CN105631217B - Front effective target selection method based on the adaptive virtual lane of this vehicle - Google Patents
Front effective target selection method based on the adaptive virtual lane of this vehicle Download PDFInfo
- Publication number
- CN105631217B CN105631217B CN201511019229.0A CN201511019229A CN105631217B CN 105631217 B CN105631217 B CN 105631217B CN 201511019229 A CN201511019229 A CN 201511019229A CN 105631217 B CN105631217 B CN 105631217B
- Authority
- CN
- China
- Prior art keywords
- vehicle
- lane
- distance
- virtual
- virtual lane
- 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
Links
Landscapes
- Radar Systems Or Details Thereof (AREA)
- Traffic Control Systems (AREA)
Abstract
The present invention is a kind of front effective target selection method based on the adaptive virtual lane of this vehicle, comprising the following steps: (i) to this vehicle, adaptively virtual lane is initialized, and forms lane region and the nucleus in the virtual lane of this vehicle；(ii) according to this vehicle movement state information and trailer-mounted radar information, the virtual lane of this vehicle is adaptively adjusted；(iii) the virtual lane position of this vehicle according to locating for radar target calculates it and is in this vehicle lane probability, carries out effective target selection.This method solves the problems, such as that various working inferoanterior effective target selects, it can be realized effective tracking to objects ahead, and when being significantly changed to the motion state of objects ahead, such as drive into or be driven out to this vehicle lane, it can capture in time or discharge effective target, effectively increase objects ahead selection performance.
Description
Technical field
The invention patent belongs to automobile technical field, be related to it is a kind of can be used for advanced driver assistance system based on this vehicle
The front effective target in adaptive virtual lane selects system and method.
Background technique
Advanced driving assistance system ADAS has become active safety system emerging in recent years.Driving assistance system can be felt
Know the form environment of automobile, and by the monitoring to automobile oneself state and ambient enviroment, submits necessary information, pacifies for driver
Full early warning and active control is carried out to vehicle.At present its mainly include adaptive learning algorithms, it is Lane Departure Warning System, preceding
Square collision early warning system, automatic emergency brake system etc..Advanced driving assistance system is advanced with radar and computer vision etc.
Based on sensing technology, travel safety and comfort are effectively increased.
The system architecture of driving assistance system mainly includes three perception, decision and control parts.Perception part mainly by
The composition such as radar, camera, laser radar, provides accurate environment Traffic Information for system, is decision and control section
Basis.Need to select front effective target in perception part.Effective target selection it is correct in time whether, greatly influence
The safety of system and comfort.
In order to carry out effective target selection, need to assess all actual objects to the threat degree of this vehicle safety.It is based on
The high correlation of this vehicle Future movement track and forward object trajectory can improve target by the tracking to moving target
The accuracy of selection, it can be difficult to meeting the requirement of high accuracy target selection under complex working condition.Longitudinal Safety Evaluation Index
TTC (Time-to-collision) can be used for effective target selection.Target longitudinal direction Safety Evaluation Index TTC and target
Relative distance it is related with relative velocity, be typically chosen the smallest target of TTC be effective target.However, being carried out using TTC effective
Target selection is still unable to satisfy accuracy and timeliness under different operating conditions.
Summary of the invention
The technical problems to be solved by the present invention are: how adaptively to be adjusted under different operating conditions to the virtual lane of this vehicle
It is whole, to achieve the purpose that timely and accurately capture effective target under different operating conditions.
In order to solve problem above, the present invention propose it is a kind of based on this vehicle adaptively virtual lane front effective target choosing
System and method is selected, this vehicle adaptively virtual lane adaptively virtual lane algorithm and is established by this vehicle, it can be in different operating conditions
Under the virtual lane of this vehicle is adaptively adjusted, timely and accurately select effective target under multi-state, for drive auxiliary system
The decision of system and control section provide basis.
The technical solution that the present invention solves the above technical problem is:
Based on this vehicle adaptively virtual lane front effective target select system, comprising:
The virtual lane setting module of vehicle forms this vehicle virtual vehicle for adaptively virtual lane to initialize to this vehicle
The lane region in road and nucleus；
Virtual lane adaptively adjusts module, is used for according to this vehicle movement state information and trailer-mounted radar information, to this vehicle
Virtual lane is adaptively adjusted；
Effective target selecting module calculates it for the virtual lane position of this vehicle according to locating for radar target and is in Ben Cheche
Road probability carries out effective target selection.
Front effective target selection method based on the adaptive virtual lane of this vehicle, comprising the following steps:
(1) to this vehicle, adaptively virtual lane is initialized, and forms lane region and the core space in the virtual lane of this vehicle
Domain；
(2) according to this vehicle movement state information and trailer-mounted radar information, the virtual lane of this vehicle is adaptively adjusted；
(3) the virtual lane position of this vehicle according to locating for radar target calculates it and is in this vehicle lane probability, carries out effective mesh
Mark selection.
The technical solution that the present invention further limits is:
Front effective target selection method above-mentioned based on the adaptive virtual lane of this vehicle, wherein in step (1), institute
Stating lane region is similar back taper, and the nucleus is similar taper, and the lane region and nucleus are about this
Vehicle longitudinal axis bilateral symmetry, the geometric profile and the distance dependent away from this vehicle of the lane region and nucleus, when initialization
It needs to be determined that parameter have:
(1) for objects ahead away from this vehicle distance dx=0, lane peak width is L1,2m≤L1≤3.5m, nucleus width
For H, 2m≤H≤3m；
(2) objects ahead is away from this vehicle distance dx=D, 25m≤D≤35m, and lane peak width is L2, and 2.2m≤L2≤
3.8m；
(3) for objects ahead away from this vehicle distance dx > D, lane peak width is L2；
(4) objects ahead is away from 0 < dx < D of this vehicle distance, lane peak width are as follows:
(5) away from this vehicle distance dx > 0, for nucleus width by FACTOR P, 0.002≤P≤0.0002 is true with following equation
It is fixed:
H=H-P*dx2。
Front effective target selection method above-mentioned based on the adaptive virtual lane of this vehicle, in step (2), adaptively
Adjustment specifically:
(1) when this vehicle drives into bend, the lane peak width in the virtual lane of this vehicle can be folded away from this vehicle distance D above section
Add and increases width lcurvg, with the increase of this wheel paths curvature, lcurvgIt can be gradually increased until maximum value LcurveMax, specifically:
When curvature is k=0, lcurve=0；
As curvature k=PcurveMax, lcurve=LcurveMax, PcurvemaxMaximum when increasing for lane regional broadband with curvature
Curvature threshold, when curvature is greater than PcurvemaxWhen, lane peak width is not further added by 0.002≤Pcurvemax≤0.005；
As curvature k < PcurveMax,
(2) when this vehicle is overtaken other vehicles, the virtual lane of this vehicle will do it adaptive adjustment, to meet front effective target meeting
The requirement for being captured or being discharged in time, specifically:
When this vehicle starts to overtake other vehicles and drive into fast traffic lane, the width of region part of the lane region towards fast traffic lane side increases
Add LovertakePlus, the width reduction L of the region part towards slow lane sideovertakeMinus, nucleus is to fast traffic lane side
To translation LovertakeCore；
When the completion of this vehicle overtakes other vehicles and sails back slow lane, the width meeting of region part of the lane region towards slow lane side
Increase LmergePlus, the width of the region part towards fast traffic lane side can reduce LmergeMinu, nucleus is to slow lane direction
Translate LmergeCore。
Front effective target selection method above-mentioned based on the adaptive virtual lane of this vehicle, step (3) specifically:
(1) lateral distance of objects ahead and this vehicle is dy, fore-and-aft distance dx, the curvature k of this vehicle driving trace, therefore
The lateral distance of objects ahead and the virtual lane center of this vehicle are as follows:
DyObj=dy-k*dx2/2
Probability of the objects ahead in this vehicle lane is calculated according to the lateral distance, specifically:
Current Probability p=1 of square mesh mark when this vehicle virtual lane nucleus, in this vehicle lane；
Current Probability p=0 of square mesh mark when outside the lane region in the virtual lane of this vehicle, in this vehicle lane；
Current square mesh mark is when outside the nucleus in the virtual lane of this vehicle and in the area of lane, in this vehicle lane
ProbabilityCorresponding lane peak width when wherein lObj is away from this vehicle fore-and-aft distance dx；
(2) effective target is selected: if there are one or more objects aheads, it is located in this front side target
Probability p > 0.5 in this vehicle lane is then selected wherein effective for this front side apart from the smallest objects ahead of this vehicle distance dx value
Target；If there is no objects ahead, it is located at the Probability p > 0.5 in this vehicle lane in this front side target, this vehicle is without front
Effective target.
The beneficial effects of the present invention are: to the position sensing of objects ahead, there are errors in environment sensing, not to this vehicle
The prediction for carrying out motion profile equally exists error, these on judge objects ahead whether can on this vehicle travel exist influence and select
Effective target brings difficulty, and especially this vehicle is in negotiation of bends operating condition and overtaking process, and the difficulty of effective target selection is more
It is high.Therefore, by establishing this vehicle, adaptively virtual lane and calculating objects ahead are in the probability in this vehicle lane to the present invention
Effective target selection is carried out, the virtual lane of this vehicle can adaptively be adjusted under different operating conditions, to reach in different works
The purpose of effective target can be timely and accurately captured under condition；The present invention improves the accuracy of effective target selection and in multiplexing
The stability of condition complex condition effective target selection is further necessity for promoting driving assistance system safety and comfort
Basis.
Detailed description of the invention
Fig. 1 is this vehicle of the invention adaptively virtual lane schematic diagram.
For this vehicle of the invention, adaptively virtual lane adaptively adjusts schematic diagram with this wheel paths curvature to Fig. 2-1.
Fig. 2-2 is the lane peak width and this wheel paths curvature relationship figure in the virtual lane of this vehicle of the invention.
Fig. 3-1 is that adaptively virtual lane starts passing behavior with this vehicle and adaptively adjusts schematic diagram this of the invention vehicle.
For this vehicle of the invention, adaptively virtual lane adaptively adjusts schematic diagram with this vehicle completion passing behavior to Fig. 3-2.
Fig. 4 is that present invention calculating objects ahead is located at this vehicle lane probability schematic diagram.
Specific embodiment
Embodiment 1
It is provided in this embodiment it is a kind of based on this vehicle adaptively virtual lane front effective target select system, comprising:
The virtual lane setting module of vehicle forms this vehicle virtual vehicle for adaptively virtual lane to initialize to this vehicle
The lane region in road and nucleus；
Virtual lane adaptively adjusts module, is used for according to this vehicle movement state information and trailer-mounted radar information, to this vehicle
Virtual lane is adaptively adjusted；
Effective target selecting module calculates it for the virtual lane position of this vehicle according to locating for radar target and is in Ben Cheche
Road probability carries out effective target selection.
The front effective target selection method based on the adaptive virtual lane of this vehicle of the present embodiment, comprising the following steps:
(ii) to this vehicle, adaptively virtual lane is initialized, and forms lane region and the core space in the virtual lane of this vehicle
Domain determines the geometric profile of lane region and nucleus:
As shown in Figure 1, the virtual lane of this vehicle mainly includes lane region and nucleus two parts in the present invention, wherein position
It determines and is located in lane locating for this vehicle in the target in nucleus.When this vehicle of current square mesh subject distance is closer, at this time
Would generally be higher to the angular resolution of the detection of objects ahead, and need more accurately to select effective target with safeguards system
Safety, so, this vehicle lane region can gradually constriction with smaller away from this vehicle distance.And simultaneously, with away from this vehicle distance
Increase, to objects ahead detection angular resolution can reduce, therefore nucleus can with the increase of distance constriction.Cause
This, the lane region in the virtual lane of this vehicle is in similar back taper on the whole, and nucleus is in similar taper.
The virtual lane of this vehicle is initialized, it is thus necessary to determine that the basic geometric profile in lane region and nucleus.This vehicle is empty
The initialization in quasi- lane is unrelated with this vehicle motion state, lane region, nucleus geometric profile with away from having at a distance from this vehicle
Close and about this vehicle longitudinal axis bilateral symmetry, when to this vehicle, adaptively virtual lane is initialized it needs to be determined that parameter
Have:
Away from this vehicle distance dx=0, lane peak width is L1, and nucleus width is H；
Away from this vehicle distance dx=D, lane peak width is L2；
Away from this vehicle distance dx > D, lane peak width is L2；
Away from 0 < dx < D of this vehicle distance, lane peak width are as follows:
Away from this vehicle distance dx > 0, nucleus width is determined by FACTOR P and following equation:
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, specific value needs are matched according to system and vehicle configuration.
(ii) according to this vehicle movement state information and trailer-mounted radar information, the virtual lane of this vehicle is adaptively adjusted:
The virtual lane of this vehicle after initialization can be used for front effective target selection, especially be able to satisfy this vehicle in straight way
On target selection demand when driving.Then, this vehicle virtual vehicle when this vehicle in negotiation of bends or when being overtaken other vehicles, after initialization
Road can not accurately carry out effective target selection.It is virtual to this vehicle therefore, it is necessary to carry out negotiation of bends in this vehicle or when overtaking other vehicles
Lane is adaptively adjusted.
As shown in Fig. 2-1 and Fig. 2-2, when this vehicle drives into bend, since the prediction to this wheel paths curvature is there are error,
It is necessary to increase accordingly lane region part, the lane peak width in the virtual lane of this vehicle can be folded away from this vehicle distance D above section
Add and increases width lcurve, with the increase of this wheel paths curvature, lcurveIt can be gradually increased until maximum value LcurveMax, specifically:
When curvature is k=0, lcurve=0；
As curvature k=PcurveMax, lcurve=LcurveMax；PcurvemaxMaximum when increasing for lane regional broadband with curvature
Curvature threshold, when curvature is greater than PcurvemaxWhen, lane peak width is not further added by 0.002≤Pcurvemax≤0.005；
As curvature k < PcurveMax,
When this vehicle is overtaken other vehicles, the overtaking process of this vehicle can be divided into three parts.First part is that this vehicle starts to surpass
Vehicle simultaneously changes lane to fast traffic lane；Second part is that this vehicle acceleration on fast traffic lane travels, and realization surmounts slow lane vehicle；The
Three parts are that the completion of this vehicle surmounts and changes lane to slow lane.It needs in first and Part III of overtaking process to this vehicle virtual vehicle
Road is adjusted, to meet the accuracy and timeliness of target selection.The virtual lane of this vehicle will do it adaptive adjustment, to meet
The requirement that front effective target can be captured or be discharged in time.
As shown in figure 3-1, when this vehicle starts to overtake other vehicles and drive into fast traffic lane, in order in time by the front mesh in slow lane
It is effective target, the width of region part of the lane region towards fast traffic lane side that mark, which discharges and selects objects ahead in fast traffic lane,
Increase LovertakePlus, the width reduction L of the region part towards slow lane sideovertakeMinus, nucleus is to fast traffic lane
Direction translates LovertakeCore。
As shown in figure 3-2, when the completion of this vehicle overtakes other vehicles and sails back slow lane, in order in time that front in fast traffic lane is effective
It is effective target, the width of region part of the lane region towards slow lane side that target, which discharges and selects objects ahead in slow lane,
Degree will increase LmrgePlus, the width of the region part towards fast traffic lane side can reduce LmergeMinus, nucleus is to slow lane
Direction translates LmergeCore。
(3) the virtual lane position of this vehicle according to locating for radar target calculates it and is in this vehicle lane probability, carries out effective mesh
Mark selection:
Position in the virtual lane of this vehicle according to locating for objects ahead calculates objects ahead and is in the general of this vehicle lane
Rate.As shown in figure 4, on the basis of this determining vehicle adaptively virtual lane, according to distance of the objects ahead away from this vehicle with before
The lateral distance of the adaptive virtual lane center of square mesh gauge length this vehicle, calculates the probability that objects ahead is in this vehicle lane.It is real
On border, lateral distance of the objects ahead away from the adaptive virtual lane center of this vehicle is objects ahead and this vehicle prediction locus
Lateral distance.The distance of the objects ahead obtained by environment sensing sensor is the relative distance on the basis of this vehicle coordinate, benefit
The lateral distance can be calculated with relative distance and the curvature of this vehicle driving trace.Specific algorithm are as follows:
When the lateral distance of objects ahead and this vehicle is dy, fore-and-aft distance dx, the curvature k of this vehicle driving trace, front
The lateral distance of target and the virtual lane center of this vehicle are as follows:
DyObj=dy-k*dx2/2
Probability of the objects ahead in this vehicle lane is calculated according to this lateral distance, aforementioned calculated vehicle is adaptively empty
Quasi- lane includes nucleus and two, lane region part, it may be assumed that current square mesh mark is identified and is in when nucleus
In this vehicle lane, i.e., the probability in this vehicle lane is 1；When current square mesh mark in lane region but is located at nucleus,
It is considered being likely to be in this vehicle lane, i.e. the probability in this vehicle lane is greater than 0 and less than 1, probability and objects ahead
Lateral distance away from the virtual lane center of this vehicle is in a linear relationship；When current square mesh mark is except the region of lane, really
Recognize and be not in this vehicle lane, i.e., the probability in this vehicle lane is 0.It is specific as follows:
Current Probability p=1 of square mesh mark when this vehicle virtual lane nucleus, in this vehicle lane；
Current Probability p=0 of square mesh mark when outside the lane region in the virtual lane of this vehicle, in this vehicle lane；
Current square mesh mark is when outside the nucleus in the virtual lane of this vehicle and in the area of lane, in this vehicle lane
Probability
Corresponding lane peak width when wherein lObj is away from this vehicle fore-and-aft distance dx.
Its Probability p being located in this vehicle lane is calculated to all targets in this front side.One or more front mesh if it exists
Its Probability p > 0.5 being located in this vehicle lane is marked, then selects to be wherein this vehicle apart from the smallest objects ahead of this vehicle distance dx value
Front effective target.If there is no any objects ahead, it is located at the Probability p > 0.5 in this vehicle lane in this front side target,
Then this vehicle is without front effective target.
Objects ahead selection method of the present embodiment based on the adaptive virtual lane of this vehicle, compared to the prominent of the prior art
Effect out are as follows: the accuracy of effective target selection and the stability in the selection of multi-state complex condition effective target are improved,
It is the further necessary basis for promoting driving assistance system safety and comfort.
In addition to the implementation, the present invention can also have other embodiments.It is all to use equivalent substitution or equivalent transformation shape
At technical solution, fall within the scope of protection required by the present invention.
Claims (2)
1. the front effective target selection method based on the adaptive virtual lane of this vehicle, comprising the following steps:
(i) to this vehicle, adaptively virtual lane is initialized, and forms lane region and the nucleus in the virtual lane of this vehicle；
(ii) according to this vehicle movement state information and trailer-mounted radar information, the virtual lane of this vehicle is adaptively adjusted；
(iii) the virtual lane position of this vehicle according to locating for radar target calculates it and is in this vehicle lane probability, carries out effective target choosing
It selects；
It is characterized by: the step (i) in, the lane region is similar back taper, and the nucleus is similar taper,
And the lane region and nucleus are about this vehicle longitudinal axis bilateral symmetry, the geometry wheel in the lane region and nucleus
It is wide with the distance dependent away from this vehicle, when initialization it needs to be determined that parameter have:
(1) objects ahead is away from this vehicle distance, lane peak width is L1, and 2m≤L1≤3.5m, nucleus width is H,
2m≤H≤3m；
(2) objects ahead is away from this vehicle distance25m≤D≤35m, lane peak width are L2,2.2m≤L2≤3.8m；
(3) objects ahead is away from this vehicle distance, lane peak width is L2；
(4) objects ahead is away from this vehicle distance, lane peak width are as follows:
；
(5) away from this vehicle distance, for nucleus width by FACTOR P, 0.002≤P≤0.0002 is determining with following equation:
。
2. the front effective target selection method as described in claim 1 based on the adaptive virtual lane of this vehicle, feature exist
In:
The step is (iii) specifically:
(1) the lateral distance of objects ahead and this vehicle is dy, fore-and-aft distance dx, the curvature k of this vehicle driving trace, therefore front
The lateral distance of target and the virtual lane center of this vehicle are as follows:
Probability of the objects ahead in this vehicle lane is calculated according to the lateral distance, specifically:
Current probability of square mesh mark when this vehicle virtual lane nucleus, in this vehicle lane；
Current probability of square mesh mark when outside the lane region in the virtual lane of this vehicle, in this vehicle lane；
Probability of current square mesh mark when outside the nucleus in the virtual lane of this vehicle and in the area of lane, in this vehicle lane, whereinFor away from this vehicle fore-and-aft distanceWhen corresponding lane peak width；
(2) effective target is selected: if there are one or more objects aheads, it is located at this vehicle in this front side target
Probability p > 0.5 in lane then selects to be wherein this front side effective target apart from this vehicle the smallest objects ahead of distance dx value；
If there is no objects ahead, it is located at Probability p > 0.5 in this vehicle lane in this front side target, this vehicle is without the effective mesh in front
Mark.
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 CN105631217A (en) | 2016-06-01 |
| CN105631217B true 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) |
Families Citing this family (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| DE102016214097A1 (en) * | 2016-07-29 | 2018-02-01 | Bayerische Motoren Werke Aktiengesellschaft | Method and device for carrying out an at least partially automated driving maneuver |
| 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 |
| DE102017208245A1 (en) * | 2017-05-16 | 2018-11-22 | Continental Automotive Gmbh | Method and device for the goal-based prediction of dynamic objects |
| KR102499398B1 (en) * | 2017-08-09 | 2023-02-13 | 삼성전자 주식회사 | Lane detection method and apparatus |
| CN110550030B (en) * | 2019-09-09 | 2021-01-12 | 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 |
| CN112703506B (en) * | 2020-04-22 | 2022-04-08 | 华为技术有限公司 | Lane line detection method and device |
| 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 |
| CN112706785B (en) * | 2021-01-29 | 2023-03-28 | 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 |
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 |
Also Published As
| Publication number | Publication date |
|---|---|
| CN105631217A (en) | 2016-06-01 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105631217B (en) | Front effective target selection method based on the adaptive virtual lane of this vehicle | |
| JP6622148B2 (en) | Ambient environment recognition device | |
| US10303959B2 (en) | Controlling host vehicle based on a predicted state of a parked vehicle | |
| US10569767B2 (en) | Vehicle control apparatus and vehicle control method | |
| KR102399963B1 (en) | Road plane output with lateral slope | |
| US9516277B2 (en) | Full speed lane sensing with a surrounding view system | |
| CN106164998B (en) | Path prediction meanss | |
| JP7156394B2 (en) | Other Vehicle Motion Prediction Method and Other Vehicle Motion Prediction Device | |
| JP6614108B2 (en) | Vehicle control apparatus and vehicle control method | |
| US10493987B2 (en) | Target-lane relationship recognition apparatus | |
| JP6363518B2 (en) | Lane marking recognition system | |
| WO2016047689A1 (en) | Device for estimating axial misalignment amount of beam sensor | |
| WO2016117603A1 (en) | Vehicle travel control device and travel control method | |
| US20200371534A1 (en) | Autonomous driving apparatus and method | |
| CN111352413A (en) | Omnidirectional sensor fusion system and method and vehicle comprising fusion system | |
| WO2019172104A1 (en) | Moving body behavior prediction device | |
| JP6544168B2 (en) | Vehicle control device and vehicle control method | |
| CN111216707A (en) | Apparatus and method for controlling autonomous driving of vehicle | |
| CN103381825B (en) | Use the full speed lane sensing of multiple photographic camera | |
| CN114559923A (en) | Automatic emergency obstacle avoidance system of unmanned vehicle and control method thereof | |
| CN112885143B (en) | System and method for correcting curvature information using surrounding vehicles | |
| US20200369296A1 (en) | Autonomous driving apparatus and method | |
| Hsu et al. | Implementation of car-following system using LiDAR detection | |
| JP2018067130A (en) | Vehicle control device and vehicle control method | |
| WO2018198769A1 (en) | Surrounding environment recognition device, display control 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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |