CN112861910A - Network simulation machine self-learning method and device - Google Patents
Network simulation machine self-learning method and device Download PDFInfo
- Publication number
- CN112861910A CN112861910A CN202110016776.2A CN202110016776A CN112861910A CN 112861910 A CN112861910 A CN 112861910A CN 202110016776 A CN202110016776 A CN 202110016776A CN 112861910 A CN112861910 A CN 112861910A
- Authority
- CN
- China
- Prior art keywords
- training
- simulation machine
- characteristic parameters
- information
- operator
- Prior art date
- Legal status (The legal status 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 status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
-
- G—PHYSICS
- G09—EDUCATION; CRYPTOGRAPHY; DISPLAY; ADVERTISING; SEALS
- G09B—EDUCATIONAL OR DEMONSTRATION APPLIANCES; APPLIANCES FOR TEACHING, OR COMMUNICATING WITH, THE BLIND, DEAF OR MUTE; MODELS; PLANETARIA; GLOBES; MAPS; DIAGRAMS
- G09B9/00—Simulators for teaching or training purposes
- G09B9/02—Simulators for teaching or training purposes for teaching control of vehicles or other craft
- G09B9/04—Simulators for teaching or training purposes for teaching control of vehicles or other craft for teaching control of land vehicles
Abstract
The invention discloses a self-learning method and a device of a network simulation machine, wherein the method comprises the following steps of switching the motion state of the simulation machine into a general mode; acquiring operator operation information and simulation machine movement information; extracting operation characteristic parameters and simulation machine motion characteristic parameters from operator operation information and simulation machine motion information respectively; searching and classifying in a classifier according to the operation characteristic parameters and the motion characteristic parameters of the simulation machine to obtain a classification result; identifying and matching the driving mode of the operator according to the classification result to obtain a driving mode matching result, and storing the driving mode matching result; according to the driving mode matching result, the motion state of the simulation machine is changed, and the driving mode can be selected by an operator to adapt to different operator styles, so that the driving comfort is improved, the vehicle using experience of the user is improved, and the technological sense of the vehicle is also improved.
Description
Technical Field
The invention relates to the field of industrial internet, in particular to a network simulation machine self-learning method and a network simulation machine self-learning device.
Background
Smart vehicles are emerging and testing on network simulation machines is required to provide a more reliable solution for smart vehicles. At present, the intelligent automobile can only provide two fixed driving modes and three fixed driving modes, but the two fixed driving modes and the three fixed driving modes cannot meet the driving preference of millions of consumers and cannot meet the requirements of operators in different driving modes, and a test self-learning method needs to be carried out on a network simulation machine.
Disclosure of Invention
The invention aims to provide a network simulation machine self-learning method and a network simulation machine self-learning device which are more comfortable to drive and meet different user requirements.
In order to achieve the above purposes, the technical scheme adopted by the invention is as follows:
the invention provides a network simulation machine self-learning method, which comprises the following steps:
switching the motion state of the simulation machine into a general mode;
acquiring operator operation information and simulation machine movement information;
extracting operation characteristic parameters and simulation machine motion characteristic parameters from the operator operation information and the simulation machine motion information respectively according to the operator operation information and the simulation machine motion information;
searching and classifying in a classifier according to the operation characteristic parameters and the motion characteristic parameters of the simulation machine to obtain a classification result;
identifying and matching the driving mode of the operator according to the classification result to obtain a driving mode matching result, and storing the driving mode matching result;
and changing the motion state of the simulation machine according to the driving mode matching result.
Optionally, the operator operation information is acquired through a simulation machine bus, and the motion information of the simulation machine is acquired through a sensor of the simulation machine;
the operating characteristic parameters include, but are not limited to, turn signal status, steering wheel angle, steering wheel angular acceleration, accelerator pedal travel, brake pedal travel, clutch pedal travel, and transmission gear, and the motion characteristic parameters include, but are not limited to, speed, position, acceleration, yaw rate, master cylinder pressure, and speed, distance, and acceleration of the simulated machine relative to surrounding simulated machines.
Optionally, the following conditions are simultaneously satisfied when the operator operation information and the simulation machine motion information are acquired:
simulating the machine running for not less than a preset time condition (1)
Maximum vehicle speed not less than 100km/h condition (2)
Accelerator pedal travel cover all position conditions 0-100% (3)
The following accelerator pedal travel within the preset time:
the travel of an accelerator pedal is more than or equal to 0 percent and less than 30 percent
The travel of an accelerator pedal is more than or equal to 30 percent and less than 65 percent
Condition (4) that the travel of the accelerator pedal is more than or equal to 65% and less than or equal to 100%
And simulating the starting process, the braking process and the steering process conditions of the machine within preset times (5).
Optionally, the classifier is generated by:
switching the motion state of the simulation machine into a general mode;
acquiring training operation information and training driving information of different trainers within preset time;
extracting training operation characteristic parameters and training movement characteristic parameters from the training operation information and the training driving information respectively according to the training operation information and the training driving information;
marking the training operation characteristic parameters and the training motion characteristic parameters of different trainees to mark corresponding driving modes of the trainees;
and learning and training the training operation characteristic parameters and the training movement characteristic parameters of different trainees to generate a classifier.
Further, the present invention also provides a network simulation machine self-learning apparatus, comprising:
the learning initialization module is used for switching the motion state of the simulation machine into a general mode;
the driving information acquisition module is used for acquiring operation information of an operator and motion information of a simulation machine;
the learning parameter extraction module is used for extracting operation characteristic parameters and simulation machine motion characteristic parameters from the operator operation information and the simulation machine motion information respectively according to the operator operation information and the simulation machine motion information;
the style classification module is used for searching and classifying in a classifier according to the operation characteristic parameters and the motion characteristic parameters to obtain a classification result;
the style matching module is used for identifying and matching the driving mode of the operator according to the classification result to obtain a driving mode matching result, and storing the driving mode matching result;
and the driving state changing module is used for changing the motion state of the simulation machine according to the driving mode matching result.
Optionally, the operator operation information is obtained through a simulation machine bus, and the motion information is obtained through a sensor installed on a simulation machine.
Optionally, the information acquisition module needs to satisfy the following conditions at the same time:
simulating that the machine has been running for no less than a predetermined time (6)
The highest vehicle speed is not less than 100km/h (7)
Accelerator pedal travel covers all position conditions 0-100% (8)
The following accelerator pedal travel within the preset time:
the travel of an accelerator pedal is more than or equal to 0 percent and less than 30 percent
The travel of an accelerator pedal is more than or equal to 30 percent and less than 65 percent
Condition (9) that the travel of the accelerator pedal is more than or equal to 65% and less than or equal to 100%
And simulating the starting process, the braking process and the steering process conditions of the machine within preset times (10).
Optionally, the style classification module includes:
the training initialization unit is used for switching the motion state of the simulation machine into a general mode;
the training information acquisition unit is used for acquiring training operation information and training driving information of different trainers within preset time;
the training parameter extraction unit is used for extracting training operation characteristic parameters and training movement characteristic parameters from the training operation information and the training driving information respectively according to the training operation information and the training driving information;
the marking unit is used for marking the training operation characteristic parameters and the training motion characteristic parameters of different trainees so as to mark the driving modes of the corresponding trainees;
and the generating unit is used for learning and training the training operation characteristic parameters and the training motion characteristic parameters of different trainers to generate the classifier.
Compared with the prior art, the invention has the beneficial effects that:
the network simulation machine self-learning method and the device thereof can enable an operator to select a driving mode of the operator by himself, so that the operator can teach own favorite vehicle by himself and can select the 'power style' of the favorite vehicle, thereby enabling the simulation machine to meet the driving mode requirements of consumers, not only being limited in several styles provided by manufacturers, realizing the self-learning capability of the driving mode of the simulation machine to adapt to different operator styles, improving the driving comfort, improving the vehicle using experience of users and increasing the technological sense of vehicles.
Drawings
FIG. 1 is a schematic diagram of a network simulation machine of the present invention during self-learning;
FIG. 2 is a graph of a driving pattern profile stored by the network simulation machine classifier/style classification module of the present invention.
Detailed Description
The present invention will be described in further detail with reference to the accompanying drawings and specific embodiments. The following description is presented to disclose the invention so as to enable any person skilled in the art to practice the invention. The preferred embodiments in the following description are given by way of example only, and other obvious variations will occur to those skilled in the art.
In fig. 1, a VCU vehicle controller collects signals related to drivability determination to recommend an operator driving mode, such as stroke information of an accelerator pedal and a brake pedal, and may establish signal communication with a MCU motor controller, an ESC electronic stability system controller, a BCM vehicle body controller, an EHU vehicle-mounted large screen controller, and the like through a CAN bus; the MCU motor controller is used for receiving a VCU vehicle controller control torque demand signal and controlling the motor to respond to a vehicle torque demand; the ESC electronic stabilization system controller is used for transmitting signals such as vehicle speed, steering wheel turning angle and the like to the VCU vehicle control unit; the BCM vehicle body controller transmits a turn signal of an operator to the VCU vehicle control unit; the EHU vehicle-mounted large screen controller is mainly used for confirming the driving requirements of an operator, can be used for starting a program for simulating the machine intelligent learning driving mode, can ensure that a user confirms whether the driving mode meets the driving requirements of the current operator, and can store a plurality of self-defined driving mode setting signals and the like.
Referring to fig. 1, the self-learning method includes the following steps:
s100) switching the motion state of the simulation machine into a general mode, after the operator selects the driving mode self-learning, before the simulation machine enters the driving mode self-learning, first, forcibly switching the driving mode of the current simulation machine into a normal mode (general mode), and then, learning the driving mode of the operator. For example. After an operator starts the console, the operator selects to enter a user-defined driving mode, and then the EHU vehicle-mounted large-screen controller sends a user-defined driving mode starting signal to the VCU vehicle controller.
Meanwhile, after the operator selects to enter the 'user-defined driving mode', the VCU vehicle controller sends a 'user-defined driving mode' word to be displayed on the central control console, so that the operator can be reminded conveniently; of course, the operator can also participate in the intelligent learning process of the VCU vehicle control unit consciously, for example, the operator wants to start faster and stronger power output, and can greatly step on the accelerator when the simulation machine just starts, and the VCU vehicle control unit can record the driving habits and characteristics of the operator at the moment and is used as a basis for a subsequent driving mode pushing.
S200) acquiring operator operation information and simulated machine motion information, specifically, in the embodiment, acquiring the operator operation information through a simulated machine bus, and acquiring the simulated machine motion information through a sensor of the simulated machine.
S300) extracting operation characteristic parameters and simulated machine motion characteristic parameters from the operator operation information and the simulated machine motion information respectively according to the operator operation information and the simulated machine motion information, wherein in the embodiment, the operation characteristic parameters comprise but are not limited to a steering lamp state, a steering wheel angle, a steering wheel angular acceleration, an accelerator pedal stroke, a brake pedal stroke, a clutch pedal stroke, a transmission gear position and the like, and the motion characteristic parameters comprise but are not limited to a speed, a position, an acceleration, a yaw angular velocity, a brake master cylinder pressure, a speed, a distance and an acceleration of the simulated machine relative to surrounding simulated machines and the like.
In the single self-learning process of the driving mode of the simulation machine, the VCU vehicle control unit can record the driving habits of an operator in real time, so that the driving mode requirement of the operator is inferred, and the driving characteristic data recorded by the VCU vehicle control unit is as follows:
travel of an accelerator pedal: recording the number of times of stepping on the accelerator and the interval of counting the change rate of the accelerator, and mainly reflecting the speed of the operator when stepping on the accelerator;
speed, position, acceleration, yaw rate, speed, distance and acceleration of the simulated machine relative to the surrounding simulated machine: the recording duration of the vehicle speed section can be recorded, and the vehicle speed change and the change rate interval in the driving process of an operator are mainly shown;
the state of the steering lamp: recording which turn lights are turned on and turn-on times of the turn lights, wherein the turn lights are mainly used for assisting in recording and representing the habit of overtaking of an operator;
steering wheel angle, steering wheel angular acceleration: recording the times that the turning angle of the steering wheel is not 0 or the times that the turning angle is larger than a certain value (preset value) and the angular acceleration when the steering wheel is operated, wherein the times and the angular acceleration are mainly used for assisting in recording and representing the habit of overtaking of an operator;
the braking times are as follows: the driving mode representation is mainly used for representing whether an operator brakes frequently and whether the brake is rapid or the rapid acceleration and rapid deceleration are performed;
when the vehicle is braked, the master cylinder pressure is sent to a VCU vehicle control unit by an ESC electronic stabilization system controller, and the VCU vehicle control unit sequentially judges whether an operator has frequent braking and sudden braking or the driving mode representation of sudden acceleration and sudden deceleration.
Meanwhile, in the present embodiment, the following conditions need to be satisfied simultaneously for acquiring the operator operation information and the simulation machine movement information:
simulating the machine running for not less than a preset time condition (1)
Maximum vehicle speed not less than 100km/h condition (2)
All positions with the accelerator pedal travel (i.e. accelerator opening) covering 0-100%
Condition (3)
The following accelerator pedal strokes within a preset time, for example, at least 20 minutes are acquired for each of the following accelerator pedal strokes:
the travel of an accelerator pedal is more than or equal to 0 percent and less than 30 percent (namely the opening degree of a small accelerator)
The travel of an accelerator pedal is more than or equal to 30 percent and less than 65 percent (namely the opening degree of the throttle of people)
The travel of the accelerator pedal is more than or equal to 65 percent and less than or equal to 100 percent (namely the throttle opening is large)
Condition (4)
And (5) at least acquiring conditions (5) of the starting process, the braking process and the steering process of the simulated machine within preset times, such as the starting process, the braking process and the steering process of the simulated machine for at least 10 times.
The purpose of the condition (1) is to enable a VCU (simulation machine controller) to acquire rich driving habits of an operator and more accurately push a driving mode torque characteristic curve, the purpose of the condition (2) is to basically ensure that all vehicle speed sections are learned, and the purpose of the condition (3) is to acquire driving actions of the operator from no stepping on the accelerator to the bottom stepping on the accelerator in the driving process.
S400) searching and classifying in the classifier according to the operation characteristic parameters and the motion characteristic parameters of the simulation machine to obtain a classification result.
N driving mode characteristic curves, which are shown in fig. 2, may be written by manufacturers in the internal memory of the VCU vehicle controller, and these driving mode characteristic curves include a linear driving mode and a linear power output, for example, the driving characteristic curve a, i.e., the normal mode (normal mode) mentioned above, has a linear relationship between the torque and the accelerator opening; some of the power generated by slightly stepping on the accelerator can be output vigorously, and the starting is very quick, such as a driving characteristic curve A; some accelerator output power at the front half section is very slow, is used for urban traffic jam road conditions, can well control the speed of the vehicle, and is suitable for many urban women. Such as curve G; some of the power is output more strongly under the opening degree of the front half section of the accelerator, so that certain 'riding dust' power requirements are met, the power output is more slowly interrupted by the accelerator, and the power output of the rear half section of the accelerator is more rapidly, so that the power-saving device is suitable for overtaking, such as a driving characteristic curve E.
S500) identifying and matching the driving mode of the operator according to the classification result to obtain a driving mode matching result, and storing the driving mode matching result.
The VCU vehicle control unit records the operator operation information and the simulation machine movement information in real time, and after the single simulation machine driving mode self-learning process is finished, the VCU recommends a driving curve according to the operator operation information and the simulation machine movement information collected in the simulation machine driving mode self-learning process.
The VCU vehicle control unit sends a driving characteristic curve learning recommended value of this time, such as a driving mode 1, to the EHU vehicle-mounted large screen controller, and after an operator clicks 'save', learning is successful;
when the operator drives the simulation machine next time, the operator can select the key through the driving mode to click and select the driving mode 1, and at the moment, the operator can experience the effect of the intelligent driving mode learning of the simulation machine last time;
in addition, a plurality of driving modes for intelligent learning, such as a driving mode 2, a driving mode 3 and the like, can be set in the VCU vehicle controller, and a user can save and delete the driving mode for simulating machine learning.
After finding out the favorite driving mode of the operator, the operator can save the favorite driving mode; therefore, the driving characteristics of the simulation machine are successfully learned intelligently, and the unique driving characteristic requirements of the public are met.
S600) changing the motion state of the simulation machine according to the driving mode matching result.
Specifically, the classifier in the step S400) is generated by the following steps:
s401) switching the motion state of the simulation machine to a general mode.
S402) acquiring training operation information and training driving information of different trainers within preset time;
s403), extracting training operation characteristic parameters and training motion characteristic parameters from the training operation information and the training driving information respectively according to the training operation information and the training driving information;
s404) marking the training operation characteristic parameters and the training motion characteristic parameters of different trainees to mark the driving modes of the corresponding trainees;
s405) learning and training the training operation characteristic parameters and the training motion characteristic parameters of different trainees according to a built-in algorithm to generate a classifier.
Referring to fig. 1, the self-learning apparatus includes:
the learning initialization module is used for switching the motion state of the simulation machine into a general mode, after the operator selects the driving mode self-learning, before the simulation machine enters the driving mode self-learning, the driving mode of the current simulation machine is first forcibly switched into a normal mode (the general mode), and the driving mode learning of the operator is carried out on the basis. For example. After an operator starts the console, the operator selects to enter a user-defined driving mode, and then the EHU vehicle-mounted large-screen controller sends a user-defined driving mode starting signal to the VCU vehicle controller.
Meanwhile, after the operator selects to enter the 'user-defined driving mode', the VCU vehicle controller sends a 'user-defined driving mode' word to be displayed on the central control console, so that the operator can be reminded conveniently; of course, the operator can also participate in the intelligent learning process of the VCU vehicle control unit consciously, for example, the operator wants to start faster and stronger power output, and can greatly step on the accelerator when the simulation machine just starts, and the VCU vehicle control unit can record the driving habits and characteristics of the operator at the moment and is used as a basis for a subsequent driving mode pushing.
The learning parameter extraction module is configured to obtain operator operation information and simulated machine motion information, and specifically, in this embodiment, the operator operation information is obtained through a simulated machine bus, and the simulated machine motion information is obtained through a sensor of a simulated machine.
And a learning parameter extraction module for extracting an operation characteristic parameter and a simulated machine motion characteristic parameter from the operator operation information and the simulated machine motion information respectively according to the operator operation information and the simulated machine motion information, wherein in the embodiment, the operation characteristic parameter comprises but is not limited to a steering lamp state, a steering wheel angle, a steering wheel angular acceleration, an accelerator pedal stroke, a brake pedal stroke, a clutch pedal stroke, a transmission gear position and the like, and the motion characteristic parameter comprises but is not limited to a speed, a position, an acceleration, a yaw angular velocity, a brake master cylinder pressure, a speed, a distance and an acceleration of the simulated machine relative to a surrounding simulated machine and the like.
In the single self-learning process of the simulation machine, the VCU vehicle control unit can record the driving habits of an operator in real time, so that the driving mode requirement of the operator is inferred, and the driving characteristic data recorded by the VCU vehicle control unit is as follows:
travel of an accelerator pedal: recording the number of times of stepping on the accelerator and the interval of counting the change rate of the accelerator, and mainly reflecting the speed of the operator when stepping on the accelerator;
speed, position, acceleration, yaw rate, speed, distance and acceleration of the simulated machine relative to the surrounding simulated machine: the recording duration of the vehicle speed section can be recorded, and the vehicle speed change and the change rate interval in the driving process of an operator are mainly shown;
the state of the steering lamp: recording which turn lights are turned on and turn-on times of the turn lights, wherein the turn lights are mainly used for assisting in recording and representing the habit of overtaking of an operator;
steering wheel angle, steering wheel angular acceleration: recording the times that the turning angle of the steering wheel is not 0 or the times that the turning angle is larger than a certain value (preset value) and the angular acceleration when the steering wheel is operated, wherein the times and the angular acceleration are mainly used for assisting in recording and representing the habit of overtaking of an operator;
the braking times are as follows: the driving mode representation is mainly used for representing whether an operator brakes frequently and whether the brake is rapid or the rapid acceleration and rapid deceleration are performed;
when the vehicle is braked, the master cylinder pressure is sent to a VCU vehicle control unit by an ESC electronic stabilization system controller, and the VCU vehicle control unit sequentially judges whether an operator has frequent braking and sudden braking or the driving mode representation of sudden acceleration and sudden deceleration.
Meanwhile, in the present embodiment, the following conditions need to be satisfied simultaneously for acquiring the operator operation information and the simulation machine movement information:
simulating that the machine has been running for no less than a predetermined time (6)
The highest vehicle speed is not less than 100km/h (7)
All positions with the accelerator pedal travel (i.e. accelerator opening) covering 0-100%
Condition (8)
The following accelerator pedal strokes within a preset time, for example, at least 20 minutes are acquired for each of the following accelerator pedal strokes:
the travel of an accelerator pedal is more than or equal to 0 percent and less than 30 percent (namely the opening degree of a small accelerator)
The travel of an accelerator pedal is more than or equal to 30 percent and less than 65 percent (namely the opening degree of the throttle of people)
The travel of the accelerator pedal is more than or equal to 65 percent and less than or equal to 100 percent (namely the throttle opening is large)
Condition (9)
And (3) simulating the starting process, the braking process and the steering process of the machine within preset times, wherein the conditions (10) are collected at least 10 times in the starting process, the braking process and the steering process of the simulated machine.
The purpose of the condition (6) is to enable the VCU to collect rich driving habits of an operator and to more accurately push a driving mode torque characteristic curve, the purpose of the condition (7) is to basically ensure that all vehicle speed sections are learned, and the purpose of the condition (8) is to collect driving actions of the operator from no stepping on the accelerator to stepping on the accelerator during the driving process.
And the style classification module is used for searching and classifying in the classifier according to the operation characteristic parameters and the motion characteristic parameters of the simulation machine to obtain a classification result.
N driving mode characteristic curves, which are shown in fig. 2, may be written by manufacturers in the internal memory of the VCU vehicle controller, and these driving mode characteristic curves include a linear driving mode and a linear power output, for example, the driving characteristic curve a, i.e., the normal mode (normal mode) mentioned above, has a linear relationship between the torque and the accelerator opening; some of the power generated by slightly stepping on the accelerator can be output vigorously, and the starting is very quick, such as a driving characteristic curve A; some accelerator output power at the front half section is very slow, is used for urban traffic jam road conditions, can well control the speed of the vehicle, and is suitable for many urban women. Such as curve G; some of the power is output more strongly under the opening degree of the front half section of the accelerator, so that certain 'riding dust' power requirements are met, the power output is more slowly interrupted by the accelerator, and the power output of the rear half section of the accelerator is more rapidly, so that the power-saving device is suitable for overtaking, such as a driving characteristic curve E.
And the style matching module is used for identifying and matching the driving mode of the operator according to the classification result to obtain a driving mode matching result and storing the driving mode matching result.
The VCU vehicle control unit records the operator operation information and the simulation machine movement information in real time, and after the single simulation machine driving mode self-learning process is finished, the VCU recommends a driving curve according to the operator operation information and the simulation machine movement information collected in the simulation machine self-learning process.
The VCU vehicle control unit sends a driving characteristic curve learning recommended value of this time, such as a driving mode 1, to the EHU vehicle-mounted large screen controller, and after an operator clicks 'save', learning is successful;
when the operator drives the simulation machine next time, the operator can select the driving mode 1 by clicking the driving mode selection key, and the operator can experience the learning effect of the driving mode of the simulation machine last time;
in addition, a plurality of driving modes for intelligent learning, such as a driving mode 2, a driving mode 3 and the like, can be set in the VCU vehicle controller, and a user can save and delete the driving mode for simulating machine learning.
After finding out the favorite driving mode of the operator, the operator can save the favorite driving mode; therefore, the driving characteristics of the simulation machine are successfully learned intelligently, and the unique driving characteristic requirements of the public are met.
And the driving state changing module is used for changing the motion state of the simulation machine according to the driving mode matching result.
Specifically, the style classification module comprises:
and the training initialization unit is used for switching the motion state of the simulation machine into a general mode.
The training information acquisition unit is used for acquiring training operation information and training driving information of different trainers within preset time;
the training parameter extraction unit is used for extracting training operation characteristic parameters and training movement characteristic parameters from the training operation information and the training driving information respectively according to the training operation information and the training driving information;
the marking unit is used for marking the training operation characteristic parameters and the training motion characteristic parameters of different trainers so as to mark the corresponding driving modes of the trainers;
and the generating unit is used for learning and training the training operation characteristic parameters and the training motion characteristic parameters of different trainers according to a built-in algorithm to generate the classifier.
The simulated machine driving pattern self-learning apparatus includes a processor, and a memory for storing a computer program, the processor for executing the computer program to cause the simulated machine self-learning apparatus to perform the simulated machine driving pattern self-learning method in any of the embodiments of the present application.
The computer system may be embodied in the form of a general purpose computing device. The computer system includes a memory, a processor, and a bus connecting the various system components.
The memory may include, for example, system memory, non-volatile storage media, and the like. The system memory stores, for example, an operating system, an application program, a Boot Loader (Boot Loader), and other programs. The system memory may include volatile storage media such as random access memory ((RAM) and/or cache memory, non-volatile storage media such as storing instructions for corresponding embodiments of at least one of the processing methods to perform the distributed transaction, non-volatile storage media including, but not limited to, disk storage, optical storage, flash memory, and the like.
The processor may be implemented as discrete hardware components, such as a general purpose processor, a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field Programmable Gate Array (FPGA) or other programmable logic device, discrete gates or transistors, or the like. Accordingly, each of the modules, such as the judging module and the determining module, may be implemented by a Central Processing Unit (CPU) executing instructions in a memory for performing the corresponding step, or may be implemented by a dedicated circuit for performing the corresponding step.
The bus may use any of a variety of bus architectures. For example, bus structures include, but are not limited to, Industry Standard Architecture (ISA) bus, Micro Channel Architecture (MCA) bus, and Peripheral Component Interconnect (PCI) bus.
The computer system may also include input-output interfaces, network interfaces, storage interfaces, and the like. The output interface, the network interface, the storage interface, and the memory and the processor may be connected by a bus. The input and output interface can provide a connection interface for input and output devices such as a display, a mouse, a keyboard and the like. The network interface provides a connection interface for various networking devices. The storage interface provides a connection interface for external storage equipment such as a floppy disk, a U disk, an SD card and the like.
Various aspects of the present disclosure are described herein with reference to flowchart illustrations and/or block diagrams of methods, apparatus and computer program products according to embodiments of the disclosure. 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 by computer-readable program instructions.
These computer-readable program instructions may be provided to a processor of a general purpose computer, special purpose computer, or other programmable apparatus to produce a machine, such that the execution of the instructions by the processor results in an apparatus that implements the functions specified in the flowchart and/or block diagram block or blocks.
These computer-readable program instructions may also be stored in a computer-readable memory that can direct a computer to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instructions which implement the function specified in the flowchart and/or block diagram block or blocks.
The simulation machine self-learning method and the device thereof can enable an operator to select a driving mode of the operator by self, so that the operator can teach own favorite vehicle and select the power style of the favorite vehicle, thereby enabling the simulation machine to meet the driving mode requirements of consumers, not only being limited in several styles provided by manufacturers, realizing the self-learning capability of the driving mode of the simulation machine, adapting to different operator styles, improving the driving comfort, improving the vehicle using experience of users and increasing the technological sense of vehicles.
Claims (8)
1. A network simulation machine self-learning method is characterized by comprising the following steps:
switching the motion state of the simulation machine into a general mode;
acquiring operator operation information and simulation machine movement information;
extracting operation characteristic parameters and simulation machine motion characteristic parameters from the operator operation information and the simulation machine motion information respectively according to the operator operation information and the simulation machine motion information;
searching and classifying in a classifier according to the operation characteristic parameters and the motion characteristic parameters of the simulation machine to obtain a classification result;
identifying and matching the driving mode of the operator according to the classification result to obtain a driving mode matching result, and storing the driving mode matching result;
and changing the motion state of the simulation machine according to the driving mode matching result.
2. The network simulation machine self-learning method as claimed in claim 1, wherein the operator operation information is obtained through a simulation machine bus, and the simulation machine movement information is obtained through a sensor of a simulation machine;
the operating characteristic parameters include, but are not limited to, turn signal status, steering wheel angle, steering wheel angular acceleration, accelerator pedal travel, brake pedal travel, clutch pedal travel, and transmission gear, and the motion characteristic parameters include, but are not limited to, speed, position, acceleration, yaw rate, master cylinder pressure, and speed, distance, and acceleration of the simulated machine relative to surrounding simulated machines.
3. The network simulation machine self-learning method as claimed in claim 2, wherein the following conditions are satisfied simultaneously when the operator operation information and the simulation machine movement information are acquired:
simulating the machine running for not less than a preset time condition (1)
Maximum vehicle speed not less than 100km/h condition (2)
Accelerator pedal travel cover all position conditions 0-100% (3)
The following accelerator pedal travel within the preset time:
the travel of an accelerator pedal is more than or equal to 0 percent and less than 30 percent
The travel of an accelerator pedal is more than or equal to 30 percent and less than 65 percent
Condition (4) that the travel of the accelerator pedal is more than or equal to 65% and less than or equal to 100%
And simulating the starting process, the braking process and the steering process conditions of the machine within preset times (5).
4. The network simulation machine self-learning method of claim 3, wherein the classifier is generated by the following steps:
switching the motion state of the simulation machine into a general mode;
acquiring training operation information and training driving information of different trainers within preset time;
extracting training operation characteristic parameters and training movement characteristic parameters from the training operation information and the training driving information respectively according to the training operation information and the training driving information;
marking the training operation characteristic parameters and the training motion characteristic parameters of different trainees to mark corresponding driving modes of the trainees;
and learning and training the training operation characteristic parameters and the training movement characteristic parameters of different trainees to generate a classifier.
5. A network-simulated machine self-learning apparatus employing the method of claim 1, comprising:
the learning initialization module is used for switching the motion state of the simulation machine into a general mode;
the driving information acquisition module is used for acquiring operation information of an operator and motion information of a simulation machine;
the learning parameter extraction module is used for extracting operation characteristic parameters and simulation machine motion characteristic parameters from the operator operation information and the simulation machine motion information respectively according to the operator operation information and the simulation machine motion information;
the style classification module is used for searching and classifying in a classifier according to the operation characteristic parameters and the motion characteristic parameters to obtain a classification result;
the style matching module is used for identifying and matching the driving mode of the operator according to the classification result to obtain a driving mode matching result, and storing the driving mode matching result;
and the driving state changing module is used for changing the motion state of the simulation machine according to the driving mode matching result.
6. The network simulation machine self-learning device as claimed in claim 5, wherein the operator operation information is obtained through a simulation machine bus, and the simulation machine movement information is obtained through a sensor of a simulation machine;
7. the network simulation machine self-learning device of claim 6, wherein the information acquisition module simultaneously satisfies the following conditions:
simulating that the machine has been running for no less than a predetermined time (6)
The highest vehicle speed is not less than 100km/h (7)
Accelerator pedal travel covers all position conditions 0-100% (8)
The following accelerator pedal travel within the preset time:
the travel of an accelerator pedal is more than or equal to 0 percent and less than 30 percent
The travel of an accelerator pedal is more than or equal to 30 percent and less than 65 percent
Condition (9) that the travel of the accelerator pedal is more than or equal to 65% and less than or equal to 100%
And simulating the starting process, the braking process and the steering process conditions of the machine within preset times (10).
8. The network-simulated machine self-learning apparatus as claimed in claim 7, wherein the style classification module comprises:
the training initialization unit is used for switching the motion state of the simulation machine into a general mode;
the training information acquisition unit is used for acquiring training operation information and training driving information of different trainers within preset time;
the training parameter extraction unit is used for extracting training operation characteristic parameters and training movement characteristic parameters from the training operation information and the training driving information respectively according to the training operation information and the training driving information;
the marking unit is used for marking the training operation characteristic parameters and the training motion characteristic parameters of different trainees so as to mark the driving modes of the corresponding trainees;
and the generating unit is used for learning and training the training operation characteristic parameters and the training motion characteristic parameters of different trainers to generate the classifier.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110016776.2A CN112861910A (en) | 2021-01-07 | 2021-01-07 | Network simulation machine self-learning method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110016776.2A CN112861910A (en) | 2021-01-07 | 2021-01-07 | Network simulation machine self-learning method and device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112861910A true CN112861910A (en) | 2021-05-28 |
Family
ID=76004573
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110016776.2A Pending CN112861910A (en) | 2021-01-07 | 2021-01-07 | Network simulation machine self-learning method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112861910A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112829758A (en) * | 2021-01-08 | 2021-05-25 | 广西宁达汽车科技有限公司 | Automobile driving style self-learning method, device, equipment and storage medium |
| CN117708438A (en) * | 2024-02-06 | 2024-03-15 | 浙江大学高端装备研究院 | Motorcycle driving mode recommendation method and system |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101633359A (en) * | 2008-07-24 | 2010-01-27 | 通用汽车环球科技运作公司 | Adaptive vehicle control system with driving style recognition |
| CN107249954A (en) * | 2014-12-29 | 2017-10-13 | 罗伯特·博世有限公司 | For the system and method using personalized driving profile operations autonomous vehicle |
| CN108995654A (en) * | 2018-07-06 | 2018-12-14 | 北京理工大学 | A kind of driver status recognition methods and system |
| CN108995653A (en) * | 2018-07-06 | 2018-12-14 | 北京理工大学 | A kind of driver's driving style recognition methods and system |
| WO2020119004A1 (en) * | 2018-12-10 | 2020-06-18 | Huawei Technologies Co., Ltd. | Personal driving style learning for autonomous driving |
-
2021
- 2021-01-07 CN CN202110016776.2A patent/CN112861910A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101633359A (en) * | 2008-07-24 | 2010-01-27 | 通用汽车环球科技运作公司 | Adaptive vehicle control system with driving style recognition |
| CN107249954A (en) * | 2014-12-29 | 2017-10-13 | 罗伯特·博世有限公司 | For the system and method using personalized driving profile operations autonomous vehicle |
| CN108995654A (en) * | 2018-07-06 | 2018-12-14 | 北京理工大学 | A kind of driver status recognition methods and system |
| CN108995653A (en) * | 2018-07-06 | 2018-12-14 | 北京理工大学 | A kind of driver's driving style recognition methods and system |
| WO2020119004A1 (en) * | 2018-12-10 | 2020-06-18 | Huawei Technologies Co., Ltd. | Personal driving style learning for autonomous driving |
Non-Patent Citations (1)
| Title |
|---|
| 李国法 等: "智能汽车决策中的驾驶行为语义解析关键技术", 《汽车安全与节能学报》, vol. 10, no. 04, 15 December 2019 (2019-12-15), pages 391 - 412 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112829758A (en) * | 2021-01-08 | 2021-05-25 | 广西宁达汽车科技有限公司 | Automobile driving style self-learning method, device, equipment and storage medium |
| CN117708438A (en) * | 2024-02-06 | 2024-03-15 | 浙江大学高端装备研究院 | Motorcycle driving mode recommendation method and system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112829758A (en) | Automobile driving style self-learning method, device, equipment and storage medium | |
| JP6966654B2 (en) | Virtual vehicle operation methods, model training methods, operation devices, and storage media | |
| CN111325230B (en) | Online learning method and online learning device for vehicle lane change decision model | |
| CN112861910A (en) | Network simulation machine self-learning method and device | |
| CN111409648B (en) | Driving behavior analysis method and device | |
| DE102017221617A1 (en) | Traffic jam estimation system and method | |
| CN111994084B (en) | Method and system for identifying driving style of driver and storage medium | |
| CN107526906A (en) | A kind of driving style device for identifying and method based on data acquisition | |
| CN113002545B (en) | Vehicle control method and device and vehicle | |
| CN112874519B (en) | Control method and system for adaptive cruise, storage medium and electronic device | |
| CN111856969B (en) | Automatic driving simulation test method and device | |
| CN112508054B (en) | Driving model training method, device, equipment and medium | |
| CN101587658A (en) | Graphics rendering engine and physics engine-based three-dimension automobile driving simulation device | |
| CN112466118A (en) | Vehicle driving behavior recognition method, system, electronic device and storage medium | |
| CN112109715B (en) | Method, device, medium and system for generating vehicle power output strategy | |
| CN112026746B (en) | Automobile energy management method, device and system, vehicle-mounted terminal and storage medium | |
| CN112569609B (en) | Vehicle and game control method and device thereof | |
| CN116340332A (en) | Method and device for updating scene library of vehicle-mounted intelligent system and vehicle | |
| CN117284302A (en) | User-specific driving mode generation method, system, vehicle, electronic equipment and storage medium | |
| Maas et al. | Simulator setup according to use case scenarios-A human-oriented method for virtual development | |
| CN113954855A (en) | Self-adaptive matching method for automobile driving mode | |
| CN115169477A (en) | Method, device and equipment for evaluating safety sense of assistant driving system and storage medium | |
| CN114238857A (en) | Experimental device and method based on driver dissatisfaction threshold acquisition | |
| CN111798717B (en) | Electric vehicle control system and method supporting VR driving training | |
| CN109733347B (en) | Man-machine coupled longitudinal collision avoidance control method |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20210528 |
|
| WD01 | Invention patent application deemed withdrawn after publication |