CN109211255A - Method for planning a route for a motor vehicle having an automatic vehicle system - Google Patents
Method for planning a route for a motor vehicle having an automatic vehicle system Download PDFInfo
- Publication number
- CN109211255A CN109211255A CN201810736269.4A CN201810736269A CN109211255A CN 109211255 A CN109211255 A CN 109211255A CN 201810736269 A CN201810736269 A CN 201810736269A CN 109211255 A CN109211255 A CN 109211255A
- Authority
- CN
- China
- Prior art keywords
- route
- positioning accuracy
- vehicle
- selected route
- verification
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 48
- 230000007613 environmental effect Effects 0.000 claims abstract description 42
- 238000001514 detection method Methods 0.000 claims abstract description 32
- 238000005259 measurement Methods 0.000 claims description 44
- 238000012795 verification Methods 0.000 claims description 40
- 238000012549 training Methods 0.000 claims description 15
- 238000013179 statistical model Methods 0.000 claims description 4
- 230000003044 adaptive effect Effects 0.000 abstract 1
- 230000004807 localization Effects 0.000 abstract 1
- 238000013528 artificial neural network Methods 0.000 description 9
- 230000008447 perception Effects 0.000 description 2
- 241000208340 Araliaceae Species 0.000 description 1
- 235000005035 Panax pseudoginseng ssp. pseudoginseng Nutrition 0.000 description 1
- 235000003140 Panax quinquefolius Nutrition 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000002349 favourable effect Effects 0.000 description 1
- 235000008434 ginseng Nutrition 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 210000004218 nerve net Anatomy 0.000 description 1
- 230000008520 organization Effects 0.000 description 1
- 238000001556 precipitation Methods 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
- G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
- G01C21/26—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 specially adapted for navigation in a road network
- G01C21/34—Route searching; Route guidance
- G01C21/3453—Special cost functions, i.e. other than distance or default speed limit of road segments
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
- G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
- G01C21/26—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 specially adapted for navigation in a road network
- G01C21/34—Route searching; Route guidance
- G01C21/3446—Details of route searching algorithms, e.g. Dijkstra, A*, arc-flags, using precalculated routes
Landscapes
- Engineering & Computer Science (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Automation & Control Theory (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Navigation (AREA)
- Traffic Control Systems (AREA)
Abstract
The invention relates to a method for planning a route for a motor vehicle having an automatic vehicle system, which takes into account route-specific positionability and the performance of the automatic vehicle system, so that an adaptive routing can be implemented, wherein a feasibility analysis of at least one route is created, wherein the feasibility analysis comprises the following steps: selecting a route to be investigated from a starting point to a target point; determining an environmental condition on the selected route that is not associated with the vehicle; determining an expected detection rate of landmarks on the selected route suitable for vehicle localization by using environmental conditions not associated with the vehicle; determining a desired positioning accuracy on the selected route by using the desired detection rate; it is determined whether the desired positioning accuracy is sufficient to be supported by the automated vehicle system for traversing the selected route.
Description
Technical field
The present invention relates to a kind of methods for for the motor vehicle programme path with automotive vehicle system.In addition, this hair
Bright to be related to a kind of motor vehicle with automotive vehicle system, wherein the Vehicular system is designed to execute route planning method.
Background technique
It modern driving assistance system (English: Advanced Driver Assistance Systems (ADAS)) and is used for
The increasingly automated Vehicular system of UAD (city automatic Pilot) has increasing need for understanding vehicle environmental and situational awareness in detail.It passes
Sensor measurement data is used as perceiving the basis of vehicle environmental.Thus object can be extracted by means of so-called detection algorithm, borrowed
Vehicle environmental can be described and analyze by helping these objects.Modern environment sensor (such as three-dimensional video-frequency video camera or laser scanner)
The bulk information that can be obtained from vehicle environmental for example in form of placemarks is combined with detection algorithm.These terrestrial references include traffic mark
Will, traffic lights, traffic lane line etc..The object detected or the terrestrial reference detected can be used for carrying out vehicle location again.Here,
The performance of entire automotive vehicle system depends primarily on the performance of environmental sensor.
Modern lane keeps auxiliary system by the reliable detection of traffic lane line and vehicle relative position.From Borrmann,
Et al. J.M. " case study for the system embedment that STELLaR-is identified about traffic lights ", intelligent transportation system (ITSC),
IEEE in 2014, the 17th international conference, the 1258th, 1265,8-11 pages, in 10 months 2014 a kind of traffic lights identification side known
Formula, wherein having inquired into the very high hardware requirement to object detection algorithms.
In Thrun, " terrestrial reference for finding Mobile Robotics Navigation " of S., robot and automation, minutes in 1998,
IEEEE international conference in 1998, page 958,963, illustrates in 16-20 days in May, 1998 a kind of for selecting vehicle volume 2
Positioningly calibration method.
Vehicle location precision needed for automotive vehicle system is more than the performance for depending on environment sensor system.In addition,
The selection of environmental condition and detection algorithm may also can generate significant impact.The performance of entire Vehicular system and route to be passed through
It is directly related with environmental condition known on the route.
Summary of the invention
The object of the present invention is to provide a kind of sides for for the motor vehicle programme path with automotive vehicle system
Method, this method consider the performance of route specific localizability and automotive vehicle system, so that the road for adapting to situation can be realized
Line gauge is drawn.
In addition, the present invention also aims to provide a kind of motor vehicle with automotive vehicle system, provide and adapt to feelings
The route planning of condition.
In order to realize the purpose, a kind of side for for the motor vehicle programme path with automotive vehicle system is proposed
Method, wherein create at least one route trafficability analysis, wherein the trafficability analysis the following steps are included:
The route to be investigated from origin-to-destination is selected,
Environmental condition unrelated with vehicle on selected route is measured,
The terrestrial reference for being suitable for that vehicle location is carried out on selected route is determined by using the environmental condition unrelated with vehicle
Expection verification and measurement ratio,
Expection positioning accuracy on selected route is determined by using expected verification and measurement ratio,
Measure whether expected positioning accuracy is enough to cross selected route with being supported by automotive vehicle system.
Automotive vehicle system can be for assisting driving and/or increasingly automated driving and/or the driving of automatic Pilot
Member's auxiliary system.
Advantageously, considering the specific localizability of sufficiently accurate route and whole system in route planning method
Performance, the especially performance of automotive vehicle system.Following route can be classified as impassabitity, i.e., along the route known
Environmental condition under and cannot achieve using environment sensor system workable for Vehicular system the positioning of meet demand.Then may be used
Around such route or route segment.This method uses the edge unrelated with vehicle to the environmental condition of exam arrangement as input
Variable.It can be obtained from positioning map suitable for the terrestrial reference of vehicle location.
This method can realize programme path, meet need on these routes with what higher possibility ensured Vehicular system
The performance asked, to help to generate favorable influence to the robustness of automotive vehicle system.Automotive vehicle is used for known
The route planning method of system is compared, and is in addition also used the environmental condition unrelated with vehicle, i.e., is not related to vehicle and/or automatic vehicle
The environmental condition of system.However, the relevant environmental condition of vehicle can also reside in the calculating of expected positioning accuracy.Vehicle phase
The environmental condition of pass may be, for example, the robustness of sensor efficiency or terrestrial reference detection algorithm.
Environmental sensor can be stereo camera or laser scanner or other suitable sensor devices.
In the method, the step of determining the expection verification and measurement ratio for being suitable for the terrestrial reference of vehicle location is not necessarily in individual method
It carries out, but can also be lain in the determination of expected positioning accuracy in step.Route planning method it is critical that by using
Determining expected positioning accuracy with the incoherent environmental condition of vehicle on selected route and then measuring expected positioning accuracy is
It is no to be enough to cross selected route with being supported by automotive vehicle system.Such as it is also feasible that by means of parameterized model and/or mind
Other methods and/or statistical model through network or machine training are to determine expected positioning accuracy or measure expected positioning accuracy
It is no to be enough to cross selected route with being supported by automotive vehicle system.In the case where parameterized model, in the detection of parametric form
Rate can explicitly or implicitly include in the method.If positioning accuracy is measured by means of neural network etc., in nerve net
Expected verification and measurement ratio is impliedly considered in the weight trained in network.Rate also be will test in statistical model by statistical weight includes
In the measurement of positioning accuracy.For understanding the present invention importantly, positioning accuracy implies or clearly depends on verification and measurement ratio (i.e.
The percentage of detectable terrestrial reference on selected route) product with the terrestrial reference quantity being present on selected route.
In addition, verification and measurement ratio that is implicit or clearly inputting in this method may also depend upon terrestrial reference present on selected route
Type.For example, traffic sign, lane boundary, traffic light signals, trees or building verification and measurement ratio may be different.In addition, detection
Rate may also depend upon the efficiency of the sensor device of environment sensor system.Used detection algorithm is for certain types ofly
Target verification and measurement ratio can also have different efficiency.By explicitly or implicitly considering verification and measurement ratio, can separately or cooperatively combine all
Above-mentioned factor determines expected positioning accuracy and then measures whether the expection positioning accuracy is enough by automated driving system branch
Cross selected route with holding.
It is preferably provided that the environmental condition unrelated with vehicle be selected route traffic density and/or weather condition and/or
Condition of road surface.
Weather condition, traffic total amount and traffic density and condition of road surface may influence the detection performance of sensing system,
To influence the verification and measurement ratio of different type terrestrial reference.Higher traffic density especially may cause a certain proportion of on selected route
Terrestrial reference at least temporarily by the occlusion in front of ambient sensor system, thus can reduce verification and measurement ratio and positioning accuracy.Cause
This, advantageously considers the correlation of positioning accuracy and present weather conditions and traffic total amount.Such as it can be by inquiring weather data
Library or traffic database determine the environmental condition unrelated with vehicle, especially weather condition and traffic total amount.
It is preferably provided that determine the shielding rate of the terrestrial reference on selected route, wherein it is preferred that by using environmental condition and/or
Suitable terrestrial reference type determines shielding rate, wherein determining positioning accuracy and/or verification and measurement ratio by using shielding rate.
Shielding rate advantageously has mapped influence of the environmental condition related to route and unrelated with vehicle to positioning accuracy.?
This, shielding rate may also depend upon the type of terrestrial reference.Therefore, upper pavement surface lower height is located at for environment sensor system
The traffic total amount and vehicle total amount that the terrestrial reference at place is more likely to be increased is blocked, this is to reduce the verification and measurement ratio of this terrestrial reference.Phase
Instead, the shielding rate for being arranged to higher terrestrial reference (such as traffic light signals) is lower.
Shielding rate can also be implied or clearly considered in the method.In parameterized model or neural network, it can pass through
Parameter or training weight carry out implicit consideration.
It more preferably provides, shielding rate and/or verification and measurement ratio and/or positioning accuracy is determined by using parameterized model,
Middle parameterized model is preferably machine training pattern, wherein more preferably by using previous passability to analyze, especially
By using previous environmental condition and/or previously determined verification and measurement ratio and/or previously determined shielding rate and/or previously determined
Positioning accuracy and/or the performance of sensor device and/or the detection algorithm of automotive vehicle system carry out training machine training pattern.
It can be advantageous by using parameterized model or determine shielding rate and/or verification and measurement ratio by using neural network
And/or positioning accuracy.Here, parameterized model or neural network be based on the trafficability analysis previously carried out, i.e., by using
The result of the trafficability analysis carried out before currently executing this method determines shielding rate and/or verification and measurement ratio and/or positioning
Precision.
Therefore it could dictate that, before carrying out trafficability analysis, especially before executing to the selection of exam arrangement, ginseng
Numberization model or neural network can undergo the training stage.
In one preferred embodiment, shielding rate is determined by using parameterized model, wherein as parametrization mould
The input variable of type using on current weather information and/or selected route Current traffic total amount and/or selected route on exist
Terrestrial reference type.
The system is based particularly on neural network based on the model parameterized with machine training method, in weather and friendship
Logical data and the environmental perception module used about the other information of environment, in vehicle side or environmental sensor and produced
Each terrestrial reference type detection probability between establish relevance.
Further preferably provide, by using shielding rate and/or on selected route detectable terrestrial reference especially
The detection of maximum quantity and/or number density and/or type and/or the performance and/or automotive vehicle system of sensor device
The precision of the precision, particularly GPS data of algorithm and/or environmental condition and/or location data determines verification and measurement ratio.
May be blocked on selected route by environmental condition (such as increased traffic total amount) using shielding rate determination with
The relevant terrestrial reference ratio of type.Then, verification and measurement ratio depends on shielding rate, and additionally depends on sensor or sensor device
Efficiency.In addition, verification and measurement ratio may also depend upon the efficiency of detection algorithm, wherein can be used especially for different types of terrestrial reference
Different detection algorithms.
It further preferably could dictate that, determine positioning accuracy by means of statistical model, wherein preferably by using expection
Verification and measurement ratio and/or expected shielding rate and/or along selected route terrestrial reference quantity and/or number density and/or type determine
Positioning accuracy.
Positioning accuracy explicitly or implicitly depend on expected verification and measurement ratio and along selected route terrestrial reference especially and type
Relevant quantity or number density.Here, verification and measurement ratio may be blocked the influence of rate.
It advantageously further could dictate that, identified positioning accuracy be compared with preset threshold value, wherein if fixed
Position precision is less than the threshold value, then the driver of motor vehicle is enable to have a possibility that crossing selected route manually and/or to another
Route executes new trafficability analysis.
In the method, driver can be notified when being lower than location accuracy threshold, vehicle is by using automotive vehicle system
Cannot be by selected route, and can then plan variation route.
Alternatively or additionally, the driver of motor vehicle can have an opportunity to determine he whether want to cross manually original plan or
The route of selection or desired receiving automatically, thus may longer strokes.
Advantageously, Global motion planning can be carried out to the general line of automotive vehicle system in the target point of definition and planned again.
Preferably provide whether be enough to cross selected route with being supported by automotive vehicle system to expected positioning accuracy
Measurement in consider localizability as optimal as possible and/or be optimized to the measurement as far as possible with sufficiently accurate positioning accuracy
On shortest section.
It further preferably could dictate that, preferably when positioning accuracy is greater than or equal to threshold value, determination is suitable for by automotive vehicle
System crosses the sensor device and/or detection algorithm of selected route with supporting.
It is beneficial to help this method and determines which sensor device is suitable for being marked with which type ofly and cross institute's routing
Line.The system is based on following situations especially with parameterized model, i.e., in weather data, traffic data and about its of environment
His information, vehicle side sensor device or environmental perception module and generated each terrestrial reference type detection probability it
Between establish relevance.By this method together with for example can from positioning map obtain about the information of placemark density and according to each
Can detect terrestrial reference type known to the locating module of Vehicular system can measure, if some road can be currently crossed by Vehicular system
Section.Here, considering the detection algorithm of the different expression form of vehicle side by this method, that is, depend on existing sensor device
Or depending on each Vehicular system of existing detection algorithm may other Vehicular systems cannot region in travel.Can have thus
It determines and is especially in which section of route using which sensor device and/or which detection algorithm to cross the road sharply
Line.
This method can detect terrestrial reference using weather data, traffic information, about the information of GPS accuracy and about along route
Density information as input variable.Determine the model of its parameter for that can do to selected route by machine training method
Whether following judgement out can travel through the route, and if so, which kind of detection algorithm can pass through the route using.
Another solution for the problem of present invention is based on is, provides a kind of with the motor-driven of automotive vehicle system
Vehicle, wherein the automotive vehicle system is designed to execute the above method.
It further preferably provides, automotive vehicle system is designed to auxiliary and drives and/or supermatic drive
It sails and/or automatic Pilot.
Detailed description of the invention
Below with reference to the accompanying drawings the present invention will be described in detail.Wherein:
Fig. 1 shows the flow chart of the route planning method for the motor vehicle with automotive vehicle system,
Fig. 2 shows the general views of the input variable of the training stage for parameterized model.
Specific embodiment
Fig. 1 shows the flow chart of the route planning method for the motor vehicle with automotive vehicle system.
In the first optional step S1, in the training stage of parameterized model, particularly neural network, based on about day
The other information source of the information of destiny evidence, the verification and measurement ratio of various types terrestrial reference and such as traffic data, preferably corresponding known
Position, which is between these input variables and the expection shielding rate of each terrestrial reference type, establishes relevance.The position can for example pass through
GPS, dead reckoning or vehicle positioning determine.
In applicable cases, this method is since the trafficability analysis in step S2.In step s 2, according to starting point and
The current route to be investigated of target point Selection utilization automotive vehicle system, which may include navigation system.
Then, in step s3, environmental condition unrelated with vehicle on selected route is determined.These environmental conditions can be
Current traffic total amount or present weather conditions on selected route, and determined by inquiry database.In addition, from positioningly
Expected terrestrial reference is obtained in figure.
In subsequent step S4, using parameterized model to determine current expected each phase on route to be investigated
Hope the shielding rate of terrestrial reference type.Here, also use using Current traffic total amount and/or present weather conditions and when necessary for
Selected route is stored in the terrestrial reference in positioning map as input variable.
In step s 5, it is determined by using the environmental condition unrelated with vehicle and is suitable for vehicle location on selected route
The verification and measurement ratio of terrestrial reference.Here, shielding rate determining in step s 4 is taken into account in the determination of verification and measurement ratio.In addition, especially existing
It is contemplated that condition relevant to vehicle, such as different sensors device are (such as three-dimensional under known environmental condition (weather, traffic etc.)
Camera or laser system) detection efficiency and different type terrestrial reference possible detection algorithm performance.
Then, in step s 6, the expection positioning accuracy on selected route is determined by using expected verification and measurement ratio.Change speech
It, specific shielding rate, the quantity of verification and measurement ratio and the terrestrial reference existing for the route, number density and type combination can be by means of system
Count estimation of the model realization to positioning accuracy.
Inspection for specific terrestrial reference type, especially as terrestrial reference on selected route or present on the section of selected route
The product of survey rate and number density obtains the positioning accuracy of selected route.
Measure whether expected positioning accuracy is enough to cross institute's routing with being supported by automotive vehicle system in another step S7
Line.The necessity of programme path is determined again based on trafficability analysis as a result,.It, can be according to this if this is necessary
Method executes, and wherein this method starts the analysis of trafficability in step S2 with new selected route again.
If positioning accuracy is enough to cross selected route with being supported by automotive vehicle system, pass through in another step S8
This method is additionally specified by Vehicular system sensor device ready for use and detection algorithm for being classified as transitable route.
In addition, can create for the plan along selected route change detection algorithm, the terrestrial reference type of variation can be responded.
For example, being automotive vehicle systems organization route along main roads.It can get enough environmental informations along the route, from
And the sufficiently accurate positioning of Vehicular system can be realized by all terrestrial references of detection " traffic sign " type.
However, expecting to have a large amount of traffic on the route in peak period.Realize the automotive vehicle system of this method
The verification and measurement ratio that can determine whether the traffic condition and institute's programme path, since the expection based on the environmental condition unrelated with vehicle is blocked
Rate, the verification and measurement ratio are significantly lower than 100%.However, good enough and especially greater than predetermined threshold value is determined as by the system
It is expected that positioning accuracy.The system, which can be realized, as a result, crosses selected route with supporting by automotive vehicle system.
In another situation, precipitation may occur in one day same time.This method redefines verification and measurement ratio.Due to
Atrocious weather condition, the verification and measurement ratio is not high enough, this is particularly depending on the increased shielding rate as caused by severe weather conditions.
Thus sufficiently accurate positioning accuracy can not be obtained.Then can select alternative route in the scope of this method, and into
It is assessed in the scope of the trafficability analysis of one step.New route is by the less road being traveling, to have lower
Shielding rate.Optionally, driver can be notified to have planned longer route by man-machine interface, and now can be on the road
Automatic running on line is selected between the manual traveling in shorter route.
Fig. 2 shows the general views of parameterized model, particularly the input variable of the training stage of neural network.
It is given in the training stage as the input parameter in neural network 14:
GPS data 10；
Traffic data 11；
Weather data 12；With
Previous verification and measurement ratio 13.
The model 15 of terrestrial reference detection probability relevant to type under different environmental conditions is obtained by the training stage.
Claims (10)
1. a kind of method for for the motor vehicle programme path with automotive vehicle system, wherein creating at least one route
Trafficability analysis, wherein the trafficability analysis the following steps are included:
The route to be investigated from starting point to target point is selected,
Environmental condition unrelated with vehicle on selected route is measured,
It is determined on selected route by using the environmental condition unrelated with vehicle suitable for the pre- of the terrestrial reference of vehicle location
Phase verification and measurement ratio,
Expection positioning accuracy on selected route is determined by using the expected verification and measurement ratio,
Measure whether the expected positioning accuracy is enough to cross selected route with being supported by the automotive vehicle system.
2. according to the method described in claim 1, wherein the environmental condition unrelated with vehicle is that the traffic of selected route is close
Degree and/or weather condition and/or condition of road surface.
3. method according to claim 1 or 2, wherein the shielding rate of the terrestrial reference on selected route is determined, wherein preferably
The shielding rate is determined by using environmental condition and/or suitable terrestrial reference type, wherein coming by using the shielding rate
Determine the positioning accuracy and/or the verification and measurement ratio.
4. according to the method described in claim 3, wherein measuring the shielding rate and/or described by using parameterized model
Verification and measurement ratio and/or the positioning accuracy, wherein the parameterized model is preferably machine training pattern, wherein further preferably
It is analyzed by using previous trafficability, especially by using previous environmental condition and/or previously determined verification and measurement ratio
And/or the performance and/or automatic vehicle of previously determined shielding rate and/or previously determined positioning accuracy and/or sensor device
The detection algorithm of system trains the machine training pattern.
5. method according to any of the preceding claims, wherein by using the shielding rate and/or in institute's routing
The quantity of detectable terrestrial reference, particularly maximum quantity and/or number density and/or type and/or sensor device on line
Performance and/or the automotive vehicle system detection algorithm and/or the environmental condition and/or location data, particularly GPS
The precision of data determines the verification and measurement ratio.
6. method according to any of the preceding claims, wherein being determined the positioning accurate by means of statistical model
Degree, wherein preferably by using the expected verification and measurement ratio and/or the expected shielding rate and/or along the terrestrial reference of selected route
Quantity and/or number density and/or type determine the positioning accuracy.
7. method according to any of the preceding claims, wherein by identified positioning accuracy and preset threshold value into
Row compares, wherein enabling the driver of the motor vehicle to have if the positioning accuracy is less than the threshold value and sailing manually
It a possibility that crossing selected route and/or new trafficability is executed to another route analyzes.
8. method according to any of the preceding claims, wherein be preferably greater than or equal to institute in the positioning accuracy
When stating threshold value, determine that the sensor device and/or detection that are suitable for crossing selected route with being supported by the automotive vehicle system are calculated
Method.
9. a kind of motor vehicle with automotive vehicle system according to any one of the preceding claims.
10. motor vehicle according to claim 9, wherein the driver assistance system be designed to auxiliary drive and/
Or supermatic driving and/or automatic Pilot.
Applications Claiming Priority (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| DE102017211556.4A DE102017211556A1 (en) | 2017-07-06 | 2017-07-06 | Method for route planning for a motor vehicle with an automated vehicle system and motor vehicle with an automated vehicle system |
| DE102017211556.4 | 2017-07-06 |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109211255A true CN109211255A (en) | 2019-01-15 |
| CN109211255B CN109211255B (en) | 2022-07-26 |
Family
ID=64666390
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810736269.4A Active CN109211255B (en) | 2017-07-06 | 2018-07-06 | Method for planning a route for a motor vehicle having an automatic vehicle system |
Country Status (3)
| Country | Link |
|---|---|
| CN (1) | CN109211255B (en) |
| DE (1) | DE102017211556A1 (en) |
| FR (1) | FR3068777B1 (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109808615A (en) * | 2019-03-22 | 2019-05-28 | 北京经纬恒润科技有限公司 | A kind of automatic Pilot method and device |
| CN111024084A (en) * | 2019-12-17 | 2020-04-17 | 国汽(北京)智能网联汽车研究院有限公司 | Automatic driving method, device, equipment and storage medium for automatic driving vehicle |
| WO2021016920A1 (en) * | 2019-07-31 | 2021-02-04 | 深圳市大疆创新科技有限公司 | Method, system and device for identifying accessibility, and computer-readable storage medium |
| CN114112421A (en) * | 2021-09-30 | 2022-03-01 | 东风汽车集团股份有限公司 | Automatic driving test method and device, electronic equipment and storage medium |
| CN114729815A (en) * | 2019-11-13 | 2022-07-08 | 梅赛德斯-奔驰集团股份公司 | Method for recognizing a distance traveled |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| GB2612910B (en) * | 2020-03-03 | 2023-12-27 | Motional Ad Llc | Control architectures for autonomous vehicles |
| DE102022203261A1 (en) * | 2022-04-01 | 2023-10-05 | Robert Bosch Gesellschaft mit beschränkter Haftung | Method for predicting the availability of a feature-based localization of a vehicle and method for controlling a vehicle |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20050216182A1 (en) * | 2004-03-24 | 2005-09-29 | Hussain Talib S | Vehicle routing and path planning |
| CN103370669A (en) * | 2011-02-16 | 2013-10-23 | 西门子公司 | Method for the autonomous localization of a driverless, motorized vehicle |
| CN104973071A (en) * | 2014-03-04 | 2015-10-14 | 沃尔沃汽车公司 | Apparatus and method for continuously establishing boundary for autonomous driving availability and automotive vehicle comprising such apparatus |
| CN105122327A (en) * | 2013-04-03 | 2015-12-02 | 罗伯特·博世有限公司 | Automatic travelling of a route |
| CN106103232A (en) * | 2014-04-09 | 2016-11-09 | 日立汽车系统株式会社 | Travel controlling system, on-vehicle display and drive-control system |
| CN106292649A (en) * | 2015-06-23 | 2017-01-04 | 沃尔沃汽车公司 | For contributing to the apparatus and method that automatic autonomous driving aid system toggles |
| US20170108865A1 (en) * | 2015-10-20 | 2017-04-20 | Robert Bosch Gmbh | Method for selecting an optimized trajectory |
| CN106908775A (en) * | 2017-03-08 | 2017-06-30 | 同济大学 | A kind of unmanned vehicle real-time location method based on laser reflection intensity |
-
2017
- 2017-07-06 DE DE102017211556.4A patent/DE102017211556A1/en active Pending
-
2018
- 2018-07-04 FR FR1856150A patent/FR3068777B1/en active Active
- 2018-07-06 CN CN201810736269.4A patent/CN109211255B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20050216182A1 (en) * | 2004-03-24 | 2005-09-29 | Hussain Talib S | Vehicle routing and path planning |
| CN103370669A (en) * | 2011-02-16 | 2013-10-23 | 西门子公司 | Method for the autonomous localization of a driverless, motorized vehicle |
| CN105122327A (en) * | 2013-04-03 | 2015-12-02 | 罗伯特·博世有限公司 | Automatic travelling of a route |
| CN104973071A (en) * | 2014-03-04 | 2015-10-14 | 沃尔沃汽车公司 | Apparatus and method for continuously establishing boundary for autonomous driving availability and automotive vehicle comprising such apparatus |
| CN106103232A (en) * | 2014-04-09 | 2016-11-09 | 日立汽车系统株式会社 | Travel controlling system, on-vehicle display and drive-control system |
| CN106292649A (en) * | 2015-06-23 | 2017-01-04 | 沃尔沃汽车公司 | For contributing to the apparatus and method that automatic autonomous driving aid system toggles |
| US20170108865A1 (en) * | 2015-10-20 | 2017-04-20 | Robert Bosch Gmbh | Method for selecting an optimized trajectory |
| CN106908775A (en) * | 2017-03-08 | 2017-06-30 | 同济大学 | A kind of unmanned vehicle real-time location method based on laser reflection intensity |
Non-Patent Citations (1)
| Title |
|---|
| SEBASTIAN THRUN: "Finding landmarks for mobile robot navigation", 《PROCEEDINGS OF THE 1998 IEEE INLERNATIONAL CONFERENCE ON ROBOTICS & AUTOMATION》 * |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109808615A (en) * | 2019-03-22 | 2019-05-28 | 北京经纬恒润科技有限公司 | A kind of automatic Pilot method and device |
| WO2021016920A1 (en) * | 2019-07-31 | 2021-02-04 | 深圳市大疆创新科技有限公司 | Method, system and device for identifying accessibility, and computer-readable storage medium |
| CN114729815A (en) * | 2019-11-13 | 2022-07-08 | 梅赛德斯-奔驰集团股份公司 | Method for recognizing a distance traveled |
| CN111024084A (en) * | 2019-12-17 | 2020-04-17 | 国汽(北京)智能网联汽车研究院有限公司 | Automatic driving method, device, equipment and storage medium for automatic driving vehicle |
| CN114112421A (en) * | 2021-09-30 | 2022-03-01 | 东风汽车集团股份有限公司 | Automatic driving test method and device, electronic equipment and storage medium |
| CN114112421B (en) * | 2021-09-30 | 2023-06-20 | 东风汽车集团股份有限公司 | Automatic driving test method and device, electronic equipment and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| FR3068777B1 (en) | 2021-09-17 |
| DE102017211556A1 (en) | 2019-01-10 |
| CN109211255B (en) | 2022-07-26 |
| FR3068777A1 (en) | 2019-01-11 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109211255A (en) | Method for planning a route for a motor vehicle having an automatic vehicle system | |
| EP3673407B1 (en) | Automatic occlusion detection in road network data | |
| US9459626B2 (en) | Learning signs from vehicle probes | |
| CN109902899B (en) | Information generation method and device | |
| US10553117B1 (en) | System and method for determining lane occupancy of surrounding vehicles | |
| CN107310550B (en) | Road vehicles travel control method and device | |
| CN109405841A (en) | Method and apparatus for participating in map abnormality detection and correction | |
| EP3789733A1 (en) | Turn lane configuration | |
| RU2661963C1 (en) | Device for calculating route of motion | |
| CN102800207A (en) | System and method for traffic signal detection | |
| CN111275997B (en) | Method for providing map data, motor vehicle and central data processing device | |
| Min et al. | Sae level 3 autonomous driving technology of the etri | |
| CN108986502B (en) | Inductive loop detection system and method | |
| CN103996298B (en) | A kind of driver behavior modeling method and device | |
| US20190360820A1 (en) | Method and device for executing at least one measure for increasing the safety of a vehicle | |
| Revilloud et al. | An improved approach for robust road marking detection and tracking applied to multi-lane estimation | |
| CN109515439A (en) | Automatic Pilot control method, device, system and storage medium | |
| CN112394725A (en) | Predictive and reactive view-based planning for autonomous driving | |
| CN110599853A (en) | Intelligent teaching system and method for driving school | |
| US20230150549A1 (en) | Hybrid log simulated driving | |
| US11820397B2 (en) | Localization with diverse dataset for autonomous vehicles | |
| JP2021120683A (en) | Output device, control method, program, and storage medium | |
| CN110765224A (en) | Processing method of electronic map, vehicle vision repositioning method and vehicle-mounted equipment | |
| CN116817957A (en) | Unmanned vehicle driving path planning method and system based on machine vision | |
| CN112985825B (en) | Method for determining the ride stability of an autopilot system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |