CN107891866A - The method that road surface is determined based on vehicle data - Google Patents
The method that road surface is determined based on vehicle data Download PDFInfo
- Publication number
- CN107891866A CN107891866A CN201611100584.5A CN201611100584A CN107891866A CN 107891866 A CN107891866 A CN 107891866A CN 201611100584 A CN201611100584 A CN 201611100584A CN 107891866 A CN107891866 A CN 107891866A
- Authority
- CN
- China
- Prior art keywords
- road surface
- threshold
- value
- road
- low friction
- 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
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
- 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
- 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
- B60W40/068—Road friction coefficient
-
- 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
-
- 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
- B60W2520/00—Input parameters relating to overall vehicle dynamics
- B60W2520/10—Longitudinal speed
- B60W2520/105—Longitudinal acceleration
-
- 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
- B60W2520/00—Input parameters relating to overall vehicle dynamics
- B60W2520/28—Wheel speed
-
- 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
- B60W2540/00—Input parameters relating to occupants
- B60W2540/10—Accelerator pedal position
-
- 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
- B60W2552/00—Input parameters relating to infrastructure
- B60W2552/40—Coefficient of friction
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60Y—INDEXING SCHEME RELATING TO ASPECTS CROSS-CUTTING VEHICLE TECHNOLOGY
- B60Y2400/00—Special features of vehicle units
- B60Y2400/30—Sensors
- B60Y2400/303—Speed sensors
- B60Y2400/3032—Wheel speed sensors
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Mathematical Physics (AREA)
- Theoretical Computer Science (AREA)
- Automation & Control Theory (AREA)
- Transportation (AREA)
- Mechanical Engineering (AREA)
- Biophysics (AREA)
- General Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- Life Sciences & Earth Sciences (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Software Systems (AREA)
- Health & Medical Sciences (AREA)
- Control Of Driving Devices And Active Controlling Of Vehicle (AREA)
- Regulating Braking Force (AREA)
Abstract
This application discloses the method that road surface is determined based on vehicle data.A kind of method for determining road surface based on vehicle data by controller is provided, methods described includes:Pre-process vehicle data;By the neutral net of the data input of pretreatment to study to obtain corresponding output;The first sample with reference to quantity is sequentially extracted from the output of neutral net, and detects the value (hereinafter referred to as " median ") of the sample among sample;And determine that road surface is high friction road surface or low friction road surface based on the median detected.
Description
The cross reference of related application
The application based on and require the 10-2016- submitted on October 4th, 2016 in Korean Intellectual Property Office
The rights and interests of the priority of No. 0127656 korean patent application, entire contents are incorporated herein by quoting herein.
Technical field
This disclosure relates to a kind of method that road surface is determined based on vehicle data, more specifically, is related to a kind of be based on from car
The vehicle data that contained network network obtains, the road surface where determining vehicle traveling are the technologies on high friction road surface or low friction road surface.
Controller LAN (CAN), local interconnect network are included according to the In-vehicle networking of the exemplary embodiment of the disclosure
(LIN), FlexRay and media guidance system transmission (MOST).
Background technology
In order to ensure the safety of driver, vehicle is already equipped with various user-friendly systems, such as ANTI LOCK
System (ABS), electronic stability control (ESC) system, intelligent cruise control (SCC) system and Senior Officer's accessory system
(ADAS)。
For optimum performance, these user-friendly systems can control the behavior of vehicle by considering pavement behavior.This
In, pavement behavior refers to the high friction road surface of such as dry asphalt roads and dry cement road and such as rainy day road, snowy day
The low friction road surface of road and dirt road.
Traditionally, following methods be present:Determine that road surface is high friction road surface or low friction road based on dynamics data
The method in face, the dynamics data such as wheel velocity, engine torque and car speed;And based on from various sensings
The data of device determine that road surface is the method on high friction road surface or low friction road surface, the various sensors such as road surface directive property
Ultrasonic sensor and microphone.
First, determine that the method on road surface determines that road surface is high friction road surface based on vehicle sliding phenomenon based on dynamics data
Or low friction road surface.Therefore, when vehicle traveling is when on the road of the special style of not quick acceleration or deceleration, it may be difficult to
Determine that the road surface that vehicle is travelling thereon is high friction road surface or low friction road surface.
Second, determine that the method on road surface needs additional installation to pass based on the data from road surface directive property ultrasonic sensor
Sensor, cause the increase of vehicle production cost.
The content of the invention
The advantages of disclosure is directed to solving the above mentioned problem occurred in the prior art, while holding is realized by prior art
It is unaffected.
A kind of method for determining road surface based on vehicle data by following steps is provided in terms of the disclosure:With corresponding
Vehicle data is pre-processed in the mode of the feature of each vehicle data;Neutral net by the data input of pretreatment to study;
Output to neutral net post-processes;And determine that road surface is high friction road surface or low friction road surface, from regardless of whether road
How is road type, quickly and accurately determines pavement behavior.
The purpose of the disclosure is not limited to object defined above, and is clearly understood that from the following description NM herein
Any other objects and advantages.Present inventive concept will be more clearly understood from the exemplary embodiment of the disclosure.In addition, aobvious and easy
See, the objects and advantages of the disclosure can be realized by the element being claimed in claim and feature and combinations thereof.
It is a kind of to determine that the method on road surface includes based on vehicle data by controller according to the one side of the disclosure:Pretreatment
Vehicle data;By the neutral net of the data input of pretreatment to study to obtain corresponding output;From the output of neutral net
Sequentially extraction first with reference to quantity sample, and detect the sample of (middle) among the sample value (hereinafter referred to as " in
Between be worth ");And determine that road surface is high friction road surface or low friction road surface based on the median detected.
It is a kind of to determine that the method on road surface includes by controller according to another aspect of the present disclosure:Pre-process vehicle data;Will
The data input of pretreatment to study neutral net to obtain corresponding output;Is sequentially extracted from the output of neutral net
The sample of one reference quantity, and calculate the average value of the sample of extraction;And it is to determine road surface based on the average value calculated
Height friction road surface or low friction road surface.
Brief description of the drawings
According to the detailed description below in conjunction with accompanying drawing, the above and other objects, features and advantages of the disclosure will more show
And it is clear to:
Fig. 1 shows the system that road surface is determined based on vehicle data using present inventive concept;
Fig. 2 shows the output of the neutral net of the exemplary embodiment according to the disclosure;
Fig. 3 shows the block diagram of the state transformation on the road surface of the exemplary embodiment according to the disclosure;
Fig. 4 shows the flow of the method that road surface is determined based on vehicle data of the exemplary embodiment according to the disclosure
Figure;And
Fig. 5 shows the method that determines road surface based on vehicle data according to another exemplary embodiment of the disclosure
Flow chart.
Embodiment
From the detailed description below in conjunction with accompanying drawing, will be more clearly understood above and other purpose of the disclosure, feature and
Advantage so that disclosure those skilled in the art can easily implement the techniques described herein thought.In addition, it will exclude
The detailed description of the known technology associated with the disclosure, in order to avoid unnecessarily obscure the main points of the disclosure.Hereinafter, by reference
The exemplary embodiment of the disclosure is described in detail in accompanying drawing.
Fig. 1 shows the logic that road surface is determined based on vehicle data of the exemplary embodiment according to the disclosure.
As shown in figure 1, according to the exemplary embodiment of the disclosure based on vehicle data determine the logic on road surface be by
The memory interconnection of the process that device (controller) performs, the processor (controller) and the instruction that wherein has program recorded thereon is managed, and
And the logic includes pretreatment operation 10, neutral net 20 and post-processing operation 30.
First, in pretreatment operation 10, can be pre-processed in a manner of corresponding to the feature of each vehicle data from
The vehicle data that In-vehicle networking is collected.
For example, longitudinal acceleration sensor (LAS) data, wheel speed sensors (WSS) data, accelerator pedal position sensor
(APS) data and steering wheel angle sensor (SAS) data can from In-vehicle networking (such as controller LAN (CAN) bus) with
Collect at 10ms intervals.Here, in pretreatment operation 10, can also be received from single data collector (not shown) LAS data,
The input of WSS data, APS data and SAS data.
Hereafter, the APS data on power (as main output caused by the operation as vehicle), can calculate APS data values
Average value and difference, to check its size and change.
In addition, wheel of vehicle rotating speed and longitudinal direction of car acceleration on representing vehicle behavior outcome, can calculate standard deviation
Difference is to check the variance of window., can by calculating the standard deviation on the rotary speed difference between front and back wheel between left and right wheels
Emphasize the behavioural characteristic as caused by road surface uneven (ways face is uneven).
In addition, on steering wheel angle, average value and poor (differential, difference) value can be calculated, so that logic is steady
Surely the change of the behavioural characteristic as caused by turn inside diameter is responded.
Hereinafter, it will be described in pretreatment operation 10.Here, the quantity of the data of single window (processing unit) is formed
The physical characteristic (transmission time difference) of each data can be confirmed as considering.For example, the quantity of data can be 50, and can be with
Arbitrarily change.
1) the standard deviation LAS_Std of 50 LAS data (value) can be calculated.
2) can be on being marked by subtracting the average speed of trailing wheel from the average speed of front-wheel and 50 values obtained to calculate
Quasi- deviation FR_Diff_Std.In other words, carried out 50 times in the calculating that the average speed of trailing wheel is subtracted from the average speed of front-wheel
Afterwards, the standard deviation of 50 end values can be calculated.Here, front-wheel includes the near front wheel and off-front wheel, trailing wheel include left rear wheel and
Off hind wheel.
3) can be on being marked by subtracting the average speed of revolver from the average speed of right wheel and 50 values obtained to calculate
Quasi- deviation LR_Diff_Std.Here, right wheel includes off-front wheel and off hind wheel, and revolver includes the near front wheel and left rear wheel.
4) the average value APS_Avg of 50 APS data (value) can be calculated.
5) 50 differences that can calculate APS data (are tied by 50 that subtract previous APS values from current APS values to obtain
Fruit value) summation APS_Diff.
6) 50 differences of SAS data can be calculated (by subtracting previous SAS values from current SAS values obtain 50
End value) summation SAS_Diff.
7) the average value SAS_Avg of 50 SAS data (value) can be calculated.
The data of these pretreatments can be input into the neutral net 20 for having completed learning process.
Neutral net 20 can be the learning-oriented neutral net being subjected to supervision.Neutral net 20 have been completed learning process with
Input pre-processes the result of LAS data, WSS data, APS data and SAS data, and obtains corresponding output (friction level).
The output of the neutral net 20 of study can be as shown in Figure 2.
In fig. 2, y-axis represents the output of neutral net 20, and x-axis represents the time.Here, the value 0.1 in x-axis corresponds to
10ms。
In fig. 2, " 210 " represent the output on the high friction road surface on such as dry asphalt roads and dry cement road, and
And " 220 " represent the output on the low friction road surface on such as snowy day road and rainy day road.
Because frictional force is uniform on height friction road surface, the stable output less than 0.5 can be obtained.But due to rubbing
It is uneven on low friction road surface to wipe power, 0.5 or bigger unstable output may be obtained.
In post-processing operation 30, the output of neutral net 20 can be post-processed, to use the defeated of neutral net 20
The road surface for out determining vehicle traveling is high friction road surface or low friction road surface.
Hereinafter, it will be described in post-processing operation 30.Here, post-processing operation, and sample can be periodically carried out
This quantity can arbitrarily change.
1) after extracting 300 samples in the output from neutral net 20, maximum can therefrom be detected.Here, it is maximum
Value can represent the transient change of the output of neutral net 20.
2) standard deviation of 300 samples of extraction can be calculated.
3) on poor between the adjacent sample of 300 samples extracted and relative value will can be calculated as.Here, sample
The absolute change of output poor and that neutral net 20 can be represented between this.
For example, when first sample value, the second sample value and the 3rd sample value are respectively 1,2 and 4, first sample value and
Difference between two sample values is 1, and the difference between the second sample value and the 3rd sample value is 2, therefore, poor and be 3.
4) after 1000 samples are sequentially extracted from the output of neutral net 20, the value of the 500th sample can be examined
Survey as median.Here, median can represent the overall state of the output of neutral net 20.Meanwhile can also be by 1000 samples
Average detection be median.
Hereinafter, reference picture 3, description is determined to the process of pavement behavior by controller.
In figure 3, " 310 " represent initial road situation.When the median of initial condition of road surface 310 exceedes first threshold
When, condition of road surface can be changed into low friction condition of road surface 320, and when it is no more than first threshold, can be by condition of road surface
Change into high friction-road situation 330.
When the median of high friction-road situation 330 exceedes Second Threshold, condition of road surface can be changed into low friction road
Road situation 320, and when it is no more than Second Threshold, present road situation can be kept.
When the median of low friction condition of road surface 320 is more than three threshold values, present road situation can be kept, and work as it
During no more than three threshold values, condition of road surface can be changed into high friction-road situation 330.
Here, when priority is placed in the stability for the system that present inventive concept is applied by user, in stable mode,
The order of threshold value can meet the 3rd threshold value<First threshold<Second Threshold.
In addition, when priority is placed on low friction road surface by user, in low friction mode of priority, the order of threshold value can
Meet first threshold<3rd threshold value<Second Threshold.
In addition, when priority is placed on high friction road surface by user, in high frictive preferential pattern, the order of threshold value can
Meet the 3rd threshold value<Second Threshold<First threshold.
In addition, when the summation of the maximum of high friction-road situation 330, standard deviation and relative value is more than the 4th threshold value
When (for example, 4), condition of road surface can be changed into low friction condition of road surface 320, and when it is no more than four threshold values, can tie up
Hold present road situation.
When the maximum of low friction condition of road surface 320 is more than five threshold values, present road situation can be kept, and work as it
During no more than five threshold values, condition of road surface can be changed into high friction-road situation 330.
Meanwhile in order to improve the reliability that road surface determines result, it can be estimated based on the sliding of the output by neutral net 20
Result is counted, pause under the following conditions determines:
1) when driving, brake is activated
- when in the average speed of the average speed of front-wheel, the average speed of trailing wheel, the average speed of right wheel and revolver extremely
Few one when being no more than preset value, it may be determined that activates brake in driving.
2) low speed section
- do not surpass when the average speed of the average speed of front-wheel, the average speed of trailing wheel, the average speed of right wheel and revolver
When crossing 10kph, low speed section can be defined as.
3) turn to
When keeping the time (period) that SAS values exceed reference value, it may be determined that to turn to.
4) rasping road
- when brake is activated more than or equal to pre-determined number within a predetermined period of time, coarse road can be defined as
Road.
By the way that present inventive concept is applied into ABS, ESC system, SCC systems, ADAS, 4WD etc., correspondence system can be improved
Performance.
Fig. 4 shows the flow of the method that road surface is determined based on vehicle data of the exemplary embodiment according to the disclosure
Figure.It illustrates the process performed by processor (controller).
First, vehicle data can be pre-processed in 401.
Next, in 402, neutral net that can be by the data input of pretreatment to study, so as to defeated corresponding to obtaining
Go out.
It is detectable to be located at after the first sample with reference to quantity is sequentially extracted in the output from neutral net 403
The value (hereinafter referred to as " median ") of sample among sample.
Then, in 404, it can determine that road surface is high friction road surface or low friction road based on the median detected
Face.
Fig. 5 shows the method that determines road surface based on vehicle data according to another exemplary embodiment of the disclosure
Flow chart.It illustrates the process performed by processor (controller).
First, vehicle data can be pre-processed in 501.
Next, in 502, neutral net that can be by the data input of pretreatment to study, so as to defeated corresponding to obtaining
Go out.
In 503, after the first sample with reference to quantity is extracted in the output sequentially from neutral net, it can calculate and carry
The average value of the sample taken.
Then, in 504, it can determine that road surface is high friction road surface or low friction road based on the average value calculated
Face.
On the other hand, computer program can be written as according to the above method of the exemplary embodiment of the disclosure.Form journey
The code and code segment of sequence easily can be inferred by the computer programmer of this area.The program of write-in is storable in computer can
In read record medium (information storage medium), and read and performed by computer, so as to implement according to the exemplary of the disclosure
The method of embodiment.The recording medium includes all types of computer readable recording medium storing program for performing.
As described above, the feature of the method on road surface is determined based on vehicle data to be:With corresponding to each vehicle data
The mode of feature pre-process vehicle data, the neutral net by the data input of pretreatment to study, to the defeated of neutral net
Go out to be post-processed, and determine that the road surface that vehicle is travelled is high friction road surface or low friction road surface, from regardless of whether road
How is type, quickly and accurately determines pavement behavior.
Hereinbefore, although describing the disclosure with reference to exemplary embodiment and accompanying drawing, disclosure not limited to this, and
Be can by disclosure those skilled in the art in appended claims are not departed from be claimed the disclosure spirit and
Various modifications and changes are carried out in the case of scope.
The symbol of each element in accompanying drawing
310 initial road situations
320 low friction condition of road surface
330 high friction-road situations
401 pretreatment vehicle datas
402 input the data pre-processed to the neutral net of study to obtain corresponding output
403 sequentially extract the first sample with reference to quantity from the output of neutral net, and detect among sample
Sample value (hereafter, median)
404 determine that road surface is high friction road surface or low friction road surface based on the median detected
501 pretreatment vehicle datas
502 input the data pre-processed to the neutral net of study to obtain corresponding output
503 sequentially extract the first sample with reference to quantity from the output of neutral net, and calculate the sample of extraction
Average value
504 average values based on calculating determine that road surface is high friction road surface or low friction road surface.
Claims (20)
1. a kind of method for being determined road surface based on vehicle data by controller, the described method comprises the following steps:
Pre-process vehicle data;
By the neutral net of the data input of pretreatment to study to obtain corresponding output;
The first sample with reference to quantity is sequentially extracted from the output of the neutral net, and detects and is located at described first
With reference to quantity sample among sample value as median;And
Based on the median detected, it is high friction road surface or low friction road surface to determine road surface.
2. according to the method for claim 1, wherein, the determination step includes:
When the median under initial condition of road surface exceedes first threshold, the initial road situation is changed into low friction
Condition of road surface, and when the median under the initial road situation is no more than the first threshold, will be described initial
Condition of road surface changes into high friction-road situation;
When the median under the high friction-road situation exceedes Second Threshold, the high friction-road situation is changed
For the low friction condition of road surface, and the median under the high friction-road situation is no more than the Second Threshold
When, keep present road situation;And
When the median under the low friction condition of road surface is more than three threshold values, present road situation is kept, and work as
When the median under the low friction condition of road surface is no more than three threshold value, the low friction condition of road surface is changed
For the high friction-road situation.
3. according to the method for claim 2, wherein, the threshold value order in mode of priority is stablized meets the 3rd threshold value
<The first threshold<The Second Threshold.
4. according to the method for claim 2, wherein, the threshold value order in low friction mode of priority meets first threshold
Value<3rd threshold value<The Second Threshold.
5. according to the method for claim 2, wherein, the threshold value order in high frictive preferential pattern meets the 3rd threshold
Value<The Second Threshold<The first threshold.
6. according to the method for claim 1, further comprise:
From the output of the neutral net extraction second with reference to quantity sample, and from described second with reference to quantity sample
Maximum is detected in this;
Calculate the described second standard deviation with reference to the sample of quantity;And
The poor summation between the adjacent sample on the sample of the described second reference quantity is calculated as relative value.
7. according to the method for claim 6, wherein, the determination step includes:Described under high friction-road situation
When the summation of maximum, the standard deviation and the relative value is more than four threshold values, the high friction-road situation is changed
For low friction condition of road surface, and when the maximum, the standard deviation and the phase under the high friction-road situation
When being no more than four threshold value to the summation of value, present road situation is kept.
8. according to the method for claim 6, wherein, the determination step includes:Described under low friction condition of road surface
When maximum is more than five threshold values, present road situation is kept, and when the maximum under the low friction condition of road surface
During no more than five threshold value, the low friction condition of road surface is changed into high friction-road situation.
9. according to the method for claim 1, wherein, the vehicle data include longitudinal acceleration sensor (LAS) data,
In wheel speed sensors (WSS) data, accelerator pedal position sensor (APS) data and steering wheel angle sensor (SAS) data
It is at least one.
10. according to the method for claim 9, wherein, the pre-treatment step includes:
Calculate the 3rd standard deviation with reference to the longitudinal acceleration sensor data of quantity;
By subtracting the average speed of trailing wheel from the average speed of front-wheel and calculating its standard deviation quantity is referred to obtain the 3rd
Value;
The 3rd reference number is obtained by subtracting the average speed of revolver from the average speed of right wheel and calculating its standard deviation
The value of amount;
Calculate the 3rd average value with reference to the accelerator pedal position sensor data of quantity;
Obtain the 3rd with reference to quantity accelerator pedal position sensor data difference and calculate itself and;
Obtain the 3rd with reference to quantity steering wheel angle sensor data difference and calculate itself and;And
Calculate the 3rd average value with reference to the steering wheel angle sensor data of quantity.
11. a kind of method for being determined road surface based on vehicle data by controller, the described method comprises the following steps:
Pre-process vehicle data;
By the neutral net of the data input of pretreatment to study to obtain corresponding output;
The first sample with reference to quantity is sequentially extracted from the output of the neutral net, and calculate the sample of extraction
Average value;And
Determine that road surface is high friction road surface or low friction road surface based on the average value calculated.
12. according to the method for claim 11, wherein, the determination step includes:
When the average value under initial condition of road surface exceedes first threshold, initial road situation is changed into low friction road
Situation, and when the average value under the initial road situation is no more than the first threshold, by the initial road
Situation changes into high friction-road situation;
When the average value under the high friction-road situation exceedes Second Threshold, the high friction-road situation is changed
For the low friction condition of road surface, and the average value under the high friction-road situation is no more than second threshold
Value, keep present road situation;And
When the average value under the low friction condition of road surface is more than three threshold values, present road situation is kept, and work as
The average value under the low friction condition of road surface is no more than the 3rd threshold value, and the low friction condition of road surface is changed into
The high friction-road situation.
13. according to the method for claim 12, wherein, the threshold value order in mode of priority is stablized meets the 3rd threshold
Value<The first threshold<The Second Threshold.
14. according to the method for claim 12, wherein, the threshold value order in low friction mode of priority meets described first
Threshold value<3rd threshold value<The Second Threshold.
15. according to the method for claim 12, wherein, the threshold value order in high frictive preferential pattern meets the described 3rd
Threshold value<The Second Threshold<The first threshold.
16. according to the method for claim 11, further comprise:
From the output of the neutral net extraction second with reference to quantity sample, and from described second with reference to quantity sample
Maximum is detected in this;
Calculate the described second standard deviation with reference to the sample of quantity;And
Calculate on described second with reference to quantity sample adjacent sample between it is poor and as relative value.
17. according to the method for claim 16, wherein, the determination step includes:Institute under high friction-road situation
When stating the summation of maximum, the standard deviation and the relative value more than four threshold values, the high friction-road situation is changed
It is changed into low friction condition of road surface, and when the maximum under the high friction-road situation, the standard deviation and described
The summation of relative value is no more than the 4th threshold value, keeps present road situation.
18. according to the method for claim 16, wherein, the determination step includes:When the institute under low friction condition of road surface
When stating maximum more than five threshold values, present road situation is kept, and when the maximum under the low friction condition of road surface
When value is no more than five threshold value, the low friction condition of road surface is changed into high friction-road situation.
19. according to the method for claim 11, wherein, the vehicle data includes longitudinal acceleration sensor (LAS) number
According to, wheel speed sensors (WSS) data, accelerator pedal position sensor (APS) data and steering wheel angle sensor (SAS) data
In it is at least one.
20. according to the method for claim 19, wherein, the pre-treatment step includes:
Calculate the 3rd standard deviation with reference to the longitudinal acceleration sensor data of quantity;
By subtracting the average speed of trailing wheel from the average speed of front-wheel and calculating its standard deviation quantity is referred to obtain the 3rd
Value;
The 3rd reference number is obtained by subtracting the average speed of revolver from the average speed of right wheel and calculating its standard deviation
The value of amount;
Calculate the 3rd average value with reference to the accelerator pedal position sensor data of quantity;
Obtain the 3rd with reference to quantity accelerator pedal position sensor data difference and calculate itself and;
Obtain the 3rd with reference to quantity steering wheel angle sensor data difference and calculate itself and;And
Calculate the 3rd average value with reference to the steering wheel angle sensor data of quantity.
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
KR10-2016-0127656 | 2016-10-04 | ||
KR1020160127656A KR101827152B1 (en) | 2016-10-04 | 2016-10-04 | Method for deciding a road surface using vehicle data |
Publications (2)
Publication Number | Publication Date |
---|---|
CN107891866A true CN107891866A (en) | 2018-04-10 |
CN107891866B CN107891866B (en) | 2021-02-05 |
Family
ID=61803196
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201611100584.5A Active CN107891866B (en) | 2016-10-04 | 2016-12-02 | Method for determining a road surface on the basis of vehicle data |
Country Status (2)
Country | Link |
---|---|
KR (1) | KR101827152B1 (en) |
CN (1) | CN107891866B (en) |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109398363A (en) * | 2018-10-24 | 2019-03-01 | 珠海格力电器股份有限公司 | Pavement grade determination method and device, storage medium and automobile |
CN111196278A (en) * | 2018-11-16 | 2020-05-26 | 上海汽车集团股份有限公司 | Slope identification and vehicle control method and device and electronic equipment |
WO2021115063A1 (en) * | 2019-12-10 | 2021-06-17 | 中国科学院深圳先进技术研究院 | Data-driven method and apparatus for identifying adhesion stability of electric-driven vehicle |
CN114084143A (en) * | 2020-07-31 | 2022-02-25 | 通用汽车环球科技运作有限责任公司 | Apparatus and method for road condition classification using sensor data |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2001039289A (en) * | 1999-07-30 | 2001-02-13 | Fuji Heavy Ind Ltd | Vehicular road surface friction coefficient estimating device |
US20040162644A1 (en) * | 2003-02-19 | 2004-08-19 | Fuji Jukogyo Kabushiki Kaisha | Vehicle motion model generating device and method for generating vehicle motion model |
CN101275900A (en) * | 2008-05-08 | 2008-10-01 | 江汉大学 | Method for recognizing road surface types based on vehicle wheel vibration |
CN101609606A (en) * | 2009-07-10 | 2009-12-23 | 清华大学 | A kind of road surface wet and slippery state identification method |
CN104540717A (en) * | 2012-08-09 | 2015-04-22 | 株式会社普利司通 | Method and device for determining state of road surface |
CN104537209A (en) * | 2014-12-09 | 2015-04-22 | 上海交通大学 | Method for judging vehicle running road types based on hidden Markov model |
Family Cites Families (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
KR0118989B1 (en) | 1994-12-14 | 1997-09-30 | 김종진 | Pre-estimation method and apparatus for carbon concentration |
JP2011107885A (en) | 2009-11-16 | 2011-06-02 | Toshiba Corp | Preprocessor in neural network learning |
KR101534985B1 (en) | 2013-12-27 | 2015-07-07 | 현대자동차주식회사 | A friction adjustment method of MDPS[Moter driven power steering] and the apparatus thereof |
-
2016
- 2016-10-04 KR KR1020160127656A patent/KR101827152B1/en active IP Right Grant
- 2016-12-02 CN CN201611100584.5A patent/CN107891866B/en active Active
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2001039289A (en) * | 1999-07-30 | 2001-02-13 | Fuji Heavy Ind Ltd | Vehicular road surface friction coefficient estimating device |
US20040162644A1 (en) * | 2003-02-19 | 2004-08-19 | Fuji Jukogyo Kabushiki Kaisha | Vehicle motion model generating device and method for generating vehicle motion model |
CN101275900A (en) * | 2008-05-08 | 2008-10-01 | 江汉大学 | Method for recognizing road surface types based on vehicle wheel vibration |
CN101609606A (en) * | 2009-07-10 | 2009-12-23 | 清华大学 | A kind of road surface wet and slippery state identification method |
CN104540717A (en) * | 2012-08-09 | 2015-04-22 | 株式会社普利司通 | Method and device for determining state of road surface |
CN104537209A (en) * | 2014-12-09 | 2015-04-22 | 上海交通大学 | Method for judging vehicle running road types based on hidden Markov model |
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109398363A (en) * | 2018-10-24 | 2019-03-01 | 珠海格力电器股份有限公司 | Pavement grade determination method and device, storage medium and automobile |
CN109398363B (en) * | 2018-10-24 | 2020-11-06 | 珠海格力电器股份有限公司 | Pavement grade determination method and device, storage medium and automobile |
CN111196278A (en) * | 2018-11-16 | 2020-05-26 | 上海汽车集团股份有限公司 | Slope identification and vehicle control method and device and electronic equipment |
WO2021115063A1 (en) * | 2019-12-10 | 2021-06-17 | 中国科学院深圳先进技术研究院 | Data-driven method and apparatus for identifying adhesion stability of electric-driven vehicle |
CN114084143A (en) * | 2020-07-31 | 2022-02-25 | 通用汽车环球科技运作有限责任公司 | Apparatus and method for road condition classification using sensor data |
Also Published As
Publication number | Publication date |
---|---|
KR101827152B1 (en) | 2018-03-22 |
CN107891866B (en) | 2021-02-05 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN107891866A (en) | The method that road surface is determined based on vehicle data | |
EP2221635B1 (en) | Method for monitoring the environment of an automobile | |
CN105849657B (en) | Virtual test for driving assistance system optimizes | |
CN107901912B (en) | Method for determining a road surface based on vehicle data | |
CN107415945A (en) | For assessing the automotive drive system and its application method of track lane-change | |
EP3309024B1 (en) | Method and system for determining friction between the ground and a tire of a vehicle | |
CN106627569A (en) | In-path target selection during lane change | |
US20110224895A1 (en) | Method and device for determining a center of gravity of a motor vehicle | |
CN110001773A (en) | Self-steering control | |
JP2015521971A (en) | An improved method for determining the absolute angular position of an automotive steering wheel | |
EP3224115B1 (en) | Understeer or oversteer detector for automobile | |
CN105324805A (en) | Method and device for avoiding a possible subsequent collision and for reducing the consequences of an accident resulting from a collision | |
CN108399214A (en) | Determine the Friction dates of target vehicle | |
CN111688690A (en) | Device and method for avoiding vehicle collapse | |
Jiang et al. | Real-time estimation and prediction of tire forces using digital map for driving risk assessment | |
CN112896173A (en) | Apparatus for estimating friction coefficient of road surface and method thereof | |
US20200041304A1 (en) | High resolution virtual wheel speed sensor | |
US11893004B2 (en) | Anomaly detection in multidimensional sensor data | |
WO2020193860A1 (en) | Modelling dynamics of a vehicle | |
CN106103228B (en) | A kind of vehicle control system | |
He et al. | Interval recognition algorithm of the pavement surface condition based on Lagrange interpolation method | |
CN108944942A (en) | The detection method and device of straight line traveling | |
US11702133B2 (en) | Yaw stability control system for a motor vehicle | |
US8412435B2 (en) | System and method for detection of spun vehicle | |
Kim et al. | NETTED: Non-Standard CAN ID Extraction System Based on Deep Neural Networks |
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 | ||
GR01 | Patent grant |