CN115503712A - Intelligent networking automobile prediction control method and system considering road running conditions - Google Patents
Intelligent networking automobile prediction control method and system considering road running conditions Download PDFInfo
- Publication number
- CN115503712A CN115503712A CN202211156074.5A CN202211156074A CN115503712A CN 115503712 A CN115503712 A CN 115503712A CN 202211156074 A CN202211156074 A CN 202211156074A CN 115503712 A CN115503712 A CN 115503712A
- Authority
- CN
- China
- Prior art keywords
- road
- vehicle
- output result
- road section
- road surface
- 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
- 238000000034 method Methods 0.000 title claims abstract description 43
- 230000006855 networking Effects 0.000 title claims abstract description 6
- 238000013528 artificial neural network Methods 0.000 claims abstract description 32
- 230000001133 acceleration Effects 0.000 claims abstract description 23
- 238000004364 calculation method Methods 0.000 claims abstract description 15
- 230000008859 change Effects 0.000 claims abstract description 15
- 230000006870 function Effects 0.000 claims description 17
- 238000012549 training Methods 0.000 claims description 16
- 238000012360 testing method Methods 0.000 claims description 10
- 241000039077 Copula Species 0.000 claims description 9
- 238000004891 communication Methods 0.000 claims description 6
- 238000013507 mapping Methods 0.000 claims description 6
- 238000010586 diagram Methods 0.000 claims description 5
- 230000008569 process Effects 0.000 claims description 5
- 238000012545 processing Methods 0.000 claims description 4
- 238000005096 rolling process Methods 0.000 claims description 4
- 238000007476 Maximum Likelihood Methods 0.000 claims description 3
- 238000012795 verification Methods 0.000 claims description 3
- 238000005259 measurement Methods 0.000 abstract description 4
- 238000007689 inspection Methods 0.000 description 4
- 238000004458 analytical method Methods 0.000 description 2
- 230000001174 ascending effect Effects 0.000 description 2
- 230000008901 benefit Effects 0.000 description 2
- 238000013524 data verification Methods 0.000 description 2
- 238000005315 distribution function Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000003746 surface roughness Effects 0.000 description 2
- 238000012935 Averaging Methods 0.000 description 1
- 238000011217 control strategy Methods 0.000 description 1
- 238000007796 conventional method Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 230000004069 differentiation Effects 0.000 description 1
- 238000010191 image analysis Methods 0.000 description 1
- 230000010365 information processing Effects 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000012886 linear function Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
- 238000004088 simulation Methods 0.000 description 1
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
- B60W30/14—Adaptive cruise control
- B60W30/16—Control of distance between vehicles, e.g. keeping a distance to preceding vehicle
-
- 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
- B60W40/00—Estimation or calculation of non-directly measurable driving parameters for road vehicle drive control systems not related to the control of a particular sub unit, e.g. by using mathematical models
-
- 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
- B60W40/00—Estimation or calculation of non-directly measurable driving parameters for road vehicle drive control systems not related to the control of a particular sub unit, e.g. by using mathematical models
- B60W40/02—Estimation or calculation of non-directly measurable driving parameters for road vehicle drive control systems not related to the control of a particular sub unit, e.g. by using mathematical models related to ambient conditions
- B60W40/06—Road conditions
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W50/00—Details of control systems for road vehicle drive control not related to the control of a particular sub-unit, e.g. process diagnostic or vehicle driver interfaces
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
- G06F30/27—Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/82—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using neural networks
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W50/00—Details of control systems for road vehicle drive control not related to the control of a particular sub-unit, e.g. process diagnostic or vehicle driver interfaces
- B60W2050/0001—Details of the control system
- B60W2050/0019—Control system elements or transfer functions
- B60W2050/0028—Mathematical models, e.g. for simulation
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W50/00—Details of control systems for road vehicle drive control not related to the control of a particular sub-unit, e.g. process diagnostic or vehicle driver interfaces
- B60W2050/0001—Details of the control system
- B60W2050/0043—Signal treatments, identification of variables or parameters, parameter estimation or state estimation
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Evolutionary Computation (AREA)
- Mathematical Physics (AREA)
- Mechanical Engineering (AREA)
- Transportation (AREA)
- Artificial Intelligence (AREA)
- Software Systems (AREA)
- General Physics & Mathematics (AREA)
- Automation & Control Theory (AREA)
- Health & Medical Sciences (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- General Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Medical Informatics (AREA)
- Data Mining & Analysis (AREA)
- Computational Linguistics (AREA)
- Biophysics (AREA)
- Biomedical Technology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Molecular Biology (AREA)
- Databases & Information Systems (AREA)
- Multimedia (AREA)
- Human Computer Interaction (AREA)
- Computer Hardware Design (AREA)
- Geometry (AREA)
- Traffic Control Systems (AREA)
Abstract
The invention discloses an intelligent networking automobile prediction control method and system considering road running conditions, wherein the method comprises the following steps: acquiring an image in front of a vehicle according to a preset frequency, extracting a road surface area from the image in front of the vehicle, performing image recognition by adopting a pre-stored neural network module, and giving and storing a first output result of a road surface parameter in front of the vehicle; receiving a road surface image of the current road section sent by a road section camera, carrying out image recognition, and giving and storing a second output result of the current road section parameter; constructing a road parameter model, judging whether the change rate of the road parameters exceeds a threshold value, if not, giving an average value of the current road section parameters based on a first output result and a second output result, and outputting; and (3) constructing a vehicle dynamic model and an angular acceleration and deceleration calculation model, and determining a maximum adhesion coefficient, a maximum braking force and an expected safety distance. According to the method and the device, the accuracy of the data is greatly improved through the measurement of the road surface parameters.
Description
Technical Field
The invention relates to the related technology of networking automobiles, in particular to an intelligent networking automobile prediction control method considering road running conditions.
Background
The current intelligent networked automobile queue prediction control technology rarely considers the actual situation of a passing road surface when the optimal speed or the queue following distance is predicted actually. The maximum driving force and the braking force owned by the vehicle can change along with the change of road conditions, if the maximum reachable acceleration and deceleration of the target vehicle is not considered, the network connection vehicle queue has no adaptability to the road environment, and the safety in actual operation cannot be ensured.
When estimating the road adhesion coefficient under the conditions of different road surface materials, road surface roughness and humidity, the most studied method is to calculate the slip rate of a target automobile in real time and set a road characteristic database under different road conditions, wherein the road characteristic database is related to the slip rate and the adhesion coefficient. When the road adhesion coefficient is estimated, the automobile is kept at a fixed slip rate as far as possible, and the wheel angle acceleration and deceleration of the automobile during driving and braking under all road conditions in the database is calculated in advance according to the model.
In the prior art, the error between the actual wheel angle acceleration and deceleration and the preset wheel angle acceleration and deceleration is taken, the road condition meeting the minimum error is determined as the road environment where the current vehicle is located, and the slip rate is adjusted according to the slip rate-road adhesion coefficient curve under the environment, so that the vehicle is ensured to have the maximum adhesion coefficient. However, the pre-calculation method has high demand on the calculated amount and large resource occupation, and in order to ensure the real-time requirement, the road classification of the set road characteristic database cannot be very detailed, and the slip ratio-road adhesion coefficient curves under different road surface roughness, wet slip, vehicle speed and other conditions can be changed, so that the calculated amount cannot be considered and the estimation accuracy cannot be maintained.
In the queue following distance control, a variable headway (VTH) control strategy, which is currently the mainstream, calculates the distance using the vehicle speed of the vehicle, the vehicle speed in front, and the vehicle acceleration in front as input quantities. In order to meet the requirement of driving safety, the distance between the following vehicles is required to be greater than the actual braking distance. The following distance control is only suitable for the situation of an ideal dry road, and the acceleration and deceleration of each vehicle cannot be at a constant value along with the change of the road surface material, temperature and humidity, and the actual braking distance can also be changed accordingly.
If the change of the braking distance caused by the maximum braking force on the premise of ensuring the safety during actual driving is not considered, the accident occurs to the front vehicle when the road adhesion condition is poor, and the rear vehicle in the queue cannot be ensured to stop at a sufficient distance.
Disclosure of Invention
The invention aims to: the intelligent networked automobile prediction control method considering the road running conditions is provided to solve one of the problems in the prior art.
The technical scheme is as follows: according to one aspect of the application, the intelligent networked automobile predictive control method considering the road running condition comprises the following steps:
s1, aiming at each vehicle, acquiring a vehicle front image according to a preset frequency, extracting a road surface area from the vehicle front image, performing image identification by adopting a pre-stored neural network module, and giving and storing a first output result of vehicle front road surface parameters;
s2, receiving a road surface image of the current road section sent by a road section camera, adopting a neural network module to perform image recognition, and giving and storing a second output result of the current road section parameter;
s3, constructing a road parameter model based on the first output result and the second output result, judging whether the change rate of the road parameter exceeds a threshold value, and if not, giving an average value of the current road section parameter based on the first output result and the second output result and outputting the average value;
s4, constructing a vehicle dynamics model and an angular acceleration and deceleration calculation model, calculating a slip rate-adhesion coefficient database by taking the average value of the current road section parameters and the material of the current road section as one of input parameters, and determining a slip rate-adhesion coefficient relation curve of the current running vehicle condition; and controlling the slip rate based on the slip rate-adhesion coefficient relation curve, and determining the maximum adhesion coefficient, the maximum braking force and the expected safety distance.
According to an aspect of the application, the step S2 further includes:
s21, collecting a traffic network map of a current area, and collecting traffic route data from the traffic network map to construct a traffic route directed graph;
s22, aiming at each passing route, road section cameras are arranged on two sides at preset intervals, the road section cameras collect road surface data according to preset frequency and store the road surface data in a storage module of each passing road section, and the road surface data comprises position information and image shooting time information of the road section cameras.
According to an aspect of the application, the step S2 further comprises:
s23, collecting pictures of cameras of all road sections of a preset passing road section according to a time sequence, processing the pictures by adopting a neural network module, constructing a model of picture information and road surface parameters, and giving a mapping set of empirical value ranges of the road surface parameters and the road surface picture information under all scenes;
and S24, verifying the empirical value range of the road surface parameters and the mapping set of the road surface picture information by adopting verification set data until the relevant standard is reached.
According to an aspect of the application, the step S2 further comprises:
s25, receiving a road surface image of the current road section sent by a road section camera, and acquiring the shooting time and the geographical position information of the current image; measuring the road section parameters of the road section by adopting a measuring device preset on the road section to obtain a measured value sequence;
s26, identifying the received road surface image by adopting a preset neural network module to obtain a calculation value sequence of the current road section parameters, namely a second output result;
s27, constructing a two-dimensional joint distribution Copula function of the measured value and the calculated value, and calculating parameters of the Copula function by adopting a maximum likelihood method through taking the measured value sequence and the calculated value sequence as one of inputs;
and S28, calculating probability distribution of the measured value and the calculated value based on the Copula function of the obtained parameter, and judging whether the measured result meets expectation or not based on the probability distribution, namely whether the similarity between the distribution of the calculated value and the distribution of the measured value meets the requirement or not.
According to an aspect of the application, the step S3 further comprises:
s31, receiving the first output result and the second output result, respectively arranging in a descending order, respectively deleting the first 20% and the second 20% of data, respectively calculating the average value of the rest data, and obtaining the average value of the first output result and the average value of the second output result;
step S32, calculating the difference value of the first output result average value and the second output result average value, judging whether the difference value is smaller than a threshold value, and if so, entering step S33;
and S33, calculating the average value of the first output result average value and the second output result average value as the average value of the current road section parameters.
According to an aspect of the application, the step S3 further comprises:
step S34, if the difference value is larger than or equal to the threshold value, acquiring a first output result and a second output result transmitted by each vehicle and road section camera, and respectively calculating the Spireman coefficients of each group of the first output result and the second output result to obtain a Spireman coefficient sequence;
step S35, calculating the variance and expectation of the spearman coefficient sequence;
and S36, judging whether the variance and the expectation of the Spanish coefficient are both smaller than a threshold value, if so, calculating the average value of the current road section parameters based on the weight coefficients corresponding to the first output result and the second output result.
According to an aspect of the present application, the step S1 further includes:
s11, acquiring a plurality of groups of traffic passing routes of different vehicles, and constructing a traffic flow network diagram through the routes;
and S12, extracting the front images on each traffic passage route according to the time sequence, marking the time and the place of each front image, and forming a front image data stream corresponding to each road section based on the time sequence.
And S13, searching the image in front of the vehicle of a certain road section acquired by each vehicle, constructing a training set and a testing set of the image in front of the vehicle, and training and testing the neural network module.
According to an aspect of the application, in step S4, the desired safety distance is:
D E to expect a safe distance, D S For the controlled amount of inter-vehicle distance, d c Is the psychological minimum safe distance, v i As the current speed of the vehicle, t all The time required for the complete braking of the vehicle in the event of an accident, t' is the communication time of the braking signal, t 1 Linearly increasing the duration of the brake, a p As acceleration of the front vehicle, a m For braking maximum acceleration of the own vehicle, d 0 For presetting a safe following distance, F M To its own maximum braking force, f 0 、f 1 Is a constant number of times, and is,the rolling resistance is indicated as a function of,the wind resistance of the running of the automobile is represented, the up-slope resistance is represented by mgsin alpha, and the gradient of the advancing direction of the automobile is represented by alpha; k and c are preset constants.
According to an aspect of the present application, there is also provided an intelligent networked automobile predictive control system considering road running conditions, comprising: at least one processor; and
a memory communicatively coupled to at least one of the processors; wherein,
the memory stores instructions executable by the processor for implementing the intelligent networked automobile predictive control method considering road operating conditions according to any one of the embodiments.
Has the advantages that: according to the method and the device, the accuracy of the data is greatly improved through the measurement of the road surface parameters, more accurate measurement and control data can be given in the subsequent simulation process, and the problems in the prior art are solved.
Drawings
Fig. 1 is a flowchart of a first embodiment of the present application.
FIG. 2 is a flow chart of the data verification of the present application.
Fig. 3 is a flowchart of the second embodiment of the present application.
FIG. 4 is a flowchart of a first step of the present application.
FIG. 5 is a flowchart of a second step in the embodiments of the present application.
Fig. 6 is a flowchart of the third step in the embodiment of the present application.
Detailed Description
Example one
As shown in fig. 1 and 2, in this embodiment, the system mainly includes two parts, one is to collect relevant image information by a vehicle-mounted camera and a road section camera. The second step is to perform calculation and control based on the above image information by constructing a vehicle dynamics model and a tire dynamics model.
Specifically, an image in front of a vehicle is intercepted by a vehicle-mounted camera according to a certain frame rate, then a road surface area part is extracted from the image in front of the vehicle, then image recognition is carried out, and related information such as the humidity and the roughness of the road surface of the vehicle is quantized according to a recognition result. Similarly, in the aspect of the road section camera, the road surface image of the current road section is intercepted according to a certain frame rate. And then outputting a nearest segment wet slip value through a data inspection module based on the quantified road surface moisture and roughness.
And (3) constructing a vehicle dynamic model and a tire dynamic model, and then calculating angular acceleration and deceleration. In the subsequent step, based on the wet roughness, a slip ratio = attachment coefficient database is constructed, and data of theoretical vehicle angular acceleration and actual error are calculated. And determining a slip rate-adhesion coefficient curve of the current running vehicle condition. Slip ratio data is then obtained based on the curve and slip ratio control is performed to determine the adhesion coefficient and the maximum braking force.
By the method, the current image is acquired through the front camera and the road section camera. Therefore, the actual condition of the road condition and the actual road surface parameters are calculated, the accuracy and the reliability of the data are improved, the better input data are provided for the subsequent control, and the accuracy of the current data is improved.
The specific operation of the data verification module is described with reference to fig. 2. In this embodiment, a model is built by the latest n segment wet slip range values obtained by the vehicle-mounted camera and the latest n segment average wet slip range values of the road section camera, so as to obtain a function model of the average wet slip range values, and whether the wet slip range value change rate in the function model exceeds a set value or not is calculated, if so, the average wet slip range values are output, and if not, the latest segment wet slip range values are output.
Example two
As shown in fig. 3, in another embodiment of the present application, an intelligent networked automobile predictive control method considering road running conditions is characterized by comprising the following steps:
s1, aiming at each vehicle, acquiring a vehicle front image according to a preset frequency, extracting a road surface area from the vehicle front image, performing image identification by adopting a pre-stored neural network module, and giving and storing a first output result of vehicle front road surface parameters;
s2, receiving a road surface image of the current road section sent by a road section camera, adopting a neural network module to perform image recognition, and giving and storing a second output result of the current road section parameter;
s3, constructing a road parameter model based on the first output result and the second output result, judging whether the change rate of the road parameter exceeds a threshold value, and if not, giving an average value of the current road section parameter based on the first output result and the second output result and outputting the average value;
s4, constructing a vehicle dynamics model and an angular acceleration and deceleration calculation model, calculating a slip rate-adhesion coefficient database by taking the average value of the current road section parameters and the material of the current road section as one of input parameters, and determining a slip rate-adhesion coefficient relation curve of the current running vehicle condition; and controlling the slip rate based on a slip rate-adhesion coefficient relation curve, and determining a maximum adhesion coefficient, a maximum braking force and an expected safety distance.
In this embodiment, image recognition is performed by the neural network module, and then road surface parameter information is recognized from the image, and the pre-vehicle image and the road surface image are processed by the neural network module. Before the method is used, a training set and a testing set of the front images and a training set and a testing set of the road surface images are constructed, and road surface parameter empirical values corresponding to partial images are input at the same time, so that the neural network module can acquire road surface parameters based on the front images and the road surface images. Therefore, after the neural network module is trained, the neural network module can be used for identifying the road condition to obtain the road parameters. In other words, the information empirical value of the road surface parameter can be obtained from the image through a large amount of image training. Thus, with the input anterior image, the neural network module may give a first output of the anterior road surface parameters. And receiving the road surface image of the current road section sent by the road section camera, performing image recognition by adopting a neural network, and giving and storing a second output result of the current road section parameter. The first output result and the second output result are images obtained by shooting the road surface by different cameras at different angles, so that the road surface parameters have certain similarity, and the road surface parameters are calculated by different data sources, so that more accurate road surface parameters can be obtained by comprehensively judging between the first output result and the second output result.
After the first output result and the second output result are obtained, the road surface parameter model is constructed based on the data, in other words, the output results are not uniform but have certain errors, so that the model needs to be constructed, the distribution condition of the road surface parameters is calculated, whether the change rate of the road section parameters exceeds a threshold value or not is judged, and if the change rate exceeds the threshold value, the road surface condition may be greatly changed, for example, the road surface is updated, so that the basic condition of the road surface is changed. In different cases, the road surface parameters obtained from different images in front of the vehicle fluctuate within a certain range, and if the basic condition of the road surface does not change, the average value thereof is substantially close to the detection value, while the fluctuation range, i.e., the variance, is within a certain range. If the basic condition of the road surface is changed greatly, the average value and the variance are obviously changed, so that in the condition, an approximate function, such as a linear function, is constructed, the change rate of the wet and slippery degree can be obtained, and whether the road surface condition is substantially changed or not can be accurately judged according to the condition that whether the change rate exceeds a threshold value or not.
After determining road parameters, such as moisture, roughness, etc., the road parameters may be used as subsequent input parameters. That is, in step 4, after the vehicle dynamics model and the tire dynamics model are constructed, the slip ratio and the maximum braking force can be determined by taking the road surface parameters and the road surface material of the road section as data sources and acquiring the numerical value of the slip ratio from the slip ratio-adhesion curve in the subsequent control process by using the parameters such as the road surface parameters and the road surface material of the road section as data sources.
Therefore, in the embodiment, the road surface parameters are calculated through the images of the two data sources, so that the accuracy of calculation is greatly improved. Compared with the prior art, the method has the advantage that the calculation accuracy is greatly improved by adopting a UKF method for estimation.
In another embodiment of the present application, in the process of constructing the method, the step S1 further includes:
s11, acquiring a plurality of groups of traffic passing routes of different vehicles, and constructing a traffic flow network diagram through the routes;
and S12, extracting the image in front of the vehicle on each traffic passage route according to the time sequence, marking the time and the place of each image in front of the vehicle, and forming a data stream of the image in front of the vehicle corresponding to each road section based on the time sequence.
And S13, searching the image in front of the vehicle of a certain road section acquired by each vehicle, constructing a training set and a testing set of the image in front of the vehicle, and training and testing the neural network module.
When the road surface parameter identification method is used, the current image in front of a road section acquired by each vehicle is identified on the basis of the constructed neural network module, and a first output result of the road surface parameter in front of the vehicle is given according to the image in front of the vehicle.
In this embodiment, first, by collecting images of a plurality of vehicles in front of a vehicle at different times and different positions, then preprocessing the images, and classifying according to time and road sections, images of different vehicles in front of a road section are obtained, for example, 2 ten thousand images of the vehicles in front of the vehicle are captured when 1 ten thousand vehicles pass through a road section, so that an image dataset of the vehicles in front of the vehicle corresponding to the road section can be extracted. A training set and a test set are constructed from the data set. And training the neural network module to obtain the neural network module, so that the relation between the front image of the current road section and the road surface parameter can be obtained. After the neural network is trained, road surface parameter information can be obtained through the images in front of the vehicle shot by the subsequent vehicles.
In another embodiment of the present application, the step S2 further includes:
s21, collecting a traffic network map of a current area, and collecting traffic route data from the traffic network map to construct a traffic route digraph; and overlapping and comparing the traffic flow network diagram with the traffic route directed diagram.
S22, aiming at each passing route, road section cameras are arranged on two sides at preset intervals, the road section cameras collect road surface data according to preset frequency and store the road surface data in a storage module of each passing road section, and the road surface data comprises position information and image shooting time information of the road section cameras.
In this embodiment, a traffic route directed graph is constructed by collecting a current traffic network map and extracting traffic route data from the graph, wherein the traffic route directed graph contains all theoretically feasible traffic routes. After the comparison and the frequency analysis with the vehicle passing route are carried out, a key traffic flow route can be extracted, so that the key traffic route can be determined, road section cameras can be arranged along the key traffic route, and then road surface images of all road sections are collected. The road surface data includes time information and position information. In a subsequent embodiment, the image data sets of the image of the front of the vehicle and the image of the road section at different times can be obtained by time and road section division.
For example, on day a, a plurality of vehicle and roadside cameras respectively take a plurality of groups of images, and the images can be collected by overlapping in time, so that the training amount is reduced.
In another embodiment of the present application, the step S2 further includes:
s23, collecting pictures of cameras of all road sections of a preset passing road section according to a time sequence, processing the pictures by adopting a neural network module, constructing a model of picture information and road surface parameters, and giving a mapping set of empirical value ranges of the road surface parameters and the road surface picture information under all scenes;
in a preferred embodiment, pictures of each road segment are extracted from the data stream of the image in front of the vehicle, and the pictures of the road segment camera are taken as a training set of the road segment. Namely, the neural network is trained in a mode of constructing a space-time accompanying image.
Road surface parameters under different scenes are obtained through searching of space-time accompanying images, and a more accurate conclusion can be given.
And S24, verifying the empirical value range of the road surface parameters and the mapping set of the road surface picture information by adopting verification set data until the relevant standard is reached.
In other words, in the application, the images in front of the vehicle and the images on the road surface can be classified based on the collection of the images, so that a better lightweight neural network module is obtained by training the same neural network module. Of course, the image of the front of the vehicle and the image of the road surface may be trained separately. For this reason, when constructing the training set and the test set, the differentiation and training can be performed according to different requirements.
In addition, the application scenes of the images can be classified according to the image data of different times and places. For example, in b day b, if the relevant road section has rainfall, the images of the front of the road section of different vehicles and the road surface images shot by the cameras of the different road sections of the road section are counted, so that the road surface parameters under different scenes can be more accurately simulated and calculated.
By classifying the images of different categories, the scenes can be distinguished. In this case, the image in front of the vehicle and the image of the road surface are distinguished according to angles such as time and place, so that different scenes can be classified, and more accurate road surface parameters can be obtained.
In another embodiment of the present application, the step S2 further includes:
s25, receiving a road surface image of the current road section sent by a road section camera, and acquiring the shooting time and the geographical position information of the current image; and measuring the road section parameters of the road section by adopting a measuring device preset on the road section to obtain a measured value sequence.
And S26, identifying the received road surface image by adopting a preset neural network module to obtain a calculation value sequence of the current road section parameters, namely a second output result.
And S27, constructing a two-dimensional joint distribution Copula function of the measured value and the calculated value, and calculating parameters of the Copula function by using a maximum likelihood method through taking the measured value sequence and the calculated value sequence as one of inputs.
And S28, calculating probability distribution of the measured value and the calculated value based on the Copula function of the obtained parameter, and judging whether the measured result meets expectation or not based on the probability distribution, namely whether the similarity between the distribution of the calculated value and the distribution of the measured value meets the requirement or not.
Specifically, the present embodiment provides an image processing method based on time flow and spatial topology, in which a traffic route directed graph is constructed, and then in each traffic route, a link camera is fixed according to a rule. The road section camera captures images of road sections in chronological order, and the vehicle-mounted camera records images of the front of the vehicle in traffic routes and chronological order. The road surface images of the same road section are classified at the same time, and then analyzed through the measured value and the calculated value. In the specific analysis, in this embodiment, the error between the measured value and the calculated value is calculated by using the joint distribution function, and whether the expected accuracy is achieved is determined. In other words, when how to judge whether the recognition result of the neural network module is accurate, the result can be obtained more accurately and quickly by adopting the joint distribution of the measured value and the calculated value. In other embodiments, the error distribution between the measured values and the actual values may be calculated, or other statistical analytical decision methods may be employed. For example, a function model between the measured value and the calculated value is constructed, and whether the error exceeds the threshold value is judged through parameters such as fitting degree and the like. Compared with the conventional method in statistics, the accuracy and speed of the method are higher by adopting the combined distribution function.
In another embodiment of the present application, the step S3 further includes:
s31, receiving the first output result and the second output result, respectively arranging the first output result and the second output result in a descending order, respectively deleting the first 20% and the second 20% of data, and respectively averaging the rest data to obtain a first output result average value and a second output result average value;
step S32, calculating the difference value of the first output result average value and the second output result average value, judging whether the difference value is smaller than a threshold value, and if the difference value is smaller than the threshold value, entering step S33;
and S33, calculating the average value of the first output result average value and the second output result average value as the average value of the current road section parameters.
In another embodiment of the present application, the step S3 further includes:
step S34, if the difference value is larger than or equal to the threshold value, acquiring a first output result and a second output result transmitted by each vehicle and road section camera, and respectively calculating the Spireman coefficients of each group of the first output result and the second output result to obtain a Spireman coefficient sequence;
step S35, calculating the variance and expectation of the spearman coefficient sequence;
and S36, judging whether the variance and the expectation of the Spanish coefficient are both smaller than a threshold value, if so, calculating the average value of the current road section parameters based on the weight coefficients corresponding to the first output result and the second output result.
In this embodiment, the first output result and the second output result are calculated, the mode of removing the front and rear related extreme parameters is adopted, and the mode of comparing the first output result with the second output result is adopted to judge how to calculate the average value of the road section parameters, so that the true value can be calculated more accurately. In the conventional embodiment, the error ranges of the first output result and the second output result with respect to the recognition calculation result of the same link at the same time are generally within a predetermined range. Therefore, how to judge whether the error is within a reasonable range needs to be solved.
In the application, the similarity of the first output result and the second output result is judged through the expectation and the variance of the spearman coefficient, and then a conclusion is given. In conclusion, the embodiment can provide a conclusion more quickly and accurately.
In another embodiment of the present application, in step S4, the desired safety distance is:
D E to expect a safe distance, D S For the controlled amount of the inter-vehicle distance, d c Is the psychological minimum safe distance, v i As the current speed of the vehicle, t all The time required for the complete braking of the vehicle in the event of an accident, t' is the communication time length of the braking signal, t 1 Linearly increasing the duration of the brake, a p As acceleration of the front vehicle, a m For braking the own vehicle at maximum acceleration, d 0 For presetting a safe following distance, F M To its own maximum braking force, f 0 、f 1 Is a constant number of times, and is,the rolling resistance is indicated as a function of,the wind resistance of the running of the automobile is represented, the up-slope resistance is represented by mgsin alpha, and the gradient of the advancing direction of the automobile is represented by alpha; k and c are preset constants.
In another embodiment of the present application, there is provided an intelligent networked automobile predictive control system considering road running conditions, including:
at least one processor; and
a memory communicatively coupled to at least one of the processors; wherein,
the memory stores instructions executable by the processor for implementing the intelligent networked automobile predictive control method considering road running conditions according to any one of the above embodiments.
It will be readily appreciated that the system includes a computer device including a memory, a processor, a network interface communicatively connected to each other via a system bus, and software installed on the computer device. As will be understood by those skilled in the art, the computer device herein is a device capable of automatically performing numerical calculation and information processing according to preset or stored instructions, and the hardware includes but is not limited to a microprocessor, an application specific integrated circuit, a programmable gate array, a digital processor, an embedded device, and the like. The computer device can be a desktop computer, a notebook, a palm computer, a cloud server and other computing devices. The computer equipment can enter man-machine interaction with a user through a keyboard, a mouse, a remote controller, a touch panel or voice control equipment and the like. The memory includes at least one type of readable storage medium including a memory, a hard disk, a random access memory, a read-only memory, a magnetic disk, an optical disk, and the like. In some embodiments, the memory may also be an external storage device of the computer device, for example, a smart memory card, an SD card, or the like is provided on the computer device. Of course, the memory may also include both internal and external storage units of the computer. In this embodiment, the memory is generally used for storing an operating system and various application software installed on the computer device, such as computer readable instructions for executing the above method. The processor may be a central processor, controller, microcontroller, or other data processing chip in some embodiments. The processor is typically used to control the overall operation of the computer device. In this embodiment, the processor is configured to execute the computer readable instructions stored in the memory or process data, such as the computer readable instructions for executing the above method. The network interface includes a wireless network interface or a wired network interface, which is typically used to establish a communication connection between the computer device and other electronic devices.
EXAMPLE III
1. To reduce the amount of calculation in estimating a road adhesion coefficient and improve the accuracy of road condition estimation. The specific road material in a road section can not change along with time, and the road material and the database under the current automobile speed are directly called by sending the road material to the networked vehicles through the intelligent network connection equipment at the intersection through the wireless communication module.
The road camera and the front camera of the vehicle respectively acquire the rough degree and the wet and slippery degree of the road through image analysis and identification, quantize and output the data to the data inspection module, the data inspection module compares the two to output, outputs reliable rough degree and wet and slippery degree values of the road, gives adjacent approximate fluctuation range, pre-calculates the expected value of angular deceleration at certain intervals in the fluctuation range, compares the error formed by actual angular deceleration, selects the minimum value of the error as the rough degree and the wet and slippery degree of the current road surface, corrects the slip rate-road surface adhesion coefficient curve, and controls the vehicle to keep the maximum adhesion coefficient to ensure that the vehicle obtains the maximum braking force.
Compared with the prior art, the method solves the problem that a database is difficult to realize accurate division of a large number of road conditions to a certain extent, determines the approximate range of the wet and rough degree of the road surface through the vehicle-mounted camera and the intersection camera, reduces the calculation amount of dynamic estimation, and improves the accuracy of the wet and rough degree of the road. The weight distribution of the camera and the weight of the camera in the data inspection module avoids the measurement errors caused by the interference of the camera and the external environment.
The VTH strategy is improved by taking the maximum achievable deceleration of the target vehicle as an input element. On the basis that the original strategy is kept, the following distance can be adjusted according to the actual motion state of two vehicles, the expected distance is adjusted according to the maximum acceleration and deceleration obtained under the condition that the maximum braking force is obtained through vehicle regulation, so that certain adaptability to the road driving environment is obtained. Under the condition of poor road environment, the maximum achievable deceleration of the vehicle can be reduced, the safe following distance is increased, and the safety of the vehicle is ensured. When the road environment is good, the maximum deceleration is increased, and f (a, a) is added p ) The minimum safe distance d can be shortened under the condition of meeting the operation condition c, Compared with the original strategy, the safety distance is further shortened so as to improve the traffic efficiency.
D E To expect a safe distance, D S For the controlled amount of the inter-vehicle distance, d c Is the psychological minimum safe distance, v i As the current speed of the vehicle, t all The time required for the complete braking of the vehicle in the event of an accident, t' is the communication time of the braking signal, t 1 Linearly increasing the duration of the brake, a p As acceleration of the front vehicle, a m Maximum (negative) acceleration of braking of the vehicle, d 0 The safe following distance is preset.
F M For its own maximum braking force, f 0 、f 1 Is a constant number of times, and is,the rolling resistance is indicated as a function of,the wind resistance of the running of the automobile is represented, the resistance of the ascending slope is represented by mgsin alpha, and the gradient of the advancing direction of the automobile is represented by alpha (alpha is positive when the ascending slope is up, and alpha is negative when the descending slope is down).
K and c are preset constants, and only when the current vehicle acceleration is larger than 0 and the acceleration difference value with the self braking is larger than a certain value when the vehicle follows, a certain amount of minimum safe vehicle following distance is reduced, so that the passing efficiency is improved.
Although the preferred embodiments of the present invention have been described in detail, the present invention is not limited to the details of the embodiments, and various equivalent changes may be made within the technical spirit of the present invention, and the technical scope of the present invention is also covered by the present invention.
Claims (9)
1. The intelligent networking automobile prediction control method considering the road running conditions is characterized by comprising the following steps of:
s1, aiming at each vehicle, acquiring a vehicle front image according to a preset frequency, extracting a road surface area from the vehicle front image, performing image identification by adopting a pre-stored neural network module, and giving and storing a first output result of vehicle front road surface parameters;
s2, receiving a road surface image of the current road section sent by a road section camera, adopting a neural network module to perform image recognition, and giving and storing a second output result of the current road section parameter;
s3, constructing a road parameter model based on the first output result and the second output result, judging whether the change rate of the road parameter exceeds a threshold value, and if not, giving an average value of the current road section parameter based on the first output result and the second output result and outputting the average value;
s4, constructing a vehicle dynamics model and an angular acceleration and deceleration calculation model, calculating a slip rate-adhesion coefficient database by taking the average value of the current road section parameters and the material of the current road section as one of input parameters, and determining a slip rate-adhesion coefficient relation curve of the current running vehicle condition; and controlling the slip rate based on the slip rate-adhesion coefficient relation curve, and determining the maximum adhesion coefficient, the maximum braking force and the expected safety distance.
2. The method for predictively controlling an intelligent networked automobile according to claim 1, wherein the step S2 further includes:
s21, collecting a traffic network map of a current area, and collecting traffic route data from the traffic network map to construct a traffic route directed graph;
s22, for each passing route, road section cameras are arranged on two sides of the passing route at preset intervals, the road section cameras collect road surface data according to preset frequency and store the road surface data in a storage module of each passing road section, and the road surface data comprise position information and image shooting time information of the road section cameras.
3. The intelligent networked automobile predictive control method taking into account road operating conditions as claimed in claim 2, wherein the step S2 further comprises:
s23, collecting pictures of cameras of all road sections of a preset passing road section according to a time sequence, processing the pictures by adopting a neural network module, constructing a model of picture information and road surface parameters, and giving a mapping set of empirical value ranges of the road surface parameters and the road surface picture information under all scenes;
and S24, verifying the empirical value range of the road surface parameters and the mapping set of the road surface picture information by adopting verification set data until the relevant standard is reached.
4. The intelligent networked automobile predictive control method considering the road running condition as claimed in claim 1, wherein said step S2 further comprises:
s25, receiving a road surface image of the current road section sent by a road section camera, and acquiring shooting time and geographical position information of the current image; measuring the road section parameters of the road section by adopting a measuring device preset on the road section to obtain a measured value sequence;
step S26, identifying the received road surface image by adopting a preset neural network module to obtain a calculation value sequence of the current road section parameters, namely a second output result;
s27, constructing a two-dimensional joint distribution Copula function of the measured value and the calculated value, and calculating parameters of the Copula function by adopting a maximum likelihood method through taking the measured value sequence and the calculated value sequence as one of inputs;
and S28, calculating probability distribution of the measured value and the calculated value based on the Copula function of the obtained parameter, and judging whether the measured result meets expectations or not based on the probability distribution, namely whether the similarity between the distribution of the calculated value and the distribution of the measured value meets the requirements or not.
5. The intelligent networked automobile predictive control method considering the road running condition as claimed in claim 1, wherein said step S3 further comprises:
s31, receiving the first output result and the second output result, respectively arranging in a descending order, respectively deleting the first 20% and the second 20% of data, respectively calculating the average value of the rest data, and obtaining the average value of the first output result and the average value of the second output result;
step S32, calculating the difference value of the first output result average value and the second output result average value, judging whether the difference value is smaller than a threshold value, and if the difference value is smaller than the threshold value, entering step S33;
and S33, calculating the average value of the first output result average value and the second output result average value as the average value of the current road section parameters.
6. The intelligent networked automobile predictive control method taking into account road operating conditions as claimed in claim 1, wherein said step S3 further comprises:
step S34, if the difference value is larger than or equal to the threshold value, acquiring a first output result and a second output result transmitted by each vehicle and road section camera, and respectively calculating the Spireman coefficients of each group of the first output result and the second output result to obtain a Spireman coefficient sequence;
step S35, calculating the variance and expectation of the spearman coefficient sequence;
and S36, judging whether the variance and the expectation of the Spireman coefficient are both smaller than a threshold value, and if so, calculating the average value of the current road section parameters based on the weight coefficients corresponding to the first output result and the second output result.
7. The intelligent networked automobile predictive control method considering the road running condition according to any one of claims 1 to 6, wherein in the process of constructing the method, the step S1 further comprises:
s11, acquiring a plurality of groups of traffic passing routes of different vehicles, and constructing a traffic flow network diagram through the routes;
and S12, extracting the front images on each traffic passage route according to the time sequence, marking the time and the place of each front image, and forming a front image data stream corresponding to each road section based on the time sequence.
S13, searching a vehicle front image of a certain road section acquired by each vehicle, constructing a vehicle front image training set and a vehicle front image testing set, and training and testing a neural network module;
when the road surface parameter identification method is used, a current vehicle-ahead image of a certain road section acquired by each vehicle is identified based on the constructed neural network module, and a first output result of the road surface parameter in front of the vehicle is given according to the vehicle-ahead image.
8. The method for predictively controlling an intelligent networked automobile according to claim 1, wherein in step S4, the expected safe distance is:
D E to expect a safe distance, D S For the controlled amount of inter-vehicle distance, d c Is the psychological minimum safe distance, v i As the current speed of the vehicle, t all The time required for the complete braking of the vehicle in the event of an accident, t' is the communication time length of the braking signal, t 1 Linearly increasing the duration of the brake, a p As acceleration of the front vehicle, a m For braking the own vehicle at maximum acceleration, d 0 For presetting a safe following distance, F M For its own maximum braking force, f 0 、f 1 Is a constant number of times, and is,the rolling resistance is indicated as a function of,the wind resistance of the running of the automobile is represented, the up-slope resistance is represented by mgsin alpha, and the gradient of the advancing direction of the automobile is represented by alpha; k and c are preset constants.
9. An intelligent networked automobile predictive control system considering road running conditions, comprising:
at least one processor; and
a memory communicatively coupled to at least one of the processors; wherein,
the memory stores instructions executable by the processor for implementing the intelligent networked automobile predictive control method considering road running conditions as claimed in any one of claims 1 to 8.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202211156074.5A CN115503712B (en) | 2022-09-22 | 2022-09-22 | Intelligent network-connected automobile predictive control method and system considering road running conditions |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202211156074.5A CN115503712B (en) | 2022-09-22 | 2022-09-22 | Intelligent network-connected automobile predictive control method and system considering road running conditions |
Publications (2)
Publication Number | Publication Date |
---|---|
CN115503712A true CN115503712A (en) | 2022-12-23 |
CN115503712B CN115503712B (en) | 2024-06-28 |
Family
ID=84505680
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202211156074.5A Active CN115503712B (en) | 2022-09-22 | 2022-09-22 | Intelligent network-connected automobile predictive control method and system considering road running conditions |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN115503712B (en) |
Citations (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US6473681B1 (en) * | 1998-04-18 | 2002-10-29 | Continental Teves Ag & Co., Ohg | Method for reducing braking distance |
JP2006236094A (en) * | 2005-02-25 | 2006-09-07 | Toyota Motor Corp | Obstacle recognition system |
JP2018072011A (en) * | 2016-10-25 | 2018-05-10 | 日産自動車株式会社 | Method and system for determining position of own vehicle |
CN109733410A (en) * | 2018-12-21 | 2019-05-10 | 浙江万安科技股份有限公司 | A kind of real-time pavement identification method of ABS and system |
CN109910897A (en) * | 2019-01-30 | 2019-06-21 | 江苏大学 | A kind of calculation of safety distance method based on road surface ahead peak adhesion coefficient |
CN110435623A (en) * | 2019-08-28 | 2019-11-12 | 吉林大学 | A kind of grading automatical emergency braking control system of the electric vehicle of adjust automatically |
CN111695418A (en) * | 2020-04-30 | 2020-09-22 | 上汽大众汽车有限公司 | Method and system for safe driving based on road condition detection |
CN111833627A (en) * | 2019-04-13 | 2020-10-27 | 长沙智能驾驶研究院有限公司 | Vehicle visual range expansion method, device and system and computer equipment |
CN113968231A (en) * | 2021-12-09 | 2022-01-25 | 吉林大学 | Intelligent driver model parameter determination method conforming to driver habits |
CN114821193A (en) * | 2022-05-26 | 2022-07-29 | 吉林大学 | Road surface adhesion coefficient online prediction device based on camera and vehicle speed sensor |
-
2022
- 2022-09-22 CN CN202211156074.5A patent/CN115503712B/en active Active
Patent Citations (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US6473681B1 (en) * | 1998-04-18 | 2002-10-29 | Continental Teves Ag & Co., Ohg | Method for reducing braking distance |
JP2006236094A (en) * | 2005-02-25 | 2006-09-07 | Toyota Motor Corp | Obstacle recognition system |
JP2018072011A (en) * | 2016-10-25 | 2018-05-10 | 日産自動車株式会社 | Method and system for determining position of own vehicle |
CN109733410A (en) * | 2018-12-21 | 2019-05-10 | 浙江万安科技股份有限公司 | A kind of real-time pavement identification method of ABS and system |
CN109910897A (en) * | 2019-01-30 | 2019-06-21 | 江苏大学 | A kind of calculation of safety distance method based on road surface ahead peak adhesion coefficient |
CN111833627A (en) * | 2019-04-13 | 2020-10-27 | 长沙智能驾驶研究院有限公司 | Vehicle visual range expansion method, device and system and computer equipment |
CN110435623A (en) * | 2019-08-28 | 2019-11-12 | 吉林大学 | A kind of grading automatical emergency braking control system of the electric vehicle of adjust automatically |
CN111695418A (en) * | 2020-04-30 | 2020-09-22 | 上汽大众汽车有限公司 | Method and system for safe driving based on road condition detection |
CN113968231A (en) * | 2021-12-09 | 2022-01-25 | 吉林大学 | Intelligent driver model parameter determination method conforming to driver habits |
CN114821193A (en) * | 2022-05-26 | 2022-07-29 | 吉林大学 | Road surface adhesion coefficient online prediction device based on camera and vehicle speed sensor |
Also Published As
Publication number | Publication date |
---|---|
CN115503712B (en) | 2024-06-28 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US10347122B2 (en) | Road condition monitoring system | |
CN108423005B (en) | Generation of feedback-based control model for autonomous vehicles | |
CN108877213B (en) | Traffic accident identification method and system | |
Yang et al. | Image-based visibility estimation algorithm for intelligent transportation systems | |
CN108645375B (en) | Rapid vehicle distance measurement optimization method for vehicle-mounted binocular system | |
CN117173913B (en) | Traffic control method and system based on traffic flow analysis at different time periods | |
US20220383736A1 (en) | Method for estimating coverage of the area of traffic scenarios | |
CN113178074A (en) | Traffic flow machine learning modeling system and method applied to vehicle | |
CN116109986A (en) | Vehicle track extraction method based on laser radar and video technology complementation | |
CN115657002A (en) | Vehicle motion state estimation method based on traffic millimeter wave radar | |
CN114771548A (en) | Data logging for advanced driver assistance system testing and verification | |
CN111183464B (en) | System and method for estimating saturation flow of signal intersection based on vehicle trajectory data | |
Luo et al. | Traffic signal transition time prediction based on aerial captures during peak hours | |
CN113380039B (en) | Data processing method and device and electronic equipment | |
CN110781730B (en) | Intelligent driving sensing method and sensing device | |
CN115503712B (en) | Intelligent network-connected automobile predictive control method and system considering road running conditions | |
JP2005216202A (en) | Device and method for predicting future value | |
CN112319505A (en) | Automatic driving lane change judgment method, device, equipment and storage medium | |
KR102616571B1 (en) | System and method for providing road traffic information based on image analysis using artificial intelligence | |
CN115049996B (en) | Double-sensor target detection fusion method and system based on evidence reasoning rule | |
CN113128847A (en) | Entrance ramp real-time risk early warning system and method based on laser radar | |
JP2000322682A (en) | System, device and method for predicting traffic flow | |
KR102448268B1 (en) | Intelligent image analysis system for accuracy enhancement of object analysis by auto learning, estimation and distribution of object based on Deep Neural Network Algorithm | |
CN113808384B (en) | Traffic condition detection method | |
CN113706586B (en) | Target tracking method and device based on multi-point position perception and storage medium |
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 | ||
CB02 | Change of applicant information | ||
CB02 | Change of applicant information |
Country or region after: China Address after: 406-413A, Building 1, Qilin Artificial Intelligence Industrial Park, Qilin Hi tech Zone, Nanjing, Jiangsu Province, 211000 Applicant after: Nanjing Changjiang Automation Research Institute Co.,Ltd. Address before: 406-413A, Building 1, Qilin Artificial Intelligence Industrial Park, Qilin Hi tech Zone, Nanjing, Jiangsu Province, 211000 Applicant before: NANJING LIGONG AUTOMATION Co.,Ltd. Country or region before: China |
|
GR01 | Patent grant | ||
GR01 | Patent grant |