CN104554257B - Parking scene recognition method for initial space searching stage of automatic parking - Google Patents

Parking scene recognition method for initial space searching stage of automatic parking Download PDF

Info

Publication number
CN104554257B
CN104554257B CN201410837016.8A CN201410837016A CN104554257B CN 104554257 B CN104554257 B CN 104554257B CN 201410837016 A CN201410837016 A CN 201410837016A CN 104554257 B CN104554257 B CN 104554257B
Authority
CN
China
Prior art keywords
parking
scene
park
parked
recognition method
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.)
Active
Application number
CN201410837016.8A
Other languages
Chinese (zh)
Other versions
CN104554257A (en
Inventor
华丁
华一丁
江浩斌
马世典
沈峥楠
吴狄
李臣
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Jiangsu University
Original Assignee
Jiangsu University
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Jiangsu University filed Critical Jiangsu University
Priority to CN201410837016.8A priority Critical patent/CN104554257B/en
Publication of CN104554257A publication Critical patent/CN104554257A/en
Application granted granted Critical
Publication of CN104554257B publication Critical patent/CN104554257B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

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
    • B60W30/06—Automatic manoeuvring for parking
    • 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
    • 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
    • B60W2510/00—Input parameters relating to a particular sub-units
    • B60W2510/20—Steering systems

Landscapes

  • Engineering & Computer Science (AREA)
  • Automation & Control Theory (AREA)
  • Transportation (AREA)
  • Mechanical Engineering (AREA)
  • Physics & Mathematics (AREA)
  • Mathematical Physics (AREA)
  • Steering Control In Accordance With Driving Conditions (AREA)
  • Control Of Driving Devices And Active Controlling Of Vehicle (AREA)

Abstract

The invention relates to a parking scene recognition method for an initial space searching stage of automatic parking. Aiming at occurrence of a recessed or raised curve in a parking scene, the parking scene recognition method for the initial space searching stage of automatic parking is provided to enable a vehicle to be parked in a target packing space positioned at the recessed or raised curve accurately. By the parking scene recognition method, the parking scene in the initial space searching stage of automatic parking can be recognized effectively, the problems of poor parking effect and low accuracy of an existing automatic parking system in recessed curve parking scenes and raised curve parking scenes are solved, environmental adaptability of the automatic parking system is improved, and intellectuality of automatic parking is further improved.

Description

A kind of initially seek the storehouse stage for automatic parking and park scene recognition method
Technical field
The present invention relates to automatic parking technical field is and in particular to a kind of initially seek the storehouse stage for automatic parking and park field Scape recognition methods.
Background technology
With the quick increase of automobile pollution, " parking difficulty " problem of modern metropolitan cities becomes increasingly conspicuous, crowded narrow Urban road, the parking area in cell roadside carry out parking manoeuvres not a duck soup for a lot of drivers.Therefore, park auxiliary Driving technology is helped to become one of study hotspot of automotive engineering field.
Initially seek the initial period that the storehouse stage is automated parking system, vital work is played to the subsequently process of parking With the effect initially seeking the storehouse stage is whether the size detecting target parking position meets the dimensional requirement of this car, target parking position The whether accurate normal use directly affecting automated parking system of identification.
At present, mostly the automated parking system on market is initially to be sought storehouse for the lateral linear of this car scene of parking, Assume the situation of concave or convex bend without reference to scene of parking, lead to its automated parking system to be moored under bend scene Car, the final vehicle parking situation effect of appearance is poor, the low shortcoming of precision of parking, in view of this it is necessary to provide a kind of being used for certainly Dynamic parking initially is sought the storehouse stage and is parked scene recognition method to solve the above problems.
Content of the invention
The situation of concave or convex bend occurs for scene of parking, patent of the present invention provides one kind to be used for automatic parking Initially seek the storehouse stage to park scene recognition method, so that the target that vehicle can accurately be stopped positioned at concave or convex bend is parked Position.
For achieving the above object, concrete technical scheme of the present invention is as follows: one kind initially seeks storehouse stage pool for automatic parking Car scene recognition method is it is characterised in that comprise the steps:
1) start automated parking system, enter and initially seek the storehouse stage；
2) gather a steering wheel angle every 50ms and be sequentially stored in array 1, wherein, first element of array 1 For initial corner；
3) two elements adjacent in array 1 are carried out making difference process, and each difference is stored in array 2；
4) obtain the arithmetic mean of instantaneous value of array 2 all elements, be designated as
5) according to initial corner andJudge to park scene；
6) subprogram of parking of corresponding scene is called according to scene of parking.
Further, above-mentioned scene of parking divides park scene, spill bend of straight line to park scene and convex bend is parked field Three kinds of scape.
Further, above-mentioned steps 5) in, the determination methods of scene of parking are as follows:
5.1) if initial corner=0,Scene of then parking is parked scene for straight line, if initial corner=0,Then it is judged as that driver is not operated according to system regulation, point out to park unsuccessfully；
5.2) if initial corner > 0,Scene of then parking is parked scene for spill bend, if initial corner > 0,Then it is judged as that driver is not operated according to system regulation, point out to park unsuccessfully；
5.3) if initial corner < 0,Scene of then parking is parked scene for convex bend, if initial corner < 0,Then it is judged as that driver is not operated according to system regulation, point out to park unsuccessfully；
Further, above-mentioned automatic parking is initially sought the storehouse stage and is parked in scene recognition method, is obtained by steering wheel angle Corresponding radius of turn r, obtains, by the rotating speed of wheel speed sensors, arc length l passed by, according to arc length formula l=r* θ, tries to achieve θ, with Whether effectively θ minimum of a value parks target parking stall foundation in scene as judging bend.
Compared with prior art, the present invention can effectively identify that automatic parking is initially sought the storehouse stage and parked scene, solves Existing automated parking system parks scene in spill bend and convex bend scene of parking parks that effect is poor, low the asking of precision Topic, improves the adaptability to environment for the automated parking system, improves the intelligent of automatic parking further.
Brief description
Fig. 1 is that automatic parking is initially sought the storehouse stage and parked scene recognition method flow chart.
Fig. 2 is convex bend automatic parking schematic diagram of a scenario.
Specific embodiment
The invention will be further described with embodiment below in conjunction with the accompanying drawings.
Fig. 1 is that automatic parking is initially sought the storehouse stage and parked scene recognition method flow chart.Method and step is as follows:
1) start automated parking system, enter and initially seek the storehouse stage；
2) automatic parking controller gathers a steering wheel angle data at regular intervals and is sequentially stored into pre-defined Array data1 in, wherein, first element of array data1 is initial corner；The system sets every 50ms and gathers first power To the value of disk rotary angle transmitter, 200 steering wheel angle values in the time of 10s, can be gathered, in order to prevent data from overflowing, system The size of setting array data1 is 300；
3) two elements adjacent in array data1 are carried out making difference process, and each difference is stored in array data2, be The size of system setting array data2 is 300；
4) obtain the arithmetic mean of instantaneous value of array data2 all elements, be designated asIt is used for judging the change of steering wheel angle Situation；
5) according to initial corner andJudge to park scene, wherein, scene of parking divides straight line to park scene, spill bend Scene of parking and convex bend are parked three kinds of scene, and the determination methods of scene of parking are as follows:
5.1) if initial corner=0,Scene of then parking is parked scene for straight line, if initial corner=0,Then it is judged as that driver is not operated according to system regulation, point out to park unsuccessfully；
5.2) if initial corner > 0,Scene of then parking is parked scene for spill bend, if initial corner > 0,Then it is judged as that driver is not operated according to system regulation, point out to park unsuccessfully；
5.3) if initial corner < 0,Scene of then parking is parked scene for convex bend, if initial corner < 0,Then it is judged as that driver is not operated according to system regulation, point out to park unsuccessfully；
6) subprogram of parking of corresponding scene is called according to scene of parking.
Fig. 2 is convex bend automatic parking schematic diagram of a scenario, and wherein, l refers to vehicle and initially seek the storehouse stage in convex bend walk The arc length crossed；L refers to tangent line at target parking position for the convex bend border；The radius of turn when bend seeks storehouse for the r value vehicle.By Steering wheel angle sensor readout direction disk corner, according to the gearratio of power train, tries to achieve front-wheel effective rotation, then obtains now Corresponding radius of turn r, can try to achieve, by wheel speed sensors, arc length l accordingly passed by, according to arc length formula l=r* θ, try to achieve θ, and Park target parking stall whether effectively judging basis in scene using its minimum of a value as judging bend.

Claims (3)

1. one kind is initially sought the storehouse stage for automatic parking and is parked scene recognition method it is characterised in that comprising the steps:
1) start automated parking system, enter and initially seek the storehouse stage；
2) gather a steering wheel angle every 50ms and be sequentially stored in array 1, wherein, first element of array 1 is first Beginning corner；
3) two elements adjacent in array 1 are carried out making difference process, and each difference is stored in array 2；
4) obtain the arithmetic mean of instantaneous value of array 2 all elements, be designated as
5) according to initial corner andJudge to park scene；
6) subprogram of parking of corresponding scene is called according to scene of parking；
Described step 5) in, the determination methods of scene of parking are as follows:
5.1) if initial corner=0,Scene of then parking is parked scene for straight line, if initial corner=0,Then it is judged as that driver is not operated according to system regulation, point out to park unsuccessfully；
5.2) if initial corner > 0,Scene of then parking is parked scene for spill bend, if initial corner > 0,Then it is judged as that driver is not operated according to system regulation, point out to park unsuccessfully；
5.3) if initial corner < 0,Scene of then parking is parked scene for convex bend, if initial corner < 0,Then it is judged as that driver is not operated according to system regulation, point out to park unsuccessfully.
2. initially seek the storehouse stage for automatic parking as claimed in claim 1 and park scene recognition method it is characterised in that mooring Parking lot scape divides park scene, spill bend of straight line to park scene and convex bend is parked three kinds of scene.
3. as claimed in claim 1 for automatic parking initially seek the storehouse stage park scene recognition method it is characterised in that by Steering wheel angle obtains corresponding radius of turn r, obtains, by the rotating speed of wheel speed sensors, arc length l passed by, according to arc length formula l Whether effectively=r* θ, tries to achieve θ, park target parking stall foundation in scene using θ minimum of a value as judging bend.
CN201410837016.8A 2014-12-29 2014-12-29 Parking scene recognition method for initial space searching stage of automatic parking Active CN104554257B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201410837016.8A CN104554257B (en) 2014-12-29 2014-12-29 Parking scene recognition method for initial space searching stage of automatic parking

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201410837016.8A CN104554257B (en) 2014-12-29 2014-12-29 Parking scene recognition method for initial space searching stage of automatic parking

Publications (2)

Publication Number Publication Date
CN104554257A CN104554257A (en) 2015-04-29
CN104554257B true CN104554257B (en) 2017-01-18

Family

ID=53071606

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201410837016.8A Active CN104554257B (en) 2014-12-29 2014-12-29 Parking scene recognition method for initial space searching stage of automatic parking

Country Status (1)

Country Link
CN (1) CN104554257B (en)

Families Citing this family (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110211420B (en) * 2019-06-25 2021-11-30 重庆长安汽车股份有限公司 Method and system for judging whether current scene is parking lot or not and computer readable storage medium
CN111137280B (en) * 2020-03-06 2021-05-04 北京百度网讯科技有限公司 Control method, device and equipment for autonomous parking and storage medium
CN112132111A (en) * 2020-10-10 2020-12-25 安徽江淮汽车集团股份有限公司 Parking typical scene extraction method, device, storage medium and device

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102398596A (en) * 2010-09-07 2012-04-04 北京经纬恒润科技有限公司 Parking control device and system and parking control method
CN102529961A (en) * 2012-03-26 2012-07-04 江苏大学 Initial carport-searching offset correction method of automatic parking system
JP2012126193A (en) * 2010-12-14 2012-07-05 Denso Corp Automatic parking system for parking lot
CN102862531A (en) * 2012-10-23 2013-01-09 浙江海康集团有限公司 Visual parking assist system with continuously variable track and control method thereof
CN203974805U (en) * 2014-07-14 2014-12-03 江苏大学 A kind of automated parking system controller

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102398596A (en) * 2010-09-07 2012-04-04 北京经纬恒润科技有限公司 Parking control device and system and parking control method
JP2012126193A (en) * 2010-12-14 2012-07-05 Denso Corp Automatic parking system for parking lot
CN102529961A (en) * 2012-03-26 2012-07-04 江苏大学 Initial carport-searching offset correction method of automatic parking system
CN102862531A (en) * 2012-10-23 2013-01-09 浙江海康集团有限公司 Visual parking assist system with continuously variable track and control method thereof
CN203974805U (en) * 2014-07-14 2014-12-03 江苏大学 A kind of automated parking system controller

Also Published As

Publication number Publication date
CN104554257A (en) 2015-04-29

Similar Documents

Publication Publication Date Title
CN110962843B (en) Automatic parking control decision method and system
US10814863B2 (en) System and method for automatic parking
JP5862670B2 (en) Driving support device and driving support method
KR102207325B1 (en) Apparatus for driver assistance
US10604185B2 (en) Method for assisting a parking procedure of a motor vehicle, electronic parking assistance system, and motor vehicle
CN103874931B (en) For the method and apparatus of the position of the object in the environment for asking for vehicle
WO2018059585A1 (en) Vehicle identification method and device, and vehicle
CN104691544A (en) Full-automatic parking system and parking method thereof
CN104554257B (en) Parking scene recognition method for initial space searching stage of automatic parking
JP6180928B2 (en) How to find an elongate passage
CN102956118A (en) Device and method for traffic sign recognition
DE102016209966A1 (en) Autonomous device and vehicle control device
CN104608766A (en) Automatic parking method and system used for intelligent vehicle through parking memory stick
CN110816540B (en) Traffic jam determining method, device and system and vehicle
CN107933552A (en) Controller of vehicle
CN103646298A (en) Automatic driving method and automatic driving system
CN104036279A (en) Intelligent vehicle running control method and system
US20160214617A1 (en) Method for determining a relative gradient of a roadway
CN101879881A (en) Adaptive bend auxiliary lighting method and device
JP6377942B2 (en) Driving assistance device
CN104732774A (en) Detecting method and detecting system for vehicle converse running
US10118617B2 (en) Vehicle control system
JP7020353B2 (en) Object detector
CN104318761B (en) Highway-scene-based detection and vehicle detection tracking optimization method
JP4703544B2 (en) Driving assistance device

Legal Events

Date Code Title Description
C06 Publication
PB01 Publication
C10 Entry into substantive examination
SE01 Entry into force of request for substantive examination
C14 Grant of patent or utility model
GR01 Patent grant