CN108216234A - A kind of electric vehicle self-adapting cruise control system and its control method - Google Patents
A kind of electric vehicle self-adapting cruise control system and its control method Download PDFInfo
- Publication number
- CN108216234A CN108216234A CN201810035225.9A CN201810035225A CN108216234A CN 108216234 A CN108216234 A CN 108216234A CN 201810035225 A CN201810035225 A CN 201810035225A CN 108216234 A CN108216234 A CN 108216234A
- Authority
- CN
- China
- Prior art keywords
- vehicle
- trailer
- mounted radar
- real
- processor
- 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.)
- Pending
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
- B60W30/00—Purposes of road vehicle drive control systems not related to the control of a particular sub-unit, e.g. of systems using conjoint control of vehicle sub-units, or advanced driver assistance systems for ensuring comfort, stability and safety or drive control systems for propelling or retarding the vehicle
- B60W30/14—Adaptive cruise control
-
- 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
Abstract
The invention discloses a kind of electric vehicle self-adapting cruise control system, including preposition vehicle-mounted thunder, for detecting the object of vehicle front；Postposition trailer-mounted radar, for detecting the object of rear view of vehicle；Side trailer-mounted radar, for detecting the object of vehicle side；Preposition imaging sensor, for obtaining the realtime graphic of vehicle front；Advance signal processor, for identifying the real-time road of vehicle front；Postsignal processor, for identifying the real-time road of rear view of vehicle；Side signal processor, for identifying the real-time road of vehicle side；Cruise control processor communicates with advance signal processor, postsignal processor and side signal processor connect respectively, and transport condition used for vehicles is controlled.The present invention can improve the deficiencies in the prior art, improve the utilization rate under the premise of processor operand is not improved, improved for running data, so as to improve the accuracy of cruise control.
Description
Technical field
The present invention relates to field of artificial intelligence, especially a kind of electric vehicle self-adapting cruise control system and its control
Method.
Background technology
With the development of artificial intelligence technology, unmanned recent years rapid development.Wherein, adaptive cruise is nothing
A basic technology in people's driving technology.Existing adaptive cruise technology, is by vehicle running state and periphery
The acquisition of environment and comprehensive descision obtain cruise control strategy.Although this mode can be realized with high accuracy in theory
Cruise control, but since vehicle itself under virtual condition and its external status data are very huge, and in real-time update
State, so this just proposes the processing capacity of processor very high requirement.The processing speed of existing portable processor
Degree is not universal high, this results in practical cruise control system that must give up a part of data, to ensure cruise control instruction
It sends out in real time.
Invention content
The technical problem to be solved in the present invention is to provide a kind of electric vehicle self-adapting cruise control system and its control method,
The deficiencies in the prior art can be solved, under the premise of processor operand is not improved, improve the utilization for running data
Rate, so as to improve the accuracy of cruise control.
In order to solve the above technical problems, the technical solution used in the present invention is as follows.
A kind of electric vehicle self-adapting cruise control system, including,
Preposition trailer-mounted radar, for detecting the object of vehicle front；
Postposition trailer-mounted radar, for detecting the object of rear view of vehicle；
Side trailer-mounted radar, for detecting the object of vehicle side；
Preposition imaging sensor, for obtaining the realtime graphic of vehicle front；
Advance signal processor is connected with preposition trailer-mounted radar and the communication of preposition imaging sensor, before identifying vehicle
The real-time road of side；
Postsignal processor is communicated with postposition trailer-mounted radar and is connected, for identifying the real-time road of rear view of vehicle；
Side signal processor is communicated with side trailer-mounted radar and is connected, for identifying the real-time road of vehicle side；
Cruise control processor leads to respectively with advance signal processor, postsignal processor and side signal processor
News connection, transport condition used for vehicles are controlled.
A kind of control method of above-mentioned electric vehicle self-adapting cruise control system, includes the following steps：
A, preposition trailer-mounted radar, postposition trailer-mounted radar and side trailer-mounted radar respectively visit the object of vehicle-surroundings
It surveys, preposition imaging sensor is acquired the image of vehicle front；
B, advance signal processor is identified the object of vehicle front according to preposition trailer-mounted radar, then will identify that
The object that obtains in image of object and preposition imaging sensor matched, by stationary object, mobile object and road markings
Carry out classification storage；
C, postsignal processor is identified the object of rear view of vehicle according to postposition trailer-mounted radar, by stationary object and
Mobile object carries out classification storage；
D, side signal processor is identified the object of vehicle side according to side trailer-mounted radar, by stationary object and
Mobile object carries out classification storage；
E, cruise control processor carries out cruise route planning according to the real-time status and road markings of vehicle's surroundings, and
Classified according to the variation tendency of vehicle running state to the real-time status of vehicle's surroundings, every a kind of real-time status is then obtained
In intersection of each state to the limitations set of vehicle running state, as every a kind of real-time status for the limit of vehicle running state
Set of circumstances processed asks its intersection after each restrictive condition set is weighted, obtains final vehicle running state again.
Preferably, in step B, the movement locus of mobile object is recorded, according to the road markings of acquisition to note
The movement locus of record is screened, and the movement locus that the movement locus section accounting for meeting road markings is more than to threshold value is protected
It stays, it is same by what is supplemented out then according to the movement locus of reservation to can not be supplemented by the road markings section of image acquisition
The different virtual roads mark of one position merges, and then merges and connect with the road markings section identified in image,
Linear fit is carried out to virtual road identification section according to the endpoint of road markings section identified in image.
Preferably, in the step E, the transport condition of vehicle reality is belonged into nerve network system and carries out feedback
Practise, vehicle travel risk rate solved according to the real-time status on vehicle actual travel state and its periphery, vehicle travel risk rate with
The learning rate of neural network is inversely proportional, and the weighting rate of each restrictive condition set is modified according to learning outcome.
Preferably, the learning objective function of neural network is,
Wherein, I is the eigenmatrix of each restrictive condition set, and k is the weighting rate of each restrictive condition set.
It is using advantageous effect caused by above-mentioned technical proposal：The present invention passes through adopting comprehensively to vehicle operation data
Collection, then classifies to Various types of data, homogeneous data is uniformly processed, then provide cruise control according to handling result
Instruction, so as to simplify processing procedure, realizes comprehensive covering of data.The present invention is using nerual network technique to cruise control
The decision logic of processor carries out adaptive learning, by rationally designing learning rate and learning objective function, can simplify study
Process reduces the operation pressure of cruise control processor.
Description of the drawings
Fig. 1 is the structure chart of a specific embodiment of the invention.
In figure：1st, preposition trailer-mounted radar；2nd, postposition trailer-mounted radar；3rd, side trailer-mounted radar；4th, preposition imaging sensor；5、
Advance signal processor；6th, advance signal processor；7th, side signal processor；8th, cruise control processor.
Specific embodiment
The standardized element used in the present invention can commercially, and shaped piece is according to specification and attached drawing
Record can carry out customized, and the specific connection mode of each part is using bolt ripe in the prior art, rivet, weldering
The conventional means such as connect, paste, this will not be detailed here.
With reference to Fig. 1, one specific embodiment of the present invention includes preposition trailer-mounted radar 1, for detecting
The object of vehicle front；
Postposition trailer-mounted radar 2, for detecting the object of rear view of vehicle；
Side trailer-mounted radar 3, for detecting the object of vehicle side；
Preposition imaging sensor 4, for obtaining the realtime graphic of vehicle front；
Advance signal processor 5 is connected with preposition trailer-mounted radar 1 and the communication of preposition imaging sensor 4, for identifying vehicle
The real-time road in front；
Postsignal processor 6 is communicated with postposition trailer-mounted radar 2 and is connected, for identifying the real-time road of rear view of vehicle；
Side signal processor 7 is communicated with side trailer-mounted radar 3 and is connected, for identifying the real-time road of vehicle side；
Cruise control processor 8, respectively with advance signal processor 5, postsignal processor 6 and side signal processor
7 communication connections, transport condition used for vehicles are controlled.
A kind of control method of above-mentioned electric vehicle self-adapting cruise control system, includes the following steps：
A, preposition trailer-mounted radar 1, postposition trailer-mounted radar 2 and side trailer-mounted radar 3 respectively carry out the object of vehicle-surroundings
Detection, preposition imaging sensor (4) are acquired the image of vehicle front；
B, advance signal processor 5 is identified the object of vehicle front according to preposition trailer-mounted radar 1, then will identification
The object gone out obtains the object in image with preposition imaging sensor 4 and is matched, by stationary object, mobile object and road road sign
Know and carry out classification storage；
C, postsignal processor 6 is identified the object of rear view of vehicle according to postposition trailer-mounted radar 2, by stationary object
Classification storage is carried out with mobile object；
D, side signal processor 7 is identified the object of vehicle side according to side trailer-mounted radar 3, by stationary object
Classification storage is carried out with mobile object；
E, cruise control processor 8 carries out cruise route planning according to the real-time status and road markings of vehicle's surroundings,
And classified according to the variation tendency of vehicle running state to the real-time status of vehicle's surroundings, every real-time shape of one kind is then obtained
Intersection of each state to the limitations set of vehicle running state in state, as every a kind of real-time status for vehicle running state
Restrictive condition set asks its intersection after each restrictive condition set is weighted, obtains final vehicle running state again.
In step B, the movement locus of mobile object is recorded, according to the road markings of acquisition to the movement rail of record
Mark is screened, and the movement locus that the movement locus section accounting for meeting road markings is more than to threshold value retains, then basis
The movement locus of reservation by the road markings section of image acquisition to can not be supplemented, by the difference of the same position supplemented out
Virtual road mark merges, and then merges and connect with the road markings section identified in image, knows according in image
The endpoint of road markings section not gone out carries out linear fit to virtual road identification section.
In step E, the transport condition of vehicle reality is belonged into nerve network system and carries out feedback learning, according to vehicle reality
The real-time status on transport condition and its periphery solves the learning rate of vehicle travel risk rate, vehicle travel risk rate and neural network
It is inversely proportional, the weighting rate of each restrictive condition set is modified according to learning outcome.
The learning objective function of neural network is,
Wherein, I is the eigenmatrix of each restrictive condition set, and k is the weighting rate of each restrictive condition set.
After the completion of each feedback learning, the eigenmatrix of restrictive condition set that weighting rate is lower is modified, is carried
Its high compactness with actual travel state.
In the description of the present invention, it is to be understood that term " longitudinal direction ", " transverse direction ", " on ", " under ", "front", "rear",
The orientation or position relationship of the instructions such as "left", "right", " vertical ", " level ", " top ", " bottom ", " interior ", " outer " is based on attached drawing institutes
The orientation or position relationship shown is for only for ease of the description present invention rather than instruction or implies that signified device or element must
There must be specific orientation, with specific azimuth configuration and operation, therefore be not considered as limiting the invention.
The basic principles, main features and the advantages of the invention have been shown and described above.The technology of the industry
Personnel are it should be appreciated that the present invention is not limited to the above embodiments, and the above embodiments and description only describe this
The principle of invention, without departing from the spirit and scope of the present invention, various changes and improvements may be made to the invention, these changes
Change and improvement all fall within the protetion scope of the claimed invention.The claimed scope of the invention by appended claims and its
Equivalent thereof.
Claims (5)
1. a kind of electric vehicle self-adapting cruise control system, it is characterised in that：Including,
Preposition trailer-mounted radar (1), for detecting the object of vehicle front；
Postposition trailer-mounted radar (2), for detecting the object of rear view of vehicle；
Side trailer-mounted radar (3), for detecting the object of vehicle side；
Preposition imaging sensor (4), for obtaining the realtime graphic of vehicle front；
Advance signal processor (5) is connected with preposition trailer-mounted radar (1) and preposition imaging sensor (4) communication, for identifying vehicle
Real-time road in front of；
Postsignal processor (6) is communicated with postposition trailer-mounted radar (2) and is connected, for identifying the real-time road of rear view of vehicle；
Side signal processor (7) is communicated with side trailer-mounted radar (3) and is connected, for identifying the real-time road of vehicle side；
Cruise control processor (8), respectively with advance signal processor (5), postsignal processor (6) and side signal processing
Device (7) communication connection, transport condition used for vehicles are controlled.
2. a kind of control method of electric vehicle self-adapting cruise control system described in claim 1, it is characterised in that including with
Lower step：
A, preposition trailer-mounted radar (1), postposition trailer-mounted radar (2) and side trailer-mounted radar (3) respectively to the object of vehicle-surroundings into
Row detection, preposition imaging sensor (4) are acquired the image of vehicle front；
B, advance signal processor (5) is identified the object of vehicle front according to preposition trailer-mounted radar (1), then will identification
The object gone out obtains the object in image with preposition imaging sensor (4) and is matched, by stationary object, mobile object and road
Mark carries out classification storage；
C, postsignal processor (6) is identified the object of rear view of vehicle according to postposition trailer-mounted radar (2), by stationary object
Classification storage is carried out with mobile object；
D, side signal processor (7) is identified the object of vehicle side according to side trailer-mounted radar (3), by stationary object
Classification storage is carried out with mobile object；
E, cruise control processor (8) carries out cruise route planning according to the real-time status and road markings of vehicle's surroundings, and
Classified according to the variation tendency of vehicle running state to the real-time status of vehicle's surroundings, every a kind of real-time status is then obtained
In intersection of each state to the limitations set of vehicle running state, as every a kind of real-time status for the limit of vehicle running state
Set of circumstances processed asks its intersection after each restrictive condition set is weighted, obtains final vehicle running state again.
3. the control method of electric vehicle self-adapting cruise control system according to claim 2, it is characterised in that：Step B
In, the movement locus of mobile object is recorded, the movement locus of record is screened according to the road markings of acquisition, it will
The movement locus section accounting for meeting road markings is retained more than the movement locus of threshold value, then according to the movement locus of reservation
To can not be supplemented by the road markings section of image acquisition, by the different virtual roads of the same position supplemented out identify into
Row merges, and then merges and connect with the road markings section identified in image, according to the road markings identified in image
The endpoint of section carries out linear fit to virtual road identification section.
4. the control method of electric vehicle self-adapting cruise control system according to claim 2, it is characterised in that：Step E
In, the transport condition of vehicle reality is belonged into nerve network system and carries out feedback learning, according to vehicle actual travel state and its
The learning rate of the real-time status solution vehicle travel risk rate on periphery, vehicle travel risk rate and neural network is inversely proportional, according to
Learning outcome is modified the weighting rate of each restrictive condition set.
5. the control method of electric vehicle self-adapting cruise control system according to claim 4, it is characterised in that：Nerve net
The learning objective function of network is,
Wherein, I is the eigenmatrix of each restrictive condition set, and k is the weighting rate of each restrictive condition set.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810035225.9A CN108216234A (en) | 2018-01-15 | 2018-01-15 | A kind of electric vehicle self-adapting cruise control system and its control method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810035225.9A CN108216234A (en) | 2018-01-15 | 2018-01-15 | A kind of electric vehicle self-adapting cruise control system and its control method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN108216234A true CN108216234A (en) | 2018-06-29 |
Family
ID=62641115
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810035225.9A Pending CN108216234A (en) | 2018-01-15 | 2018-01-15 | A kind of electric vehicle self-adapting cruise control system and its control method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108216234A (en) |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104417562A (en) * | 2013-08-29 | 2015-03-18 | 株式会社电装 | Method and apparatus for recognizing road shape, program, and recording medium |
| DE202014006922U1 (en) * | 2014-08-27 | 2015-11-30 | GM Global Technology Operations LLC (n. d. Ges. d. Staates Delaware) | Device for controlling a motor vehicle, motor vehicle |
| CN105197012A (en) * | 2015-10-10 | 2015-12-30 | 广东轻工职业技术学院 | Automatic vehicle control method |
| CN105487070A (en) * | 2014-10-06 | 2016-04-13 | 日本电产艾莱希斯株式会社 | Radar system, radar signal processing device, vehicle driving control device and method and computer program |
| CN105667518A (en) * | 2016-02-25 | 2016-06-15 | 福州华鹰重工机械有限公司 | Lane detection method and device |
| JP2016215769A (en) * | 2015-05-19 | 2016-12-22 | 株式会社デンソー | Vehicle control device |
| CN107161146A (en) * | 2017-04-05 | 2017-09-15 | 吉利汽车研究院（宁波）有限公司 | A kind of highway accessory system |
| JP2017198633A (en) * | 2016-04-28 | 2017-11-02 | 本田技研工業株式会社 | Vehicle control system, vehicle control method, and vehicle control program |
| CN107544518A (en) * | 2017-10-17 | 2018-01-05 | 芜湖伯特利汽车安全系统股份有限公司 | The ACC/AEB systems and vehicle driven based on personification |
-
2018
- 2018-01-15 CN CN201810035225.9A patent/CN108216234A/en active Pending
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104417562A (en) * | 2013-08-29 | 2015-03-18 | 株式会社电装 | Method and apparatus for recognizing road shape, program, and recording medium |
| DE202014006922U1 (en) * | 2014-08-27 | 2015-11-30 | GM Global Technology Operations LLC (n. d. Ges. d. Staates Delaware) | Device for controlling a motor vehicle, motor vehicle |
| CN105487070A (en) * | 2014-10-06 | 2016-04-13 | 日本电产艾莱希斯株式会社 | Radar system, radar signal processing device, vehicle driving control device and method and computer program |
| JP2016215769A (en) * | 2015-05-19 | 2016-12-22 | 株式会社デンソー | Vehicle control device |
| CN105197012A (en) * | 2015-10-10 | 2015-12-30 | 广东轻工职业技术学院 | Automatic vehicle control method |
| CN105667518A (en) * | 2016-02-25 | 2016-06-15 | 福州华鹰重工机械有限公司 | Lane detection method and device |
| JP2017198633A (en) * | 2016-04-28 | 2017-11-02 | 本田技研工業株式会社 | Vehicle control system, vehicle control method, and vehicle control program |
| CN107161146A (en) * | 2017-04-05 | 2017-09-15 | 吉利汽车研究院（宁波）有限公司 | A kind of highway accessory system |
| CN107544518A (en) * | 2017-10-17 | 2018-01-05 | 芜湖伯特利汽车安全系统股份有限公司 | The ACC/AEB systems and vehicle driven based on personification |
Non-Patent Citations (1)
| Title |
|---|
| 吴光强 等: "汽车自适应巡航控制系统研究现状与发展趋势", 《同济大学学报（自然科学版）》 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10860896B2 (en) | FPGA device for image classification | |
| CN108537197B (en) | Lane line detection early warning device and method based on deep learning | |
| CN114384920B (en) | Dynamic obstacle avoidance method based on real-time construction of local grid map | |
| WO2021249071A1 (en) | Lane line detection method, and related apparatus | |
| US9053433B2 (en) | Assisting vehicle guidance over terrain | |
| CN108304807A (en) | A kind of track foreign matter detecting method and system based on FPGA platform and deep learning | |
| CN106097755A (en) | For identifying the method parked place and/or vacate place | |
| CN108197610A (en) | A kind of track foreign matter detection system based on deep learning | |
| CN111291697B (en) | Method and device for detecting obstacles | |
| CN112298194B (en) | Lane changing control method and device for vehicle | |
| CN107132840B (en) | Cross-country electrically-driven unmanned vehicle longitudinal/transverse/vertical personification cooperative control method | |
| CN111311675A (en) | Vehicle positioning method, device, equipment and storage medium | |
| CN112698653A (en) | Robot autonomous navigation control method and system based on deep learning | |
| CN112068549A (en) | Unmanned system cluster control method based on deep reinforcement learning | |
| CN113052295B (en) | Training method of neural network, object detection method, device and equipment | |
| CN111899515A (en) | Vehicle detection system based on wisdom road edge calculates gateway | |
| CN110083099A (en) | One kind meeting automobile function safety standard automatic Pilot architecture system and working method | |
| Saleem et al. | Steering angle prediction techniques for autonomous ground vehicles: a review | |
| EP2405383A1 (en) | Assisting with guiding a vehicle over terrain | |
| CN110263836B (en) | Bad driving state identification method based on multi-feature convolutional neural network | |
| CN113255553B (en) | Sustainable learning method based on vibration information supervision | |
| DE112022001861T5 (en) | MOTION CONSISTENCY MEASUREMENT FOR THE OPERATION OF AN AUTONOMOUS VEHICLE | |
| Dong et al. | A vision-based method for improving the safety of self-driving | |
| CN112232257A (en) | Traffic abnormity determining method, device, equipment and medium | |
| CN108216234A (en) | A kind of electric vehicle self-adapting cruise control system and its control method |
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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20180629 |