修改和添加，或者改变步骤之间的顺序。
以上所述的结构框图中所示的功能块可以实现为硬件、软件、固件或者它们的组合。当以硬件方式实现时，其可以例如是电子电路、专用集成电路(ASIC)、适当的固件、插件、功能卡等等。当以软件方式实现时，本申请的元素是被用于执行所需任务的程序或者代码段。程序或者代码段可以存储在机器可读介质中，或者通过载波中携带的数据信号在传输介质 或者通信链路上传送。“机器可读介质”可以包括能够存储或传输信息的任何介质。机器可读介质的例子包括电子电路、半导体存储器设备、ROM、闪存、可擦除ROM(EROM)、软盘、CD-ROM、光盘、硬盘、光纤介质、射频(RF)链路，等等。代码段可以经由诸如因特网、内联网等的计算机网络被下载。
还需要说明的是，本申请中提及的示例性实施例，基于一系列的步骤或者装置描述一些方法或系统。但是，本申请不局限于上述步骤的顺序，也就是说，可以按照实施例中提及的顺序执行步骤，也可以不同于实施例中的顺序，或者若干步骤同时执行。
上面参考根据本公开的实施例的方法、装置(系统)和计算机程序产品的流程图和/或框图描述了本公开的各方面。应当理解，流程图和/或框图中的每个方框以及流程图和/或框图中各方框的组合可以由计算机程序指令实现。这些计算机程序指令可被提供给通用计算机、专用计算机、或其它可编程数据处理装置的处理器，以产生一种机器，使得经由计算机或其它可编程数据处理装置的处理器执行的这些指令使能对流程图和/或框图的一个或多个方框中指定的功能/动作的实现。这种处理器可以是但不限于是通用处理器、专用处理器、特殊应用处理器或者现场可编程逻辑电路。还可理解，框图和/或流程图中的每个方框以及框图和/或流程图中的方框的组合，也可以由执行指定的功能或动作的专用硬件来实现，或可由专用硬件和计算机指令的组合来实现。
以上所述，仅为本申请的具体实施方式，所属领域的技术人员可以清楚地了解到，为了描述的方便和简洁，上述描述的系统、模块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。应理解，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，可轻易想到各种等效的修改或替换，这些修改或替换都应涵盖在本申请的保护范围之内。

Claims (15)

  1. 一种车辆控制方法，包括：
    在一个控制周期中，获取车辆的当前速度、目标速度、当前加速度以及当前油门刹车值；
    根据所述当前速度与所述目标速度，确定第一加速度；根据所述当前速度、所述当前油门刹车值以及预先确定的目标动力学模型，确定第二加速度；其中，所述目标动力学模型记载有速度、加速度以及油门刹车值之间的对应关系；
    根据所述第一加速度、所述第二加速度以及所述当前加速度确定目标加速度；
    根据所述目标加速度、所述当前速度以及所述目标动力学模型，确定目标油门刹车值，所述目标油门刹车值用于对车辆的执行机构进行控制。
  2. 根据权利要求1所述的方法，其中，所述根据所述第一加速度、所述第二加速度以及所述当前加速度确定目标加速度，包括：
    针对所述第二加速度与所述当前加速度求差，得到第三加速度；
    针对所述第三加速度与预设的反馈系数相乘，得到第四加速度；
    针对所述第四加速度进行滤波，得到补偿加速度；
    根据所述第一加速度与所述补偿加速度，确定所述目标加速度。
  3. 根据权利要求2所述的方法，其中，所述针对所述第四加速度进行滤波，得到补偿加速度，包括：
    采用第一惯性滤波器对所述第四加速度进行滤波，得到所述补偿加速度；
    其中，所述第一惯性滤波器的滤波器系数与速度误差反相关，所述速度误差为所述目标速度与所述当前速度之间差值的绝对值。
  4. 根据权利要求1所述的方法，其中，所述根据所述当前速度与所述目标速度，确定第一加速度，包括：
    将所述当前速度与所述目标速度输入至PID控制器，输出所述第一加 速度。
  5. 根据权利要求1所述的方法，其中，所述根据所述目标加速度、所述当前速度以及所述目标动力学模型，确定目标油门刹车值之后，所述方法还包括：
    针对所述目标油门刹车值进行滤波，得到油门刹车控制指令，所述油门刹车控制指令用于控制车辆的油门或刹车。
  6. 根据权利要求5所述的方法，其中，所述针对所述目标油门刹车值进行滤波，得到油门刹车控制指令，包括：
    采用第二惯性滤波器对所述目标油门刹车值进行滤波，得到所述油门刹车控制指令；
    其中，所述第二惯性滤波器的滤波器系数与速度误差反相关，所述速度误差为所述目标速度与所述当前速度之间差值的绝对值。
  7. 根据权利要求5所述的方法，其中，所述针对所述目标油门刹车值进行滤波，得到油门刹车控制指令，还包括：
    针对所述目标油门刹车值进行滤波，得到初始控制量；
    按照预设数值范围对所述初始控制量进行限幅，得到所述油门刹车控制指令。
  8. 根据权利要求1所述的方法，其中，所述在一个控制周期中，获取当前速度、目标速度以及当前油门刹车值之前，所述方法还包括：
    确定至少一个阶跃信号，每一所述阶跃信号均包括第一油门值、第一期望速度以及第一刹车值，所述阶跃信号用于指示车辆在第一运动阶段以所述第一油门值从静止加速至所述第一期望速度，并在第二运动阶段以所述第一刹车值从所述第一期望速度减速至静止；
    分别获取每一所述阶跃信号对应的第一运动参数对应关系与第二运动参数对应关系，所述第一运动参数对应关系指示车辆在任一阶跃信息对应的第一运动阶段中，速度与加速度的对应关系；所述第二运动参数对应关系指示车辆在任一阶跃信息对应的第二运动阶段中，速度与加速度的对应 关系；
    根据所述阶跃信号对应的第一运动参数对应关系与第二运动参数对应关系，确定所述目标动力学模型。
  9. 根据权利要求8所述的方法，其中，所述根据所述阶跃信号对应的第一运动参数对应关系与第二运动参数对应关系，确定所述目标动力学模型，包括：
    针对所述阶跃信号对应的第一运动参数对应关系与第二运动参数对应关系进行滤波和/或曲线拟合的处理；
    根据处理后的所述第一运动参数对应关系与所述第二运动参数对应关系，确定所述目标动力学模型。
  10. 根据权利要求8所述的方法，其中，所述目标动力学模型包括第一动力学模型与第二动力学模型；
    其中，在所述第一动力学模型中，以速度与油门刹车值为输入，以加速度为输出；
    在所述第二动力学模型中，以加速度与速度为输入，以油门刹车值为输出。
  11. 一种车辆控制装置，所述装置包括：
    第一获取模块，用于在一个控制周期中，获取车辆的当前速度、目标速度、当前加速度以及当前油门刹车值；
    第一确定模块，用于根据所述当前速度与所述目标速度，确定第一加速度；根据所述当前速度、所述当前油门刹车值以及预先确定的目标动力学模型，确定第二加速度；其中，所述目标动力学模型记载有速度、加速度以及油门刹车值之间的对应关系；
    第二确定模块，用于根据所述第一加速度、所述第二加速度以及所述当前加速度确定目标加速度；
    第三确定模块，用于根据所述目标加速度、所述当前速度以及所述目标动力学模型，确定目标油门刹车值，所述目标油门刹车值用于对车辆的执行机构进行控制。
  12. 一种电子设备，所述设备包括：处理器以及存储有计算机程序指令的存储器；
    所述处理器执行所述计算机程序指令时实现如权利要求1-10任意一项所述的车辆控制方法。
  13. 一种计算机存储介质，所述计算机存储介质上存储有计算机程序指令，所述计算机程序指令被处理器执行时实现如权利要求1-10任意一项所述的车辆控制方法。
  14. 一种计算机程序产品，所述计算机程序产品可被处理器执行以实现如权利要求1-10任意一项所述的车辆控制方法。
  15. 一种芯片，所述芯片包括处理器和通信接口，提供的通信接口和提供的处理器耦合，提供的处理器用于运行程序或指令，实现如权利要求1-10任意一项所述的车辆控制方法。
PCT/CN2022/079377 2021-03-08 2022-03-04 车辆控制方法、装置、设备及计算机存储介质 WO2022188716A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202110251342.0A CN115056797A (zh) 2021-03-08 2021-03-08 车辆控制方法、装置、设备及计算机存储介质
CN202110251342.0 2021-03-08

Publications (1)

Publication Number Publication Date
WO2022188716A1 true WO2022188716A1 (zh) 2022-09-15

Family

ID=83196872

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2022/079377 WO2022188716A1 (zh) 2021-03-08 2022-03-04 车辆控制方法、装置、设备及计算机存储介质

Country Status (2)

Country Link
CN (1) CN115056797A (zh)
WO (1) WO2022188716A1 (zh)

Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2013006485A (ja) * 2011-06-23 2013-01-10 Nissan Motor Co Ltd 走行支援装置及び走行支援方法
CN109204310A (zh) * 2017-06-29 2019-01-15 上海汽车集团股份有限公司 车辆动力控制方法及装置
CN109606366A (zh) * 2018-12-29 2019-04-12 百度在线网络技术（北京）有限公司 用于控制车辆的方法和装置
CN109747651A (zh) * 2018-12-27 2019-05-14 东软睿驰汽车技术（沈阳）有限公司 一种车辆控制方法、装置及系统
CN110857670A (zh) * 2018-08-24 2020-03-03 广州汽车集团股份有限公司 一种汽车驱动力控制方法及电子设备
CN111661060A (zh) * 2019-03-05 2020-09-15 阿里巴巴集团控股有限公司 建立车辆纵向运动模型的方法、装置及计算机系统
CN112046503A (zh) * 2020-09-17 2020-12-08 腾讯科技（深圳）有限公司 一种基于人工智能的车辆控制方法、相关装置及存储介质

Patent Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2013006485A (ja) * 2011-06-23 2013-01-10 Nissan Motor Co Ltd 走行支援装置及び走行支援方法
CN109204310A (zh) * 2017-06-29 2019-01-15 上海汽车集团股份有限公司 车辆动力控制方法及装置
CN110857670A (zh) * 2018-08-24 2020-03-03 广州汽车集团股份有限公司 一种汽车驱动力控制方法及电子设备
CN109747651A (zh) * 2018-12-27 2019-05-14 东软睿驰汽车技术（沈阳）有限公司 一种车辆控制方法、装置及系统
CN109606366A (zh) * 2018-12-29 2019-04-12 百度在线网络技术（北京）有限公司 用于控制车辆的方法和装置
CN111661060A (zh) * 2019-03-05 2020-09-15 阿里巴巴集团控股有限公司 建立车辆纵向运动模型的方法、装置及计算机系统
CN112046503A (zh) * 2020-09-17 2020-12-08 腾讯科技（深圳）有限公司 一种基于人工智能的车辆控制方法、相关装置及存储介质

Also Published As

Publication number Publication date
CN115056797A (zh) 2022-09-16

Similar Documents

Publication Publication Date Title
Persson et al. Stop and go controller for adaptive cruise control
CN104247252B (zh) 车辆用减振控制装置以及车辆用减振控制方法
Wang et al. Multirate estimation and control of body slip angle for electric vehicles based on onboard vision system
CN110626342B (zh) 车间距离控制装置
CN104718103A (zh) 电动车辆的电动机控制装置
CN111123701B (zh) 基于管道预测模型的自动驾驶路径跟踪抗干扰控制方法
CN110116730B (zh) 一种车辆制动控制方法、系统、设备和介质
US20200385005A1 (en) Bend control optimization method and system
Li et al. Velocity tracking control based on throttle-pedal-moving data mapping for the autonomous vehicle
WO2022188716A1 (zh) 车辆控制方法、装置、设备及计算机存储介质
CN117170228A (zh) 面向虚拟编组高速列车间隔控制的自适应滑模控制方法
Lu et al. Nonlinear longitudinal controller implementation and comparison for automated cars
CN116118822B (zh) 一种列车编组运行时的主动避碰控制方法、系统及介质
JP6720714B2 (ja) 電動車両の制御方法、及び電動車両の制御装置
WO2023241050A1 (zh) 车辆横向控制方法、系统及车辆
JP6191777B2 (ja) 電動車両の制御装置および電動車両の制御方法
Mizutani et al. Vehicle speed control by a robotic driver considering time delay and parametric variations
CN113715820B (zh) 一种基于速度补偿pid的车辆速度控制方法及装置
Nakonechnyi et al. Investigation of the control law influence on the dynamic characteristics of vehicle movement control system model
Bingöl et al. String stability under actuator saturation on straight level roads: sufficient conditions and optimal trajectory generation
Bachache et al. The Steering Actuator System to Improve Driving of Autonomous Vehicles based on Multi-Sensor Data Fusion
Villagra et al. Robust grey-box closed-loop stop-and-go control
CN114194153B (zh) 一种无人机车对位控制方法及装置
CN115837899B (zh) 动车组制动系统的多模型自适应故障补偿控制方法及系统
Ayyıldız et al. Adaptive sliding mode control of mobile robot and comparison with PID controller

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: 22766241

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: 22766241

Country of ref document: EP

Kind code of ref document: A1