CN105631217A - Vehicle self-adaptive virtual lane based front effective target selection system and method - Google Patents
Vehicle self-adaptive virtual lane based front effective target selection system and method Download PDFInfo
- Publication number
- CN105631217A CN105631217A CN201511019229.0A CN201511019229A CN105631217A CN 105631217 A CN105631217 A CN 105631217A CN 201511019229 A CN201511019229 A CN 201511019229A CN 105631217 A CN105631217 A CN 105631217A
- Authority
- CN
- China
- Prior art keywords
- car
- track
- self
- effective target
- virtual
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16Z—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS, NOT OTHERWISE PROVIDED FOR
- G16Z99/00—Subject matter not provided for in other main groups of this subclass
Landscapes
- Radar Systems Or Details Thereof (AREA)
- Traffic Control Systems (AREA)
Abstract
The invention discloses a vehicle self-adaptive virtual lane based front effective target selection system and method. The front effective target selection system and method comprises the following steps that 1, a vehicle self-adaptive virtual lane is initialized, and a lane region and a core region of the vehicle self-adaptive virtual lane are formed; 2, self-adaptive adjustment is conducted on the vehicle self-adaptive virtual lane according to vehicle motion state information and vehicle-mounted radar information; 3, the probability that a radar target is located in the vehicle lane is calculated according to the position of the radar target located in the vehicle virtual lane, and effective target selection is performed. By means of the front effective target selection method, the problem of effective target selection in the front under multiple conditions is effectively solved, effective tracking of targets in the front can be achieved, effective targets can be caught or released in time when the motions of the targets in the front are remarkably changed, such as driving in or out of the vehicle lane, and the selection performance of the targets in the front is effectively improved.
Description
Technical field
Patent of the present invention belongs to automobile technical field, it relates to a kind of front effective target selective system based on the virtual track of this car self-adaptation and method that can be used for advanced driver assistance system.
Background technology
Advanced drive assist system ADAS has become active security system emerging in recent years. Drive assist system can the form environment of perception automobile, and by the supervision of automobile oneself state and surrounding environment, for officer submit necessary information, safe early warning and vehicle is carried out ACTIVE CONTROL. It mainly comprises adaptive learning algorithms, Lane Departure Warning System, front collision early warning system, automatic emergency brake system etc. at present. Advanced drive assist system, based on the wireless sensor networks such as radar and computer vision, effectively improves travel safety and comfortable property.
The system architecture of drive assist system mainly comprises perception, decision-making and control three parts. Perception part forms primarily of radar, camera, lidar etc., for system provides environment Traffic Information accurately, is decision-making and the basis of control part. Perception part needs select front effective target. It is correct whether timely that effective target is selected, and greatly have impact on the security of system and comfortable property.
In order to carry out effective target selection, it is necessary to assess all actual objects to the threaten degree of this car security. Based on the high correlation of this car Future movement track and forward object trajectory, by the tracking to moving target, the accuracy of target selection can be improved, it can be difficult to the requirement of split hair caccuracy target selection under meeting complex working condition. Longitudinal safety evaluation index TTC (Time-to-collision) can also be used for effective target and select. Longitudinal safety evaluation index TTC is relevant with relative distance and the speed of relative movement of target for target, and the general target selecting TTC minimum is effective target. But, it may also be useful to TTC carries out accuracy and the promptness that effective target is selected still cannot meet under different operating mode.
Summary of the invention
Technical problem to be solved by this invention is: how under different operating mode, the virtual track of this car to be carried out self-adaptative adjustment, to reach the object that can catch effective target under different operating mode timely and accurately.
In order to overcome the above problems, the present invention proposes a kind of front effective target selective system based on the virtual track of this car self-adaptation and method, by this car self-adaptation virtual track algorithm and set up the virtual track of this car self-adaptation, under different operating mode, the virtual track of this car can be carried out self-adaptative adjustment, effective target is selected timely and accurately, for decision-making and the control part of drive assist system provides basis under multi-state.
The present invention solves the technical scheme of above technical problem:
Based on the front effective target selective system in the virtual track of this car self-adaptation, comprising:
Car virtual track setting module, for the virtual track of this car self-adaptation is carried out initialize, forms region, track and the nucleus in the virtual track of this car;
Virtual track self-adaptative adjustment module, for according to this car movement state information and vehicle-mounted radar information, carrying out self-adaptative adjustment to the virtual track of this car;
Effective target selects module, and for the virtual track of this car residing for radar target position calculation, it is in this car track probability, carries out effective target selection.
Based on the front effective target system of selection in the virtual track of this car self-adaptation, comprise the following steps:
(i) the virtual track of this car self-adaptation is carried out initialize, form region, track and the nucleus in the virtual track of this car;
(ii) according to this car movement state information and vehicle-mounted radar information, the virtual track of this car is carried out self-adaptative adjustment;
(iii) the virtual track of this car residing for radar target position calculation its be in this car track probability, carry out effective target selection.
The technical scheme that the present invention limits further is:
The aforesaid front effective target system of selection based on the virtual track of this car self-adaptation, wherein step (i) in, region, described track is back taper, described nucleus is taper, and region, described track and nucleus symmetrical about this car longitudinal center line, the geometric profile of region, described track and nucleus with apart from the distance dependent of this car, during initialize it needs to be determined that parameter have:
(1) objects ahead is apart from this spacing dx=0, and track peak width is L1,2m��L1��3.5m, and nucleus width is H, 2m��H��3m;
(2) objects ahead is apart from this spacing dx=D, 25m��D��35m, and track peak width is L2,2.2m��L2��3.8m;
(3) objects ahead is apart from this spacing dx > D, and track peak width is L2;
(4) objects ahead is apart from this spacing 0 < dx < D, and track peak width is:
(5) apart from this spacing dx > 0, nucleus width by FACTOR P, 0.002��P��0.0002, determine with following formula:
H=H-P*dx2��
The aforesaid front effective target system of selection based on the virtual track of this car self-adaptation, step (ii) in, self-adaptative adjustment is specially:
(1), when this car sails bend into, the track peak width in the virtual track of this car superposition can increase width l apart from this spacing D with upper partcurve, along with the increase of this wheel paths curvature, lcurveCan increase until maximum value L graduallycurveMax, it is specially:
When curvature is k=0, lcurve=0;
As curvature k=PcurveMax, lcurve=LcurveMax, PcurvemaxFor maximum curvature threshold when track regional broadband increases with curvature, when curvature is greater than PcurvemaxTime, track peak width no longer increases by 0.002��Pcurvemax�� 0.005;
As curvature k < PcurveMax,
(2) when this car is overtaken other vehicles, the virtual track of this car can carry out self-adaptative adjustment, by the requirement caught in time or discharge, can be specially to meet front effective target:
When this car starts to overtake other vehicles and sails motorway into, track area surface increases L to the width of the area part of side, motorwayovertakePlus, reduce L towards the width of the area part of slow lane sideovertakeMinus, nucleus translates L to direction, motorwayovertakeCore;
When this car completes to overtake other vehicles and sails back slow lane, track area surface can increase L to the width of the area part of slow lane sidemergePlus, L can be reduced towards the width of the area part of side, motorwaymergeMinus, nucleus translates L to slow lane directionmergeCore��
The aforesaid front effective target system of selection based on the virtual track of this car self-adaptation, (iii) step is specially:
(1) the lateral distance of objects ahead and this car is dy, and longitudinally distance is dx, the curvature k of this car driving trace, and therefore the lateral distance of objects ahead and the virtual lane center of this car is:
DyObj=dy-k*dx2/2
Calculate the probability of objects ahead in this car track according to described lateral distance, it be specially:
Current square mesh mark when this car virtual track nucleus, its Probability p=1 in this car track;
When current square mesh mark is outside the region, track in the virtual track of this car, its Probability p=0 in this car track;
The nucleus of current square mesh mark in the virtual track of this car is outer and in the district of track time, its probability in this car trackTrack peak width corresponding when wherein lObj is distance dx longitudinal apart from this car;
(2) effective target is selected: if in this front side target, there is its Probability p being positioned at this car track of one or more objects ahead 0.5, then the objects ahead selecting its middle distance this spacing dx value minimum is this front side effective target; If this front side target does not exist its Probability p being positioned at this car track of objects ahead > 0.5, then this car is without front effective target.
The invention has the beneficial effects as follows: in environment sensing, the position detection of objects ahead is existed error, be there is error equally in the prediction of this car Future movement track, on judging, whether objects ahead can travel this car to exist affect and select effective target to bring difficulty for these, especially this car is in negotiation of bends operating mode and overtaking process, and the difficulty that effective target is selected is higher. Therefore, the present invention carries out effective target selection by setting up the virtual track of this car self-adaptation and calculate the objects ahead probability that is in this car track, under different operating mode, the virtual track of this car can be carried out self-adaptative adjustment, to reach the object that can catch effective target under different operating mode timely and accurately; Invention increases the accuracy that effective target is selected and the stability selected at multi-state complex condition effective target, it is the necessary basis promoting drive assist system security and comfortable property further.
Accompanying drawing explanation
Fig. 1 is the present invention's this car self-adaptation virtual track schematic diagram.
Fig. 2-1 is for the virtual track of the present invention's this car self-adaptation is with this wheel paths curvature self-adaptative adjustment schematic diagram.
Fig. 2-2 is track peak width and this wheel paths curvature relationship figure in the virtual track of this car of the present invention.
Fig. 3-1 starts passing behavior self-adaptative adjustment schematic diagram for the virtual track of the present invention's this car self-adaptation with this car.
Fig. 3-2 completes passing behavior self-adaptative adjustment schematic diagram for the virtual track of the present invention's this car self-adaptation with this car.
Fig. 4 is that the present invention calculates objects ahead and is positioned at this car track probability schematic diagram.
Embodiment
Embodiment 1
A kind of front effective target selective system based on the virtual track of this car self-adaptation that the present embodiment provides, comprising:
Car virtual track setting module, for the virtual track of this car self-adaptation is carried out initialize, forms region, track and the nucleus in the virtual track of this car;
Virtual track self-adaptative adjustment module, for according to this car movement state information and vehicle-mounted radar information, carrying out self-adaptative adjustment to the virtual track of this car;
Effective target selects module, and for the virtual track of this car residing for radar target position calculation, it is in this car track probability, carries out effective target selection.
The front effective target system of selection based on the virtual track of this car self-adaptation of the present embodiment, comprises the following steps:
(i) the virtual track of this car self-adaptation is carried out initialize, forms region, track and the nucleus in the virtual track of this car, it is determined that the geometric profile of region, track and nucleus:
As shown in Figure 1, in the present invention, the virtual track of this car mainly comprises region, track and nucleus two portions, and namely the target being wherein positioned at nucleus determines to be positioned at track residing for this car. When current square mesh this spacing of subject distance is nearer; now usually can be higher to the angle-resolved rate of the detection of objects ahead; and need to select effective target to guarantee system security more accurately, so, region, this car track is along with the less meeting constriction gradually apart from this spacing. And, along with the increase apart from this spacing, the angle-resolved rate of objects ahead detection can be reduced simultaneously, therefore nucleus can along with the increase of distance constriction. Therefore, the region, track in the virtual track of this car is back taper on the whole, and nucleus is tapered.
To the virtual track initialize of this car, it is necessary to determine the basic geometric profile of region, track and nucleus. The initialize in the virtual track of this car is unrelated with this car kinestate, the geometric profile of region, track, nucleus with apart from the distance dependent of this car and symmetrical about this car longitudinal center line, when the virtual track of this car self-adaptation is carried out initialize it needs to be determined that parameter have:
Apart from this spacing dx=0, track peak width is L1, and nucleus width is H;
Apart from this spacing dx=D, track peak width is L2;
Apart from this spacing dx > 0, track peak width is L2;
Apart from this spacing 0 < dx < D, track peak width is:
Apart from this spacing dx > 0, nucleus width is determined by FACTOR P and following formula:
H=H-P*dx2��
Wherein, 2m��L1��3.5m, 2m��H��3m, 2.2m��L2��3.8m, 25m��D��35m, 0.002��P��0.0002, concrete numerical value needs to mate according to system and vehicle configuration.
(ii) according to this car movement state information and vehicle-mounted radar information, the virtual track of this car is carried out self-adaptative adjustment:
The virtual track of this car after initialize, it is possible to select for front effective target, especially can meet target selection demand when this car travels on straight way. Then, when this car is in negotiation of bends or when overtaking other vehicles, the virtual track of this car after initialize can not accurately carry out effective target selection. Consequently, it is desirable to when this car carries out negotiation of bends or overtakes other vehicles, the virtual track of this car is carried out self-adaptative adjustment.
As shown in Fig. 2-1 and Fig. 2-2, when this car sails bend into, owing to the prediction of this wheel paths curvature is existed error, it is necessary to corresponding increase track area part, the track peak width in the virtual track of this car superposition can increase width l apart from this spacing D with upper partcurve, along with the increase of this wheel paths curvature, lcurveCan increase until maximum value L graduallycurveMax, it is specially:
When curvature is k=0, lcurve=0;
As curvature k=PcurveMax, lcurve=LcurveMax; PcurvemaxFor maximum curvature threshold when track regional broadband increases with curvature, when curvature is greater than PcurvemaxTime, track peak width no longer increases by 0.002��Pcurvemax�� 0.005;
As curvature k < PcurveMax,
When this car is overtaken other vehicles, the overtaking process of this car can be divided into three parts. First part is that this car starts to overtake other vehicles and changes to motorway; Second section is that this car acceleration on motorway travels, it is achieved to surmounting of slow lane vehicle; Part III is that this car completes to surmount and changes to slow lane. First and Part III at overtaking process need to be adjusted in the virtual track of this car, to meet accuracy and the promptness of target selection. The virtual track of this car can carry out self-adaptative adjustment, can by the requirement caught in time or discharge to meet front effective target.
As shown in figure 3-1, when this car starts to overtake other vehicles and sails motorway into, in order to can in time the objects ahead in slow lane be discharged and select objects ahead in motorway to be effective target, width from track area surface to the area part of side, motorway increase LovertakePlus, reduce L towards the width of the area part of slow lane sideovertakeMinus, nucleus translates L to direction, motorwayovertakeCore��
As shown in figure 3-2, when this car completes to overtake other vehicles and sails back slow lane, in order to can in time front effective target in motorway be discharged and select objects ahead in slow lane to be effective target, track area surface can increase L to the width of the area part of slow lane sidemergePlus, L can be reduced towards the width of the area part of side, motorwaymergeMinus, nucleus translates L to slow lane directionmergeCore��
(iii) the virtual track of this car residing for radar target position calculation its be in this car track probability, carry out effective target selection:
Position in the virtual track of this car residing for objects ahead, calculates the probability that objects ahead is in this car track. As shown in Figure 4, on the basis in the virtual track of this car self-adaptation determined, according to objects ahead apart from the Distance geometry objects ahead of this car apart from the lateral distance of the virtual lane center of this car self-adaptation, calculate the probability that objects ahead is in this car track. In fact, objects ahead is objects ahead and the lateral distance of this car prediction locus apart from the lateral distance of the virtual lane center of this car self-adaptation. The distance of the objects ahead obtained by environment sensing sensor is the relative distance taking this car coordinate as benchmark, utilizes the curvature of relative distance and this car driving trace can calculate this lateral distance. Specific algorithm is:
When the lateral distance of objects ahead and this car is dy, longitudinally distance is dx, and the lateral distance of the virtual lane center of the curvature k of this car driving trace, objects ahead and this car is:
DyObj=dy-k*dx2/2
The probability of objects ahead in this car track is calculated according to this lateral distance, the aforementioned virtual track of this calculated car self-adaptation comprises nucleus and two, region, track part, that is: current square mesh mark is when nucleus, it is identified and is in this car track, and the probability being namely in this car track is 1; Current square mesh mark is in region, track but when not being positioned at nucleus, and it is considered to likely be in this car track, and the probability being namely in this car track is greater than 0 and be less than 1, and its probability and objects ahead are linear apart from the lateral distance of the virtual lane center of this car; When current square mesh mark is outside region, track, its this confirmation is not in this car track, and the probability being namely in this car track is 0. Specific as follows:
Current square mesh mark when this car virtual track nucleus, its Probability p=1 in this car track;
When current square mesh mark is outside the region, track in the virtual track of this car, its Probability p=0 in this car track;
The nucleus of current square mesh mark in the virtual track of this car is outer and in the district of track time, its probability in this car track
Track peak width corresponding when wherein lObj is distance dx longitudinal apart from this car.
The all targets of this front side are calculated its Probability p being positioned at this car track. If there is its Probability p being positioned at this car track of one or more objects ahead > 0.5, then the objects ahead selecting its middle distance this spacing dx value minimum is this front side effective target. If this front side target does not exist its Probability p being positioned at this car track of any objects ahead > 0.5, then this car is without front effective target.
The present embodiment is based on the objects ahead system of selection in the virtual track of this car self-adaptation, it compares to the outstanding effect of prior art: improves the accuracy that effective target is selected and the stability selected at multi-state complex condition effective target, is the necessary basis promoting drive assist system security and comfortable property further.
In addition to the implementation, the present invention can also have other enforcement modes. All employings are equal to replacement or the technical scheme of equivalent transformation formation, all drop on the protection domain of requirement of the present invention.
Claims (5)
1. based on the front effective target selective system in the virtual track of this car self-adaptation, it is characterised in that: comprising:
Car virtual track setting module, for the virtual track of this car self-adaptation is carried out initialize, forms region, track and the nucleus in the virtual track of this car;
Virtual track self-adaptative adjustment module, for according to this car movement state information and vehicle-mounted radar information, carrying out self-adaptative adjustment to the virtual track of this car;
Effective target selects module, and for the virtual track of this car residing for radar target position calculation, it is in this car track probability, carries out effective target selection.
2. based on the front effective target system of selection in the virtual track of this car self-adaptation, it is characterised in that: comprise the following steps:
(1) the virtual track of this car self-adaptation is carried out initialize, form region, track and the nucleus in the virtual track of this car;
(2) according to this car movement state information and vehicle-mounted radar information, the virtual track of this car is carried out self-adaptative adjustment;
(3) the virtual track of this car residing for radar target position calculation its be in this car track probability, carry out effective target selection.
3. as claimed in claim 2 based on the front effective target system of selection in the virtual track of this car self-adaptation, it is characterized in that: in described step (), region, described track is back taper, described nucleus is taper, and region, described track and nucleus symmetrical about this car longitudinal center line, the geometric profile of region, described track and nucleus with apart from the distance dependent of this car, during initialize it needs to be determined that parameter have:
(1) objects ahead is apart from this spacing dx=0, and track peak width is L1,2m��L1��3.5m, and nucleus width is H, 2m��H��3m;
(2) objects ahead is apart from this spacing dx=D, 25m��D��35m, and track peak width is L2,2.2m��L2��3.8m;
(3) objects ahead is apart from this spacing dx > D, and track peak width is L2;
(4) objects ahead is apart from this spacing 0 < dx < D, and track peak width is:
(5) apart from this spacing dx > 0, nucleus width by FACTOR P, 0.002��P��0.0002, determine with following formula:
H=H-P*dx2��
4. as claimed in claim 2 based on the front effective target system of selection in the virtual track of this car self-adaptation, it is characterised in that:
In described step (two), self-adaptative adjustment is specially:
(1) when this car sails bend into, the track peak width in the virtual track of this car superposition can increase width apart from this spacing D with upper partAlong with the increase of this wheel paths curvature,Can increase until maximum value graduallyIt is specially:
When curvature is k=0,
Work as curvaturePcurvemaxFor maximum curvature threshold when track regional broadband increases with curvature, when curvature is greater than PcurvemaxTime, track peak width no longer increases, 0.002��Pcurvemax�� 0.005;
Work as curvature
(2) when this car is overtaken other vehicles, the virtual track of this car can carry out self-adaptative adjustment, by the requirement caught in time or discharge, can be specially to meet front effective target:
When this car starts to overtake other vehicles and sails motorway into, track area surface increases to the width of the area part of side, motorwayWidth towards the area part of slow lane side reducesNucleus translates to direction, motorway
When this car completes to overtake other vehicles and sails back slow lane, track area surface can increase to the width of the area part of slow lane sideWidth towards the area part of side, motorway can reduceNucleus translates to slow lane direction
5. as claimed in claim 2 based on the front effective target system of selection in the virtual track of this car self-adaptation, it is characterised in that:
Described step (three) be specially:
(1) lateral distance of objects ahead and this car is dy, and longitudinally distance is dx, the curvature k of this car driving trace, and therefore the lateral distance of objects ahead and the virtual lane center of this car is:
DyObj=dy-k*dx2/2
Calculate the probability of objects ahead in this car track according to described lateral distance, it be specially:
Current square mesh mark when this car virtual track nucleus, its Probability p=1 in this car track;
When current square mesh mark is outside the region, track in the virtual track of this car, its Probability p=0 in this car track;
The nucleus of current square mesh mark in the virtual track of this car is outer and in the district of track time, its probability in this car trackTrack peak width corresponding when wherein lObj is distance dx longitudinal apart from this car;
(2) effective target is selected: if in this front side target, there is its Probability p > 0.5 being positioned at this car track of one or more objects ahead, then the objects ahead selecting its middle distance this spacing dx value minimum is this front side effective target; If there is not its Probability p > 0.5 being positioned at this car track of objects ahead in this front side target, then this car is without front effective target.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201511019229.0A CN105631217B (en) | 2015-12-30 | 2015-12-30 | Front effective target selection method based on the adaptive virtual lane of this vehicle |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201511019229.0A CN105631217B (en) | 2015-12-30 | 2015-12-30 | Front effective target selection method based on the adaptive virtual lane of this vehicle |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN105631217A true CN105631217A (en) | 2016-06-01 |
| CN105631217B CN105631217B (en) | 2018-12-21 |
Family
ID=56046146
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201511019229.0A Active CN105631217B (en) | 2015-12-30 | 2015-12-30 | Front effective target selection method based on the adaptive virtual lane of this vehicle |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105631217B (en) |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108732588A (en) * | 2017-04-21 | 2018-11-02 | 百度在线网络技术（北京）有限公司 | A kind of radar scanner, method and equipment |
| CN109311476A (en) * | 2016-07-29 | 2019-02-05 | 宝马股份公司 | The method and apparatus of traveling manoeuvre for implementing at least partly to automate |
| CN109389026A (en) * | 2017-08-09 | 2019-02-26 | 三星电子株式会社 | Lane detection method and equipment |
| CN110168312A (en) * | 2017-05-16 | 2019-08-23 | 大陆汽车有限责任公司 | Method and apparatus based on target prediction dynamic object |
| CN110550030A (en) * | 2019-09-09 | 2019-12-10 | 深圳一清创新科技有限公司 | Lane changing control method and device for unmanned vehicle, computer equipment and storage medium |
| CN112677972A (en) * | 2020-12-25 | 2021-04-20 | 际络科技(上海)有限公司 | Adaptive cruise method and apparatus, device and medium |
| CN112706785A (en) * | 2021-01-29 | 2021-04-27 | 重庆长安汽车股份有限公司 | Method and device for selecting cognitive target of driving environment of automatic driving vehicle and storage medium |
| WO2021212379A1 (en) * | 2020-04-22 | 2021-10-28 | 华为技术有限公司 | Lane line detection method and apparatus |
| CN114043993A (en) * | 2022-01-13 | 2022-02-15 | 深圳佑驾创新科技有限公司 | Key target selection method and device suitable for intelligent driving vehicle |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20010037165A1 (en) * | 2000-03-30 | 2001-11-01 | Noriaki Shirai | Method of selecting a preceding vehicle, a preceding vehicle selecting apparatus, and a recording medium for selecting a preceding vehicle |
| CN1532101A (en) * | 2003-03-20 | 2004-09-29 | 日产自动车株式会社 | Keeping and control device and method for automobile track |
| CN102693645A (en) * | 2011-03-21 | 2012-09-26 | 株式会社电装 | Method and apparatus for recognizing shape of road for vehicles |
| CN104183131A (en) * | 2013-05-28 | 2014-12-03 | 现代自动车株式会社 | Apparatus and method for detecting traffic lane using wireless communication |
| CN104517465A (en) * | 2013-10-03 | 2015-04-15 | 株式会社电装 | Preceding vehicle selection apparatus |
| US20150239472A1 (en) * | 2014-02-21 | 2015-08-27 | Denso Corporation | Vehicle-installed obstacle detection apparatus having function for judging motion condition of detected object |
-
2015
- 2015-12-30 CN CN201511019229.0A patent/CN105631217B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20010037165A1 (en) * | 2000-03-30 | 2001-11-01 | Noriaki Shirai | Method of selecting a preceding vehicle, a preceding vehicle selecting apparatus, and a recording medium for selecting a preceding vehicle |
| CN1532101A (en) * | 2003-03-20 | 2004-09-29 | 日产自动车株式会社 | Keeping and control device and method for automobile track |
| CN102693645A (en) * | 2011-03-21 | 2012-09-26 | 株式会社电装 | Method and apparatus for recognizing shape of road for vehicles |
| CN104183131A (en) * | 2013-05-28 | 2014-12-03 | 现代自动车株式会社 | Apparatus and method for detecting traffic lane using wireless communication |
| CN104517465A (en) * | 2013-10-03 | 2015-04-15 | 株式会社电装 | Preceding vehicle selection apparatus |
| US20150239472A1 (en) * | 2014-02-21 | 2015-08-27 | Denso Corporation | Vehicle-installed obstacle detection apparatus having function for judging motion condition of detected object |
Cited By (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US11433882B2 (en) | 2016-07-29 | 2022-09-06 | Bayerische Motoren Werke Aktiengesellschaft | Method and device for performing an at least partially automated driving maneuver |
| CN109311476A (en) * | 2016-07-29 | 2019-02-05 | 宝马股份公司 | The method and apparatus of traveling manoeuvre for implementing at least partly to automate |
| CN108732588B (en) * | 2017-04-21 | 2020-12-18 | 百度在线网络技术（北京）有限公司 | Radar scanning device, method and equipment |
| CN108732588A (en) * | 2017-04-21 | 2018-11-02 | 百度在线网络技术（北京）有限公司 | A kind of radar scanner, method and equipment |
| CN110168312A (en) * | 2017-05-16 | 2019-08-23 | 大陆汽车有限责任公司 | Method and apparatus based on target prediction dynamic object |
| CN110168312B (en) * | 2017-05-16 | 2023-09-12 | 大陆智行德国有限公司 | Method and device for predicting dynamic object based on target |
| CN109389026A (en) * | 2017-08-09 | 2019-02-26 | 三星电子株式会社 | Lane detection method and equipment |
| CN109389026B (en) * | 2017-08-09 | 2023-10-17 | 三星电子株式会社 | Lane detection method and apparatus |
| CN110550030A (en) * | 2019-09-09 | 2019-12-10 | 深圳一清创新科技有限公司 | Lane changing control method and device for unmanned vehicle, computer equipment and storage medium |
| WO2021212379A1 (en) * | 2020-04-22 | 2021-10-28 | 华为技术有限公司 | Lane line detection method and apparatus |
| CN112677972A (en) * | 2020-12-25 | 2021-04-20 | 际络科技(上海)有限公司 | Adaptive cruise method and apparatus, device and medium |
| CN112706785A (en) * | 2021-01-29 | 2021-04-27 | 重庆长安汽车股份有限公司 | Method and device for selecting cognitive target of driving environment of automatic driving vehicle and storage medium |
| CN114043993B (en) * | 2022-01-13 | 2022-04-29 | 深圳佑驾创新科技有限公司 | Key target selection method and device suitable for intelligent driving vehicle |
| CN114043993A (en) * | 2022-01-13 | 2022-02-15 | 深圳佑驾创新科技有限公司 | Key target selection method and device suitable for intelligent driving vehicle |
Also Published As
| Publication number | Publication date |
|---|---|
| CN105631217B (en) | 2018-12-21 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105631217A (en) | Vehicle self-adaptive virtual lane based front effective target selection system and method | |
| CN109035862B (en) | Multi-vehicle cooperative lane change control method based on vehicle-to-vehicle communication | |
| CN109501799B (en) | Dynamic path planning method under condition of Internet of vehicles | |
| EP3474254B1 (en) | Surrounding environment recognition device | |
| US10814876B2 (en) | Vehicle lane-changing control method, vehicle lane-changing control device and related equipment | |
| CN110103969B (en) | Vehicle control method, device and system and vehicle | |
| EP1898232B1 (en) | Method and system for collision avoidance | |
| CN109987092A (en) | A kind of determination method on vehicle obstacle-avoidance lane-change opportunity and the control method of avoidance lane-change | |
| CN109050533B (en) | Automatic lane changing control method and device for vehicle | |
| US8112225B2 (en) | Method and system for collision avoidance | |
| JP5300357B2 (en) | Collision prevention support device | |
| EP3741639A1 (en) | Vehicle control device | |
| EP2759897B1 (en) | Method and arrangement for determining a trajectory | |
| CN112046484B (en) | Q learning-based vehicle lane-changing overtaking path planning method | |
| US20200238980A1 (en) | Vehicle control device | |
| CN111661055B (en) | Lane changing control method and system for automatic driving vehicle | |
| WO2021103510A1 (en) | Method, device and storage medium for controlling autonomous vehicle | |
| CN108032859B (en) | Automatic lane change control method and device and automobile | |
| US20200353918A1 (en) | Vehicle control device | |
| Cao et al. | An optimal hierarchical framework of the trajectory following by convex optimisation for highly automated driving vehicles | |
| EP3738849A1 (en) | Vehicle control device | |
| JP7156394B2 (en) | Other Vehicle Motion Prediction Method and Other Vehicle Motion Prediction Device | |
| CN104417561A (en) | Context-aware threat response arbitration | |
| EP3741638A1 (en) | Vehicle control device | |
| CN114194215A (en) | Intelligent vehicle obstacle avoidance and track changing planning method and system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |