JP2022538275A - Parameter arrangement method and device, electronic device and storage medium - Google Patents

Abstract

The present invention relates to a parameter allocation method and device, electronic equipment, and storage media. The method is applied to a smart device including a controller, the controller includes a first controller and a second controller, the method comprises obtaining control data output from the controller, a step in which control data output from one controller includes first control data and control data output from the second controller includes second control data; and based on the first control data and the second control data , locating the parameters of the second controller. [Selection drawing] Fig. 1

Description

TECHNICAL FIELD The present invention relates to the field of computer technology, and more particularly to a parameter placement method and apparatus, electronic equipment, and storage media.

With the development of self-driving technology, more and more academic institutions and technology companies are beginning to be involved in the research and development of self-driving technology. Among them, controllers are attracting more and more attention as indispensable modules for autonomous driving systems. How to assign parameters to controllers accurately, efficiently, at low cost, and safely has become a problem to be solved urgently.

The present invention provides technical solutions for parameter allocation.

One aspect of the present invention provides a parameter placement method. The parameter arrangement method is applied to a smart device including a plurality of controllers, the plurality of controllers includes at least a first controller and a second controller, and the parameter arrangement method is output from each of the plurality of controllers. a step of acquiring control data output from the first controller, wherein the control data output from the first controller includes first control data, and the control data output from the second controller includes second control data; arranging parameters of the second controller based on the first control data and the second control data.

acquiring control data output from each of a plurality of controllers of a smart device (wherein the plurality of controllers includes a first controller and a second controller, and the control data output from the first controller is 1 control data, and the control data output from the second controller includes second control data), arranging the parameters of the second controller based on the first control data and the second control data By doing so, the first controller is the reference controller and the second controller is the controller to be adjusted, and reliable parameters are found for the second controller accurately, effectively and at low cost. This can reduce the risk of runaway of the smart device (e.g., vehicle) when further adjusting parameters for the second controller later, and potential traffic accidents due to improper parameter allocation of the second controller. safety risks can be reduced.

In one possible implementation, the step of obtaining control data output from each of the plurality of controllers obtains first reference trajectory data and first state data of the smart device in a first mode. and generating the respective control data based on the first reference trajectory data and the first state data via the plurality of controllers.

In this implementation method, the control data is generated based on the first reference trajectory data and the first state data via the controller, and a second controller is generated based on the generated first control data and second control data. By arranging the parameters of , the parameters of the second controller obtained by arranging can be more applied to the real scene.

In one possible implementation, the parameter configuration method further comprises controlling driving of the smart device in a first mode based on the first control data.

According to the implementation method, by controlling the running of the smart device in the first mode based on the first control data, parameters can be arranged for the second controller in the actual vehicle. It is possible to reduce the cost of debugging the controller by switching back and forth between the controller and the actual vehicle, and the second controller after parameter allocation can be more applied to the actual scene.

In one possible implementation, the parameter placement method comprises obtaining second reference trajectory data and second state data of the smart device in a first mode; generating third control data based on the second reference trajectory data and the second state data;

further comprising controlling driving of the smart device in a first mode based on the third control data.

According to the implementation method, by controlling the running of the smart device in the first mode based on the third control data, it is possible to perform parameter adjustment for the second controller in the actual vehicle. It is possible to reduce the cost of debugging the controller by switching back and forth between the controller and the actual vehicle, and the second controller after parameter adjustment can be more applied to the actual scene.

In one possible implementation, the parameter configuration method comprises the steps of obtaining actual trajectory data generated by the smart device in the first mode while driving; and adjusting parameters of the second controller.

In this implementation method, by adjusting the parameters of the second controller based on the difference between the actual trajectory data and the second reference trajectory data, the second controller can be more accurately adapted to the smart device. , to achieve more precise control and a safer and more comfortable driving experience.

In one possible implementation, the first controller is a controller that does not include a vehicle dynamics model and the second controller is a controller that includes a vehicle dynamics model.

According to the above implementation scheme, the controller without the vehicle dynamics model is the reference controller, the controller with the vehicle dynamics model is the controller to be tuned, and the controller with the vehicle dynamics model is the controller to which the reliable parameters are accurately calculated. and can be found efficiently and at low cost, so that the risk of runaway of smart devices (e.g., vehicles) can be reduced later when further parameter adjustments are made to the controller, including the vehicle dynamics model; Potential traffic accident safety risks due to incorrect parameterization of the controller, including the vehicle dynamics model, can be reduced. This makes it convenient for field debugging engineers to perform large-scale real-vehicle controller performance testing tasks.

In one possible implementation, the smart device includes a smart mobile device, and the control data includes at least one of steering data, accelerator data, braking data and indicator lamp data.

According to this implementation method, it is possible to realize precise automatic control of the smart mobile device.

In one possible implementation, the step of controlling the driving of the smart device in the first mode based on the third control data comprises: the difference between the first control data and the second control data controlling travel of the smart device in a first mode based on the third control data, wherein the predetermined condition is a first target control of the first control data The types of the first target control data and the second target control data are the same, including that a difference between the data and the second target control data of the second control data belongs to a threshold range.

In the implementation method, when the difference between the first control data and the second control data satisfies a predetermined condition, the driving of the smart device is controlled based on the third control data output from the second controller. Therefore, under the premise of reducing the risk of a runaway smart device (e.g., vehicle) and reducing the safety risk of a potential traffic accident due to the improper arrangement of the parameters of the second controller, the parameters after the adjustment of the second controller are It can be applied to a more realistic scene.

Another aspect of the invention provides a parameter placement device. The parameter arrangement device is applied to a smart device including a plurality of controllers, the plurality of controllers includes at least a first controller and a second controller, and the parameter arrangement device is output from each of the plurality of controllers. wherein the control data output from the first controller includes first control data, and the control data output from the second controller includes second control data. a first acquisition module comprising;

a configuration module for configuring parameters of the second controller based on the first control data and the second control data.

In one possible implementation, the first acquisition module acquires first reference trajectory data and first state data of the smart device in a first mode, and via the plurality of controllers, obtains the first state data. Based on the 1 reference trajectory data and the first state data, the respective control data are generated.

In one possible implementation, the parameter configuration device further comprises a first control module for controlling running of the smart device in a first mode according to the first control data.

In one possible implementation, the parameter locator comprises: a second acquisition module for acquiring second reference trajectory data and second state data of the smart device being in a first mode; a generating module for generating third control data based on the second reference trajectory data and the second state data via a smart device in a first mode based on the third control data; a second control module for controlling travel of the .

In one possible implementation, the parameter allocation device comprises a third acquisition module for acquiring actual trajectory data generated when the smart device in the first mode travels, the second reference trajectory data and the an adjustment module for adjusting parameters of the second controller according to actual trajectory data.

In one possible implementation, the first controller is a controller that does not include a vehicle dynamics model and the second controller is a controller that includes a vehicle dynamics model.

In one possible implementation, the smart device includes a smart mobile device, and the control data includes at least one of steering data, accelerator data, braking data and indicator lamp data.

In one possible implementation, the second control module, based on the third control data, generates a first and the predetermined condition is that the difference between the first target control data of the first control data and the second target control data of the second control data is within a threshold range. and the types of the first target control data and the second target control data are the same.

Another aspect of the invention provides an electronic device. The electronic device comprises one or more processors and a memory for storing executable instructions, wherein the one or more processors invoke the executable instructions stored in the memory to perform the above configured to perform a parameter placement method;

Another aspect of the invention provides a computer-readable storage medium. Computer program instructions are stored on the computer readable storage medium, and the parameter placement method is implemented when the computer program instructions are executed by the processor.

Another aspect of the invention provides a computer program product. The computer program product stores computer readable instructions and causes a computer to perform the parameter placement method when the computer readable instructions are executed.

In an embodiment of the present invention, control data output from each of a plurality of controllers of a smart device is acquired (wherein the plurality of controllers includes a first controller and a second controller, and output from the first controller The control data output from the second controller includes first control data, and the control data output from the second controller includes second control data), based on the first control data and the second control data, the 2 Arrange the parameters of the controller. This allows the first controller to be the reference controller and the second controller to be the controller to be tuned, and find reliable parameters for the second controller accurately, efficiently and at low cost. Further, while the placement of the second controller is realized based on the first control data actually output from the first controller, the first control data is usually used before the placement of the second controller is completed. The ability to control the smart device allows the parameters of the second controller to be better adapted to the current application of the smart device. And later, in the process of further adjusting the parameters of the second controller, it is possible to reduce the risk of runaway of the smart device (e.g., vehicle), and the safety of potential traffic accidents caused by the inappropriate setting of the parameters of the second controller. Risk can be reduced.

It is to be understood that the above general description and the following detailed description are merely exemplary and interpretive and are not intended to limit the invention.

Other features and aspects of the invention will become apparent from the following detailed description of exemplary embodiments with reference to the drawings.

The drawings herein are incorporated into and constitute a part of the specification. These drawings show embodiments consistent with the present invention and are used to interpret the solution of the present invention together with the description of the specification.
Fig. 4 shows a flow chart of a parameter allocation method according to an embodiment of the present invention; 1 shows a schematic diagram of a PID-based controller (PID controller) in an embodiment of the invention; FIG. Fig. 2 shows a schematic diagram of a core unit of a PID-based controller in an embodiment of the invention; FIG. 4 shows a schematic diagram of the control effect after being adjusted by the three parameters of the PID-based controller in an embodiment of the present invention; 1 shows a schematic diagram of an MPC-based controller (MPC controller) in an embodiment of the invention; FIG. Fig. 2 shows a schematic diagram of a core unit of an MPC-based controller in an embodiment of the invention; FIG. 4 shows a schematic diagram of a vehicle dynamics model in an MPC-based controller according to an embodiment of the invention; FIG. 4 shows a schematic diagram of the core unit's objective function optimization in the MPC-based controller of an embodiment of the present invention; FIG. 4 shows a schematic diagram of the core unit's objective function optimization in the MPC-based controller of an embodiment of the present invention; FIG. 4 shows a schematic diagram of the core unit's objective function optimization in the MPC-based controller of an embodiment of the present invention; FIG. 4 shows a schematic diagram of the optimization process of an MPC-based controller in an embodiment of the invention; 1 shows a schematic diagram of the overall architecture of an automated driving system according to an embodiment of the present invention; FIG. FIG. 4 shows a schematic diagram of using a reference controller to guide parameter placement by a tuned controller in an embodiment of the present invention. FIG. 4 shows a schematic diagram of a flow of parameterization of a controller according to an embodiment of the present invention; FIG. 4 shows a schematic diagram of a control result of an MPC-based controller in an embodiment of the present invention; FIG. 4 shows a schematic diagram of a control result of an MPC-based controller in an embodiment of the present invention; FIG. 4 shows a schematic diagram of a control result of an MPC-based controller in an embodiment of the present invention; FIG. 4 shows a schematic diagram of a control result of an MPC-based controller in an embodiment of the present invention; FIG. 4 shows a schematic diagram of lateral trajectory error, orientation error and longitudinal velocity error over time under control of an MPC-based controller in an embodiment of the present invention; FIG. 4 shows a schematic diagram of lateral trajectory error, orientation error and longitudinal velocity error over time in the control of an MPC-based controller after parameter tuning for the MPC-based controller in an embodiment of the present invention; . 1 shows a block diagram of a parameter placement device according to an embodiment of the present invention; FIG. FIG. 8 shows a block diagram of an electronic device 800 according to an embodiment of the invention. 19 shows a block diagram of an electronic device 1900 according to an embodiment of the invention. FIG.

Various illustrative embodiments, features, and aspects of the invention are described in detail below with reference to the drawings. The same reference numerals in the drawings indicate elements with the same or similar function. Although the drawings show various aspects of the embodiments, they are not necessarily drawn to scale unless otherwise indicated.

The term "exemplary" as used herein means "exemplary, exemplary, or illustrative." Any embodiment described herein as "exemplary" should not be construed as superior or better than other embodiments.

The term "and/or" in this text is merely for describing the relationship of related objects and can indicate that there are three kinds of relationships. For example, A and/or B can represent three situations: A exists alone, A and B exist simultaneously, and B exists alone. In addition, the term "at least one" in the text represents any one of a plurality of types or any combination of at least two of a plurality of types. For example, including at least one of A, B, and C means including any one or more elements selected from the set consisting of A, B, and C.

Also, a great deal of specific detail is provided in the specific embodiments below in order that the present invention may be better described. As will be appreciated by those skilled in the art, the present invention may be practiced as well without some of the specific details. In some instances, methods, means, devices and circuits that are well known to those skilled in the art have not been described in detail so as to obscure the subject matter of the present invention.

In an embodiment of the present invention, control data output from a controller of a smart device is obtained (where the controller includes a first controller and a second controller, and the control data output from the first controller is The control data output from the second controller includes first control data, and the control data output from the second controller includes second control data, and the parameters of the second controller are arranged based on the first control data and the second control data. do. This allows the first controller to be the reference controller and the second controller to be the controller to be tuned, and find reliable parameters for the second controller accurately, efficiently and at low cost. Further, while the placement of the second controller is realized based on the first control data actually output from the first controller, the first control data is usually used before the placement of the second controller is completed. The ability to control the smart device allows the parameters of the second controller to be better adapted to the current application of the smart device. And later, in the process of further adjusting the parameters of the second controller, it is possible to reduce the risk of runaway of the smart device (e.g., vehicle), and the safety of potential traffic accidents caused by the inappropriate setting of the parameters of the second controller. Risk can be reduced.

It should be noted that the smart device may further include controllers other than the first controller and the second controller. In embodiments of the present invention, the types of controllers included in the smart device, the number of controllers of each type, etc. are not limited. In the embodiment of the present invention, the smart device includes a first controller and a second controller as an example to describe the technical solution according to the embodiment of the present invention.

FIG. 1 shows a flow chart of a parameter allocation method according to an embodiment of the present invention. The parameter placement method may be applied to a parameter placement device. For example, the parameter placement method may be performed by a terminal device or a server or other processing device. However, the terminal equipment may be in-vehicle equipment, user equipment (UE), mobile equipment, user terminal, terminal, personal digital assistant (PDA), handheld equipment, computing equipment, wearable equipment, etc. good. In some possible implementations, the parameter placement method may be implemented by a processor invoking computer readable instructions stored in memory. The parameter arrangement method is applied to a smart device, the smart device including a plurality of controllers, the plurality of controllers including at least a first controller and a second controller. The smart devices may include smart mobile devices such as vehicles or mobile robots. In the following, the embodiments of the present invention will be described with the smart device being a vehicle as an example. As shown in FIG. 1, the parameter placement method includes steps S11 to S12.

In step S11, control data output from each of the plurality of controllers is acquired, the control data output from the first controller includes first control data, and the control data output from the second controller is , including second control data.

The controller in the embodiments of the present invention may be a controller for trajectory tracking in automatic driving or a controller with other functions, and the embodiments of the present invention are not limited thereto. Control data output from the controller (first control data output from the first controller and/or second control data output from the second controller) may be used to control the smart device. The first controller and the second controller may obtain the first control data and the second control data, respectively, based on the same input data. The first control data output from the first controller and the second control data output from the second controller may be obtained multiple times during the parameter allocation process of the second controller. For example, the first control data output from the first controller and the second control data output from the second controller may be simultaneously obtained for any one of a plurality of times to compare the two. . Of course, the first control data and the second control data may be acquired in this order, or the second control data and the first control data may be acquired in this order, in a certain order. What should be explained is that the order of the first control data and the second control data is not limited in the acquisition process of the control data.

In step S12, the parameters of the second controller are arranged based on the first control data and the second control data.

In an embodiment of the present invention, parameters of the second controller may be arranged based on a difference between the first control data and the second control data. For example, parameters of the second controller may be initialized and/or adjusted based on the difference between the first control data and the second control data.

Initializing the parameters of the second controller refers to performing an initial placement on the parameters of the second controller. Adjusting the parameters of the second controller refers to adjusting the parameters of the second controller whose initialization has been completed. In one possible implementation, the parameters of the second controller that have been initialized may be the default second controller parameters, specifically the parameters of the second controller that are arranged in consideration of past experience. It may be a parameter, or a shipping parameter placed before the second controller is shipped, and is not limited here.

In the embodiment of the present invention, while the placement of the second controller is realized based on the first control data actually output from the first controller, before the placement of the second controller is completed, the first Since the control data can be used to control the smart device, the parameters of the second controller can be better adapted to the current application of the smart device. In addition, in the process of further adjusting parameters for the second controller later, it is possible to reduce the risk of runaway of smart equipment (e.g., a vehicle), and prevent potential traffic accidents due to improper parameter allocation of the second controller. Safety risks can be reduced.

In one possible implementation, obtaining control data output from each of the plurality of controllers includes obtaining first reference trajectory data and first state data of the smart device in a first mode. and generating respective control data based on the first reference trajectory data and the first state data via the plurality of controllers.

In this implementation, the first reference trajectory data may represent reference trajectory data obtained in the process of arranging the parameters of the second controller based on the first control data and the second control data. The first reference trajectory data may include a reference trajectory and target velocities of a plurality of passing points on the reference trajectory, and the first reference trajectory data may be output from a trajectory planning module in an automated driving system. .

In this implementation, the first state data may represent smart device state data obtained during the process of configuring the parameters of the second controller based on the first control data and the second control data. The first state data may be obtained in real time. For example, the first state data may include one or a combination of multiple items such as position, velocity and acceleration of the smart device.

In this implementation, the smart device has at least a first mode, for example, the first mode may be a fully automatic operation mode or a semi-automatic operation mode. The smart device may also have a second mode. For example, the second mode may be a fully artificial operation mode. The smart device may further comprise a third mode. For example, when the first mode is the fully automatic operation mode, the third mode may be the semi-automatic operation mode. Alternatively, when the first mode is the semi-automatic operation mode, the third mode may be the fully automatic operation mode. Each mode may further include sub-modes to allow finer partitioning for each mode. Here, the mode type of the smart device and the specific parameters of the sub-modes are not limited.

In this implementation scheme, the first controller may generate first control data based on the first reference trajectory data and the first state data. The first control data represents control data generated by the first controller and corresponding to the first reference trajectory data and the first state data. The second controller may generate second control data based on the first reference trajectory data and the first state data. The second control data represents control data generated by the second controller and corresponding to the first reference trajectory data and the first state data. The second control data may refer to control data generated by the second controller in the process of arranging the parameters of the second controller based on the first control data and the second control data.

In this implementation method, the control data is generated based on the first reference trajectory data and the first state data via the controller, and the second controller is generated based on the generated first control data and second control data. By arranging the parameters of , the parameters of the second controller obtained by arranging can be more applied to the real scene.

In one possible implementation, after obtaining control data output from the controller, the method further comprises controlling driving of the smart device in a first mode according to the first control data. include.

In this implementation method, the first controller may be the current controller of the smart device to control the running of the smart device in the first mode based on the first control data. For example, the first controller may be the current controller of the smart device via a switcher of the smart device.

According to the implementation method, by controlling the running of the smart device in the first mode based on the first control data, it is possible to perform parameter allocation for the second controller in the actual vehicle. For example, it is possible to reduce the cost of debugging the controller by switching back and forth between a device that simulates driving of a vehicle and the actual vehicle, and it is possible to apply the second controller after parameter placement to a more real scene. .

In one possible implementation, after arranging the parameters of the second controller, the method obtains second reference trajectory data and second state data of the smart device in a first mode; generating third control data based on the second reference trajectory data and the second state data via the second controller; and controlling travel of the equipment.

In this implementation method, the second reference trajectory data may represent reference trajectory data obtained in the process of controlling the traveling of the smart device based on the third control data. The second reference trajectory data may include the reference trajectory and target velocities of a plurality of passing points on the reference trajectory, and the second reference trajectory data may be output from a trajectory planning module in the automated driving system. . The first reference trajectory data may include content in the second reference trajectory data. That is, the second reference trajectory data may be reference trajectory data subsequent to the first reference trajectory data. For example, the smart device acquires the second reference trajectory data after traveling along the first reference trajectory data for a certain period of time. Alternatively, the second reference trajectory data and the first reference trajectory data may be different when the smart device changes the traveling route.

In this implementation, the second state data may represent state data of the smart device obtained during the process of controlling the running of the smart device based on the third control data. The second state data may be obtained in real time. For example, the second state data may include one or a combination of multiple items such as position, velocity and acceleration of the smart device.

In this implementation, the third control data may represent control data generated by the second controller and corresponding to the second reference trajectory data and the second state data. The third control data may refer to control data generated by a second controller in the process of controlling travel of the smart device based on the third control data.

According to the implementation method, by controlling the running of the smart device in the first mode based on the third control data, it is possible to perform parameter adjustment for the second controller in the actual vehicle. It is possible to reduce the cost of debugging the controller by switching back and forth between the controller and the actual vehicle, and the second controller after parameter adjustment can be more applied to the actual scene.

In one possible implementation, after controlling the driving of the smart device in the first mode according to the third control data, the method includes: Further comprising obtaining actual trajectory data and adjusting parameters of the second controller according to the second reference trajectory data and the actual trajectory data.

The actual trajectory data may include the actual trajectory and the velocities of a plurality of points on the actual trajectory. Based on the second reference trajectory data and the actual trajectory data, it is possible to identify the orientation error, the lateral trajectory error and the longitudinal velocity error between the two. A parameter of the second controller can be adjusted based on.

In this implementation method, by adjusting the parameters of the second controller based on the difference between the actual trajectory data and the second reference trajectory data, the second controller can be more accurately adapted to the smart device. , to achieve more precise control and a safer and more comfortable driving experience.

In one possible implementation, the smart device includes a smart mobile device, and the control data includes at least one of steering data, accelerator data, braking data and indicator lamp data.

In this implementation, the steering wheel steering data may include one or more of the steering wheel rotation angle, number of rotations, direction of rotation, and so on. The accelerator data may include one or a combination of multiple items of accelerator magnitude, accelerator speed, and the like. The accelerator magnitude may be expressed in a manner such as a percentage of the maximum accelerator amount. The brake data may include one or a combination of terms of brake strength, brake speed, and the like. Brake strength may be indicated in a formula such as percentage of maximum brake strength. The indicator lamp data may include one or more combinations of indicator lamp type, length of time, and the like. According to this implementation scheme, precise automatic control for smart mobile devices can be achieved.

In one possible implementation, controlling the driving of the smart device in the first mode based on the third control data is such that the difference between the first control data and the second control data satisfies a predetermined condition. controlling travel of the smart device in the first mode based on the third control data in response to satisfying: The predetermined condition includes that a difference between first target control data of the first control data and second target control data of the second control data belongs to a threshold range, and the first target control data and the type of the second target control data are the same.

In such implementations, the first target control data may include one or more types of data of the first control data, and correspondingly, the second target control data includes It may contain one or more types of data. However, the data types included in the first target control data and the second target control data are the same. For example, the first target control data includes steering wheel data, accelerator data and brake data among the first control data, and the second target control data includes steering wheel data, accelerator data and brake data among the second control data. Contains data. Further, for example, the first target control data includes steering wheel data, accelerator data, brake data, and indicator lamp data among the first control data, and the second target control data includes steering wheel steering data among the second control data. , accelerator data, brake data and indicator lamp data.

In this implementation scheme, the threshold range may be one parameter as the threshold. A predetermined condition is satisfied when the difference between the first target control data of the first control data and the second target control data of the second control data is equal to or less than the threshold. Alternatively, the threshold range may have two thresholds as upper and lower limits. A predetermined condition is satisfied when the difference between the first target control data of the first control data and the second target control data of the second control data belongs to the threshold range.

As an example of the implementation method, the first target control data includes at least one of steering data, accelerator data, brake data, and indicator lamp data among the first control data, and the second target control data includes , at least one of steering data, accelerator data, brake data and indicator lamp data of the second control data. The predetermined conditions are that a difference between the steering wheel data in the first control data and the steering wheel steering data in the second control data is equal to or less than a first threshold, and the accelerator data in the first control data. and the accelerator data of the second control data is equal to or less than a second threshold, and the difference between the brake data of the first control data and the brake data of the second control data is the first and at least one of a difference between indicator lamp data in the first control data and indicator lamp data in the second control data being equal to or smaller than a fourth threshold. .

In this implementation method, the second controller may be the current controller of the smart device, and the smart device may be controlled to run in the first mode based on the third control data. For example, the second controller may be the current controller of the smart device via a switcher.

In this implementation method, the difference between the indicator lamp data in the first control data and the indicator lamp data in the second control data is obtained by equalizing the indicator lamp type and the time length in the indicator lamp data. You may

In this implementation method, when the difference between the first control data and the second control data satisfies a predetermined condition, the running of the smart device is controlled based on the third control data output from the second controller. , under the premise that it can reduce the risk of runaway of smart devices (e.g., vehicles) and reduce the safety risk of potential traffic accidents due to the unreasonable setting of the parameters of the second controller, after adjusting the second controller parameters can be applied to a more realistic scene.

In this implementation method, it may be determined that the parameters of the second controller are relatively reliable when the difference between the first control data and the second control data satisfies a predetermined condition.

In one possible implementation, the first controller is a controller that does not include a vehicle dynamics model and the second controller is a controller that includes a vehicle dynamics model.

For example, the first controller is a PI (P: Proportional, I: Integral, integral) based controller or a PID (P: Proportional, I: Integral, D: Derivative, differential) based controller, etc. The second controller may be an MPC (Model Predictive Control) based controller or an LQR (Linear Quadratic Regulator) based controller, or the like.

In this implementation, the second controller is based on a vehicle dynamics model, ie a Dynamic Bicycle Model. A vehicle dynamics model can dynamically model vehicle kinematic behavior, and modeling based on a set of reasonable assumptions (e.g., small angle assumptions, error) is better than modeling based on direct reference angles and reference positions. is also advantageous for model linearization), simplifies the nonlinear model into a linear model, which is used to predict the future finite time behavior or driving trajectory of the vehicle.

According to the above implementation scheme, the controller without the vehicle dynamics model is the reference controller, the controller with the vehicle dynamics model is the controller to be tuned, and the controller with the vehicle dynamics model is the controller to which the reliable parameters are accurately calculated. and can be found efficiently and at low cost, so that the risk of runaway of smart devices (e.g., vehicles) can be reduced later when further parameter adjustments are made to the controller, including the vehicle dynamics model; Potential traffic accident safety risks due to incorrect parameterization of the controller, including the vehicle dynamics model, can be reduced. This makes it convenient for field debugging engineers to perform large-scale real-vehicle controller performance testing tasks.

FIG. 2 shows a schematic diagram of a PID-based controller (PID controller) in an embodiment of the invention. A PID-based controller can provide longitudinal velocity closed-loop control and lateral position closed-loop control. As a result, automatic driving of an unmanned vehicle is realized. Besides the feedback control shown in FIG. 2, the PID-based controller also includes feedforward control. As shown in FIG. 2, the PID-based controller outputs first control data based on the error between the first reference trajectory data output from the trajectory planning module and the first state data of the vehicle. can control the running of the car.

FIG. 3 shows a schematic diagram of a core unit of a PID-based controller in an embodiment of the invention. As shown in FIG. 3, the PID-based controller can complete the control task by adjusting only three parameters. These three parameters are the proportional term Kp, the integral term Ki and the differential term Kd respectively. In autonomous driving systems, PI-based controllers are generally able to meet the control requirements of the system. That is, Kp causes the automatic driving system to respond immediately, and Ki cancels the steady-state error in the automatic driving system.

FIG. 4 shows a schematic diagram of the control effect after being adjusted by the three parameters of the PID-based controller in an embodiment of the present invention. In FIG. 4, line 41 is the reference trajectory, 42 is the actual trajectory without control, and 43 is the actual trajectory under control of the PID-based controller. Since a PID-based controller can complete automatic control over an unmanned vehicle just by adjusting two parameters, Kp and Ki, and can be debugged very easily, in the embodiment of the present invention, a PI-based controller may be used as a reference controller for guiding parameterization by a second controller that includes a vehicle dynamics model. In embodiments of the present invention, appropriate parameters for the PI-based controller may be selected by manual parameter tuning, or automatic parameter tuning methods in related art may be used to select appropriate parameters for the PI-based controller. .

FIG. 5 shows a schematic diagram of an MPC-based controller (MPC controller) in an embodiment of the invention. MPC-based controllers are capable of longitudinal velocity closed-loop control and lateral position closed-loop control. As a result, automatic driving of an unmanned vehicle is realized. Besides the feedback control shown in FIG. 5, the MPC-based controller also includes feedforward control. As shown in FIG. 5, the MPC-based controller outputs second control data based on the error between the first reference trajectory data output from the trajectory planning module and the first state data of the vehicle. Alternatively, the vehicle may be controlled by outputting third control data based on the error between the second reference trajectory data output from the trajectory planning module and the second state data of the vehicle.

FIG. 6 shows a schematic diagram of the core unit of the MPC-based controller in an embodiment of the invention. As shown in FIG. 6, the MPC-based controller includes two core units: a vehicle dynamics model and an optimizer. The vehicle dynamics model predicts possible future driving trajectories of the vehicle, the optimizer solves one optimization problem, finds the trajectory that minimizes the objective function J from multiple candidate predicted trajectories, and uses the second control data Or acquire the third control data. This ensures that the MPC-based controller drives the vehicle as close as possible to the first reference trajectory data or the second reference trajectory data.

は、ｅ１の微分を表し、

は、ｅ１の二次微分を表し、ｅ２及びｅ３は、これと類似する。本発明の実施例におけるＭＰＣベースのコントローラは、車両動力学モデルに基づいて、車両運動挙動を動的にモデル化し、一連の合理的な仮定により、非線形モデルを図７に示す線形モデルとして簡素化してもよい。当該モデルは、車両の未来の有限な時間内の挙動又は走行軌跡を予測する。図７において、ＳＴ（ｓｔｅｅｒ）は、ハンドルステアリングデータ（例えば、ハンドル回転角度）を表し、ＴＨ（ｔｈｒｏｔｔｌｅ）は、アクセルデータ（例えば、最大アクセル量に対する百分率）を表し、ＢＲ（ｂｒａｋｅ）は、ブレーキデータ（例えば、最大ブレーキ強さに対する百分率）を表す。 FIG. 7 shows a schematic diagram of a vehicle dynamics model in the MPC-based controller of an embodiment of the invention. In FIG. 7, 71 represents a car, the top is the head of the car, and the bottom is the tail. The steering error e1 may be obtained based on the difference between the orientation of the reference point on the reference trajectory in the first reference trajectory data or the second reference trajectory data and the current vehicle head orientation. A lateral trajectory error e2 may be obtained based on the minimum distance between the current position of the car (eg, the geometric center point of the car) and the tangent to the reference point. For example, the lateral trajectory error e2 may be equal to the minimum distance between the current position of the car and the tangent to the reference point. A longitudinal velocity (Lon Velocity) error e3 may be obtained based on the difference between the reference velocity in the first reference trajectory data or the second reference trajectory data and the actual velocity of the vehicle. In FIG. 7,

represents the derivative of e1, and

represents the second derivative of e1, and e2 and e3 are analogous to this. The MPC-based controller in an embodiment of the present invention dynamically models the vehicle dynamics behavior based on the vehicle dynamics model, and through a set of reasonable assumptions, simplifies the nonlinear model into the linear model shown in FIG. may The model predicts the future finite time behavior or trajectory of the vehicle. In FIG. 7, ST (steer) represents steering wheel steering data (e.g., steering wheel rotation angle), TH (throttle) represents accelerator data (e.g., percentage of maximum accelerator amount), and BR (brake) represents braking. Represents data (e.g. percentage of maximum brake strength).

を示す。ベクトル化後の目標関数は、

となる。ただし、

である。ベクトル化された目標関数から分かるように、ＭＰＣベースのコントローラが配置すべきパラメータは、８つある。その中、Ｑベクトルは、配置すべきパラメータを６つ含み、それらは、それぞれｑ１、ｑ２、ｑ３、ｑ４、ｑ５及びｑ６である。Ｒベクトルは、配置すべきパラメータを２つ含み、それらは、それぞれｒ１及びｒ２である。図８Ａは、車の予測軌跡の車道における位置の模式図を示し、図８Ａは、車道の中心線の位置及び予測範囲を更に示す。予測軌跡は、予測された制御動作シーケンス（制御動作データは、ハンドルステアリングデータ、アクセルデータ、ブレーキデータ、指示ランプデータのうちの少なくとも１項を含んでもよい）を実行して生成された軌跡である。図８Ｂは、ｔ＋１時点～ｔ＋７時点の横方向軌跡誤差ｃｔｅ_ｔ＋１～ｃｔｅ_ｔ＋７（即ち、ｅ２）の模式図を示す。横座標は、時間であり、縦座標は、距離である。それ相応に、ｔ＋１時点～ｔ＋７時点の向き誤差ｅ１は、それぞれｈｅ_ｔ＋１～ｈｅ_ｔ＋７と示されてもよく、ｔ＋１～ｔ＋７時点の縦方向速度誤差ｅ３は、それぞれｖｅ_ｔ＋１～ｖｅ_ｔ＋７と示されてもよい。 FIG. 8C shows a schematic diagram of the core unit objective function optimization in the MPC-based controller of an embodiment of the present invention. In FIG. 8C, ΔST represents the amount of change in ST (steering data) between two adjacent time points, and ΔTH represents the amount of change in TH (accelerator data) between two adjacent time points. , ΔBR represent the amount of change in BR (brake data) between two adjacent time points. FIG. 8C is the objective function

indicates The objective function after vectorization is

becomes. however,

is. As can be seen from the vectorized objective function, there are eight parameters that the MPC-based controller should deploy. Among them, the Q-vector contains 6 parameters to be placed, which are q1, q2, q3, q4, q5 and q6 respectively. The R vector contains two parameters to be placed, r1 and r2 respectively. FIG. 8A shows a schematic diagram of the position of the predicted trajectory of the vehicle on the roadway, and FIG. 8A further shows the position and predicted range of the centerline of the roadway. A predicted trajectory is a trajectory generated by executing a predicted control action sequence (the control action data may include at least one of steering data, accelerator data, brake data, and indicator lamp data). . FIG. 8B shows a schematic diagram of the lateral trajectory errors cte _t+1 to cte _t+7 (ie, e2) from time t+1 to time t+7. The abscissa is time and the ordinate is distance. Correspondingly, the orientation errors e1 at times t+1 to t+7 may be denoted he _t+1 to he _t+7 , respectively, and the longitudinal velocity errors e3 at times t+1 to t+7 may be denoted ve _t+1 to ve _t+7 , respectively. good too.

FIG. 9 shows a schematic diagram of the optimization process of an MPC-based controller in an embodiment of the invention. The goal of the parameterization of MPC-based controllers is to minimize J, as shown in FIG. After Q and R are located, parameter tuning causes the MPC-based controller to perform trajectory prediction and evaluation (computation of objective function J) for potential control motion sequences in the manner shown in FIG. The best control operation sequence may be obtained as the second control data or the third control data. FIG. 9 shows a schematic diagram of the predicted trajectory of the car when J=50, J=30 and J=10. As shown in FIG. 9, when J=10, the predicted trajectory of the vehicle is closest to the centerline of the roadway, so the control action sequence corresponding to J=10 is the best control action sequence.

Usually, the number of parameters to be adjusted for a controller that includes a vehicle dynamics model is greater than the number of parameters to be adjusted for a controller that does not include a vehicle dynamics model. For example, there are two parameters to adjust for a PI-based controller, a proportional term (K _p ) and an integral term (K _i ), respectively. A PI controller without a model is simple and easy to debug, but lacks control accuracy. On the other hand, a controller that includes a vehicle dynamics model, such as an MPC-based controller, can model the vehicle dynamics behavior and more accurately describe the future motion trajectory of the vehicle. In an embodiment of the present invention, behavior modeling is performed on the unmanned vehicle through a controller (second controller) that includes a vehicle dynamics model, and a more accurate automatic control effect can be obtained. However, controllers that include vehicle dynamics models typically include multiple parameters. For example, an MPC-based controller contains eight parameters to adjust. Among them, 6 parameters to be adjusted adjust the system state (orientation error, lateral trajectory error, longitudinal velocity error), and 2 parameters to be adjusted are the system input (steering angle) , acceleration amount or brake amount). Since the debug difficulty of 8 parameters is generally greater than the debug difficulty of 2 parameters, the method according to the present invention takes the PID controller as the reference controller, and based on the first control data and the second control data, MPC Adjust the parameters to be adjusted in the controller. Before the adjustment of the parameters to be adjusted by the MPC controller is completed, the PID controller is still used as the current controller to control the driving of the unmanned vehicle. This can reduce potential traffic accidents due to the use of an untuned MPC controller.

FIG. 10 shows a schematic diagram of the overall architecture of an automated driving system according to an embodiment of the present invention. As shown in FIG. 10, reference trajectory data (eg, first reference trajectory data, second reference trajectory data) is output via the trajectory planning module, and vehicle status data (eg, first state data, second state data). The controller (the first controller and/or the second controller) outputs control data (the first controller outputs the first control data, the second controller outputs the second 2 control data and/or output the third control data). By writing control data to the car via a bus (write bus), closed-loop control for the car is realized and the car is driven to run.

FIG. 11 shows a schematic diagram of using a reference controller to guide parameter placement by a tuned controller in an embodiment of the present invention. As shown in FIG. 11, the reference controller may be a PID-based controller or the like, the regulated controller may be a LQR-based controller or an MPC-based controller, or the like, and the reference controller may be a regulated controller. A controller may direct the placement of the parameters (eg, Q vector, R vector, etc.). For example, r1 may be adjusted based on the difference between the steering data of the first control data and the steering data of the second control data. Adjust r2 based on the difference, adjust q1 and q2 based on orientation error e1, adjust q3 and q4 based on lateral trajectory error e2, and adjust q5 and q6 based on longitudinal velocity error e3. You may

FIG. 12 shows a schematic diagram of a flow of parameterization of a controller according to an embodiment of the present invention. As shown in FIG. 12, after the automated driving system is activated, a first controller (a controller that does not include a vehicle dynamics model, such as a PI-based controller) and a second controller (a controller that includes a vehicle dynamics model, such as an LQR controller) base controller or MPC-based controller) may begin operation simultaneously. Turn on the switcher and select the first controller to use as the current controller for the unmanned vehicle. That is, the first control data output from the first controller is distributed to the vehicle actuator to drive the unmanned vehicle. In the process of making the first controller the current controller of the unmanned vehicle, the values of the proportional term and the integral term are adjusted so that the first controller can complete accurate control of the unmanned vehicle on straight lines and curves. That is, the control data output from the first controller can drive the unmanned vehicle to correctly track the reference trajectory. Once the first controller successfully matches the automatic driving system (that is, the unmanned vehicle can track the reference trajectory correctly under the control of the first controller), the first control data output from it is the reference control can be thought of as data. Such reference control data allows the driverless vehicle to accurately complete normal autonomous driving tasks.

After the first controller successfully matches the autonomous driving system, the comparator may be turned on. A comparator compares the difference between the first control data output from the first controller and the second control data output from the second controller, and the second control data output from the arranged second controller is compared with the second control data output from the second controller. The parameters of the second controller are arranged based on the difference between the first control data and the second control data so that the difference from the first control data output from the first controller is minimized. If the difference between the first control data and the second control data satisfies a predetermined condition, it may be determined that the second controller has acquired relatively reliable parameters. As an illustration, when the parameters of the MPC-based controller are Q=[0.0,0.0,1,0,0,1] ^T , R=[0.4,0.8] ^T , the MPC-based The second control data output from the controller of the PI-based controller essentially matches the first control data output from the PI-based controller. In other words, an MPC-based controller for the parameter can be used to achieve the same trajectory tracking effect as a PI-based controller.

13a-13d show schematic diagrams of control results of an MPC-based controller in an embodiment of the present invention. FIG. 13a shows a schematic diagram of the reference trajectory and the actual trajectory of the unmanned vehicle under the control of an MPC-based controller. A UTM (Universal Transverse Mercator grid system) coordinate system is adopted in FIG. 13a. Figure 13b shows a schematic diagram of the distance between the reference longitudinal velocity and the actual longitudinal velocity of the unmanned vehicle under control of the MPC-based controller. FIG. 13c shows a schematic diagram of the reference heading orientation and the actual heading orientation of an unmanned vehicle under the control of an MPC-based controller. FIG. 13d shows a schematic diagram of the reference steering angle and the actual steering angle of the unmanned vehicle under the control of the MPC-based controller. The distances in Figures 13b-13d may represent the distance from the starting point of the autonomous driving task. As shown in FIGS. 13a-13d, the MPC-based controller has parameters (Q=[0.0,0.0,1,0,0,1] ^T , R=[0.4,0.8] ^T ) completed the automatic operation. In terms of evaluation data, the parameters can ensure that MPC-based controllers can safely complete basic autonomous driving tasks, but performance needs to be further improved.

FIG. 14 shows a schematic diagram of cross track error (CTE), orientation error and longitudinal velocity error over time under control of an MPC-based controller in an embodiment of the present invention. In FIG. 14, the abscissa is time and the unit is seconds. As shown in FIG. 14, the lateral trajectory error is large. That is, the lateral control accuracy of MPC-based controllers is lacking. As a result, the unmanned vehicle runs off the center line of the roadway. Further parameter adjustments may be made to the MPC-based controller so that the control of the MPC-based controller is more precise. In an embodiment of the present invention, after configuring the parameters of the second controller according to the first control data and the second control data, through the switcher the second controller is the current controller of the unmanned vehicle, and through the second controller By controlling the unmanned vehicle and further adjusting the parameters of the second controller based on the second reference trajectory data and the actual trajectory data, the second controller can be more accurately adapted to the autonomous driving system. For problems with large lateral trajectory errors, the parameters of the MPC-based controller (Q=[0.0,0.0,1,0,0,1] ^T , R=[0.4,0.8] ^T ) may be adjusted. As an example, Q=[0.03,0.0,1,0,0,1] ^T and R=[0.4,0.8] ^T may be adjusted. That is, by increasing the degree of penalty for lateral trajectory error, an MPC-based controller can control an unmanned vehicle to drive closer to the roadway centerline.

FIG. 15 is a schematic diagram of lateral trajectory error, orientation error and longitudinal velocity error over time under control of an MPC-based controller after parameter tuning for the MPC-based controller in an embodiment of the present invention. Figure shows. In the example shown in FIG. 15, after performing parameter tuning on the MPC-based controller, the lateral trajectory error was reduced by about 50% compared to before parameter tuning. As shown in Fig. 13d, the actual steering wheel angle output from the MPC-based controller is more frequent than the reference steering wheel angle variation, resulting in a rough driving experience due to the directional steering not being smooth. By further adjusting the parameters of the MPC-based controller, the steering angle changes in the control data output therefrom may be made smoother.

In one example, an automatic vehicle may be selected as the test platform. The average vehicle speed is 20 km/h and the test path is to go straight ahead, turn left and go straight, turn right and go straight.

Embodiments of the present invention can be applied to applications such as an automatic driving system, a driving assistance system, an automatic parking system, etc., and the embodiments of the present invention are not limited thereto.

In an embodiment of the present invention, control data output from each of a plurality of controllers of a smart device is acquired (wherein the plurality of controllers includes a first controller and a second controller, and output from the first controller The control data output from the second controller includes first control data, and the control data output from the second controller includes second control data), the second control data based on the first control data and the second control data By locating the parameters of the controllers so that the first controller is the reference controller and the second controller is the controller to be adjusted, reliable parameters are found for the second controller accurately, effectively and at low cost. This can reduce the risk of runaway of the smart device (e.g., vehicle) when further adjusting parameters for the second controller later, and potential traffic accidents due to improper parameter allocation of the second controller. safety risks can be reduced.

It will be appreciated that any of the above method embodiments referred to in the present invention may be combined with each other to form combined embodiments without contradicting the underlying logic. Due to space limitations, the description will not be repeated in the present invention.

As can be appreciated by those skilled in the art, in the above methods of specific embodiments, the order of steps does not imply a strict execution order and does not impose any limitations on the implementation procedure. The specific order of execution for each step should be specified in its function and possible underlying logic.

Moreover, the present invention further provides a parameter allocation device, an electronic device, a computer-readable storage medium, and a program. Any of the above may be used to implement any parameter placement method according to the present invention. For the corresponding technical solutions and descriptions, please refer to the relevant descriptions in the method section and will not be repeated.

FIG. 16 shows a block diagram of a parameter locator according to an embodiment of the invention. The apparatus is applied to a smart device including a plurality of controllers, the plurality of controllers including a first controller and a second controller. As shown in FIG. 16, the parameter placement device comprises a first acquisition module 21 and a placement module 22 . A first acquisition module 21 acquires control data output from each of the plurality of controllers, wherein the control data output from the first controller includes first control data and is output from the second controller The control data includes second control data. A configuration module 22 configures parameters of the second controller based on the first control data and the second control data.

In one possible implementation, the first acquisition module 21 acquires first reference trajectory data and first state data of the smart device that is in a first mode, and via the plurality of controllers, the The control data is generated based on the first reference trajectory data and the first state data.

In one possible implementation, the device further comprises a first control module for controlling running of the smart device in a first mode based on the first control data.

In one possible implementation, the device comprises a second acquisition module for acquiring second reference trajectory data and second state data of the smart device being in a first mode, and via the second controller: , a generation module for generating third control data based on the second reference trajectory data and the second state data; and a driving of the smart device in the first mode based on the third control data. and a second control module for controlling.

In one possible implementation, the device comprises a third acquisition module for acquiring actual trajectory data generated by the smart device in the first mode while driving, the second reference trajectory data and the actual trajectory and an adjustment module for adjusting parameters of the second controller in response to the data.

In one possible implementation, the first controller is a controller that does not include a vehicle dynamics model and the second controller is a controller that includes a vehicle dynamics model.

In one possible implementation, the smart device includes a smart mobile device, and the control data includes at least one of steering data, accelerator data, braking data and indicator lamp data.

In one possible implementation, the second control module, based on the third control data, generates a first mode to control the running of the smart device. The predetermined condition includes that a difference between first target control data of the first control data and second target control data of the second control data belongs to a threshold range, and the first target control data and the type of the second target control data are the same.

In an embodiment of the present invention, control data output from a controller of a smart device is obtained (where the controller includes a first controller and a second controller, and the control data output from the first controller is The control data output from the second controller includes first control data, and the control data output from the second controller includes second control data, and the parameters of the second controller are arranged based on the first control data and the second control data. do. This allows the first controller to be the reference controller and the second controller to be the controller to be tuned, and find reliable parameters for the second controller accurately, efficiently and at low cost. Further, while the placement of the second controller is realized based on the first control data actually output from the first controller, the first control data is usually used before the placement of the second controller is completed. The ability to control the smart device allows the parameters of the second controller to be better adapted to the current application of the smart device. Then, in the process of further adjusting the parameters of the second controller later, it is possible to reduce the risk of the smart device (e.g., vehicle) running out of control, and the possibility of a potential traffic accident due to the inappropriate setting of the parameters of the second controller. Safety risks can be reduced.

In some embodiments, the functions possessed by or the modules included in the apparatus according to the embodiments of the present invention may be for performing the methods described in the above method embodiments, the specific implementation of which is Reference can be made to the description of the method embodiment above, which is not repeated here for the sake of brevity.

Embodiments of the invention further provide a computer-readable storage medium. A computer readable storage medium stores computer program instructions, and the method is performed when the computer program instructions are executed by a processor. The computer-readable storage medium may be a non-volatile computer-readable storage medium or a volatile computer-readable storage medium.

Embodiments of the invention further provide a computer program product. The computer program product includes computer readable code, and when the computer readable code is run on the device, a processor in the device executes instructions for performing a parameter placement method according to any of the embodiments above.

Embodiments of the present invention further provide another computer program product. The computer program product stores computer readable instructions which, when executed, cause the computer to perform the operations of the parameter placement method according to any of the embodiments described above.

Embodiments of the present invention further provide an electronic device. The electronic device comprises one or more processors and memory for storing executable instructions. The one or more processors are configured to perform the method by calling executable instructions stored in the memory.

An electronic device may be provided as a terminal, server or other form of device.

FIG. 17 shows a block diagram of an electronic device 800 according to an embodiment of the invention. For example, the electronic device 800 may be a device such as an in-vehicle device, a mobile phone, a computer, a digital broadcast terminal, a message transmission/reception device, a game console, a tablet device, a medical device, a fitness device, a personal digital assistant, or the like.

Referring to FIG. 17, electronic device 800 includes one or more of the following units: processing unit 802, memory 804, power supply unit 806, multimedia unit 808, audio unit 810, input/output (I/O) An interface 812, a sensor unit 814 and a communication unit 816 may be provided.

The processing unit 802 typically controls the general operation of the electronic device 800, such as operations related to display, telephone calls, data communications, camera operations and recording operations. The processing unit 802 may comprise one or more processors 820 that execute instructions to perform all or part of the method steps described above. Processing unit 802 may also comprise one or more modules to facilitate interaction between processing unit 802 and other units. For example, processing unit 802 may include multimedia modules to facilitate interaction between multimedia unit 808 and processing unit 802 .

Memory 804 is configured to store each type of data to support operations on electronic device 800 . Examples of this data include any application program or method instructions for operating electronic device 800, contact data, phonebook data, messages, pictures, videos, and the like. Memory 804 may be any type of volatile or nonvolatile storage device or combination thereof, such as static random access memory (SRAM), electrically erasable programmable read only memory (EEPROM), erasable programmable read only memory. (EPROM), programmable read only memory (PROM), read only memory (ROM), magnetic memory, flash memory, magnetic disk or optical disk.

Power supply unit 806 provides power to each of the units of electronic device 800 . Power supply unit 806 may include a power management system, one or more power supplies, and other units involved in the generation, management and distribution of power for electronic device 800 .

A multimedia unit 808 comprises a screen that provides one output interface between the electronic device 800 and the user. In some examples, the screen may include a liquid crystal display (LCD) and a touch panel (TP). If the screen includes a touch panel, it may be implemented as a touch screen to receive input signals from the user. A touch panel includes one or more touch sensors to sense touches, slides, and gestures on the touch panel. The touch sensor can not only sense the boundaries of a touch or slide action, but also detect the duration and pressure associated with the touch or slide action. In some embodiments, multimedia unit 808 includes one front and/or back camera head. The front camera head and/or the back camera head can receive external multimedia data when the electronic device 800 is in an operating mode, such as a photography mode or a video mode. Each of the front and back camera heads may be one fixed optical lens system or may have a focal length and optical zoom capability.

Audio unit 810 is configured to output and/or input audio signals. For example, the audio unit 810 comprises a microphone (MIC), which is configured to receive external audio signals when the electronic device 800 is in operating modes, such as calling mode, recording mode and voice recognition mode. be. The received audio signal can also be stored in memory 804 or transmitted via communication unit 816 . In some embodiments, audio unit 810 further includes a speaker for outputting audio signals.

I/O interface 812 provides an interface between processing unit 802 and peripheral interface modules, which may be keyboards, click wheels, buttons, and the like. These buttons may include, but are not limited to, home page button, volume button, boot button and lock button.

Sensor unit 814 includes one or more sensors for providing state estimates to electronic device 800 on various aspects. For example, the sensor unit 814 can detect the on/off state of the electronic device 800 , the relative position of the unit, for example, the unit is the display and numeric keypad of the electronic device 800 . The sensor unit 814 also detects changes in the position of the electronic device 800 or a unit of the electronic device 800, the presence or absence of contact between the user and the electronic device 800, the orientation or acceleration/deceleration of the electronic device 800, and the temperature change of the electronic device 800. can be further detected. Sensor unit 814 may include a proximity sensor for detecting the presence of nearby objects when there is no physical contact. The sensor unit 814 may also include optical sensors used for imaging applications, such as CMOS or CCD image sensors. In some embodiments, the sensor unit 814 may further include an acceleration sensor, gyro sensor, magnetic sensor, pressure sensor or temperature sensor.

Communication unit 816 is configured to facilitate wireless or wired communications between electronic device 800 and other user devices. The electronic device 800 can access wireless networks based on communication standards, such as WiFi, 2G, 3G, 4G/LTE, 5G, or combinations thereof. In one exemplary embodiment, communication unit 816 receives broadcast signals or broadcast-related information from an external broadcast management system via a broadcast channel. In one exemplary embodiment, the communication unit 816 may also include a near-field communication (NFC) module to facilitate short-range communication. For example, in the NFC module, it may be implemented by Radio Frequency Identification (RFID) technology, Infrared Data Association (IrDA) technology, Ultra Wideband (UWB) technology, Bluetooth (BT) technology and other technologies.

In an exemplary embodiment, the electronic device 800 includes one or more application specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic to perform the methods described above. It may be implemented by a device (PLD), field programmable gate array (FPGA), controller, microcontroller, microprocessor or other electronic components.

The illustrative embodiment further provides a non-volatile computer-readable storage medium, such as memory 804, containing computer program instructions. The computer program instructions may be executed by processor 820 of electronic device 800 to implement the method.

FIG. 18 shows a block diagram of an electronic device 1900 according to an embodiment of the invention. For example, electronic device 1900 may be provided as a server. Referring to FIG. 18, the electronic device 1900 includes a processing unit 1922, and the processing unit 1922 further includes one or more processors and memory resources represented by a memory 1932, the memory 1932 for processing. Stores instructions that may be executed by unit 1922, such as application programs. An application program stored in memory 1932 may comprise one or more modules, each module corresponding to a set of instructions. The processing unit 1922 is also configured to implement the method by executing instructions.

The electronic device 1900 includes a power supply unit 1926 configured to perform power management of the electronic device 1900; a wired or wireless network interface 1950 configured to connect the electronic device 1900 to a network; /O) interface 1958. The electronic device 1900 uses an operating system stored in the memory 1932, such as Windows (registered trademark) Server, Mac (registered trademark) OS X, Unix (registered trademark), Linux (registered trademark), FreeBSD (registered trademark), or others. You can operate.

Exemplary embodiments further provide a non-volatile computer-readable storage medium, eg, memory 1932 containing computer program instructions. The computer program instructions are executed by the processing unit 1922 of the electronic device 1900 to implement the method.

The invention may be a system, method and/or computer program product. A computer program product may include a computer-readable storage medium. A computer readable storage medium carries computer readable program instructions for causing a processor to implement aspects of the present invention.

A computer-readable storage medium may be a tangible device that retains and stores instructions for use with a command-executing device. A computer-readable storage medium may be, for example, but not limited to, an electrical storage device, a magnetic storage device, an optical storage device, an electromagnetic storage device, a semiconductor storage device, or any suitable combination of the foregoing. More specific examples (non-exhaustive list) of computer readable storage media are portable computer disks, hard disks, random access memory (RAM), read only memory (ROM), erasable programmable read only memory (EPROM or flash memory). ), Static Random Access Memory (SRAM), Portable Compressed Disk Read Only Memory (CD-ROM), Digital Versatile Disk (DVD), Memory Stick, Floppy Disk, Mechanical Encoding Devices, e.g. Including punch cards or protrusion-in-channel structures, and any suitable combination of the above. Computer-readable storage media, as used herein, refers to instantaneous signals themselves, e.g., radio waves or other freely propagating electromagnetic waves, electromagnetic waves propagated through waveguides or other transmission media (e.g., fiber optic cables) light pulses over wires), or as electrical signals transmitted over wires.

The computer readable program instructions described herein may be downloaded from a computer readable storage medium to each computing/processing device, or transferred to an external computer or externally via networks such as the Internet, local area networks, wide area networks and/or wireless networks. It may be downloaded to a storage device. A network may include copper transmission cables, fiber optic transmission, wireless transmission, routers, firewalls, switches, gateway computers and/or edge servers. A network adapter or network interface in each computing/processing device receives computer-readable program instructions from the network and forwards the computer-readable program instructions for storage on a computer-readable storage medium in each computing/processing device.

Computer program instructions for carrying out the operations of the present invention may be assembly instructions, Instruction Set Architecture (ISA) instructions, machine instructions, machine-related instructions, microcode, firmware instructions, state setting data, or one or more of It may be source code or target code written in any combination of programming languages. The programming languages include object-oriented programming languages (eg, Smalltalk, C++, etc.) and conventional process programming languages (eg, "C" language) or similar programming languages. The computer-readable program instructions may be executed entirely on the user computer, partially executed on the user computer, executed as a separate software package, or partially executed on the user computer. but partly may be executed on the remote computer, or may be executed entirely on the remote computer or server. In the case of a remote computer, the remote computer may be connected to the user computer via any kind of network, including a local area network (LAN) or a wide area network (WAN), or to an external computer. (eg, connected to the Internet using an Internet Service Provider). In some embodiments, state information in computer readable program instructions is used to customize electronic circuits, such as programmable logic circuits, field programmable gate arrays (FPGAs), or programmable logic arrays (PLAs) with personalization. The electronic circuitry is capable of implementing aspects of the invention by executing computer readable program instructions.

Aspects of the present invention are described herein with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and/or block diagrams, and combinations of blocks in the flowchart illustrations and/or block diagrams, can be implemented in computer readable program instructions.

These computer readable program instructions can be supplied to a processor of a general purpose computer, special purpose computer or other programmable data processing apparatus to produce a machine. As such, an apparatus that, when executed by a processor of a computer or other programmable data processing apparatus, implements the functions/acts specified in one or more of the blocks in the flowchart illustrations and/or block diagrams. , is generated. These computer readable program instructions may be stored on a computer readable storage medium. These instructions cause computers, programmable data processing devices, and/or other equipment to operate in specific manners. As such, a computer-readable medium having instructions stored thereon may comprise an article of manufacture, which includes instructions for each aspect of implementing the functions/acts specified in one or more blocks in the flowcharts and/or block diagrams. including.

The computer readable program instructions may be loaded into a computer, other programmable data processing device, or other equipment. Thus, a series of operational steps are performed on a computer, other programmable data processing device, or other machine to produce a computer-implemented process. The instructions executed on the computer, other programmable data processing device, or other device, thereby implement the functions/acts specified in one or more of the blocks in the flowchart illustrations and/or block diagrams.

The flowcharts and block diagrams in the drawings illustrate the possible architectural architecture, functionality, and operation of systems, methods and computer program products according to several embodiments of the present invention. In this regard, each block in a flowchart or block diagram may represent part of a module, program segment or instruction. A portion of said module, program segment or instruction contains one or more executable instructions for performing a defined logical function. In some alternative implementations, the functions marked in the block may occur out of the order noted in the figures. For example, two consecutive blocks may indeed be executed essentially in parallel, and sometimes in reverse order, depending on their functionality. It should be noted that each block in the block diagrams and/or flowchart illustrations, and combinations of blocks in the block diagrams and/or flowchart illustrations, are implemented in dedicated hardware-based systems that perform the specified functions or acts. Alternatively, it may be implemented in a combination of dedicated hardware and computer instructions.

Said computer program product may be specifically implemented in hardware, software or a combination thereof. In one alternative embodiment, the computer program product may be embodied as a computer storage medium, and in another alternative embodiment, the computer program product is a software product, such as a Software Development Kit. Kit, SDK) or the like.

Above, each embodiment of the present invention was described. The above description is illustrative, not exhaustive, and not limited to each disclosed embodiment. Many modifications and variations will be apparent to those skilled in the art without departing from the scope and spirit of each described embodiment. The terms in this text are chosen to best interpret the principle, practical application, or technical improvement over the technology in the market of each embodiment, or to enable those skilled in the art to understand each embodiment disclosed herein. be.

This application claims priority to a Chinese patent application entitled "Parameter Allocation Method and Device, Electronic Device and Storage Medium" with application number 202010290979.6, filed on April 14, 2020. , the entire content of the Chinese patent application is incorporated herein by reference.

Claims (12)

A parameter placement method comprising:
The parameter arrangement method is applied to a smart device including a plurality of controllers, the plurality of controllers including at least a first controller and a second controller;
The parameter arrangement method is
obtaining control data output from each of the plurality of controllers, wherein the control data output from the first controller includes first control data, and the control data output from the second controller includes first control data; 2 including control data;
and a step of arranging parameters of the second controller based on the first control data and the second control data. The step of obtaining control data output from each of the plurality of controllers includes:
obtaining first reference trajectory data and first state data of the smart device in a first mode;
2. The parameter arrangement according to claim 1, comprising generating the respective control data based on the first reference trajectory data and the first state data via the plurality of controllers. Method. 3. The method of claim 1 or 2, further comprising controlling driving of the smart device in the first mode based on the first control data. obtaining second reference trajectory data and second state data of the smart device in a first mode;
generating third control data based on the second reference trajectory data and the second state data via the second controller;
4. The method of any one of claims 1 to 3, further comprising: controlling driving of the smart device in the first mode based on the third control data. a step of acquiring actual trajectory data generated by the smart device in the first mode while traveling;
5. The method of claim 4, further comprising adjusting parameters of the second controller according to the second reference trajectory data and the actual trajectory data. 6. A controller according to any one of claims 1 to 5, wherein the first controller is a controller that does not include a vehicle dynamics model and the second controller is a controller that includes a vehicle dynamics model. Parameter placement method. 7. The smart device comprises a smart mobile device, and the control data comprises at least one of steering wheel data, accelerator data, brake data and indicator lamp data. The parameter allocation method according to item 1. The step of controlling travel of the smart device in the first mode based on the third control data includes:
controlling travel of the smart device in the first mode based on the third control data in response to a difference between the first control data and the second control data satisfying a predetermined condition;
The predetermined condition includes that a difference between first target control data of the first control data and second target control data of the second control data belongs to a threshold range, and the first target control data and the second target control data are of the same type. A parameter placement device,
The parameter placement device is applied to a smart device including a plurality of controllers, the plurality of controllers including at least a first controller and a second controller,
The parameter placement device comprises:
A first acquisition module for acquiring control data output from each of the plurality of controllers, wherein the control data output from the first controller includes first control data, and the control data output from the second controller a first acquisition module wherein the control data includes second control data;
an arrangement module for arranging parameters of the second controller based on the first control data and the second control data. an electronic device,
comprising one or more processors and a memory for storing executable instructions;
The one or more processors are characterized in that they are arranged to execute the parameter placement method according to any one of claims 1 to 8 by invoking executable instructions stored in the memory. and electronic devices. A computer readable storage medium on which computer program instructions are stored, comprising:
A computer readable storage medium, characterized in that, when said computer program instructions are executed by a processor, a parameter placement method according to any one of claims 1 to 8 is implemented. A computer program product for storing computer readable instructions, characterized in that, when said computer readable instructions are executed, cause a computer to perform a parameter placement method according to any one of claims 1 to 8. computer program product.

Images