CN110843765A - Automatic driving method and device and electronic equipment - Google Patents
Automatic driving method and device and electronic equipment Download PDFInfo
- Publication number
- CN110843765A CN110843765A CN201911203048.1A CN201911203048A CN110843765A CN 110843765 A CN110843765 A CN 110843765A CN 201911203048 A CN201911203048 A CN 201911203048A CN 110843765 A CN110843765 A CN 110843765A
- Authority
- CN
- China
- Prior art keywords
- vehicle
- information
- motion state
- driving control
- comfort
- 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
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W30/00—Purposes of road vehicle drive control systems not related to the control of a particular sub-unit, e.g. of systems using conjoint control of vehicle sub-units, or advanced driver assistance systems for ensuring comfort, stability and safety or drive control systems for propelling or retarding the vehicle
- B60W30/02—Control of vehicle driving stability
- B60W30/025—Control of vehicle driving stability related to comfort of drivers or passengers
Abstract
The invention provides an automatic driving method, an automatic driving device and electronic equipment, wherein passenger information and vehicle motion state parameters are acquired, and vehicle driving control information corresponding to the passenger information is determined; calculating the riding comfort of the vehicle during the running process of the vehicle based on the passenger information and the vehicle motion state parameter; adjusting the vehicle driving control information based on the vehicle ride comfort. By the present invention, the vehicle riding comfort level of the occupant can be calculated, and the vehicle driving control information can also be adjusted based on the vehicle riding comfort level, that is, automatic driving control is performed based on the vehicle riding comfort level of the occupant.
Description
Technical Field
The invention relates to the field of automatic driving, in particular to an automatic driving method, an automatic driving device and electronic equipment.
Background
In order to change the original motion state in the automatic driving process of the vehicle, behaviors such as turning, braking or accelerating can occur, but the motion state of the vehicle can be suddenly changed by the behaviors, so that the riding experience with poor comfort is brought to passengers.
In order to improve the comfort of the occupants, there is a need for an autonomous vehicle control method that can be based on the comfort of the occupants.
Disclosure of Invention
In view of the above, the present invention provides an automatic driving method, an automatic driving device and an electronic apparatus, so as to solve the problem of urgently needing a control method of an automatic driving vehicle based on the comfort of passengers.
In order to solve the technical problems, the invention adopts the following technical scheme:
an autonomous driving method comprising:
acquiring passenger information and vehicle motion state parameters, and determining vehicle driving control information corresponding to the passenger information;
calculating the riding comfort of the vehicle during the running process of the vehicle based on the passenger information and the vehicle motion state parameter;
and adjusting the vehicle driving control information based on the vehicle riding comfort, and performing automatic driving control based on the adjusted vehicle driving control information.
Preferably, calculating the ride comfort of the vehicle during the running of the vehicle based on the occupant information and the vehicle motion state parameter includes:
obtaining a comfort degree calculation model, and calculating the riding comfort degree of the vehicle based on the passenger information, the vehicle motion state parameters and the comfort degree calculation model; the comfort degree calculation model represents the corresponding relation among the passenger information, the vehicle motion state parameters and the vehicle riding comfort degree;
wherein the generation process of the comfort level calculation model comprises the following steps:
acquiring passenger sample information, vehicle motion state sample information and environmental state sample information of different target driving objects in different road types and different driving modes;
obtaining comfort level parameters determined by the target driving object;
determining the comfort level calculation model based on the occupant sample information, the vehicle motion state sample information, the environmental state sample information, and the comfort level information.
Preferably, after the acquiring passenger sample information, vehicle motion state sample information and environment state sample information of different target driving objects in different road types and different driving modes, the method further includes:
carrying out data preprocessing on the vehicle motion state sample information and the environment state sample information; the data preprocessing comprises data time axis alignment, data validity check, singular value processing and data filtering;
extracting preset characteristic quantity from the vehicle motion state sample information and the environment state sample information subjected to data preprocessing;
correspondingly, determining the comfort level calculation model based on the occupant sample information, the vehicle motion state sample information, the environment state sample information, and the comfort level information includes:
and performing machine learning according to the passenger sample information, the preset characteristic quantity and the comfort level information to obtain the comfort level calculation model.
Preferably, adjusting the vehicle driving control information based on the vehicle riding comfort, and performing automatic driving control based on the adjusted vehicle driving control information includes:
obtaining a vehicle motion state prediction parameter according to a vehicle dynamic model and the vehicle driving control information;
calculating a predicted value of the riding comfort of the vehicle in the running process of the vehicle based on the passenger information and the predicted parameter of the motion state of the vehicle;
and if the predicted value of the riding comfort degree of the vehicle is not within the preset comfort degree range, adjusting the vehicle driving control information to obtain new vehicle driving control information, and returning to execute the step of obtaining the vehicle motion state prediction parameter according to the vehicle dynamics model and the vehicle driving control information until the predicted value of the riding comfort degree of the vehicle is within the preset comfort degree range, and controlling the vehicle to run through the latest vehicle driving control information.
An autopilot device comprising:
the information acquisition module is used for acquiring passenger information and vehicle motion state parameters and determining vehicle driving control information corresponding to the passenger information;
the comfort degree calculation module is used for calculating the riding comfort degree of the vehicle in the running process of the vehicle based on the passenger information and the vehicle motion state parameter;
and the vehicle control module is used for adjusting the vehicle driving control information based on the vehicle riding comfort and carrying out automatic driving control based on the adjusted vehicle driving control information.
Preferably, the comfort level calculating module is configured to, when calculating the riding comfort level of the vehicle during the running of the vehicle based on the occupant information and the vehicle motion state parameter, specifically:
obtaining a comfort degree calculation model, and calculating the riding comfort degree of the vehicle based on the passenger information, the vehicle motion state parameters and the comfort degree calculation model; the comfort degree calculation model represents the corresponding relation among the passenger information, the vehicle motion state parameters and the vehicle riding comfort degree;
correspondingly, the automatic driving device further comprises:
the data acquisition module is used for acquiring passenger sample information, vehicle motion state sample information and environment state sample information of different target driving objects in different road types and different driving modes;
the parameter acquisition module is used for acquiring comfort level parameters determined by the target driving object;
and the model training module is used for determining the comfort degree calculation model based on the passenger sample information, the vehicle motion state sample information, the environment state sample information and the comfort degree information.
Preferably, the automatic driving apparatus further includes:
the data processing module is used for carrying out data preprocessing on the vehicle motion state sample information and the environment state sample information; the data preprocessing comprises data time axis alignment, data validity check, singular value processing and data filtering;
the data extraction module is used for extracting preset characteristic quantity from the vehicle motion state sample information and the environment state sample information which are subjected to data preprocessing;
correspondingly, the model training module is configured to, when determining the comfort level calculation model based on the occupant sample information, the vehicle motion state sample information, the environmental state sample information, and the comfort level information, specifically:
and performing machine learning according to the passenger sample information, the preset characteristic quantity and the comfort level information to obtain the comfort level calculation model.
Preferably, the vehicle control module includes:
the parameter determination submodule is used for obtaining a vehicle motion state prediction parameter according to a vehicle dynamic model and the vehicle driving control information;
the numerical calculation submodule is used for calculating a predicted value of the riding comfort of the vehicle in the running process of the vehicle on the basis of the passenger information and the vehicle motion state prediction parameter;
and the driving control sub-module is used for adjusting the vehicle driving control information to obtain new vehicle driving control information if the predicted value of the vehicle riding comfort degree is not within the preset comfort degree range, and returning to execute the step of obtaining the vehicle motion state prediction parameter according to the vehicle dynamics model and the vehicle driving control information until the predicted value of the vehicle riding comfort degree is within the preset comfort degree range, and controlling the vehicle to run through the latest vehicle driving control information.
An electronic device, comprising: a memory and a processor;
wherein the memory is used for storing programs;
the processor calls a program and is used to:
acquiring passenger information and vehicle motion state parameters, and determining vehicle driving control information corresponding to the passenger information;
calculating the riding comfort of the vehicle during the running process of the vehicle based on the passenger information and the vehicle motion state parameter;
and adjusting the vehicle driving control information based on the vehicle riding comfort, and performing automatic driving control based on the adjusted vehicle driving control information.
Compared with the prior art, the invention has the following beneficial effects:
the invention provides an automatic driving method, an automatic driving device and electronic equipment, wherein passenger information and vehicle motion state parameters are acquired, and vehicle driving control information corresponding to the passenger information is determined; calculating the riding comfort of the vehicle during the running process of the vehicle based on the passenger information and the vehicle motion state parameter; adjusting the vehicle driving control information based on the vehicle ride comfort. By the present invention, the vehicle riding comfort level of the occupant can be calculated, and the vehicle driving control information can also be adjusted based on the vehicle riding comfort level, that is, automatic driving control is performed based on the vehicle riding comfort level of the occupant.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the provided drawings without creative efforts.
FIG. 1 is a flow chart of a method for automatic driving according to an embodiment of the present invention;
FIG. 2 is a flow chart of another method of automatic driving according to an embodiment of the present invention;
FIG. 3 is a flowchart of a method for providing yet another automatic driving method according to an embodiment of the present invention;
fig. 4 is a schematic structural diagram of an automatic steering device according to an embodiment of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
The embodiment of the invention provides an automatic driving method which can be applied to an automatic driving controller, such as an Electronic Control Unit (ECU) and the like. Referring to fig. 1, the automatic driving method may include:
and S11, acquiring the passenger information and the vehicle motion state parameters, and determining the vehicle driving control information corresponding to the passenger information.
The passenger information can be the age and name of the passenger, only one passenger in the vehicle is generally set, namely only the driver exists, the image information of the driver can be collected through the image collecting equipment, and the age and the sex of the driver can be obtained through image recognition operation. Such as sexed women, aged around 25 years. The automatic driving controller stores in advance a correspondence relationship between occupant information and vehicle driving control information, such as age 25, sex, and vehicle driving control information corresponding to a vehicle speed of about 60 KM/h. The vehicle driving control information in which the occupant information is stored in advance is the vehicle driving control information of the occupant most suitable for the sex and age.
The vehicle running state parameters CAN be obtained from the CAN bus, and CAN comprise parameters such as vehicle speed, forward speed, transverse speed, forward acceleration, transverse acceleration, downward acceleration, pitch angle, roll angle, forward angular speed, tangential angular speed, downward angular speed, forward angular acceleration, tangential angular acceleration, downward angular acceleration and the like.
And S12, calculating the vehicle riding comfort degree in the vehicle driving process based on the passenger information and the vehicle motion state parameters.
Specifically, the riding comfort of the vehicle refers to the comfort of the passenger in the riding process, if the vehicle speed is proper, the comfort is high when the passenger turns and changes lanes, and if the vehicle speed is too fast, the passenger cannot support sudden braking, the comfort is low.
The riding comfort of the vehicle is determined based on a pre-constructed comfort calculation model, and in a specific implementation, the step S12 may specifically include:
obtaining a comfort degree calculation model, and calculating the riding comfort degree of the vehicle based on the passenger information, the vehicle motion state parameters and the comfort degree calculation model; the comfort degree calculation model represents the corresponding relation among the passenger information, the vehicle motion state parameters and the vehicle riding comfort degree.
And inputting the passenger information and the vehicle motion state parameters into the comfort degree calculation model, namely outputting the riding comfort degree of the vehicle.
In addition, the comfort level calculation model is generated by a machine learning algorithm based on a large amount of data, and the generation process of the comfort level calculation model is introduced:
referring to fig. 2, the generation process of the comfort level calculation model may include:
and S21, acquiring passenger sample information, vehicle motion state sample information and environment state sample information of different target driving objects in different road types and different driving modes.
Before a comfort degree calculation model is constructed, a large amount of test data needs to be acquired, and manually driven vehicles run on different road types such as expressways or urban roads and different driving modes such as free straight running, lane changing, car following and the like. It should be noted that different persons (different ages or different sexes) are required to drive the vehicle, for example, men and women in different age groups from 20 to 50 years are automatically driven by the vehicle under different road types and different driving modes.
And in the running process of the vehicle, the passenger sample information is the age and the sex of the passenger. The vehicle motion state sample information is similar to the vehicle motion state information and includes parameters such as vehicle speed, forward speed, lateral speed, forward acceleration, lateral acceleration, downward acceleration, pitch angle, roll angle, forward angular speed, tangential angular speed, downward angular speed, forward angular acceleration, tangential angular acceleration, downward angular acceleration, and the like.
The environmental state sample information refers to an external environment where the vehicle runs and can be acquired through equipment such as a radar and a camera arranged on the vehicle, and the environmental state sample information can be longitudinal distance and transverse distance of an obstacle from the vehicle, longitudinal speed of the obstacle, type of the obstacle, transverse distance of a lane line from the vehicle, curvature of the lane line, an included angle between the vehicle and the tangential direction of the lane line and the like.
And S22, preprocessing the vehicle motion state sample information and the environment state sample information.
The data preprocessing comprises data time axis alignment, data validity check, singular value processing and data filtering, and the data preprocessing is carried out on the vehicle motion state sample information and the environment state sample information so as to ensure the accuracy of the data.
It should be noted that, during the driving of the vehicle, the driver may pass through different road types and different driving modes, and at this time, data of different road types and different driving modes needs to be segmented, that is, each group of data only includes data of one road type and one driving mode.
And S23, extracting preset characteristic quantity from the vehicle motion state sample information and the environment state sample information which are subjected to data preprocessing.
Specifically, in machine learning, due to the needs of different models, data needs to be normalized, for example, data is subjected to non-quantitative tempering, and common methods include a standardization method, an extremization method, an averaging method, a standard deviation method, a variance method, a quartile method, a method and the like.
In addition, the significance of the features of the existing data is not high, and some features need to be constructed from the existing data, and the original features are converted, for example, by squaring a single variable and the like.
And S24, obtaining the comfort degree parameter determined by the target object.
Specifically, the target driving object subjectively scores the scoring dimensions such as pitching feeling, acceleration intensity, acceleration frequency, braking intensity, braking frequency, rolling feeling, steering acceleration, steering frequency and the like to obtain a score of each dimension.
And S25, performing machine learning according to the occupant sample information, the preset characteristic quantity and the comfort level information to obtain the comfort level calculation model.
Specifically, the driving comfort under different driving modes is evaluated on line by utilizing a machine learning model through passenger sample information, the preset characteristic quantity and the comfort information, and the comfort calculation model representing the corresponding relation among the passenger information, the vehicle motion state parameters and the vehicle riding comfort can be obtained if the root mean square error of an online estimated value of the driving comfort and an artificial calibration value meets the requirement.
In the present embodiment, steps S22-23 may be regarded as preferable steps, but not essential steps, that is, step S24 may be directly performed after step S21 is performed. In addition, "machine learning is performed according to the occupant sample information, the preset feature quantity, and the comfort level information to obtain the comfort level calculation model," which can be used as a specific implementation manner for "determining the comfort level calculation model based on the occupant sample information, the vehicle motion state sample information, the environmental state sample information, and the comfort level information.
And S13, adjusting the vehicle driving control information based on the vehicle riding comfort, and performing automatic driving control based on the adjusted vehicle driving control information.
Specifically, after the vehicle riding comfort level is calculated, if the vehicle riding comfort level is not high, the vehicle driving control information can be adjusted, and then the automatic driving control is performed, so that the adjusted vehicle driving control information can improve the vehicle riding comfort level of the passenger.
In the embodiment, passenger information and vehicle motion state parameters are acquired, and vehicle driving control information corresponding to the passenger information is determined; calculating the riding comfort of the vehicle during the running process of the vehicle based on the passenger information and the vehicle motion state parameter; adjusting the vehicle driving control information based on the vehicle ride comfort. By the present invention, the vehicle riding comfort level of the occupant can be calculated, and the vehicle driving control information can also be adjusted based on the vehicle riding comfort level, that is, automatic driving control is performed based on the vehicle riding comfort level of the occupant.
In addition, the embodiment of the invention trains the model through a large amount of data acquisition and processing based on the subjective evaluation of the comfort of the passengers, and can predict the influence of the vehicle running state on the comfort of the passengers through the trained model. In addition, in the process of establishing the model, in order to meet different evaluations of comfort of different passengers, in the process of subjective evaluation, data for evaluating the comfort of the passengers with different sexes and ages is collected.
Alternatively, on the basis of the above description of "adjusting the vehicle driving control information based on the vehicle riding comfort, and performing automatic driving control based on the adjusted vehicle driving control information",
the specific implementation process of the invention is described in another specific implementation mode. Specifically, referring to fig. 3, step S14 may include:
and S31, obtaining vehicle motion state prediction parameters according to the vehicle dynamic model and the vehicle driving control information.
Specifically, the obtained vehicle driving control information is the vehicle driving control information most suitable for the age and sex of the occupant. There is still a need to verify whether the vehicle driving control information is appropriate for the current occupant. And inputting the vehicle driving control information into a vehicle dynamic model to obtain the current vehicle motion state prediction parameters. The vehicle dynamics model is pre-established.
It should be noted that the current vehicle state prediction parameter is not a real vehicle state parameter of the vehicle, but is data predicted based on a vehicle dynamics model.
And S32, calculating a predicted value of the riding comfort of the vehicle in the running process of the vehicle based on the passenger information and the predicted parameter of the motion state of the vehicle.
Specifically, similar to the process of calculating the riding comfort of the vehicle, the occupant information and the vehicle motion state prediction parameter are input into a comfort calculation model, and a predicted value of the riding comfort of the vehicle can be obtained.
S33, judging whether the predicted value of the riding comfort of the vehicle is in a preset comfort range; if so, go to step S35; if not, go to step S34.
Specifically, whether the predicted value of the riding comfort level of the vehicle is within the preset comfort level range or not is judged, namely, whether the passenger is comfortable or not is judged under the current driving of the vehicle, if the predicted value of the riding comfort level of the vehicle is not within the preset comfort level range, the passenger is considered to be uncomfortable, and if the predicted value of the riding comfort level of the vehicle is within the preset comfort level range, the passenger is considered to be comfortable.
And S34, adjusting the vehicle driving control information to obtain new vehicle driving control information.
The vehicle driving control information can be adjusted by adopting intelligent optimization algorithms such as a particle swarm algorithm, a genetic algorithm, an ant colony algorithm and the like, so that new vehicle driving control information is obtained.
After executing step S34, return is made to execution of step S32.
And S35, controlling the vehicle to run through the latest vehicle driving control information.
Specifically, if the vehicle is within the preset comfort level range, it indicates that the passenger is comfortable to ride, and at this time, the vehicle automatic driving control may be performed through the adjusted latest vehicle driving control information.
In the embodiment, in order to meet the comfortable states expected by different passengers, the respective expected comfortable range is determined under the condition of ensuring the running safety of the vehicle, the vehicle control parameters are adjusted, the parameters related to the comfortable sense are optimized on line, the comfortable sense of the passengers reaches the expected value, and the riding comfortable sense of the intelligent driving automobile is greatly improved.
Alternatively, on the basis of the embodiment of the automatic driving method, another embodiment of the present invention provides an automatic driving apparatus, and referring to fig. 4, the automatic driving apparatus may include:
the information acquisition module 101 is configured to acquire occupant information and vehicle motion state parameters, and determine vehicle driving control information corresponding to the occupant information;
a comfort degree calculation module 102, configured to calculate a vehicle riding comfort degree during vehicle driving based on the occupant information and the vehicle motion state parameter;
and the vehicle control module 103 is configured to adjust the vehicle driving control information based on the vehicle riding comfort, and perform automatic driving control based on the adjusted vehicle driving control information.
Optionally, on the basis of this embodiment, the comfort level calculating module is configured to, when calculating the riding comfort level of the vehicle in the vehicle driving process based on the occupant information and the vehicle motion state parameter, specifically:
obtaining a comfort degree calculation model, and calculating the riding comfort degree of the vehicle based on the passenger information, the vehicle motion state parameters and the comfort degree calculation model; the comfort degree calculation model represents the corresponding relation among the passenger information, the vehicle motion state parameters and the vehicle riding comfort degree;
correspondingly, the automatic driving device further comprises:
the data acquisition module is used for acquiring passenger sample information, vehicle motion state sample information and environment state sample information of different target driving objects in different road types and different driving modes;
the parameter acquisition module is used for acquiring comfort level parameters determined by the target driving object;
and the model training module is used for determining the comfort degree calculation model based on the passenger sample information, the vehicle motion state sample information, the environment state sample information and the comfort degree information.
Optionally, on the basis of this embodiment, the automatic driving apparatus further includes:
the data processing module is used for carrying out data preprocessing on the vehicle motion state sample information and the environment state sample information; the data preprocessing comprises data time axis alignment, data validity check, singular value processing and data filtering;
the data extraction module is used for extracting preset characteristic quantity from the vehicle motion state sample information and the environment state sample information which are subjected to data preprocessing;
correspondingly, the model training module is configured to, when determining the comfort level calculation model based on the occupant sample information, the vehicle motion state sample information, the environmental state sample information, and the comfort level information, specifically:
and performing machine learning according to the passenger sample information, the preset characteristic quantity and the comfort level information to obtain the comfort level calculation model.
In the embodiment, passenger information and vehicle motion state parameters are acquired, and vehicle driving control information corresponding to the passenger information is determined; calculating the riding comfort of the vehicle during the running process of the vehicle based on the passenger information and the vehicle motion state parameter; adjusting the vehicle driving control information based on the vehicle ride comfort. By the present invention, the vehicle riding comfort level of the occupant can be calculated, and the vehicle driving control information can also be adjusted based on the vehicle riding comfort level, that is, automatic driving control is performed based on the vehicle riding comfort level of the occupant.
In addition, the embodiment of the invention trains the model through a large amount of data acquisition and processing based on the subjective evaluation of the comfort of the passengers, and can predict the influence of the vehicle running state on the comfort of the passengers through the trained model. In addition, in the process of establishing the model, in order to meet different evaluations of comfort of different passengers, in the process of subjective evaluation, data for evaluating the comfort of the passengers with different sexes and ages is collected.
It should be noted that, for the working process of each module in this embodiment, please refer to the corresponding description in the above embodiments, which is not described herein again.
Optionally, on the basis of any one of the above embodiments of the automatic driving device, the vehicle control module includes:
the parameter determination submodule is used for obtaining a vehicle motion state prediction parameter according to a vehicle dynamic model and the vehicle driving control information;
the numerical calculation submodule is used for calculating a predicted value of the riding comfort of the vehicle in the running process of the vehicle on the basis of the passenger information and the vehicle motion state prediction parameter;
and the driving control sub-module is used for adjusting the vehicle driving control information to obtain new vehicle driving control information if the predicted value of the vehicle riding comfort degree is not within the preset comfort degree range, and returning to execute the step of obtaining the vehicle motion state prediction parameter according to the vehicle dynamics model and the vehicle driving control information until the predicted value of the vehicle riding comfort degree is within the preset comfort degree range, and controlling the vehicle to run through the latest vehicle driving control information.
In the embodiment, in order to meet the comfortable states expected by different passengers, the respective expected comfortable range is determined under the condition of ensuring the running safety of the vehicle, the vehicle control parameters are adjusted, the parameters related to the comfortable sense are optimized on line, the comfortable sense of the passengers reaches the expected value, and the riding comfortable sense of the intelligent driving automobile is greatly improved.
It should be noted that, for the working processes of each module and sub-module in this embodiment, please refer to the corresponding description in the above embodiments, which is not described herein again.
Optionally, on the basis of the embodiment of the automatic driving method and apparatus, another embodiment of the present invention provides an electronic device, which may include: a memory and a processor;
wherein the memory is used for storing programs;
the processor calls a program and is used to:
acquiring passenger information and vehicle motion state parameters, and determining vehicle driving control information corresponding to the passenger information;
calculating the riding comfort of the vehicle during the running process of the vehicle based on the passenger information and the vehicle motion state parameter;
and adjusting the vehicle driving control information based on the vehicle riding comfort, and performing automatic driving control based on the adjusted vehicle driving control information.
Further, calculating the vehicle ride comfort during the vehicle driving process based on the occupant information and the vehicle motion state parameter, comprising:
obtaining a comfort degree calculation model, and calculating the riding comfort degree of the vehicle based on the passenger information, the vehicle motion state parameters and the comfort degree calculation model; the comfort degree calculation model represents the corresponding relation among the passenger information, the vehicle motion state parameters and the vehicle riding comfort degree;
wherein the generation process of the comfort level calculation model comprises the following steps:
acquiring passenger sample information, vehicle motion state sample information and environmental state sample information of different target driving objects in different road types and different driving modes;
obtaining comfort level parameters determined by the target driving object;
determining the comfort level calculation model based on the occupant sample information, the vehicle motion state sample information, the environmental state sample information, and the comfort level information.
Further, after the obtaining of the passenger sample information, the vehicle motion state sample information and the environment state sample information of different target driving objects in different road types and different driving modes, the method further includes:
carrying out data preprocessing on the vehicle motion state sample information and the environment state sample information; the data preprocessing comprises data time axis alignment, data validity check, singular value processing and data filtering;
extracting preset characteristic quantity from the vehicle motion state sample information and the environment state sample information subjected to data preprocessing;
correspondingly, determining the comfort level calculation model based on the occupant sample information, the vehicle motion state sample information, the environment state sample information, and the comfort level information includes:
and performing machine learning according to the passenger sample information, the preset characteristic quantity and the comfort level information to obtain the comfort level calculation model.
Further, adjusting the vehicle driving control information based on the vehicle riding comfort, and performing automatic driving control based on the adjusted vehicle driving control information, including:
obtaining a vehicle motion state prediction parameter according to a vehicle dynamic model and the vehicle driving control information;
calculating a predicted value of the riding comfort of the vehicle in the running process of the vehicle based on the passenger information and the predicted parameter of the motion state of the vehicle;
and if the predicted value of the riding comfort degree of the vehicle is not within the preset comfort degree range, adjusting the vehicle driving control information to obtain new vehicle driving control information, and returning to execute the step of obtaining the vehicle motion state prediction parameter according to the vehicle dynamics model and the vehicle driving control information until the predicted value of the riding comfort degree of the vehicle is within the preset comfort degree range, and controlling the vehicle to run through the latest vehicle driving control information.
In the embodiment, passenger information and vehicle motion state parameters are acquired, and vehicle driving control information corresponding to the passenger information is determined; calculating the riding comfort of the vehicle during the running process of the vehicle based on the passenger information and the vehicle motion state parameter; adjusting the vehicle driving control information based on the vehicle ride comfort. By the present invention, the vehicle riding comfort level of the occupant can be calculated, and the vehicle driving control information can also be adjusted based on the vehicle riding comfort level, that is, automatic driving control is performed based on the vehicle riding comfort level of the occupant.
In addition, the embodiment of the invention trains the model through a large amount of data acquisition and processing based on the subjective evaluation of the comfort of the passengers, and can predict the influence of the vehicle running state on the comfort of the passengers through the trained model. In addition, in the process of establishing the model, in order to meet different evaluations of comfort of different passengers, in the process of subjective evaluation, data for evaluating the comfort of the passengers with different sexes and ages is collected.
The previous description of the disclosed embodiments is provided to enable any person skilled in the art to make or use the present invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the invention. Thus, the present invention is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
Claims (9)
1. An automatic driving method, characterized by comprising:
acquiring passenger information and vehicle motion state parameters, and determining vehicle driving control information corresponding to the passenger information;
calculating the riding comfort of the vehicle during the running process of the vehicle based on the passenger information and the vehicle motion state parameter;
and adjusting the vehicle driving control information based on the vehicle riding comfort, and performing automatic driving control based on the adjusted vehicle driving control information.
2. The autopilot method of claim 1 wherein calculating a vehicle ride comfort during vehicle travel based on the occupant information and the vehicle motion state parameter comprises:
obtaining a comfort degree calculation model, and calculating the riding comfort degree of the vehicle based on the passenger information, the vehicle motion state parameters and the comfort degree calculation model; the comfort degree calculation model represents the corresponding relation among the passenger information, the vehicle motion state parameters and the vehicle riding comfort degree;
wherein the generation process of the comfort level calculation model comprises the following steps:
acquiring passenger sample information, vehicle motion state sample information and environmental state sample information of different target driving objects in different road types and different driving modes;
obtaining comfort level parameters determined by the target driving object;
determining the comfort level calculation model based on the occupant sample information, the vehicle motion state sample information, the environmental state sample information, and the comfort level information.
3. The automatic driving method according to claim 2, further comprising, after the obtaining of occupant sample information, vehicle motion state sample information, and environmental state sample information for different target driving objects in different road types and different driving modes:
carrying out data preprocessing on the vehicle motion state sample information and the environment state sample information; the data preprocessing comprises data time axis alignment, data validity check, singular value processing and data filtering;
extracting preset characteristic quantity from the vehicle motion state sample information and the environment state sample information subjected to data preprocessing;
correspondingly, determining the comfort level calculation model based on the occupant sample information, the vehicle motion state sample information, the environment state sample information, and the comfort level information includes:
and performing machine learning according to the passenger sample information, the preset characteristic quantity and the comfort level information to obtain the comfort level calculation model.
4. The autopilot method of claim 1 wherein adjusting the vehicle driving control information based on the vehicle ride comfort and performing autopilot control based on the adjusted vehicle driving control information comprises:
obtaining a vehicle motion state prediction parameter according to a vehicle dynamic model and the vehicle driving control information;
calculating a predicted value of the riding comfort of the vehicle in the running process of the vehicle based on the passenger information and the predicted parameter of the motion state of the vehicle;
and if the predicted value of the riding comfort degree of the vehicle is not within the preset comfort degree range, adjusting the vehicle driving control information to obtain new vehicle driving control information, and returning to execute the step of obtaining the vehicle motion state prediction parameter according to the vehicle dynamics model and the vehicle driving control information until the predicted value of the riding comfort degree of the vehicle is within the preset comfort degree range, and controlling the vehicle to run through the latest vehicle driving control information.
5. An autopilot device, comprising:
the information acquisition module is used for acquiring passenger information and vehicle motion state parameters and determining vehicle driving control information corresponding to the passenger information;
the comfort degree calculation module is used for calculating the riding comfort degree of the vehicle in the running process of the vehicle based on the passenger information and the vehicle motion state parameter;
and the vehicle control module is used for adjusting the vehicle driving control information based on the vehicle riding comfort and carrying out automatic driving control based on the adjusted vehicle driving control information.
6. The autopilot device of claim 5, wherein the comfort level calculation module is configured to calculate a vehicle ride comfort level during vehicle travel based on the occupant information and the vehicle motion state parameter, in particular to:
obtaining a comfort degree calculation model, and calculating the riding comfort degree of the vehicle based on the passenger information, the vehicle motion state parameters and the comfort degree calculation model; the comfort degree calculation model represents the corresponding relation among the passenger information, the vehicle motion state parameters and the vehicle riding comfort degree;
correspondingly, the automatic driving device further comprises:
the data acquisition module is used for acquiring passenger sample information, vehicle motion state sample information and environment state sample information of different target driving objects in different road types and different driving modes;
the parameter acquisition module is used for acquiring comfort level parameters determined by the target driving object;
and the model training module is used for determining the comfort degree calculation model based on the passenger sample information, the vehicle motion state sample information, the environment state sample information and the comfort degree information.
7. The autopilot device of claim 6 further comprising:
the data processing module is used for carrying out data preprocessing on the vehicle motion state sample information and the environment state sample information; the data preprocessing comprises data time axis alignment, data validity check, singular value processing and data filtering;
the data extraction module is used for extracting preset characteristic quantity from the vehicle motion state sample information and the environment state sample information which are subjected to data preprocessing;
correspondingly, the model training module is configured to, when determining the comfort level calculation model based on the occupant sample information, the vehicle motion state sample information, the environmental state sample information, and the comfort level information, specifically:
and performing machine learning according to the passenger sample information, the preset characteristic quantity and the comfort level information to obtain the comfort level calculation model.
8. The autopilot device of claim 5 wherein the vehicle control module includes:
the parameter determination submodule is used for obtaining a vehicle motion state prediction parameter according to a vehicle dynamic model and the vehicle driving control information;
the numerical calculation submodule is used for calculating a predicted value of the riding comfort of the vehicle in the running process of the vehicle on the basis of the passenger information and the vehicle motion state prediction parameter;
and the driving control sub-module is used for adjusting the vehicle driving control information to obtain new vehicle driving control information if the predicted value of the vehicle riding comfort degree is not within the preset comfort degree range, and returning to execute the step of obtaining the vehicle motion state prediction parameter according to the vehicle dynamics model and the vehicle driving control information until the predicted value of the vehicle riding comfort degree is within the preset comfort degree range, and controlling the vehicle to run through the latest vehicle driving control information.
9. An electronic device, comprising: a memory and a processor;
wherein the memory is used for storing programs;
the processor calls a program and is used to:
acquiring passenger information and vehicle motion state parameters, and determining vehicle driving control information corresponding to the passenger information;
calculating the riding comfort of the vehicle during the running process of the vehicle based on the passenger information and the vehicle motion state parameter;
and adjusting the vehicle driving control information based on the vehicle riding comfort, and performing automatic driving control based on the adjusted vehicle driving control information.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911203048.1A CN110843765A (en) | 2019-11-29 | 2019-11-29 | Automatic driving method and device and electronic equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911203048.1A CN110843765A (en) | 2019-11-29 | 2019-11-29 | Automatic driving method and device and electronic equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110843765A true CN110843765A (en) | 2020-02-28 |
Family
ID=69606493
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911203048.1A Pending CN110843765A (en) | 2019-11-29 | 2019-11-29 | Automatic driving method and device and electronic equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110843765A (en) |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111861128A (en) * | 2020-06-20 | 2020-10-30 | 清华大学 | Method and system for evaluating connection comfortableness of automatic driving vehicle in man-machine cooperative operation process and storage medium |
| CN112208541A (en) * | 2020-10-13 | 2021-01-12 | 清华大学 | Intelligent passenger compartment parameterization determination method and device and computer equipment |
| CN112353393A (en) * | 2020-11-09 | 2021-02-12 | 清华大学 | Intelligent driving automobile passenger state detection system |
| CN112353392A (en) * | 2020-11-09 | 2021-02-12 | 清华大学 | Method for evaluating comfort of intelligent driving automobile passenger |
| CN113370984A (en) * | 2021-06-30 | 2021-09-10 | 中国科学技术大学先进技术研究院 | Multi-index-based comprehensive evaluation method and system for comfort of automatic driving vehicle |
| WO2022095985A1 (en) * | 2020-11-09 | 2022-05-12 | 清华大学 | Method and system for evaluating comfort of passenger of intelligent driving vehicle |
| WO2023273282A1 (en) * | 2021-06-30 | 2023-01-05 | 上海商汤临港智能科技有限公司 | Planning method and apparatus for vehicle driving behavior, electronic device, and storage medium |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104260725A (en) * | 2014-09-23 | 2015-01-07 | 北京理工大学 | Intelligent driving system with driver model |
| US10093252B2 (en) * | 2016-04-01 | 2018-10-09 | Uber Technologies, Inc. | Transport facilitation system for configuring a service vehicle for a user |
| CN109177979A (en) * | 2018-08-27 | 2019-01-11 | 百度在线网络技术（北京）有限公司 | Assess data processing method, device and the readable storage medium storing program for executing of comfort level of riding |
| CN109515441A (en) * | 2017-09-19 | 2019-03-26 | 上汽通用汽车有限公司 | Vehicle speed control system for intelligent driving vehicle |
| CN109910798A (en) * | 2019-04-04 | 2019-06-21 | 白冰 | A kind of device and method adjusting vehicle-state |
| CN109987085A (en) * | 2019-04-15 | 2019-07-09 | 深圳鸿鹏新能源科技有限公司 | Vehicle and its control method and device |
-
2019
- 2019-11-29 CN CN201911203048.1A patent/CN110843765A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104260725A (en) * | 2014-09-23 | 2015-01-07 | 北京理工大学 | Intelligent driving system with driver model |
| US10093252B2 (en) * | 2016-04-01 | 2018-10-09 | Uber Technologies, Inc. | Transport facilitation system for configuring a service vehicle for a user |
| CN109515441A (en) * | 2017-09-19 | 2019-03-26 | 上汽通用汽车有限公司 | Vehicle speed control system for intelligent driving vehicle |
| CN109177979A (en) * | 2018-08-27 | 2019-01-11 | 百度在线网络技术（北京）有限公司 | Assess data processing method, device and the readable storage medium storing program for executing of comfort level of riding |
| CN109910798A (en) * | 2019-04-04 | 2019-06-21 | 白冰 | A kind of device and method adjusting vehicle-state |
| CN109987085A (en) * | 2019-04-15 | 2019-07-09 | 深圳鸿鹏新能源科技有限公司 | Vehicle and its control method and device |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111861128A (en) * | 2020-06-20 | 2020-10-30 | 清华大学 | Method and system for evaluating connection comfortableness of automatic driving vehicle in man-machine cooperative operation process and storage medium |
| CN111861128B (en) * | 2020-06-20 | 2024-03-22 | 清华大学 | Method, system and storage medium for evaluating connection pipe comfort in man-machine cooperative control process of automatic driving vehicle |
| CN112208541A (en) * | 2020-10-13 | 2021-01-12 | 清华大学 | Intelligent passenger compartment parameterization determination method and device and computer equipment |
| CN112353393A (en) * | 2020-11-09 | 2021-02-12 | 清华大学 | Intelligent driving automobile passenger state detection system |
| CN112353392A (en) * | 2020-11-09 | 2021-02-12 | 清华大学 | Method for evaluating comfort of intelligent driving automobile passenger |
| CN112353392B (en) * | 2020-11-09 | 2022-03-15 | 清华大学 | Method for evaluating comfort of intelligent driving automobile passenger |
| WO2022095985A1 (en) * | 2020-11-09 | 2022-05-12 | 清华大学 | Method and system for evaluating comfort of passenger of intelligent driving vehicle |
| CN113370984A (en) * | 2021-06-30 | 2021-09-10 | 中国科学技术大学先进技术研究院 | Multi-index-based comprehensive evaluation method and system for comfort of automatic driving vehicle |
| WO2023273282A1 (en) * | 2021-06-30 | 2023-01-05 | 上海商汤临港智能科技有限公司 | Planning method and apparatus for vehicle driving behavior, electronic device, and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110843765A (en) | Automatic driving method and device and electronic equipment | |
| KR102343684B1 (en) | How to generate control data to assist drivers based on rules | |
| CN109733390B (en) | Self-adaptive lane change early warning method based on driver characteristics | |
| CN111775949B (en) | Personalized driver steering behavior auxiliary method of man-machine co-driving control system | |
| CN101054092B (en) | Driver workload-based vehicle stability enhancement control | |
| KR102301093B1 (en) | Method and device for optimizing driver assistance systems | |
| CN110103956A (en) | Automatic overtaking track planning method for unmanned vehicle | |
| CN108944943B (en) | Bend following model based on risk dynamic balance theory | |
| CN111325230A (en) | Online learning method and online learning device of vehicle lane change decision model | |
| CN109436085B (en) | Driving style-based drive-by-wire steering system transmission ratio control method | |
| CN112699721B (en) | Context-dependent adjustment of off-road glance time | |
| CN109808706A (en) | Learning type assistant driving control method, device, system and vehicle | |
| CN111332362A (en) | Intelligent steer-by-wire control method integrating individual character of driver | |
| DE102012220146A1 (en) | Method for characterizing driving behavior of driver of e.g. motor car, involves obtaining accumulation information of trends over deviation time and providing accumulation information for characterizing driving behavior | |
| CN111688700A (en) | Driving mode switching system, method and device and storage medium | |
| JP2020042786A (en) | Processing method of car image, processing device of car image and computer-readable storage medium | |
| CN109387374B (en) | Lane keeping level evaluation method | |
| CN112991685A (en) | Traffic system risk assessment and early warning method considering fatigue state influence of driver | |
| CN112560782A (en) | Vehicle lane changing behavior identification method based on random forest algorithm | |
| CN112418646A (en) | Vehicle comfort evaluation method and device and readable storage medium | |
| CN113353083B (en) | Vehicle behavior recognition method | |
| CN108238045B (en) | Vehicle control method and vehicle | |
| CN116238544B (en) | Running control method and system for automatic driving vehicle | |
| CN115107786B (en) | Driving behavior correction system and method for intelligent automobile | |
| CN110103968A (en) | Unmanned vehicle autonomous overtaking track planning system based on three-dimensional laser radar |
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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20200228 |