CN117325875A - Vehicle long-term speed prediction method based on individual driving characteristics - Google Patents
Vehicle long-term speed prediction method based on individual driving characteristics Download PDFInfo
- Publication number
- CN117325875A CN117325875A CN202311630380.2A CN202311630380A CN117325875A CN 117325875 A CN117325875 A CN 117325875A CN 202311630380 A CN202311630380 A CN 202311630380A CN 117325875 A CN117325875 A CN 117325875A
- Authority
- CN
- China
- Prior art keywords
- speed
- long
- driving
- term
- matrix
- 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
- 230000007774 longterm Effects 0.000 title claims abstract description 59
- 238000000034 method Methods 0.000 title claims abstract description 37
- 239000011159 matrix material Substances 0.000 claims abstract description 85
- 230000001133 acceleration Effects 0.000 claims abstract description 61
- 230000008859 change Effects 0.000 claims abstract description 7
- 238000005070 sampling Methods 0.000 claims description 16
- 238000007726 management method Methods 0.000 description 4
- 238000009825 accumulation Methods 0.000 description 3
- 230000006870 function Effects 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 230000008901 benefit Effects 0.000 description 2
- 238000012512 characterization method Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 238000004088 simulation Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 230000008447 perception Effects 0.000 description 1
- 238000005096 rolling process Methods 0.000 description 1
- 125000006850 spacer group Chemical group 0.000 description 1
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
- B60W40/10—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 vehicle motion
- B60W40/105—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
- 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
- B60W50/0097—Predicting future 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
- B60W2050/0001—Details of the control system
- B60W2050/0019—Control system elements or transfer functions
-
- 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
- B60W2552/05—Type of road, e.g. motorways, local streets, paved or unpaved roads
-
- 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
- B60W2556/00—Input parameters relating to data
- B60W2556/10—Historical data
-
- 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
- B60W2556/00—Input parameters relating to data
- B60W2556/40—High definition maps
-
- 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
- B60W2556/00—Input parameters relating to data
- B60W2556/45—External transmission of data to or from the vehicle
- B60W2556/50—External transmission of data to or from the vehicle of positioning data, e.g. GPS [Global Positioning System] data
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
- Y02T10/00—Road transport of goods or passengers
- Y02T10/10—Internal combustion engine [ICE] based vehicles
- Y02T10/40—Engine management systems
Landscapes
- Engineering & Computer Science (AREA)
- Automation & Control Theory (AREA)
- Transportation (AREA)
- Mechanical Engineering (AREA)
- Physics & Mathematics (AREA)
- Mathematical Physics (AREA)
- Human Computer Interaction (AREA)
- Navigation (AREA)
Abstract
The invention relates to the technical field of vehicle speed prediction, in particular to a vehicle long-term speed prediction method based on individual driving characteristics. The long-term speed prediction method of the vehicle firstly builds a personalized reference speed expression matrix and a personalized reference acceleration expression matrix based on historical driving journey data; then, on-line obtaining future driving journey information, generating a long-term speed prediction reference sequence matrix, predicting speed fluctuation change of a driver, and generating a long-term speed prediction curve of a future driving scene; after the prediction is completed, the effectiveness of the method is evaluated; and finally updating the personalized reference speed expression matrix and the personalized reference acceleration expression matrix on line. The long-term speed prediction method of the vehicle can effectively combine the navigation map information of the vehicle and take the operation characteristics of a driver into consideration, and a long-term speed prediction reference sequence matrix which accords with the individuation of the driver is generated, so that a new information source is provided for energy management of a new energy automobile.
Description
Technical Field
The invention relates to the technical field of vehicle speed prediction, in particular to a vehicle long-term speed prediction method based on individual driving characteristics.
Background
With the increase of the future traffic information sensing modes of the vehicle end, the acquisition of more and more traffic information in future driving scenes becomes possible, and meanwhile, rich traffic information provides a new information source for the development of vehicle functions. Especially for a hybrid electric vehicle, if the speed profile under the future driving journey can be obtained and acted on the long-term energy management of the hybrid electric vehicle, the energy utilization optimization effect can be effectively improved. However, most researches at present use vehicle-end information to conduct short-time speed prediction, and researches on long-time speed prediction are few for the vehicle-end information, and the main reason is that on one hand, acquired future driving scene information is limited, and on the other hand, accurate prediction of future driving scenes and speed performance is difficult.
Compared with the method that a large-range multi-source sensing channel is adopted in the city range to predict the traffic flow rates of different road sections and upload the traffic flow rates to the cloud end, the vehicle end can only acquire the traffic jam degree and the road type of the future driving journey from the vehicle navigation map, and the driving operation characteristics and the speed profile expression of a driver in the future traffic environment are difficult to acquire only by means of the two information types. Further, due to the fact that the styles and the operation characteristics of drivers are different, the speed performances of different drivers in the same driving environment are obviously different, and the long-time speed prediction result performances also have the obvious characteristics of thousands of vehicles and thousands of people. Therefore, the future driving speed profile is difficult to accurately predict by only depending on the information perception of the vehicle end to the future driving scene, and the future driving speed profile is predicted by combining the personalized operation characteristic data of the driver, so that the obtained long-term speed prediction result has more referential property and can be effectively used as a new information source for vehicle function development.
Disclosure of Invention
Aiming at the defects in the prior art, the invention provides a vehicle long-term speed prediction method based on individual driving characteristics, which comprises the steps of firstly constructing an individual reference speed expression matrix and an individual reference acceleration expression matrix based on historical driving travel data; then, on-line obtaining future driving journey information, generating a long-time speed prediction reference sequence matrix, and predicting speed fluctuation change of a driver; after the prediction is completed, the validity of a long-time speed prediction curve of a future driving scene is evaluated; and finally, updating the personalized reference speed expression matrix and the personalized reference acceleration expression matrix on line.
The long-term speed prediction method of the vehicle has obvious individuation, can effectively act on energy management of the new energy automobile, and remarkably improves the energy utilization effect of the new energy automobile by planning the energy utilization track in advance; meanwhile, as the operation data of the driver are accumulated, the accuracy of the prediction result is gradually improved.
The technical scheme of the invention is as follows:
a vehicle long-term speed prediction method based on individual driving characteristics comprises the following steps:
step S1, acquiring historical driving journey data of a driver through a vehicle speed sensor and a vehicle navigation map;
s2, constructing a personalized reference speed expression matrix based on historical driving journey data;
s3, constructing a personalized reference acceleration expression matrix based on historical driving journey data;
s4, acquiring future driving scene information through a vehicle navigation map, and acquiring a long-term speed prediction reference sequence matrix based on a personalized reference speed expression matrix;
s5, predicting speed fluctuation change according to the long-term speed prediction reference sequence matrix and the personalized reference acceleration expression matrix, and finally generating a long-term speed prediction curve for a future driving scene;
step S6, evaluating the validity of a long-term speed prediction curve of a future driving scene, if so, executing step S7, and if not, returning to step S4;
and S7, updating the personalized reference speed expression matrix and the personalized reference acceleration expression matrix on line, and returning to the step S4.
Preferably, the historical driving range data includes speed performance, acceleration performance and driving events under different road types and traffic congestion levels.
Preferably, the road types include urban roads, urban expressways, suburban roads, mountain roads and expressways, the traffic congestion degree is classified into 12 classes, and the driving event is classified into an acceleration event and a deceleration event.
Preferably, the personalized reference speed expression matrix corresponds to speed data of each road type and traffic jam degree, and the speed data in the matrix grid accords with Gaussian distribution.
Preferably, the personalized reference acceleration expression matrix corresponds to the acceleration data of each road type, the traffic jam degree and the driving event, and the speed data distribution in the matrix grid is determined by adopting a non-parameter kernel density estimation method.
Preferably, the step S4 specifically includes:
step S401, starting a car navigation map, setting a future driving route, and dividing the future driving route into a plurality of driving units;
step S402, obtaining the road type and the traffic jam degree of each driving unit;
step S403, sampling by adopting a Monte Carlo random sampling method based on a personalized reference speed representation matrix to obtain speed data corresponding to each driving unit;
step S404, the speed data of each driving unit are connected in series to generate a long-term speed prediction reference sequence matrix.
Preferably, the step S5 specifically includes:
step S501, judging whether each running unit is in an acceleration event or a deceleration event based on the speed data difference value of the adjacent running units in the long-term speed prediction reference sequence matrix;
step S502, sampling by adopting a Monte Carlo random sampling method based on a personalized reference acceleration expression matrix to obtain acceleration data corresponding to each driving unit;
step S503, predicting a speed fluctuation change of each driving unit, and generating a long-term speed prediction curve of a future driving scene.
Preferably, the step S6 specifically includes: and calculating the root mean square error of the predicted speeds of all the running units in the long-term speed prediction curve of the future driving scene, if the root mean square error is larger than the threshold value, the prediction is invalid, and when the predictions of any 5 continuous adjacent running units are invalid, the long-term speed prediction curve of the future driving scene is re-predicted, and returning to the step S4, otherwise, executing the step S7.
Preferably, the step S7 specifically includes: recording actual speed data and acceleration data of the future driving route corresponding to different road types and traffic jam degrees, respectively adding the actual speed data and the acceleration data into a personalized reference speed expression matrix and a personalized reference acceleration expression matrix, and returning to the step S4.
Compared with the prior art, the invention has the beneficial effects that:
(1) According to the long-term speed prediction method for the vehicle based on the individual driving characteristics, long-term speed prediction under future driving journey can be achieved only through the vehicle speed sensor and the vehicle navigation map which are mounted at the vehicle end.
(2) According to the long-term speed prediction method for the vehicle, which is provided by the invention, the operation data of the driver is fully considered, and along with the accumulation of the operation data of the driver, the built personalized reference speed expression matrix and personalized reference acceleration expression matrix tend to be stable, and the predicted long-term speed prediction reference sequence matrix is high in accuracy.
(3) The personalized reference speed expression matrix and the personalized reference acceleration expression matrix designed by the invention occupy small space memory in the controller and have high calculation speed.
(4) The output long-term speed prediction result can be used in the new energy automobile energy management process, and a new information source is provided for the energy optimal utilization of the new energy automobile.
Drawings
So that the manner in which the above recited embodiments of the present invention and the manner in which the same are attained and can be understood in detail, a more particular description of the invention, briefly summarized above, may be had by reference to the embodiments thereof which are illustrated in the appended drawings, which drawings are intended to be illustrative, and which drawings, however, are not to be construed as limiting the invention in any way, and in which other drawings may be obtained by those skilled in the art without the benefit of the appended claims.
Fig. 1 is a flowchart of a proposed method for predicting long-term speed of a vehicle based on personalized driving characteristics.
Detailed Description
In order that the above-recited objects, features and advantages of the present invention will be more clearly understood, a more particular description of the invention will be rendered by reference to the appended drawings and appended detailed description. It should be noted that, without conflict, the embodiments of the present invention and features in the embodiments may be combined with each other.
In the following description, numerous specific details are set forth in order to provide a thorough understanding of the present invention, however, the present invention may be practiced in other ways than those described herein, and therefore the scope of the present invention is not limited to the specific embodiments disclosed below.
The invention provides a long-term speed prediction method of a vehicle based on individual driving characteristics, which can effectively combine navigation map information of a vehicle and simultaneously consider the operation characteristics of a driver to generate a long-term speed prediction reference sequence matrix conforming to the individual characteristics of the driver, thereby providing a new information source for energy management of a new energy automobile. The method specifically comprises the following steps as shown in fig. 1:
step 1: historical driving journey data of a driver are obtained through a vehicle speed sensor and a vehicle navigation map, wherein the historical driving journey data comprise speed performance, acceleration performance and driving events under different road types and traffic jam degrees.
Wherein the road types are divided into urban roads, urban expressways, suburban roads, mountain roads and expressways, corresponding to 1-5 categories, and the traffic congestion degree is determined byIs divided into 1-12 stages as a spacer unit, and the speed corresponding to the 12 th stage is +.>. The driving event is classified into an acceleration event and a deceleration event.
Step 2: a personalized reference speed representation matrix is constructed based on the historical driving range data.
The built personalized reference speed expression matrix is thatIs a two-dimensional matrix of (a) and (b).
The speed of the personalized reference speed representation matrix corresponding to the same matrix grid is represented as discretized distribution data, and the speed data corresponding to each matrix grid is analyzed through statistics so as to accord with Gaussian distribution characteristics. For effectively characterizing the speed data, extracting the mean value and standard deviation of the corresponding speed data under each same matrix grid, wherein the specific characterization is shown in a formula (1).
（1）
Wherein,is->Road class,/-for>Speed data at the level of traffic congestion, +.>In the form of a gaussian distribution,is->Road class,/-for>Speed average under level traffic congestion level, +.>Is->Road class,/-for>Standard deviation of speed at the level of traffic congestion.
Step 3: and constructing a personalized reference acceleration performance matrix based on the historical driving journey data.
Wherein the driving event comprises two types, namely an acceleration event E1 and a deceleration event E2, and the accelerations corresponding to the two types of acceleration events are respectively,/>。
The built personalized reference acceleration expression matrix is thatEach matrix grid corresponds to acceleration data under different road types, traffic congestion degrees and different driving events respectively, and the acceleration data is represented as discretized data. The probability distribution of the acceleration data is determined using a non-parametric kernel density estimation method, and an i Pan Nieqie kov kernel function (Epanechnikov) is selected as the kernel. In order to effectively characterize the acceleration data, the probability distribution bandwidth and the total number of samples of the acceleration data corresponding to each matrix grid are extracted, and the specific characterization is shown in a formula (2).
（2）
Wherein,is->Road class,/-for>Level traffic congestion degree,/-degree>Acceleration data under class driving event, +.>Estimating a distribution for nuclear density->Is->Road class,/-for>Level traffic congestion degree,/-degree>Non-parametric kernel density estimation bandwidth under driving-like event,/->Is->Road class,/-for>Level traffic congestion degree,/-degree>Total number of samples under class driving event.
Step 4: and acquiring future driving scene information through the vehicle navigation map, and acquiring a long-term speed prediction reference sequence matrix based on the personalized basic speed expression matrix.
Guide for starting carThe navigation map sets a future driving route, divides the future driving route into a plurality of driving units, and the length of each driving unit can be set as followsAnd acquiring the road type and the traffic jam degree of each running unit.
Based on the personalized reference speed representation matrix, sampling Gaussian distribution values of speed data corresponding to the road type and the traffic congestion degree of each driving unit by adopting a Monte Carlo random sampling method, wherein the extracted values are used as reference speed values. And serially connecting the reference speed values obtained by sampling each driving unit to generate a long-time speed prediction reference sequence matrix.
Step 5: and predicting speed fluctuation change according to the long-term speed prediction reference sequence matrix and the personalized reference acceleration expression matrix, and generating a long-term speed prediction curve of a future driving scene.
Because the reference speed values sampled by different spatial positions (i.e. different driving units) are different, the corresponding driving event can be determined by connecting two adjacent reference speed values, specifically, the speed data difference value of the adjacent driving units in the long-term speed prediction reference sequence matrix is used for judging whether each driving unit is in an acceleration event or a deceleration event.
Secondly, based on a personalized reference acceleration expression matrix, adopting a Monte Carlo random sampling method to generate random variables which accord with the corresponding kernel density estimation probability distribution characteristics, namely corresponding acceleration data;
finally, predicting the speed fluctuation of each driving unit, taking the reference speed value of the corresponding driving unit as the initial speed, and carrying out speed simulation by combining the random sampling acceleration expression, wherein the number of acceleration samples in each driving unit is required to meet the accumulated driving mileageUp to the length of the driving unit, i.e.)>And should ensure adjacencyThe speeds of the running units can be effectively spliced, namely, the final value speed of the upper running unit and the initial speed of the lower running unit are kept consistent, and the final value speed of the upper running unit is cut off according to the initial speed of the lower running unit serving as a target value, and the final value speed of the upper running unit is specifically shown in formulas (3) - (7). And repeating the steps to finish the speed fluctuation simulation under each driving unit.
（3）
（4）
（5）
（6）
（7）
Wherein,is->Reference speed value for driving unit, +.>，/>，/>Respectively->Corresponding first, second ∈under the driving unit>Person, th->Acceleration values of random samples, +.>In units of sampling periods, usually，/>，/>，/>For randomly sampling the first, the +.>Person, th->Speed value after the individual acceleration values, +.>，For randomly sampling the first, second, first +.>Mileage after each acceleration value.
Step 6: and evaluating the effectiveness of the long-term speed prediction curve of the future driving scene, and rolling and updating the long-term speed prediction curve of the future driving scene.
Because the driving scene has dynamic property and randomness, the car navigation map rolls in real time to send the traffic information of the future driving journey, and the validity of the long-term speed prediction curve of the future driving scene needs to be evaluated.
Calculating root mean square error of predicted speeds of each driving unit in long-term speed prediction curve of future driving scene, wherein the prediction is effective within a set threshold value as shown in formula (8), and the threshold value is generally set asMarking the effective zone bit as 1; continuously counting whether the prediction of each driving unit is a valid zone bit, and updating a long-term speed prediction curve of a future driving scene when 5 continuous adjacent driving units are invalid, namely executing the step 4-5 again; otherwise, continuing to use the long-term speed prediction curve of the latest future driving scene.
（8）
Wherein,is->Root mean square error of the predicted speed of the driving unit, +.>Is->Duration corresponding to the driving unit, < > for>For time (I)>For the actual vehicle speed value>The predicted vehicle speed value is obtained in step 5.
Step 7: and updating the personalized reference speed expression matrix and the personalized reference acceleration expression matrix on line. As driving trip data is accumulated, speed data of a driver under different road types and traffic congestion degrees tend to be stable and show obvious distribution characteristics.
The on-line updating rule of the personalized reference speed expression matrix is that the speed states corresponding to different road types and traffic jam degrees in the running process are recorded, the average value and standard deviation corresponding to different matrix grids are updated in real time by adopting an average value and standard deviation data recursion formula, when the accumulation of the new speed data corresponding to different speed expression matrix grids reaches more than 500 groups, the average value and standard deviation of the speed distribution under the corresponding matrix grids are automatically updated by combining with the sample data of the historical personalized reference speed expression matrix, and the new personalized reference speed expression matrix is started in the next long-time speed prediction.
Similarly, the on-line updating rule of the personalized reference acceleration expression matrix is that the acceleration states corresponding to different road types, traffic jam degrees and driving events in the driving process are recorded, when the acceleration data accumulation under different matrix grids reaches more than 500 groups, the sample data of the historical personalized reference acceleration expression matrix are combined, the bandwidth and the sample number corresponding to the acceleration distribution under the matrix grids are automatically updated, and a new personalized reference acceleration expression matrix is started in the next long-time speed prediction.
In the present invention, unless explicitly specified and limited otherwise, the terms "mounted," "connected," "secured," and the like are to be construed broadly, and may be, for example, fixedly connected, detachably connected, or integrally formed; can be mechanically or electrically connected; can be directly connected or indirectly connected through an intermediate medium, and can be communicated with the inside of two elements or the interaction relationship of the two elements. The specific meaning of the above terms in the present invention can be understood by those of ordinary skill in the art according to the specific circumstances.
In the present invention, unless expressly stated or limited otherwise, a first feature "above" or "below" a second feature may include both the first and second features being in direct contact, as well as the first and second features not being in direct contact but being in contact with each other through additional features therebetween. Moreover, a first feature being "above," "over" and "on" a second feature includes the first feature being directly above and obliquely above the second feature, or simply indicating that the first feature is higher in level than the second feature. The first feature being "under", "below" and "beneath" the second feature includes the first feature being directly under and obliquely below the second feature, or simply means that the first feature is less level than the second feature.
In the present invention, the terms "first," "second," "third," "fourth" are used for descriptive purposes only and are not to be construed as indicating or implying relative importance. The term "plurality" refers to two or more, unless explicitly defined otherwise.
The above description is only of the preferred embodiments of the present invention and is not intended to limit the present invention, but various modifications and variations can be made to the present invention by those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (9)
1. The vehicle long-term speed prediction method based on the individual driving characteristics is characterized by comprising the following steps of:
step S1, acquiring historical driving journey data of a driver through a vehicle speed sensor and a vehicle navigation map;
s2, constructing a personalized reference speed expression matrix based on historical driving journey data;
s3, constructing a personalized reference acceleration expression matrix based on historical driving journey data;
s4, acquiring future driving scene information through a vehicle navigation map, and acquiring a long-term speed prediction reference sequence matrix based on a personalized reference speed expression matrix;
s5, predicting speed fluctuation change according to the long-term speed prediction reference sequence matrix and the personalized reference acceleration expression matrix, and finally generating a long-term speed prediction curve for a future driving scene;
step S6, evaluating the validity of a long-term speed prediction curve of a future driving scene, if so, executing step S7, and if not, returning to step S4;
and S7, updating the personalized reference speed expression matrix and the personalized reference acceleration expression matrix on line, and returning to the step S4.
2. The vehicle long-term speed prediction method according to claim 1, wherein the historical driving course data includes speed performance, acceleration performance, and driving event under different road types and degrees of traffic congestion.
3. The method for predicting long-term speed of a vehicle according to claim 2, wherein the road type includes five types of urban roads, urban express roads, suburban roads, mountain roads and expressways, the degree of traffic congestion is classified into 12 classes, and the driving event is classified into an acceleration event and a deceleration event.
4. The method for predicting long-term speed of a vehicle according to claim 1, wherein the personalized reference speed expression matrix corresponds to speed data under each road type and traffic congestion level, and the speed data in the matrix grid conforms to gaussian distribution.
5. The method for predicting long-term speed of a vehicle according to claim 1, wherein the personalized reference acceleration expression matrix corresponds to acceleration data of each road type, traffic congestion degree and driving event, and speed data distribution in a matrix grid is determined by adopting a non-parametric kernel density estimation method.
6. The method for predicting long-term speed of a vehicle according to claim 1, wherein the step S4 specifically includes:
step S401, starting a car navigation map, setting a future driving route, and dividing the future driving route into a plurality of driving units;
step S402, obtaining the road type and the traffic jam degree of each driving unit;
step S403, sampling by adopting a Monte Carlo random sampling method based on a personalized reference speed representation matrix to obtain speed data corresponding to each driving unit;
step S404, the speed data of each driving unit are connected in series to generate a long-term speed prediction reference sequence matrix.
7. The method for predicting long-term speed of a vehicle according to claim 6, wherein the step S5 specifically includes:
step S501, judging whether each running unit is in an acceleration event or a deceleration event based on the speed data difference value of the adjacent running units in the long-term speed prediction reference sequence matrix;
step S502, sampling by adopting a Monte Carlo random sampling method based on a personalized reference acceleration expression matrix to obtain acceleration data corresponding to each driving unit;
step S503, predicting a speed fluctuation change of each driving unit, and generating a long-term speed prediction curve of a future driving scene.
8. The method for predicting long-term speed of a vehicle according to claim 7, wherein the step S6 specifically includes: and calculating the root mean square error of the predicted speeds of all the running units in the long-term speed prediction curve of the future driving scene, if the root mean square error is larger than the threshold value, the prediction is invalid, and when the predictions of any 5 continuous adjacent running units are invalid, the long-term speed prediction curve of the future driving scene is re-predicted, and returning to the step S4, otherwise, executing the step S7.
9. The method for predicting long-term speed of a vehicle according to claim 8, wherein the step S7 specifically includes: recording actual speed data and acceleration data of the future driving route corresponding to different road types and traffic jam degrees, respectively adding the actual speed data and the acceleration data into a personalized reference speed expression matrix and a personalized reference acceleration expression matrix, and returning to the step S4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311630380.2A CN117325875B (en) | 2023-12-01 | 2023-12-01 | Vehicle long-term speed prediction method based on individual driving characteristics |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311630380.2A CN117325875B (en) | 2023-12-01 | 2023-12-01 | Vehicle long-term speed prediction method based on individual driving characteristics |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117325875A true CN117325875A (en) | 2024-01-02 |
| CN117325875B CN117325875B (en) | 2024-02-02 |
Family
ID=89293886
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311630380.2A Active CN117325875B (en) | 2023-12-01 | 2023-12-01 | Vehicle long-term speed prediction method based on individual driving characteristics |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117325875B (en) |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20150344036A1 (en) * | 2014-05-30 | 2015-12-03 | The Regents Of The University Of Michigan | Vehicle speed profile prediction using neural networks |
| JP5874837B2 (en) * | 2012-09-19 | 2016-03-02 | トヨタ自動車株式会社 | Vehicle driving behavior prediction device |
| CN111080018A (en) * | 2019-12-20 | 2020-04-28 | 南京航空航天大学 | Intelligent internet automobile speed prediction method based on road traffic environment |
| CN111291924A (en) * | 2020-01-17 | 2020-06-16 | 同济大学 | Geometric algebraic deep neural network model method for long-term traffic speed prediction |
| CN113947259A (en) * | 2021-11-09 | 2022-01-18 | 吉林大学 | Method for predicting vehicle speeds of drivers in different styles based on GRU neural network |
| CN116443032A (en) * | 2023-05-22 | 2023-07-18 | 联合汽车电子有限公司 | Method, system, equipment and storage medium for predicting future long-term vehicle speed |
| US20230236088A1 (en) * | 2020-10-02 | 2023-07-27 | Avl List Gmbh | Computer-aided method and device for predicting speeds for vehicles on the basis of probability |
| CN116901981A (en) * | 2023-08-30 | 2023-10-20 | 南京林业大学 | Online self-learning Markov vehicle speed prediction method |
| CN117056765A (en) * | 2023-10-13 | 2023-11-14 | 西北工业大学 | Vehicle speed multi-time scale prediction method, system, equipment, medium and terminal |
| CN117131955A (en) * | 2023-10-27 | 2023-11-28 | 北京航空航天大学 | Short-time vehicle speed prediction method considering multiple constraint conditions |
-
2023
- 2023-12-01 CN CN202311630380.2A patent/CN117325875B/en active Active
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP5874837B2 (en) * | 2012-09-19 | 2016-03-02 | トヨタ自動車株式会社 | Vehicle driving behavior prediction device |
| US20150344036A1 (en) * | 2014-05-30 | 2015-12-03 | The Regents Of The University Of Michigan | Vehicle speed profile prediction using neural networks |
| CN111080018A (en) * | 2019-12-20 | 2020-04-28 | 南京航空航天大学 | Intelligent internet automobile speed prediction method based on road traffic environment |
| CN111291924A (en) * | 2020-01-17 | 2020-06-16 | 同济大学 | Geometric algebraic deep neural network model method for long-term traffic speed prediction |
| US20230236088A1 (en) * | 2020-10-02 | 2023-07-27 | Avl List Gmbh | Computer-aided method and device for predicting speeds for vehicles on the basis of probability |
| CN113947259A (en) * | 2021-11-09 | 2022-01-18 | 吉林大学 | Method for predicting vehicle speeds of drivers in different styles based on GRU neural network |
| CN116443032A (en) * | 2023-05-22 | 2023-07-18 | 联合汽车电子有限公司 | Method, system, equipment and storage medium for predicting future long-term vehicle speed |
| CN116901981A (en) * | 2023-08-30 | 2023-10-20 | 南京林业大学 | Online self-learning Markov vehicle speed prediction method |
| CN117056765A (en) * | 2023-10-13 | 2023-11-14 | 西北工业大学 | Vehicle speed multi-time scale prediction method, system, equipment, medium and terminal |
| CN117131955A (en) * | 2023-10-27 | 2023-11-28 | 北京航空航天大学 | Short-time vehicle speed prediction method considering multiple constraint conditions |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117325875B (en) | 2024-02-02 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111806239B (en) | Electric vehicle endurance mileage measuring method, electronic device, and storage medium | |
| US10408636B2 (en) | Apparatus and method for vehicle economy improvement | |
| CN109558988B (en) | Electric vehicle energy consumption prediction method and system based on big data fusion | |
| CN108198425A (en) | A kind of construction method of Electric Vehicles Driving Cycle | |
| WO2021218313A1 (en) | Method and device for determining remaining mileage of vehicle and vehicle | |
| CN114435138B (en) | Vehicle energy consumption prediction method and device, vehicle and storage medium | |
| CN111688713B (en) | Driving behavior analysis method and device | |
| CN111080018B (en) | Intelligent network-connected automobile speed prediction method based on road traffic environment | |
| CN108335483B (en) | Method and system for inferring traffic jam diffusion path | |
| CN104792543A (en) | Constructing method of road cyclic conditions | |
| US11661067B2 (en) | Method for ascertaining driving profiles | |
| CN110738855A (en) | Road traffic flow condition prediction method for data sparse time periods | |
| Smuts et al. | A critical review of factors influencing the remaining driving range of electric vehicles | |
| CN116572799B (en) | Power battery charge duration prediction method, system and terminal based on deep learning | |
| CN113642768A (en) | Vehicle running energy consumption prediction method based on working condition reconstruction | |
| CN110254435B (en) | Driving style recognition method | |
| CN117325875B (en) | Vehicle long-term speed prediction method based on individual driving characteristics | |
| FR3022206A1 (en) | DRIVING ASSISTANCE METHOD FOR SENSITIZING THE DRIVER OF A VEHICLE FOR FUEL CONSUMPTION AND / OR OTHER CONSUMPTION SOURCE OF THE VEHICLE | |
| CN117128966B (en) | Vehicle charging path planning method and device based on multi-factor coupling | |
| CN115641721B (en) | Multi-source traffic flow index fusion and road condition calculation method based on fusion index | |
| CN108846571A (en) | A kind of net connectionization electric car macroscopic view energy consumption estimation method | |
| Chatterjee et al. | Level of service criteria on Indian multilane highways based on platoon characteristics | |
| JP2006023886A (en) | Traffic information system | |
| CN116580564B (en) | Traffic flow prediction method and device | |
| CN115641712B (en) | Road traffic state estimation method, electronic device, 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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |