CN109767619A - A kind of intelligent network connection pure electric automobile driving cycle prediction technique - Google Patents
A kind of intelligent network connection pure electric automobile driving cycle prediction technique Download PDFInfo
- Publication number
- CN109767619A CN109767619A CN201811635195.1A CN201811635195A CN109767619A CN 109767619 A CN109767619 A CN 109767619A CN 201811635195 A CN201811635195 A CN 201811635195A CN 109767619 A CN109767619 A CN 109767619A
- Authority
- CN
- China
- Prior art keywords
- vehicle
- information
- indicate
- prediction
- acceleration
- 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 24
- 238000005096 rolling process Methods 0.000 claims abstract description 23
- 238000001514 detection method Methods 0.000 claims abstract description 7
- 230000001133 acceleration Effects 0.000 claims description 26
- 238000012937 correction Methods 0.000 claims description 5
- 239000011159 matrix material Substances 0.000 claims description 5
- 241000736199 Paeonia Species 0.000 abstract 2
- 235000006484 Paeonia officinalis Nutrition 0.000 abstract 2
- 238000004891 communication Methods 0.000 description 6
- 238000012545 processing Methods 0.000 description 3
- 238000011161 development Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000005265 energy consumption Methods 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- 238000012546 transfer Methods 0.000 description 2
- 230000005540 biological transmission Effects 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000011217 control strategy Methods 0.000 description 1
- 235000013399 edible fruits Nutrition 0.000 description 1
- 230000005611 electricity Effects 0.000 description 1
- 238000004134 energy conservation Methods 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 238000003912 environmental pollution Methods 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 230000010365 information processing Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000006855 networking Effects 0.000 description 1
- 238000007619 statistical method Methods 0.000 description 1
Landscapes
- Traffic Control Systems (AREA)
Abstract
The invention discloses a kind of intelligent networks to join pure electric automobile driving cycle prediction technique, and video detection system obtains traffic information, onboard sensor obtains vehicle traveling information, GPS satellite positioning system obtains vehicle position information, and passes to cloud server；If road is currently the road conditions that pass unimpeded, the following work information is predicted according to markov rolling forecast method；If congestion road conditions, then predict according to the historical data of this Chinese herbaceous peony rear vehicle；If jogging road conditions, then the prediction of the following work information is carried out according to the historical data of markov rolling forecast method and this Chinese herbaceous peony rear vehicle, prediction result is passed into master controller, acquire feed back input of the error of predicted value and actual value as prediction next time.The present invention uses the method acquiring road condition information in real time of intelligent network connection, improves the accuracy of prediction, guarantees the future travel work information predicted closer to actual condition information.
Description
Technical field
The present invention relates to intelligent networks to join automobile technical field, and in particular to a kind of intelligent network connection pure electric automobile driving cycle
Prediction technique.
Background technique
With being on the rise for environmental pollution and energy crisis, with energy conservation and environmental protection, no pollution, low noise pure electric vehicle vapour
Vehicle becomes one of important development object.However pure electric automobile is single finite energy source, continual mileage is short to be become
The main reason for limiting pure electric automobile development.In different zones, vehicle actual operating mode has very big difference.Vehicle is practical
Driving cycle will have a direct impact on the energy consumption and continual mileage of pure electric automobile, can optimize pure electricity to the prediction of future travel operating condition
The energy management control strategy of electrical automobile further increases the energy consumption and continual mileage performance of pure electric automobile.Currently, pure electric vehicle
Operating condition prediction of the automobile running working condition prediction predominantly based on historical information, by carrying out statistical analysis, benefit to historical data
It is predicted with statistics rule combination intelligent algorithm, however this method can not know current work condition environment, precision of prediction
It is not high；The operating condition prediction that real-time ambient enviroment is combined with historical information is seemed very necessary thus.
Summary of the invention
The purpose of the present invention is to provide a kind of intelligent networks to join pure electric automobile driving cycle prediction technique, it is intended to utilize vehicle
Networked system, it is contemplated that surrounding work condition environment ensure that the future travel work information of prediction closer to the following actual condition
Information realizes that technical scheme is as follows:
A kind of intelligent network connection pure electric automobile driving cycle prediction technique, includes the following steps:
Step 1), video detection system acquisition road information are simultaneously sent to cloud server, and cloud server carries out it
Processing obtains vehicle flowrate, vehicle and vehicle centroid position；
Step 2), car-mounted terminal obtains car speed and acceleration information, GPS satellite positioning system obtain vehicle location letter
Breath, and the information of acquisition is transmitted to cloud server, cloud server stores data, analyzed and is calculated；
Step 3), cloud server according to the speed, acceleration of acquisition, position, vehicle, vehicle flowrate and vehicle centroid away from
Operating condition prediction is carried out from information to calculate；If the road conditions that pass unimpeded, using markov rolling forecast method prediction future travel operating condition letter
Breath；If congestion road conditions, then future travel information is predicted according to the historical information between Che-vehicle；If jogging road conditions,
It then compares, takes and current shape by markov rolling forecast result and by the result that historical information between Che-vehicle is predicted
State phase close values are as prediction result；
Prediction result is transmitted to master controller by step 4), and master controller obtains the mistake between prediction result and actual value
Difference adjusts next prediction result.
Further, the markov rolling forecast method predicts future travel work information, specifically: when taking rolling history
Between historical data in window T, state demarcation is carried out to speed-acceleration, the frequency converted between each state is calculated and constitutes transfer
State matrix takes the product of maximum probability value and current state as predicted value, and according to Current traffic traffic information to prediction
Value is modified:Wherein, vtIndicate present speed, atExpression is worked as
Preacceleration, vt+1Indicate NextState speed, at+1Indicate NextState acceleration, KcIndicate the amendment system passed unimpeded under road conditions
Number, KhIndicate the correction factor under jogging road conditions, maxPijIndicate the maximum probability that NextState is transferred to from state i；Described turn
Shifting state matrix
Further, when the congestion road conditions, cloud server is gone the same way according to this vehicle with the history row of n vehicle after m forward
Data are sailed, are predicted:Wherein μiIndicate fore-aft vehicle
It whether is same type, L with this vehicleiIndicate length of the fore-aft vehicle centroid position apart from this vehicle centroid position, viIndicate fore-aft vehicle
Rolling the average speed in historical time window T, aiIndicate that fore-aft vehicle is rolling the average acceleration in historical time window T；
The μiWhen being 1, fore-aft vehicle and this vehicle are same types of vehicles, the μiWhen being 0, fore-aft vehicle and this vehicle are not same type vehicles
?.
Further, when the jogging road conditions, with current state phase close values according to vt+1=vt±min{|vt+1,c-vt|,|
vt+1,m-vt|}、at+1=at±min{|at+1,c-at|,|at+1,m-at| prediction result is obtained, wherein vt+1,cIt indicates to pass through Che-vehicle
The NextState speed of historical information prediction, vt+1,mIndicate the NextState speed obtained by markov rolling forecast,
at+1,cIt indicates through Che-vehicle historical information prediction NextState acceleration, at+1,mExpression is obtained by markov rolling forecast
The NextState acceleration arrived.
The invention has the benefit that
(1) Markov forecast techniques driving cycle is compared with being suitable for change the little steady operating condition that passes unimpeded, and in vehicle comparatively dense
When, it can mutually be restricted between vehicle and vehicle, Markov forecast techniques driving cycle can generate biggish error.The present invention considers currently
Traffic information, and different prediction modes is chosen according to current traffic information, to effectively improve the accuracy of prediction.
(2) present invention is by speed-acceleration error when the prediction result acquired and actual travel, as predicting next time
Feed back input, to prediction constantly adjusted, to guarantee precision of prediction.
Detailed description of the invention
Fig. 1 is the hardware frame figure of the embodiment of the present invention；
Fig. 2 is the structural schematic diagram of the embodiment of the present invention；
Fig. 3 is the specific flow chart of the embodiment of the present invention.
Specific embodiment
Invention is further described in detail with reference to the accompanying drawings and detailed description.
As shown in Figure 1 be the hardware frame figure of the embodiment of the present invention: video detection system acquires road information and passes through nothing
Line communication network passes to cloud server, obtains vehicle, vehicle flowrate and vehicle centroid position after cloud server processing,
The vehicle position information that the vehicle traveling information and GPS satellite positioning system that onboard sensor obtains obtain passes to car-mounted terminal
And master controller, network passes to cloud server to car-mounted terminal by wireless communication, cloud server handles data,
Prediction result is back to master controller and compared with actual value by analysis and calculating.
Be illustrated in figure 2 the structural schematic diagram of the embodiment of the present invention: video detection system includes switching regulator sensor, data
Acquisition Instrument and video camera；Camera arrangements carry out continuously recording at crossing, to traffic conditions, and switching regulator sensor is equally arranged in
Crossing, the length is the overall width in lane, width is about the 70% of ordinary vehicle type vehicle commander；Video camera and sensor are collected
Information send and be stored in data collecting instrument, network passes data to cloud service to data collecting instrument by wireless communication
Device carries out information processing.The external minimum rectangle area of vehicle's contour is extracted in video camera acquired image data with preliminary
It identifies vehicle, the centroid position of each vehicle is obtained by the detection zone of analysis switching regulator sensor composition, introduces and expands
The trace model of kalman filtering, the frame number in region accurately differentiates type of vehicle to calculating vehicle profile target after testing, has
Body is divided into carriage type, middle vehicle and large-scale vechicle, in addition, region vehicle after testing in the switching regulator sensor statistical unit period
Number obtains vehicle flowrate data.Vehicle position information is obtained by GPS satellite positioning system, is handled first vehicle position data,
The speed of service of different function grade road is obtained, then the road is calculated according to function path difference and vehicle flowrate data and exists
Shared weight in the whole network provides the index index value for being converted to 0-10, index range is denoted as the road conditions that pass unimpeded for 0-2, by 2-6
Jogging road conditions are denoted as, 6-10 is denoted as congestion road conditions；L mass center length between vehicle in figure.
It is illustrated in figure 3 the specific flow chart of the embodiment of the present invention:
Step 1), video detection system acquires road information and network transfers information to cloud service by wireless communication
Device, cloud server carry out digitized processing to information, obtain vehicle flowrate, vehicle and vehicle centroid position；
Step 2), car-mounted terminal obtain car speed, acceleration information and GPS satellite positioning system by onboard sensor
System obtains vehicle position information, and the speed, acceleration of acquisition and location information are transmitted to cloud by network by wireless communication
Server is held, cloud server stores data, analyzed and calculated；
Step 3), cloud server according to the speed, acceleration of acquisition, position, vehicle, vehicle flowrate and vehicle centroid away from
Operating condition prediction is carried out from information to calculate；
If the road conditions that pass unimpeded, then future travel work information is predicted using markov rolling forecast method: taking rolling
Historical data in historical time window T carries out state demarcation to speed-acceleration, calculates the frequency structure converted between each state
At transfering state matrixTake the product of maximum probability value and current state as predicted value, and root
Predicted value is modified according to Current traffic traffic information:
Wherein, vtIndicate present speed, atIndicate current acceleration, vt+1Indicate NextState speed, at+1Indicate next shape
State
Acceleration, KcIndicate the correction factor to pass unimpeded under road conditions, KhIndicate the correction factor under jogging road conditions, maxPijTable
Show the maximum probability that NextState is transferred to from state i.
If congestion road conditions, due to mutually restricting between vehicle, driving cycle is roughly the same, then according between Che-vehicle
Historical information (being stored in car networking) predicts that future travel information, cloud server is according to vehicle location, vehicle, vehicle
Away from, speed and acceleration information, obtains and predicted with this vehicle history running data of n vehicle after m forward of going the same way together.It is gathering around
Under stifled road conditions, speed variation is smaller, and vehicle operation data is influenced and more close then to the shadow of this vehicle apart from this vehicle by surrounding vehicles
Sound is bigger, therefore when predicting NextState velocity and acceleration, the error of current state velocity and acceleration is adjusted:
Wherein, μiIt indicates that when fore-aft vehicle and this vehicle are same types be 1, is otherwise 0, LiIndicate fore-aft vehicle centroid position
Length apart from this vehicle centroid position, viIndicate that fore-aft vehicle is rolling the average speed in historical time window T, aiIndicate front and back
Average acceleration of the vehicle in receding horizon T.
If jogging road conditions, then by markov rolling forecast result and the knot predicted by historical information between Che-vehicle
Fruit compares, and asks two kinds of results of prediction and calculation with current state phase close values as prediction result, it may be assumed that
vt+1=vt±min{|vt+1,c-vt|,|vt+1,m-vt|} (5)
at+1=at±min{|at+1,c-at|,|at+1,m-at|} (6)
Wherein, vt+1,cIt indicates through Che-vehicle historical information prediction NextState speed, vt+1,mIndicating can by Ma Er
The NextState speed that husband's rolling forecast obtains, at+1,cIt indicates through Che-vehicle historical information prediction NextState acceleration,
at+1,mIndicate the NextState acceleration obtained by markov rolling forecast.
Step 4), by prediction result, network transmission to master controller, master controller obtains the speed of prediction by wireless communication
Error between degree, acceleration and actual speed, acceleration, and using the error as the feed back input predicted next time, it is right
Prediction result is constantly adjusted.
Above-mentioned, although the foregoing specific embodiments of the present invention is described with reference to the accompanying drawings, not protects model to the present invention
The limitation enclosed, those skilled in the art should understand that, based on the technical solutions of the present invention, those skilled in the art are not
Need to make the creative labor the various modifications or changes that can be made still within protection scope of the present invention.
Claims (6)
1. a kind of intelligent network joins pure electric automobile driving cycle prediction technique, which comprises the steps of:
Step 1), video detection system acquisition road information are simultaneously sent to cloud server, and cloud server handles it
Obtain vehicle flowrate, vehicle and vehicle centroid position；
Step 2), car-mounted terminal obtains car speed and acceleration information, GPS satellite positioning system obtain vehicle position information,
And the information of acquisition is transmitted to cloud server, cloud server stores data, analyzed and is calculated；
Step 3), cloud server is according to the speed, acceleration of acquisition, position, vehicle, vehicle flowrate and vehicle centroid distance letter
Breath carries out operating condition prediction and calculates；If the road conditions that pass unimpeded, future travel work information is predicted using markov rolling forecast method；If
For congestion road conditions, then future travel information is predicted according to the historical information between Che-vehicle；If jogging road conditions, then will
Markov rolling forecast result and by between Che-vehicle historical information predict result compare, take and current state phase
Close values are as prediction result；
Prediction result is transmitted to master controller by step 4), and master controller obtains the error between prediction result and actual value, adjusts
Whole prediction result next time.
2. intelligent network according to claim 1 joins pure electric automobile driving cycle prediction technique, which is characterized in that the horse
Er Kefu rolling forecast method predicts future travel work information, specifically: the historical data rolled in historical time window T is taken, it is right
Speed-acceleration carries out state demarcation, calculates the frequency converted between each state and constitutes transfering state matrix, takes maximum probability value
Product with current state is modified predicted value as predicted value, and according to Current traffic traffic information:Wherein, vtIndicate present speed, atIndicate current acceleration, vt+1
Indicate NextState speed, at+1Indicate NextState acceleration, KcIndicate the correction factor to pass unimpeded under road conditions, KhIndicate jogging road
Correction factor under condition, maxPijIndicate the maximum probability that NextState is transferred to from state i.
3. intelligent network according to claim 2 joins pure electric automobile driving cycle prediction technique, which is characterized in that described turn
Shifting state matrix
4. intelligent network according to claim 1 or 2 joins pure electric automobile driving cycle prediction technique, which is characterized in that institute
When stating congestion road conditions, cloud server is gone the same way according to this vehicle with the history running data of n vehicle after m forward, is predicted:Wherein μiIt indicates fore-aft vehicle and whether this vehicle is similar
Type, LiIndicate length of the fore-aft vehicle centroid position apart from this vehicle centroid position, viIndicate that fore-aft vehicle is rolling historical time window
Average speed in T, aiIndicate that fore-aft vehicle is rolling the average acceleration in historical time window T.
5. intelligent network according to claim 4 joins pure electric automobile driving cycle prediction technique, which is characterized in that the μi
When being 1, fore-aft vehicle and this vehicle are same types of vehicles, the μiWhen being 0, fore-aft vehicle and this vehicle are not same types of vehicles.
6. intelligent network according to claim 4 joins pure electric automobile driving cycle prediction technique, which is characterized in that described slow
When walking along the street condition, with current state phase close values according to vt+1=vt±min{|vt+1,c-vt|,|vt+1,m-vt|}、at+1=at±min{|
at+1,c-at|,|at+1,m-at| prediction result is obtained, wherein vt+1,cIt indicates through Che-vehicle historical information prediction NextState vehicle
Speed, vt+1,mIndicate the NextState speed obtained by markov rolling forecast, at+1,cIt indicates to pass through Che-vehicle historical information
The NextState acceleration of prediction, at+1,mIndicate the NextState acceleration obtained by markov rolling forecast.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811635195.1A CN109767619B (en) | 2018-12-29 | 2018-12-29 | Intelligent networking pure electric vehicle running condition prediction method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811635195.1A CN109767619B (en) | 2018-12-29 | 2018-12-29 | Intelligent networking pure electric vehicle running condition prediction method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109767619A true CN109767619A (en) | 2019-05-17 |
| CN109767619B CN109767619B (en) | 2021-05-25 |
Family
ID=66453011
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811635195.1A Active CN109767619B (en) | 2018-12-29 | 2018-12-29 | Intelligent networking pure electric vehicle running condition prediction method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109767619B (en) |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110610611A (en) * | 2019-09-26 | 2019-12-24 | 江苏大学 | Driving safety evaluation method for intelligent network-connected vehicle in mixed-driving traffic flow |
| CN111402582A (en) * | 2020-03-12 | 2020-07-10 | 东南大学 | Control method for electric automobile to borrow lane special for automatic driving in intelligent network connection environment |
| CN111693060A (en) * | 2020-06-08 | 2020-09-22 | 西安电子科技大学 | Path planning method based on congestion level prediction analysis |
| CN111831972A (en) * | 2020-07-16 | 2020-10-27 | 宁波工程学院 | Hybrid vehicle working condition prediction method and system based on road condition change |
| CN111831853A (en) * | 2020-07-16 | 2020-10-27 | 深圳市商汤科技有限公司 | Information processing method, device, equipment and system |
| CN113094967A (en) * | 2021-03-31 | 2021-07-09 | 北京理工大学 | Unmanned vehicle position prediction method and device |
| CN113267345A (en) * | 2021-04-23 | 2021-08-17 | 联合汽车电子有限公司 | Method for predicting resistance of unknown road section in front of vehicle, storage medium, controller and system |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105416077A (en) * | 2015-12-01 | 2016-03-23 | 北京理工大学 | Energy management system and method for electric automobile |
| CN108128309A (en) * | 2017-09-01 | 2018-06-08 | 特百佳动力科技有限公司 | A kind of method that vehicle working condition is predicted in real time |
| CN108198425A (en) * | 2018-02-10 | 2018-06-22 | 长安大学 | A kind of construction method of Electric Vehicles Driving Cycle |
| CN108734810A (en) * | 2018-04-17 | 2018-11-02 | 江苏大学 | A kind of pure electric automobile driving cycle prediction technique based on car networking |
-
2018
- 2018-12-29 CN CN201811635195.1A patent/CN109767619B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105416077A (en) * | 2015-12-01 | 2016-03-23 | 北京理工大学 | Energy management system and method for electric automobile |
| CN108128309A (en) * | 2017-09-01 | 2018-06-08 | 特百佳动力科技有限公司 | A kind of method that vehicle working condition is predicted in real time |
| CN108198425A (en) * | 2018-02-10 | 2018-06-22 | 长安大学 | A kind of construction method of Electric Vehicles Driving Cycle |
| CN108734810A (en) * | 2018-04-17 | 2018-11-02 | 江苏大学 | A kind of pure electric automobile driving cycle prediction technique based on car networking |
Non-Patent Citations (7)
| Title |
|---|
| CHAO SUN等: "Velocity Predictors for Predictive Energy Management in Hybrid Electric Vehicles", 《 IEEE TRANSACTIONS ON CONTROL SYSTEMS TECHNOLOGY》 * |
| HUI LIU等: "Markov velocity predictor and radial basis function neural network-based real-time energy management strategy for plug-in hybrid electric vehicles", 《ENERGY》 * |
| 丁峰等: "基于行驶工况分类的混合动力车辆速度预测方法与能量管理策略", 《汽车工程》 * |
| 张昕等: "基于马尔可夫链的混合动力汽车行驶工况预测研究", 《汽车工程》 * |
| 张锐: "城市道路汽车行驶工况的构建与研究", 《中国优秀硕士学位论文全文数据库 工程科技Ⅱ辑》 * |
| 徐小俊等: "电动汽车城市行驶工况构建", 《科学技术与工程》 * |
| 曹磊等: "基于马尔可夫链的汽车行驶工况预测", 《内燃机与动力装置》 * |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110610611A (en) * | 2019-09-26 | 2019-12-24 | 江苏大学 | Driving safety evaluation method for intelligent network-connected vehicle in mixed-driving traffic flow |
| CN111402582A (en) * | 2020-03-12 | 2020-07-10 | 东南大学 | Control method for electric automobile to borrow lane special for automatic driving in intelligent network connection environment |
| CN111402582B (en) * | 2020-03-12 | 2021-05-25 | 东南大学 | Control method for electric automobile to borrow lane special for automatic driving in intelligent network connection environment |
| CN111693060A (en) * | 2020-06-08 | 2020-09-22 | 西安电子科技大学 | Path planning method based on congestion level prediction analysis |
| CN111693060B (en) * | 2020-06-08 | 2022-03-04 | 西安电子科技大学 | Path planning method based on congestion level prediction analysis |
| CN111831972A (en) * | 2020-07-16 | 2020-10-27 | 宁波工程学院 | Hybrid vehicle working condition prediction method and system based on road condition change |
| CN111831853A (en) * | 2020-07-16 | 2020-10-27 | 深圳市商汤科技有限公司 | Information processing method, device, equipment and system |
| CN113094967A (en) * | 2021-03-31 | 2021-07-09 | 北京理工大学 | Unmanned vehicle position prediction method and device |
| CN113267345A (en) * | 2021-04-23 | 2021-08-17 | 联合汽车电子有限公司 | Method for predicting resistance of unknown road section in front of vehicle, storage medium, controller and system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109767619B (en) | 2021-05-25 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109767619A (en) | A kind of intelligent network connection pure electric automobile driving cycle prediction technique | |
| CN110249609B (en) | Bandwidth constrained image processing for autonomous vehicles | |
| EP3647735A1 (en) | Adjusting lateral clearance for a vehicle using a multi-dimensional envelope | |
| KR20230074694A (en) | Extended object tracking using radar | |
| US10120381B2 (en) | Identifying significant locations based on vehicle probe data | |
| WO2021218313A1 (en) | Method and device for determining remaining mileage of vehicle and vehicle | |
| WO2020146447A1 (en) | Field theory based perception for autonomous vehicles | |
| CN110610512B (en) | Unmanned aerial vehicle target tracking method based on BP neural network fusion Kalman filtering algorithm | |
| KR102543567B1 (en) | Object tracking supporting autonomous vehicle navigation | |
| CN103903468A (en) | Time early-warning method for traffic jam and device thereof | |
| KR102549266B1 (en) | Long-term object tracking supporting autonomous vehicle navigation | |
| CN108320508A (en) | One kind is based on plan of travel prediction future traffic congestion situation method and its system | |
| CN109067857A (en) | A kind of car networking big data analysis intelligent optimization algorithm | |
| CN111703418A (en) | Multi-vehicle distributed cooperative collision avoidance method and device based on vehicle-vehicle communication | |
| JP2018085113A (en) | Vehicle control apparatus and method of operating the same | |
| CN110825112B (en) | Oil field dynamic invasion target tracking system and method based on multiple unmanned aerial vehicles | |
| US20230333237A1 (en) | Merge-split techniques for sensor data filtering | |
| Qian et al. | Vehicular networking-enabled vehicle state prediction via two-level quantized adaptive Kalman filtering | |
| CN115358412A (en) | Asynchronous federal optimization method based on edge auxiliary vehicle network | |
| AU2020104213A4 (en) | Blockchain for 5g-enabled iot for industrial automation | |
| Gao et al. | Longitudinal control for mengshi autonomous vehicle via cloud model | |
| CN108241866A (en) | A kind of method, apparatus guided to driving behavior and vehicle | |
| CN115892038A (en) | Operation method of intelligent vehicle running control system | |
| KR102419526B1 (en) | Field theory-based perception of autonomous vehicles | |
| Ren et al. | Intelligent path planning and obstacle avoidance algorithms for autonomous vehicles based on enhanced rrt algorithm |
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 | ||
| TR01 | Transfer of patent right | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20240308 Address after: 401329 No. 99, Xinfeng Avenue, Jinfeng Town, Gaoxin District, Jiulongpo District, Chongqing Patentee after: Chongqing Science City Intellectual Property Operation Center Co.,Ltd. Country or region after: China Address before: Zhenjiang City, Jiangsu Province, 212013 Jingkou District Road No. 301 Patentee before: JIANGSU University Country or region before: China |