CN117932234A - Data processing method and system for manufacturing brake calibration table - Google Patents
Data processing method and system for manufacturing brake calibration table Download PDFInfo
- Publication number
- CN117932234A CN117932234A CN202410338613.XA CN202410338613A CN117932234A CN 117932234 A CN117932234 A CN 117932234A CN 202410338613 A CN202410338613 A CN 202410338613A CN 117932234 A CN117932234 A CN 117932234A
- Authority
- CN
- China
- Prior art keywords
- vehicle
- data
- driving
- brake pedal
- navigation
- 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.)
- Granted
Links
- 238000003672 processing method Methods 0.000 title claims abstract description 30
- 238000004519 manufacturing process Methods 0.000 title claims abstract description 25
- 230000001133 acceleration Effects 0.000 claims abstract description 66
- 238000012545 processing Methods 0.000 claims abstract description 51
- 238000013528 artificial neural network Methods 0.000 claims abstract description 46
- 238000001914 filtration Methods 0.000 claims abstract description 45
- 238000000034 method Methods 0.000 claims abstract description 30
- 230000006641 stabilisation Effects 0.000 claims abstract description 21
- 238000011105 stabilization Methods 0.000 claims abstract description 21
- 238000013507 mapping Methods 0.000 claims abstract description 16
- 238000007781 pre-processing Methods 0.000 claims abstract description 12
- 238000012216 screening Methods 0.000 claims abstract description 11
- 239000011159 matrix material Substances 0.000 claims description 28
- 230000003068 static effect Effects 0.000 claims description 25
- 230000008569 process Effects 0.000 claims description 16
- 230000006399 behavior Effects 0.000 claims description 14
- 210000002569 neuron Anatomy 0.000 claims description 12
- 230000008859 change Effects 0.000 claims description 11
- 238000001514 detection method Methods 0.000 claims description 9
- 230000006870 function Effects 0.000 claims description 9
- 238000013459 approach Methods 0.000 claims description 8
- 238000005457 optimization Methods 0.000 claims description 8
- 238000004590 computer program Methods 0.000 claims description 7
- 238000004458 analytical method Methods 0.000 claims description 6
- 238000007405 data analysis Methods 0.000 claims description 6
- 238000012549 training Methods 0.000 claims description 6
- 230000007704 transition Effects 0.000 claims description 6
- 239000000446 fuel Substances 0.000 claims description 5
- 230000035484 reaction time Effects 0.000 claims description 5
- 238000003860 storage Methods 0.000 claims description 5
- 238000010276 construction Methods 0.000 claims description 3
- 230000014759 maintenance of location Effects 0.000 claims description 3
- 230000035945 sensitivity Effects 0.000 claims description 3
- 238000012546 transfer Methods 0.000 claims description 3
- 238000005516 engineering process Methods 0.000 description 8
- 238000012360 testing method Methods 0.000 description 6
- 230000004044 response Effects 0.000 description 5
- 238000011161 development Methods 0.000 description 3
- 238000003491 array Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 2
- 238000002474 experimental method Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 238000005299 abrasion Methods 0.000 description 1
- 238000013499 data model Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 230000000630 rising effect Effects 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
Classifications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
- Y02T10/00—Road transport of goods or passengers
- Y02T10/10—Internal combustion engine [ICE] based vehicles
- Y02T10/40—Engine management systems
Landscapes
- Navigation (AREA)
Abstract
The invention discloses a data processing method and a system for manufacturing a brake calibration table, which relate to the technical field of vehicle navigation data processing and comprise the steps of collecting vehicle data in a driving scene and preprocessing the vehicle data; based on the preprocessed vehicle data, screening vehicle speed stable points through a sliding window, and constructing a vehicle navigation distance constraint model; and outputting the mapping relation between the brake pedal and the longitudinal acceleration under different driving modes under the combination of Kalman filtering and a neural network through the vehicle speed stabilization point and the vehicle navigation distance constraint, and optimizing the vehicle navigation and the driving track. According to the method, the vehicle speed stable points are screened through the sliding window, the vehicle navigation distance constraint model is constructed, and the driving safety and the navigation efficiency are improved; through the advantages of Kalman filtering and a neural network, the relationship between the use of the brake pedal and the longitudinal acceleration is deeply analyzed and predicted, and the accuracy and the driving experience and the safety of the vehicle navigation data processing are improved.
Description
Technical Field
The invention relates to the technical field of vehicle navigation data processing, in particular to a data processing method and system for manufacturing a brake calibration table.
Background
In the modern automobile industry, development of vehicle data processing technology has become a key for improving driving safety and efficiency, with rising automatic driving technology, accurate prediction and control of vehicle behaviors have become particularly important, traditional vehicle data processing methods mainly depend on basic sensor data such as vehicle speed, acceleration and the like, and simple data processing algorithms often look at a great deal of difficulty when processing complex driving scenes, especially in dynamically changing road conditions and changeable driving modes, and in recent years, vehicle data processing starts to change to higher-level data analysis and prediction models, especially the combined use of Kalman filtering and neural networks, along with the development of computing power and machine learning technology, so that new views are provided for vehicle behavior analysis.
However, despite the continual advances in technology, existing vehicle data processing methods still have some drawbacks, firstly, most methods are not efficient in processing high-dimensional and complex data and difficult to respond in real time, and secondly, the existing techniques often lack accuracy in processing uncertainty and nonlinearity problems, which is particularly obvious in complex driving environments, and furthermore, the existing techniques have certain limitations in fusing multi-source data to make comprehensive decisions, such as difficulty in accurately predicting vehicle behaviors in different driving modes.
The invention screens the speed stabilization point by utilizing the sliding window technology, which is helpful for identifying the key moment in the driving process, can provide an accurate reference for the subsequent data processing, combines the Kalman filtering and the neural network technology, not only improves the accuracy of the data processing, but also effectively solves the problems of nonlinearity and uncertainty, and the combination utilizes the advantages of the Kalman filtering in the state estimation and the strong capability of the neural network in the mode identification and prediction, and can more accurately output the mapping relation between the brake pedal and the longitudinal acceleration in different driving modes by the method, thereby optimizing the vehicle navigation and the driving track, not only improving the driving safety and comfort, but also laying a solid foundation for the development of an intelligent driving system.
Disclosure of Invention
The present invention has been made in view of the above-described problems.
Therefore, the technical problems solved by the invention are as follows: the existing vehicle navigation data processing method has the problems of low efficiency, low accuracy, limitation and how to carry out throttle brake control and vehicle navigation planning through the vehicle navigation data.
In order to solve the technical problems, the invention provides the following technical scheme: a data processing method for manufacturing a brake calibration table comprises the steps of collecting vehicle data in a driving scene and preprocessing the vehicle data; based on the preprocessed vehicle data, screening vehicle speed stable points through a sliding window, and constructing a vehicle navigation distance constraint model; and outputting the mapping relation between the brake pedal and the longitudinal acceleration under different driving modes under the combination of Kalman filtering and a neural network through the vehicle speed stabilization point and the vehicle navigation distance constraint, and optimizing the vehicle navigation and the driving track.
As a preferable scheme of the data processing method for manufacturing the brake calibration table, the invention comprises the following steps: the vehicle data in the acquired driving scene comprises vehicle speed data, brake pedal data, longitudinal acceleration data, RTK and navigation data, vehicle state data and driver behavior data; the vehicle speed data comprises an instantaneous vehicle speed and an average vehicle speed; the brake pedal data comprises a brake pedal angle, a brake pedal depth and a brake pedal use frequency; the longitudinal acceleration data comprises an acceleration peak value and an acceleration change rate; the RTK and navigation data comprise real-time geographic coordinates, a driving route and a driving distance; the vehicle state data includes engine parameters, vehicle load, and fuel efficiency; the driver behavior data includes a maneuver input, a reaction time.
As a preferable scheme of the data processing method for manufacturing the brake calibration table, the invention comprises the following steps: the preprocessing of the vehicle data comprises the steps of carrying out noise processing on vehicle speed data, brake pedal data, longitudinal acceleration data, RTK (real time kinematic) and navigation data in the vehicle data through a first-order filter, setting noise fluctuation constraint, removing peak and burr data, carrying out merging processing on the residual data, and expressing a filter difference equation as follows:
；
Wherein t represents time, y (t) represents a real-time output value, x (t) represents a real-time input value, y (t-1) is an output value at the previous moment, and a is a coefficient of the filter; RTK and navigation data noise fluctuation constraint Expressed as:
；
wherein, For the length of the time window,/>To adjust the coefficient,/>Controlling sensitivity and filtering degree of RTK and navigation data noise,/>For RTK and navigation data, when/>And when the data is larger than 0.6, the RTK and the navigation data are noise data, and data removal is carried out.
When (when)And when the data is smaller than or equal to 0.6, the RTK and the navigation data are normal data, and data retention is carried out.
As a preferable scheme of the data processing method for manufacturing the brake calibration table, the invention comprises the following steps: the step of screening the vehicle speed stable point through the sliding window comprises the steps of importing noise-processed vehicle speed data into the sliding window, wherein the single vehicle speed data time window is thatThe data points in the sliding window are expressed as:
；
wherein, Representing the speed at time t,/>All speed data representing the length T of the time window; the vehicle speed setting C at the vehicle speed stabilization point in the sliding window is expressed as:
；
Wherein n is a positive integer divided by 10, and the average speed in the sliding window Expressed as:
；
The absolute value of the average vehicle speed over the length T of the continuous time window is expressed as:
；
Setting a threshold value of the data average difference value When meeting/>Combining the information of two continuous time windows into a new time window when the/>, is not satisfiedAnd eliminating the data.
As a preferable scheme of the data processing method for manufacturing the brake calibration table, the invention comprises the following steps: the construction of the vehicle navigation distance constraint model comprises the steps of carrying out constraint analysis on the distance between the vehicle and the object in the running process of the vehicle based on vehicle data, comprehensively analyzing the vehicle data condition, and when the vehicle approaches to the static object, the constraint model is a static vehicle navigation distance constraint modelExpressed as:
；
wherein, For instantaneous vehicle speed,/>For longitudinal acceleration,/>For brake pedal depth,/>And/>Respectively representing RTK real-time geographic coordinates and points on a predetermined travel route,/>For vehicle load,/>For the driver reaction time,/>To adjust the coefficient,/>And/>And when the static vehicle navigation distance constraint model value is more than 0m and less than or equal to 2m, the vehicle navigation distance is a dangerous distance, the vehicle and the static object have collision risk, the brake pedal performs deceleration processing, the vehicle is subjected to track planning through RTK and navigation data, and the braking processing is performed when the vehicle navigation distance is continuously reduced by 50%.
When the static vehicle navigation distance constraint model value is greater than 2 meters, the vehicle navigation distance is a safe distance, the vehicle and the static object have no collision risk, and the vehicle is subjected to track planning through RTK and navigation data.
When the vehicle approaches to the dynamic object, the constraint model is a dynamic vehicle navigation distance constraint modelExpressed as:
；
wherein, For dynamic object movement characteristic parameter,/>For dynamic movement adjustment of coefficients,/>And the relative moving speed of the vehicle and the dynamic object is represented, when the constraint model value of the dynamic vehicle navigation distance is more than 1 meter and less than or equal to 3 meters, the vehicle navigation distance is a dangerous distance, a brake pedal is subjected to deceleration processing, the vehicle is subjected to track planning through RTK and navigation data, and when the vehicle navigation distance is continuously reduced by 30%, braking processing is performed.
When the dynamic vehicle navigation distance constraint model value is greater than 0 meter and less than or equal to 1 meter, the vehicle navigation distance is a dangerous distance, track planning is carried out on the vehicle through RTK and navigation data, if the track planning cannot avoid collision danger, the vehicle opens double flashes and whistles, the dynamic object is warned of collision risk and braking is carried out, and when the dynamic vehicle navigation distance constraint model value is greater than 3 meters, the vehicle navigation distance is a safe distance.
As a preferable scheme of the data processing method for manufacturing the brake calibration table, the invention comprises the following steps: the combination of the Kalman filtering and the neural network comprises training a state estimator, a Kalman gain and a measured state quantity in the Kalman filtering through the neural network, obtaining the relation between the final predicted steady-state vehicle speed and the depth of a brake pedal, establishing a data analysis model, and selecting the vehicle state quantity and the observed quantity to be expressed as:
；
wherein, Depth detection value of brake pedal at time t,/>Representing the speed at time t,/>Representing the time difference,/>The longitudinal acceleration at time t is indicated.
Through state transition matrixControl matrix/>A kalman prediction equation is established, expressed as:
；
wherein, Estimated value representing brake pedal depth at time t,/>Representing an estimate of brake pedal depth at the last instant,/>A longitudinal acceleration estimation value representing the last time; introducing a covariance matrix represents an uncertainty in determining an estimate, expressed as:
；
wherein, Representing the prediction covariance matrix at time t,/>Error of last time,/>Is process noise; establishing a Kalman filtering observation model expressed as:
；
wherein, Is the detection value of time t-The state vector is the state vector of the last moment, H is an observation matrix, and v is observation noise; the state update for the kalman filter is expressed as:
；
Wherein R is an observed noise covariance matrix, Is Kalman gain; updating the noise covariance matrix, establishing a neural network structure comprising an input layer, an implicit layer and an output layer, and obtaining a predicted value/>Gain matrix for Kalman filteringObserved value of observation equation/>Inputting an established neural network; taking the error between the Kalman filtering value and the true value as the output of the neural network, and the training process of the neural network is expressed as follows:
；
wherein, As learning factor,/>Is a momentum factor,/>Representing the weight change between the ith neuron in the l-1 layer and the jth neuron in the l layer connected by the time t,/>Representing the difference between the expected output and the true output value of the layer I neuron,/>The output of the ith neuron of the first layer 1 at time t is represented, and the transfer function is a sigmoid function.
As a preferable scheme of the data processing method for manufacturing the brake calibration table, the invention comprises the following steps: the method comprises the steps of outputting the mapping relation between the brake pedal and the longitudinal acceleration under different driving modes, wherein the mapping relation between the brake pedal and the longitudinal acceleration under different driving modes comprises the steps of predicting the mapping relation among the vehicle speed, the depth of the brake pedal and the acceleration based on the combination of Kalman filtering and a neural network through the vehicle speed stabilization point and the vehicle navigation distance constraint, and optimizing the vehicle navigation and the driving track, and the driving modes comprise a linear driving mode, a north-south driving mode, a comfortable driving mode and a motion driving mode.
The linear driving mode comprises the steps of driving a vehicle on a linear road, controlling a brake pedal and limiting longitudinal acceleration based on a static vehicle navigation distance constraint model and a dynamic vehicle navigation distance constraint model, recording vehicle navigation distance constraint data, and optimizing a driving track.
The north-south driving mode comprises the steps of driving a vehicle in an urban or changeable road environment, performing brake pedal control and longitudinal acceleration limitation through a depth detection value of a brake pedal based on the combination of Kalman filtering and a neural network, recording vehicle navigation distance constraint data, and performing driving track optimization.
The comfortable driving mode comprises the steps of driving a vehicle under urban roads or congested traffic conditions, performing brake pedal control and longitudinal acceleration limitation based on a static vehicle navigation distance constraint model, recording vehicle navigation distance constraint data, and performing driving track optimization.
The motion driving mode comprises the steps of driving a vehicle on a track or an open road, performing brake pedal control and longitudinal acceleration limitation based on a dynamic vehicle navigation distance constraint model combining Kalman filtering and a neural network, recording vehicle navigation distance constraint data, and performing driving track optimization.
Another object of the present invention is to provide a data processing system for manufacturing a brake calibration table, which can output the mapping relation between the brake pedal and the longitudinal acceleration in different driving modes through the combination of the vehicle speed stabilization point and the vehicle navigation distance constraint and under the combination of the kalman filtering and the neural network, optimize the vehicle navigation and the driving track and the longitudinal control performance of the vehicle, and solve the problems of low processing efficiency of the current vehicle navigation data and the reduction of the longitudinal control performance caused by the abrasion of the vehicle in the using process.
As a preferred embodiment of the data processing system for manufacturing a brake calibration table according to the present invention, the data processing system further comprises: the system comprises a data processing module, a vehicle speed constraint module and a pedal control module; the data processing module is used for collecting vehicle data in a driving scene and preprocessing the vehicle data; the vehicle speed constraint module is used for screening vehicle speed stable points through a sliding window based on the preprocessed vehicle data, and constructing a vehicle navigation distance constraint model; the pedal control module is used for outputting the mapping relation between the brake pedal and the longitudinal acceleration under different driving modes through the restraint of the vehicle speed stabilization point and the vehicle navigation distance and under the combination of Kalman filtering and a neural network, so as to optimize the vehicle navigation, the driving track and the longitudinal control performance.
A computer device comprising a memory storing a computer program and a processor executing the computer program is the step of implementing a data processing method for making a brake calibration table.
A computer readable storage medium having stored thereon a computer program which, when executed by a processor, implements the steps of a data processing method for making a brake calibration table.
The invention has the beneficial effects that: according to the data processing method for manufacturing the brake calibration table, clear and accurate basic data are provided for more complex data analysis and model construction by preprocessing the vehicle data, and the analysis precision and response speed of vehicle data processing are improved; the vehicle speed stabilization points are screened through the sliding window, a vehicle navigation distance constraint model is constructed, key moments and modes in the driving process are effectively identified, the understanding and predicting capacity of the vehicle behavior are improved, the vehicle navigation system is enabled to be more intelligent and high in adaptability, and the driving safety and the navigation efficiency are improved; through the advantages of Kalman filtering and a neural network, the complex relationship between the use of the brake pedal and the longitudinal acceleration of the vehicle is deeply analyzed and predicted, so that the vehicle navigation system can be more accurately adapted to different driving conditions and environments, the accuracy and driving experience of vehicle navigation data processing are improved, the safety is improved, and the invention has better effects in the aspects of accuracy, efficiency and reliability.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for the description of the embodiments will be briefly described below, it being obvious that the drawings in the following description are only some embodiments of the present invention, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a flowchart showing a data processing method for manufacturing a brake calibration table according to a first embodiment of the present invention.
FIG. 2 is a flowchart of a third embodiment of a data processing system for manufacturing a brake calibration table according to the present invention.
Detailed Description
So that the manner in which the above recited objects, features and advantages of the present invention can be understood in detail, a more particular description of the invention, briefly summarized above, may be had by reference to the embodiments, some of which are illustrated in the appended drawings. All other embodiments, which can be made by one of ordinary skill in the art based on the embodiments of the present invention without making any inventive effort, shall fall within the scope of the present invention.
Example 1
Referring to fig. 1, for one embodiment of the present invention, there is provided a data processing method for manufacturing a brake calibration table, including:
S1: and collecting vehicle data in a driving scene, and preprocessing the vehicle data.
Further, collecting vehicle data in the driving scene including vehicle speed data, brake pedal data, longitudinal acceleration data, RTK and navigation data, vehicle state data and driver behavior data; the vehicle speed data comprises an instantaneous vehicle speed and an average vehicle speed; the brake pedal data comprises a brake pedal angle, a brake pedal depth and a brake pedal use frequency; the longitudinal acceleration data comprises an acceleration peak value and an acceleration change rate; the RTK and navigation data comprise real-time geographic coordinates, a driving route and a driving distance; the vehicle state data includes engine parameters, vehicle load, and fuel efficiency; the driver behavior data includes a maneuver input, a reaction time.
It should be noted that, preprocessing the vehicle data includes noise processing the vehicle speed data, the brake pedal data, the longitudinal acceleration data, the RTK and the navigation data in the vehicle data through a first order filter, setting noise fluctuation constraint, removing peak and burr data, merging the remaining data, and expressing a filter difference equation as follows:
；
Wherein t represents time, y (t) represents a real-time output value, x (t) represents a real-time input value, y (t-1) is an output value at the previous moment, and a is a coefficient of the filter; RTK and navigation data noise fluctuation constraint Expressed as:
；
wherein, For the length of the time window,/>To adjust the coefficient,/>Controlling sensitivity and filtering degree of RTK and navigation data noise,/>For RTK and navigation data, when/>When the data is larger than 0.6, the RTK and the navigation data are noise data, and data removal is carried out; when/>And when the data is smaller than or equal to 0.6, the RTK and the navigation data are normal data, and data retention is carried out.
It should also be noted that the angle, depth and frequency of use of the brake pedal are covered and directly related to driving safety and vehicle control efficiency, the use mode of the brake pedal can reveal driving habits of a driver, such as frequent or sudden braking possibly pointing to aggressive or unsafe driving behaviors, longitudinal acceleration data, including acceleration peak value and change rate, are important parameters for evaluating dynamic response of the vehicle and driving style of the driver, the acceleration data are helpful for analyzing dynamic performance of the vehicle and acceleration habits of the driver, in terms of data preprocessing, a first order filter is adopted for noise processing of the vehicle data, peaks and burrs in the data are effectively removed, useful information is reserved, the processing not only improves the accuracy of the data, but also provides a more reliable basis for subsequent data analysis and decision, particularly noise processing of RTK and navigation data, and the accuracy and reliability of a navigation system are ensured by setting a threshold value, so that the navigation efficiency and driving safety are improved.
S2: and screening the vehicle speed stabilization points through a sliding window based on the preprocessed vehicle data, and constructing a vehicle navigation distance constraint model.
Further, the step of screening the vehicle speed stable point through the sliding window comprises the step of importing the vehicle speed data after noise processing into the sliding window, wherein the single vehicle speed data time window is thatThe data points in the sliding window are expressed as:
；
wherein, Representing the speed at time t,/>All speed data representing the length T of the time window; the vehicle speed setting C at the vehicle speed stabilization point in the sliding window is expressed as:
；
Wherein n is a positive integer divided by 10, and the average speed in the sliding window Expressed as:
；
The absolute value of the average vehicle speed over the length T of the continuous time window is expressed as:
；
Setting a threshold value of the data average difference value When meeting/>Combining the information of two continuous time windows into a new time window when the/>, is not satisfiedAnd eliminating the data.
It should be noted that, constructing the vehicle navigation distance constraint model includes performing constraint analysis on the distance between the vehicle and the object in the running process of the vehicle based on the vehicle data, comprehensively analyzing the vehicle data condition, and when the vehicle approaches to the static object, the constraint model is the static vehicle navigation distance constraint modelExpressed as:
；
wherein, For instantaneous vehicle speed,/>For longitudinal acceleration,/>For brake pedal depth,/>And/>Respectively representing RTK real-time geographic coordinates and points on a predetermined travel route,/>For vehicle load,/>For the driver reaction time,/>To adjust the coefficient,/>And/>And when the static vehicle navigation distance constraint model value is more than 0m and less than or equal to 2m, the vehicle navigation distance is a dangerous distance, the vehicle and the static object have collision risk, the brake pedal performs deceleration processing, the vehicle is subjected to track planning through RTK and navigation data, and the braking processing is performed when the vehicle navigation distance is continuously reduced by 50%.
When the static vehicle navigation distance constraint model value is greater than 2 meters, the vehicle navigation distance is a safe distance, the vehicle and the static object have no collision risk, and the vehicle is subjected to track planning through RTK and navigation data.
When the vehicle approaches to the dynamic object, the constraint model is a dynamic vehicle navigation distance constraint modelExpressed as:
；
wherein, For dynamic object movement characteristic parameter,/>For dynamic movement adjustment of coefficients,/>And the relative moving speed of the vehicle and the dynamic object is represented, when the constraint model value of the dynamic vehicle navigation distance is more than 1 meter and less than or equal to 3 meters, the vehicle navigation distance is a dangerous distance, a brake pedal is subjected to deceleration processing, the vehicle is subjected to track planning through RTK and navigation data, and when the vehicle navigation distance is continuously reduced by 30%, braking processing is performed.
When the dynamic vehicle navigation distance constraint model value is greater than 0 meter and less than or equal to 1 meter, the vehicle navigation distance is a dangerous distance, track planning is carried out on the vehicle through RTK and navigation data, if the track planning cannot avoid collision danger, the vehicle opens double flashes and whistles, the dynamic object is warned of collision risk and braking is carried out, and when the dynamic vehicle navigation distance constraint model value is greater than 3 meters, the vehicle navigation distance is a safe distance.
It should be further noted that, firstly, the sliding window speed stabilization point screening effectively identifies and analyzes the speed stabilization point by introducing the noise-processed speed data into the sliding window, and the application of this technique not only improves the accuracy of the speed data, but also helps to better understand the driving habit and behavior pattern of the driver, for example, by analyzing the speed setting C at the speed stabilization point, the driving speed of the vehicle can be effectively predicted and adjusted, thereby improving the fuel efficiency and reducing unnecessary acceleration or deceleration, secondly, the vehicle navigation distance constraint model is constructed based on the vehicle data, such as the instantaneous speed, the longitudinal acceleration, the brake pedal depth and the RTK and the navigation data, constraint analysis is performed on the distance between the vehicle and the object during the driving process, which is particularly important in terms of improving the driving safety, for example, when the vehicle approaches to a static object, the system calculates a safe distance, and avoids collision by the brake pedal deceleration process when the vehicle approaches to the dynamic object, and accordingly adjusts the driving locus and speed of the vehicle, so as to ensure the safe distance, and the two key factors are not improved, and the driving performance of the vehicle is not improved, and the driving risk is also improved, and the driving risk is greatly reduced by the system is able to respond to the real-time and the real-time traffic situation is optimized, and the driving system is able to respond to the real-time and the driving situation is optimized.
S3: and outputting the mapping relation between the brake pedal and the longitudinal acceleration under different driving modes under the combination of Kalman filtering and a neural network through the vehicle speed stabilization point and the vehicle navigation distance constraint, and optimizing the vehicle navigation and the driving track.
Further, the combination of the Kalman filtering and the neural network comprises training a state estimator, a Kalman gain and a measured state quantity in the Kalman filtering through the neural network, obtaining the relation between the final predicted steady-state vehicle speed and the depth of a brake pedal, establishing a data analysis model, and selecting the vehicle state quantity and the observed quantity to be expressed as:
；
wherein, Depth detection value of brake pedal at time t,/>Representing the speed at time t,/>Representing the time difference,/>The longitudinal acceleration at time t is indicated.
Through state transition matrixControl matrix/>A kalman prediction equation is established, expressed as:
；
wherein, Estimated value representing brake pedal depth at time t,/>Representing an estimate of brake pedal depth at the last instant,/>Representing the estimated longitudinal acceleration at the last instant.
Introducing a covariance matrix represents an uncertainty in determining an estimate, expressed as:
；
wherein, Representing the prediction covariance matrix at time t,/>Error of last time,/>Is process noise; establishing a Kalman filtering observation model expressed as:
；
wherein, Is the detection value of time t-The state vector is the state vector of the last moment, H is an observation matrix, and v is observation noise; the state update for the kalman filter is expressed as:
；
Wherein R is an observed noise covariance matrix, Is Kalman gain; updating the noise covariance matrix, establishing a neural network structure comprising an input layer, an implicit layer and an output layer, and obtaining a predicted value/>Gain matrix for Kalman filteringObserved value of observation equation/>Inputting an established neural network; taking the error between the Kalman filtering value and the true value as the output of the neural network, and the training process of the neural network is expressed as follows:
；
wherein, As learning factor,/>Is a momentum factor,/>Representing the weight change between the ith neuron in the l-1 layer and the jth neuron in the l layer connected by the time t,/>Representing the difference between the expected output and the true output value of the layer I neuron,/>The output of the ith neuron of the first layer 1 at time t is represented, and the transfer function is a sigmoid function.
It should be noted that outputting the mapping relation between the brake pedal and the longitudinal acceleration in different driving modes includes combining the Kalman filtering with the neural network based on the vehicle speed stabilization point and the vehicle navigation distance constraint, and predicting the mapping relation among the vehicle speed, the depth of the brake pedal and the acceleration to optimize the vehicle navigation and the driving track, wherein the driving modes include a straight driving mode, a north-south driving mode, a comfortable driving mode and a moving driving mode.
The linear driving mode comprises the steps of driving a vehicle on a linear road, controlling a brake pedal and limiting longitudinal acceleration based on a static vehicle navigation distance constraint model and a dynamic vehicle navigation distance constraint model, recording vehicle navigation distance constraint data, and optimizing a driving track.
The north-south driving mode comprises the steps of driving a vehicle in an urban or changeable road environment, performing brake pedal control and longitudinal acceleration limitation through a depth detection value of a brake pedal based on the combination of Kalman filtering and a neural network, recording vehicle navigation distance constraint data, and performing driving track optimization.
The comfortable driving mode comprises the steps of driving a vehicle under urban roads or congested traffic conditions, performing brake pedal control and longitudinal acceleration limitation based on a static vehicle navigation distance constraint model, recording vehicle navigation distance constraint data, and performing driving track optimization.
The motion driving mode comprises the steps of driving a vehicle on a track or an open road, performing brake pedal control and longitudinal acceleration limitation based on a dynamic vehicle navigation distance constraint model combining Kalman filtering and a neural network, recording vehicle navigation distance constraint data, and performing driving track optimization.
It should also be noted that the present invention integrates the kalman filtering and neural network technology, and aims to optimize the vehicle navigation and driving track, this combination not only improves the accuracy of data processing, but also enhances the adaptability of the system to complex driving environments, firstly, the kalman filtering is an effective linear dynamic system state estimation method, it provides an optimized mode to estimate the system state, such as the speed and position of the vehicle, by considering process noise and observation noise, in the present invention, the kalman filtering is used to estimate the depth of the brake pedal and the vehicle speed, this is crucial for understanding the dynamic behavior of the vehicle, the kalman filtering can predict the vehicle state at the next moment through the state transition matrix and the control matrix, thereby providing data support for driving decisions, secondly, the introduction of the neural network further enhances the processing capacity of the system, the neural network extracts pattern and relation from complex data, the neural network is used to train and optimize the output of the kalman filtering, thereby improving the accuracy of the prediction, and learning data, the neural network can better understand the speed and the complex speed, and the different driving modes are not predicted according to the complex speed and the different driving modes, and the different driving modes are also provided by combining the characteristics of the state transition matrix and the state transition matrix, the different from the navigation mode and the navigation system, and the different driving mode are more recommended, in addition, the driving mode is different from the driving mode is better predicted, and the driving mode is better predicted and the driving mode is different from the driving mode.
Example 2
In order to verify the beneficial effects of the invention, two vehicles with similar configurations are selected, one vehicle is provided with an advanced sensor and a data processing unit by using a traditional vehicle data processing system (comparison vehicle), the other vehicle is provided with an advanced sensor and a data processing unit, the vehicle speed, the use condition of a brake pedal, acceleration, RTK and navigation data, the vehicle state and driver behavior data can be acquired and processed in real time, the experiment is carried out in an urban traffic environment, including urban roads and highways in peak time, the experimental vehicle uses the method of the invention, the acquired data is preprocessed by a first-order filter, noise is removed, a vehicle navigation distance constraint model is constructed by analyzing a vehicle speed stabilization point by using a Kalman filter and a neural network technology, and the comparison vehicle uses the traditional vehicle data processing method.
Referring to table 1, during the experiment, both vehicles were driven on the same route and condition, and key data such as vehicle speed, brake pedal frequency of use, acceleration change, navigation efficiency, and safety response time were recorded.
Table 1 test data recording table
The test vehicle is superior to the comparison vehicle in terms of various indexes, and particularly, the average speed of the test vehicle is higher than that of the comparison vehicle, so that the road condition can be effectively utilized, the running efficiency is improved, meanwhile, the use frequency of a brake pedal of the test vehicle is obviously lower than that of the comparison vehicle, the potential safety hazard and the fuel consumption caused by frequent braking are reduced, in terms of the longitudinal acceleration change rate, the test vehicle shows smoother acceleration and deceleration processes, the riding comfort is improved, the potential danger caused by rapid acceleration or rapid braking is also reduced, the adaptability and the high efficiency of the method in a complex traffic environment are proved by the improvement of the navigation efficiency, the road condition change can be responded more quickly, the unnecessary running time is reduced, and most importantly, the safety response time of the test vehicle is obviously shorter than that of the comparison vehicle, so that the response can be made more quickly under the emergency condition, and the running safety is greatly improved.
In summary, the experimental results clearly show the remarkable advantages of the invention in terms of improving urban driving efficiency and safety, which not only embody the innovativeness of the invention, but also prove the great potential and practical value of the invention in practical application, so the invention has creativity.
Example 3
Referring to FIG. 2, a data processing system for manufacturing a brake calibration table is provided according to an embodiment of the present invention, and includes a data processing module, a vehicle speed constraint module, and a pedal control module.
The data processing module is used for collecting vehicle data in a driving scene and preprocessing the vehicle data; the vehicle speed constraint module is used for screening vehicle speed stable points through a sliding window based on the preprocessed vehicle data, and constructing a vehicle navigation distance constraint model; the pedal control module is used for outputting the mapping relation between the brake pedal and the longitudinal acceleration under different driving modes through the combination of the Kalman filtering and the neural network by means of the vehicle speed stabilization point and the vehicle navigation distance constraint, and optimizing the vehicle navigation, the driving track and the longitudinal control performance.
The functions, if implemented in the form of software functional units and sold or used as a stand-alone product, may be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention may be embodied essentially or in a part contributing to the prior art or in a part of the technical solution in the form of a software product stored in a storage medium, comprising several instructions for causing a computer device (which may be a personal computer, a server, a network device, etc.) to perform all or part of the steps of the method of the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a random access Memory (RAM, randomAccess Memory), a magnetic disk, an optical disk, or other various media capable of storing program codes.
Logic and/or steps represented in the flowcharts or otherwise described herein, e.g., a ordered listing of executable instructions for implementing logical functions, can be embodied in any computer-readable medium for use by or in connection with an instruction execution system, apparatus, or device, such as a computer-based system, processor-containing system, or other system that can fetch the instructions from the instruction execution system, apparatus, or device and execute the instructions. For the purposes of this description, a "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transport the program for use by or in connection with the instruction execution system, apparatus, or device.
More specific examples (a non-exhaustive list) of the computer-readable medium would include the following: an electrical connection (electronic device) having one or more wires, a portable computer diskette (magnetic device), a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disc read-only memory (CDROM). Additionally, the computer-readable medium may even be paper or other suitable medium upon which the program is printed, as the program may be electronically captured, via, for instance, optical scanning of the paper or other medium, then compiled, interpreted or otherwise processed in a suitable manner, if necessary, and then stored in a computer memory.
It is to be understood that portions of the present invention may be implemented in hardware, software, firmware, or a combination thereof. In the above-described embodiments, the various steps or methods may be implemented in software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, may be implemented using any one or combination of the following techniques, as is well known in the art: discrete logic circuits having logic gates for implementing logic functions on data signals, application specific integrated circuits having suitable combinational logic gates, programmable Gate Arrays (PGAs), field Programmable Gate Arrays (FPGAs), and the like. It should be noted that the above embodiments are only for illustrating the technical solution of the present invention and not for limiting the same, and although the present invention has been described in detail with reference to the preferred embodiments, it should be understood by those skilled in the art that the technical solution of the present invention may be modified or substituted without departing from the spirit and scope of the technical solution of the present invention, which is intended to be covered in the scope of the claims of the present invention.
It should be noted that the above embodiments are only for illustrating the technical solution of the present invention and not for limiting the same, and although the present invention has been described in detail with reference to the preferred embodiments, it should be understood by those skilled in the art that the technical solution of the present invention may be modified or substituted without departing from the spirit and scope of the technical solution of the present invention, which is intended to be covered in the scope of the claims of the present invention.
Claims (10)
1. A data processing method for manufacturing a brake calibration table, comprising:
Collecting vehicle data in a driving scene, and preprocessing the vehicle data;
Based on the preprocessed vehicle data, screening vehicle speed stable points through a sliding window, and constructing a vehicle navigation distance constraint model;
And outputting the mapping relation between the brake pedal and the longitudinal acceleration under different driving modes under the combination of Kalman filtering and a neural network through the vehicle speed stabilization point and the vehicle navigation distance constraint, and optimizing the vehicle navigation and the driving track.
2. The data processing method for manufacturing a brake calibration table according to claim 1, wherein: the vehicle data in the acquired driving scene comprises vehicle speed data, brake pedal data, longitudinal acceleration data, RTK and navigation data, vehicle state data and driver behavior data;
the vehicle speed data comprises an instantaneous vehicle speed and an average vehicle speed;
The brake pedal data comprises a brake pedal angle, a brake pedal depth and a brake pedal use frequency;
The longitudinal acceleration data comprises an acceleration peak value and an acceleration change rate;
the RTK and navigation data comprise real-time geographic coordinates, a driving route and a driving distance;
the vehicle state data includes engine parameters, vehicle load, and fuel efficiency;
the driver behavior data includes a maneuver input, a reaction time.
3. The data processing method for manufacturing a brake calibration table according to claim 2, wherein: the preprocessing of the vehicle data comprises the steps of carrying out noise processing on vehicle speed data, brake pedal data, longitudinal acceleration data, RTK (real time kinematic) and navigation data in the vehicle data through a first-order filter, setting noise fluctuation constraint, removing peak and burr data, carrying out merging processing on the residual data, and expressing a filter difference equation as follows:
；
wherein t represents time, y (t) represents a real-time output value, x (t) represents a real-time input value, y (t-1) is an output value at the previous moment, and a is a coefficient of the filter;
RTK and navigation data noise fluctuation constraint Expressed as:
；
wherein, For the length of the time window,/>To adjust the coefficient,/>Controlling sensitivity and filtering degree of RTK and navigation data noise,/>For RTK and navigation data, when/>When the data is larger than 0.6, the RTK and the navigation data are noise data, and data removal is carried out;
When (when) And when the data is smaller than or equal to 0.6, the RTK and the navigation data are normal data, and data retention is carried out.
4. A data processing method for making a brake calibration table as claimed in claim 3, wherein: the step of screening the vehicle speed stable point through the sliding window comprises the steps of importing noise-processed vehicle speed data into the sliding window, wherein the single vehicle speed data time window is thatThe data points in the sliding window are expressed as:
；
wherein, Representing the speed at time t,/>All speed data representing the length T of the time window;
The vehicle speed setting C at the vehicle speed stabilization point in the sliding window is expressed as:
；
Wherein n is a positive integer divided by 10, and the average speed in the sliding window Expressed as:
；
The absolute value of the average vehicle speed over the length T of the continuous time window is expressed as:
；
Setting a threshold value of the data average difference value When meeting/>Combining the information of two continuous time windows into a new time window when the/>, is not satisfiedAnd eliminating the data.
5. The data processing method for manufacturing a brake calibration table according to claim 4, wherein: the construction of the vehicle navigation distance constraint model comprises the steps of carrying out constraint analysis on the distance between the vehicle and the object in the running process of the vehicle based on vehicle data, comprehensively analyzing the vehicle data condition, and when the vehicle approaches to the static object, the constraint model is a static vehicle navigation distance constraint modelExpressed as:
；
wherein, For instantaneous vehicle speed,/>For longitudinal acceleration,/>For brake pedal depth,/>And/>Respectively representing RTK real-time geographic coordinates and points on a predetermined travel route,/>For vehicle load,/>In order for the driver to react to the time,To adjust the coefficient,/>And/>When the static vehicle navigation distance constraint model value is more than 0m and less than or equal to 2m, the vehicle navigation distance is a dangerous distance, the vehicle and a static object have collision risk, a brake pedal performs deceleration processing, track planning is performed on the vehicle through RTK and navigation data, and braking processing is performed when the vehicle navigation distance is continuously reduced by 50%;
When the static vehicle navigation distance constraint model value is greater than 2 meters, the vehicle navigation distance is a safe distance, the vehicle and a static object have no collision risk, and track planning is carried out on the vehicle through RTK and navigation data;
when the vehicle approaches to the dynamic object, the constraint model is a dynamic vehicle navigation distance constraint model Expressed as:
；
wherein, For dynamic object movement characteristic parameter,/>For dynamic movement adjustment of coefficients,/>Representing the relative moving speed of the vehicle and the dynamic object, when the constraint model value of the dynamic vehicle navigation distance is more than 1 meter and less than or equal to 3 meters, the vehicle navigation distance is a dangerous distance, a brake pedal is subjected to deceleration processing, the vehicle is subjected to track planning through RTK and navigation data, and when the vehicle navigation distance is continuously reduced by 30%, braking processing is performed;
When the dynamic vehicle navigation distance constraint model value is greater than 0 meter and less than or equal to 1 meter, the vehicle navigation distance is a dangerous distance, track planning is carried out on the vehicle through RTK and navigation data, if the track planning cannot avoid collision danger, the vehicle opens double flashes and whistles, the dynamic object is warned of collision risk and braking is carried out, and when the dynamic vehicle navigation distance constraint model value is greater than 3 meters, the vehicle navigation distance is a safe distance.
6. The data processing method for manufacturing a brake calibration table according to claim 5, wherein: the combination of the Kalman filtering and the neural network comprises training a state estimator, a Kalman gain and a measured state quantity in the Kalman filtering through the neural network, obtaining the relation between the final predicted steady-state vehicle speed and the depth of a brake pedal, establishing a data analysis model, and selecting the vehicle state quantity and the observed quantity to be expressed as:
；
wherein, Depth detection value of brake pedal at time t,/>Representing the speed at time t,/>The time difference is indicated as such,The longitudinal acceleration at the time t is represented;
Through state transition matrix Control matrix/>A kalman prediction equation is established, expressed as:
；
wherein, Estimated value representing brake pedal depth at time t,/>Representing an estimate of brake pedal depth at the last instant,/>A longitudinal acceleration estimation value representing the last time;
Introducing a covariance matrix represents an uncertainty in determining an estimate, expressed as:
；
wherein, Representing the prediction covariance matrix at time t,/>Error of last time,/>Is process noise;
Establishing a Kalman filtering observation model expressed as:
；
wherein, Is the detection value of time t-The state vector is the state vector of the last moment, H is an observation matrix, and v is observation noise;
The state update for the kalman filter is expressed as:
；
Wherein R is an observed noise covariance matrix, Is Kalman gain;
updating the noise covariance matrix, establishing a neural network structure comprising an input layer, an hidden layer and an output layer, and obtaining a predicted value Gain matrix of Kalman filteringObserved value of observation equation/>Inputting an established neural network;
Taking the error between the Kalman filtering value and the true value as the output of the neural network, and the training process of the neural network is expressed as follows:
；
wherein, As learning factor,/>Is a momentum factor,/>Representing the weight change between the ith neuron in the l-1 layer and the jth neuron in the l layer connected by the time t,/>Representing the difference between the expected output and the true output value of the layer I neuron,/>The output of the ith neuron of the first layer 1 at time t is represented, and the transfer function is a sigmoid function.
7. The data processing method for manufacturing a brake calibration table according to claim 6, wherein: the method comprises the steps that the mapping relation between a brake pedal and longitudinal acceleration in different driving modes is output, the mapping relation among the vehicle speed, the depth of the brake pedal and the acceleration is predicted based on the combination of Kalman filtering and a neural network through a vehicle speed stabilization point and a vehicle navigation distance constraint, the vehicle navigation and driving track is optimized, and the driving modes comprise a linear driving mode, a north-south driving mode, a comfortable driving mode and a motion driving mode;
The linear driving mode comprises the steps of driving a vehicle on a linear road, controlling a brake pedal and limiting longitudinal acceleration based on a static vehicle navigation distance constraint model and a dynamic vehicle navigation distance constraint model, recording vehicle navigation distance constraint data, and optimizing a driving track;
The north-south driving mode comprises the steps of driving a vehicle in an urban or changeable road environment, performing brake pedal control and longitudinal acceleration limitation through a depth detection value of a brake pedal based on the combination of Kalman filtering and a neural network, recording vehicle navigation distance constraint data, and performing driving track optimization;
The comfortable driving mode comprises the steps of driving a vehicle under urban roads or congested traffic conditions, controlling a brake pedal and limiting longitudinal acceleration based on a static vehicle navigation distance constraint model, recording vehicle navigation distance constraint data, and optimizing a driving track;
the motion driving mode comprises the steps of driving a vehicle on a track or an open road, performing brake pedal control and longitudinal acceleration limitation based on a dynamic vehicle navigation distance constraint model combining Kalman filtering and a neural network, recording vehicle navigation distance constraint data, and performing driving track optimization.
8. A system employing the data processing method for manufacturing a brake calibration table according to any one of claims 1 to 7, wherein: the system comprises a data processing module, a vehicle speed constraint module and a pedal control module;
the data processing module is used for collecting vehicle data in a driving scene and preprocessing the vehicle data;
The vehicle speed constraint module is used for screening vehicle speed stable points through a sliding window based on the preprocessed vehicle data, and constructing a vehicle navigation distance constraint model;
The pedal control module is used for outputting the mapping relation between the brake pedal and the longitudinal acceleration under different driving modes through the restraint of the vehicle speed stabilization point and the vehicle navigation distance and under the combination of Kalman filtering and a neural network, so as to optimize the vehicle navigation, the driving track and the longitudinal control performance.
9. A computer device comprising a memory and a processor, the memory storing a computer program, characterized in that the processor, when executing the computer program, carries out the steps of the data processing method for making a brake calibration table according to any one of claims 1 to 7.
10. A computer-readable storage medium, on which a computer program is stored, characterized in that the computer program, when being executed by a processor, carries out the steps of the data processing method for making a brake calibration table according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410338613.XA CN117932234B (en) | 2024-03-25 | 2024-03-25 | Data processing method and system for manufacturing brake calibration table |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410338613.XA CN117932234B (en) | 2024-03-25 | 2024-03-25 | Data processing method and system for manufacturing brake calibration table |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117932234A true CN117932234A (en) | 2024-04-26 |
| CN117932234B CN117932234B (en) | 2024-06-07 |
Family
ID=90761470
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410338613.XA Active CN117932234B (en) | 2024-03-25 | 2024-03-25 | Data processing method and system for manufacturing brake calibration table |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117932234B (en) |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115271040A (en) * | 2022-07-22 | 2022-11-01 | 中山大学 | Vehicle quality estimation method based on adaptive extended Kalman filtering |
| CN115576322A (en) * | 2022-10-19 | 2023-01-06 | 北京建筑大学 | Adaptive cruise control method based on Kalman filtering improved model |
| US20230054246A1 (en) * | 2020-05-06 | 2023-02-23 | Beijing Institute Of Technology | Iterative joint estimation method of vehicle mass and road gradient based on mmrls and sh-stf |
| CN115762182A (en) * | 2022-11-03 | 2023-03-07 | 北京踏歌智行科技有限公司 | Vehicle intelligent track prediction method based on kinematic constraint |
| CN116811916A (en) * | 2023-07-05 | 2023-09-29 | 江苏安必行无线科技有限公司 | Automatic driving system based on 5G vehicle road cooperation |
| CN117485369A (en) * | 2023-11-14 | 2024-02-02 | 珠海城市职业技术学院 | Real-time detection method for deformation obstacle in logistics robot transportation |
| CN117719519A (en) * | 2024-01-29 | 2024-03-19 | 清华大学深圳国际研究生院 | Vehicle running state estimation method |
-
2024
- 2024-03-25 CN CN202410338613.XA patent/CN117932234B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20230054246A1 (en) * | 2020-05-06 | 2023-02-23 | Beijing Institute Of Technology | Iterative joint estimation method of vehicle mass and road gradient based on mmrls and sh-stf |
| CN115271040A (en) * | 2022-07-22 | 2022-11-01 | 中山大学 | Vehicle quality estimation method based on adaptive extended Kalman filtering |
| CN115576322A (en) * | 2022-10-19 | 2023-01-06 | 北京建筑大学 | Adaptive cruise control method based on Kalman filtering improved model |
| CN115762182A (en) * | 2022-11-03 | 2023-03-07 | 北京踏歌智行科技有限公司 | Vehicle intelligent track prediction method based on kinematic constraint |
| CN116811916A (en) * | 2023-07-05 | 2023-09-29 | 江苏安必行无线科技有限公司 | Automatic driving system based on 5G vehicle road cooperation |
| CN117485369A (en) * | 2023-11-14 | 2024-02-02 | 珠海城市职业技术学院 | Real-time detection method for deformation obstacle in logistics robot transportation |
| CN117719519A (en) * | 2024-01-29 | 2024-03-19 | 清华大学深圳国际研究生院 | Vehicle running state estimation method |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117932234B (en) | 2024-06-07 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10235881B2 (en) | Autonomous operation capability configuration for a vehicle | |
| RU2681984C1 (en) | System and method for determining trajectory for vehicle | |
| CN109871599B (en) | Unmanned vehicle operation safety index evaluation method | |
| US6879969B2 (en) | System and method for real-time recognition of driving patterns | |
| CN112285740A (en) | Vehicle condition detection | |
| CN113370996B (en) | Automatic driving lane change following decision method and system and automatic driving vehicle | |
| CN112668779A (en) | Preceding vehicle motion state prediction method based on self-adaptive Gaussian process | |
| CN113253739A (en) | Driving behavior decision method for expressway | |
| CN113920740A (en) | Vehicle-road cooperative driving system and method combining vehicle association degree and game theory | |
| CN115675098B (en) | Intelligent network-connected automobile kinetic energy recovery system, method, equipment and storage medium based on user characteristic difference | |
| CN111783943A (en) | Driver braking strength prediction method based on LSTM neural network | |
| CN112677982A (en) | Vehicle longitudinal speed planning method based on driver characteristics | |
| Santin et al. | Cruise controller with fuel optimization based on adaptive nonlinear predictive control | |
| CN114639267A (en) | Vehicle collision avoidance early warning method in vehicle-road cooperative environment | |
| Si et al. | Big data-based driving pattern clustering and evaluation in combination with driving circumstances | |
| CN117932234B (en) | Data processing method and system for manufacturing brake calibration table | |
| EP4017773B1 (en) | A method for quantifying extreme traffic behavior | |
| CN115416656B (en) | Automatic driving lane changing method, device and medium based on multi-target track planning | |
| CN116811854A (en) | Method and device for determining running track of automobile, automobile and storage medium | |
| CN115963840A (en) | Intelligent vehicle formation control method based on deep reinforcement learning under communication topology switching | |
| Vedula et al. | Novel Approaches for Model-Based Development-Part I: Developing a Real-World Driver Model | |
| CN115923813B (en) | Driving behavior analysis method and system based on speed rapid change characteristics | |
| Zhang et al. | A recognition model for acceleration intention of automobile drivers based on fuzzy clustering | |
| CN115547047A (en) | Intelligent internet vehicle following model based on attention model | |
| Sun et al. | Prediction of Lane Change on the Expressway Based on Logistic Regression |
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 | ||
| GR01 | Patent grant |