WO2023046521A1 - PRÜFUNG EINER DIGITALEN STRAßENKARTE AUF LOKALE PLAUSIBILITÄT - Google Patents
PRÜFUNG EINER DIGITALEN STRAßENKARTE AUF LOKALE PLAUSIBILITÄT Download PDFInfo
- Publication number
- WO2023046521A1 WO2023046521A1 PCT/EP2022/075330 EP2022075330W WO2023046521A1 WO 2023046521 A1 WO2023046521 A1 WO 2023046521A1 EP 2022075330 W EP2022075330 W EP 2022075330W WO 2023046521 A1 WO2023046521 A1 WO 2023046521A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- road map
- digital road
- determined
- pose
- behavior
- Prior art date
Links
- 238000000034 method Methods 0.000 claims abstract description 21
- 230000004044 response Effects 0.000 claims abstract description 12
- 238000004590 computer program Methods 0.000 claims description 6
- 230000008859 change Effects 0.000 claims description 4
- 230000006872 improvement Effects 0.000 claims description 4
- 230000009471 action Effects 0.000 description 4
- 238000010276 construction Methods 0.000 description 3
- 238000012937 correction Methods 0.000 description 3
- 230000004807 localization Effects 0.000 description 3
- 238000010606 normalization Methods 0.000 description 3
- 230000001427 coherent effect Effects 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000012544 monitoring process 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
- G01C21/28—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 specially adapted for navigation in a road network with correlation of data from several navigational instruments
- G01C21/30—Map- or contour-matching
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/56—Context or environment of the image exterior to a vehicle by using sensors mounted on the vehicle
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/09—Arrangements for giving variable traffic instructions
- G08G1/0962—Arrangements for giving variable traffic instructions having an indicator mounted inside the vehicle, e.g. giving voice messages
- G08G1/09626—Arrangements for giving variable traffic instructions having an indicator mounted inside the vehicle, e.g. giving voice messages where the origin of the information is within the own vehicle, e.g. a local storage device, digital map
Definitions
- the present invention relates to the checking of digital road maps that are used, for example, by at least partially automated vehicles or by driver assistance systems.
- Driver assistance systems and systems for at least partially automated driving use digital road maps to plan vehicle actions. Based on a pose of the vehicle, which is determined on the basis of sensor data and/or information from a localization system, for example one that is entirely or partially satellite-based, information is retrieved from the road map and included in the planning.
- a localization system for example one that is entirely or partially satellite-based
- the digital road maps In order for the vehicle actions carried out by the vehicle to be appropriate to the respective traffic situation, the digital road maps must be kept up-to-date at all times. However, even if all updates provided by the respective manufacturer are imported promptly, a traffic situation can still be changed at short notice so that it is no longer correctly reproduced by the digital road map. For example, a construction site can be set up overnight, making one lane unusable.
- WO 2019/038 185 A1 discloses using a mobile device to record corrections for a digital map previously received from an external server and to send back a highly accurate map enriched by these corrections to the external server. Disclosure of Invention
- the pose includes a position and an orientation relative to the coordinate system of the digital road map.
- a vehicle's pose includes both its position and the direction in which it is oriented. Both the position and the orientation determine what exactly can be seen from the vehicle.
- the pose can be determined, for example, by any localization device and represents an input of the method described here.
- the localization device can, for example, match features visible from the vehicle against features in the digital road map.
- observations of a scene are obtained from the at least one pose.
- this can be the pose of a vehicle to be controlled in the scenery, and the observations can be made from this vehicle.
- the vehicle to be controlled is also referred to in common parlance as an ego vehicle.
- the actual behavior of one or more other road users is determined from the observations. This can in particular include, for example, identifying and tracking moving objects based on the observations.
- Various aspects of the actual behavior of these road users can be determined from the trajectories of the other road users determined in this way. These aspects can in particular include aspects that cannot be inferred directly from the scenery, such as from traffic signs, lane markings or other information that can be evaluated directly.
- a target behavior of the other road user(s) is determined on the basis of one or more features of the digital road map.
- features of the digital road map that have an impact on the intended behavior of road users are • the topology of carriageways and/or lanes, including proposed connections between such carriageways or lanes;
- the digital road map shows the actual conditions visible from the predetermined pose, at least in relation to the features from which the target behavior was determined , reproduces correctly. If, on the other hand, the actual behavior is not in line with the target behavior, one or more features of the digital road map that are associated with the target behavior can be falsified, i.e. recognized as not corresponding to the actual circumstances.
- this actual behavior must be consistent with the target behavior.
- a target behavior determined from a completely different pose cannot be consistent with an actual behavior that relates to a different pose and thus to a different traffic situation.
- the other road user must also objectively behave in a way that corresponds to the target behavior.
- the actual behavior is not consistent with the target behavior determined using the digital road map, this does not yet allow a clear conclusion to be drawn as to the exact cause.
- the possible contributions of the various causes can be modeled, at least in part, probabilistically. For example, it is more likely that a driver will ignore a speed limit due to the comparatively low threat of sanctions than running a red traffic light or even ignoring the turning ban on a motorway.
- Such an automated system can be completely shut down, which can mean, for example, bringing the vehicle to a standstill on a pre-planned emergency stop trajectory.
- the other road user(s) and/or their actual behavior can be transferred, for example, to the reference system of the digital road map.
- they can then be associated with features of the digital road map that are relevant to their target behavior. Not all features recorded in the digital road map affect the target behavior of every road user. For example, entry into a street may only be prohibited for vehicles that exceed a certain size or weight.
- statements relating to several other road users who are associated with one and the same feature of the digital road map can be combined to form a statement as to the extent to which this feature is plausible.
- the influence of individual other road users who deliberately do not follow a prescribed target behavior can be suppressed.
- a basic assumption for the plausibility check is that the majority of other road users will also follow a specified target behavior.
- the actual behavior of many other road users with regard to the feature of the digital road map can be aggregated with a majority decision or a similar mechanism.
- a conditional probability or chance is determined for at least one feature of the digital road map that this feature is plausible under the condition of the determined actual behavior. This allows the stochastic character of the behavior of other road users to be mapped.
- a chance denotes the quotient of the conditional probability that the characteristic is plausible under the condition of the determined actual behavior and the conditional probability that the characteristic is not plausible under the condition of the same determined actual behavior.
- conditional probability or chance is determined under the additional assumption of an unconditional basic probability or basic chance that the feature is plausible.
- prior knowledge about trust in the correctness of the digital road map can be introduced.
- the base probability or base chance can be monotonically reduced as the digital road maps age. In this way, for example, experience can be taken into account that, on average, a certain percentage of the information changes in the year after publication of a typical city map.
- conditional probability or chance that the characteristic is plausible under the condition of the determined actual behavior of many other road users can then contain a product of conditional probabilities or chances, in particular according to Bayes' theorem, that the actual behavior of one of these other road users is plausible under the condition of the feature of the digital road map.
- conditional probabilities or chances are comparatively transparent and therefore easy to determine.
- c is a normalization constant
- the normalization constant c is the reciprocal of the unconditional ones Probability p(b 1 . . . b N ) that the behavior bi, b N of the other road users 1, N is plausible.
- the observations are advantageously obtained with at least one sensor carried by a vehicle.
- the predetermined pose is then determined based on a comparison of these observations with the digital road map.
- the examination of the extent to which the digital road map is plausible can then be used, for example, to continuously check while the vehicle is driving whether the planning of actions by this vehicle is based on coherent information.
- the primary goal is to detect inconsistencies in the first place and to react to them.
- a number of candidate changes to the specified pose are determined in response to the digital road map not correctly representing the actual conditions visible from the specified pose.
- the digital road map is checked again in the manner described above to determine the extent to which it correctly reflects the actual conditions visible from the changed pose.
- it is determined that the determination of the predetermined pose from the observations obtained by the sensor is faulty.
- a number of candidate changes to the digital road map are determined in response to the fact that the digital road map does not correctly reflect the actual circumstances visible from the specified pose.
- the digital road map modified in this way is checked again in each case to determine the extent to which it correctly reproduces the actual conditions visible from the specified pose.
- a modified digital road map that best reflects the actual conditions appears reproduces, then in place of the previous digital road map. In this way, certain errors or inaccuracies in the digital road map can be "healed" automatically.
- the expected target behavior is that
- a candidate change on the digital road map can be that a lane is blocked . This is one of the most common short-term changes, for example due to a newly set up construction site. If the automated test is now repeated with the digital road map modified in this way and the actual behavior now coincides with the target behavior, the cause of the original discrepancy is clarified. This knowledge can be fed back to the manufacturer of the digital road map, for example, so that the road map is updated promptly for all users.
- the automated check of the digital road map is mainly used for continuous monitoring of whether the overall system made up of the digital road map, determination of the vehicle's pose and detection of the vehicle's surroundings is still functioning properly. Therefore, in response to the fact that the digital road map correctly reproduces the actual conditions visible from the specified pose, the digital road map is used for the behavior planning of an at least partially automated vehicle and/or a driver assistance system in a vehicle. The vehicle is then controlled on the basis of this behavior planning.
- the method can be fully or partially computer-implemented.
- the invention therefore also relates to a computer program with machine-readable instructions which, when executed on one or more computers, cause the computer or computers to carry out the method described. In this sense, control devices for vehicles and embedded systems for technical devices that are also able to execute machine-readable instructions are also to be regarded as computers.
- the invention also relates to a machine-readable data carrier and/or a download product with the computer program.
- a downloadable product is a digital product that can be transmitted over a data network, i.e. can be downloaded by a user of the data network and that can be offered for sale in an online shop for immediate download, for example.
- a computer can be equipped with the computer program, with the machine-readable data carrier or with the downloadable product.
- FIG. 1 embodiment of the method 100 for the plausibility check of a digital road map
- FIG. 2 Exemplary traffic situation in which a discrepancy between target behavior 2b and actual behavior 2a of another road user 2 occurs.
- FIG. 1 is a schematic flow chart of an exemplary embodiment of the method 100 for checking whether a digital road map 3 correctly reproduces the actual conditions visible from at least one predetermined pose la.
- step 110 observations lb of a scene 1 are procured from the at least one pose la.
- the observations 1b can be obtained with at least one sensor 51 carried by a vehicle 50.
- the specified pose la can then be determined using a comparison of these observations lb with the digital road map 3.
- step 120 the actual behavior 2a of one or more other road users 2 is determined from the observations 1b.
- a target behavior 2b of the other road user(s) 2 is determined on the basis of one or more features 3a of the digital road map 3.
- the other road user(s) 2 and/or their actual behavior 2a can be transferred to the reference system of the digital road map 3.
- the other road user(s) 2 in this reference system can then be associated with features 3a of the digital road map 3 that are relevant to their target behavior 2b.
- step 140 it is checked whether the actual behavior 2a is consistent with the target behavior 2b.
- statements relating to several other road users 2 associated with one and the same feature 3a of the digital road map 3 can be combined to form a statement as to the extent to which this feature 3a is plausible.
- a conditional probability or chance can be determined for at least one feature 3a of the digital road map 3 that this feature 3a is plausible under the condition of the determined actual behavior 2a.
- conditional probability or chance can be determined under the additional assumption of an unconditional basic probability or basic chance that feature 3a is plausible.
- this basic probability or basic chance can be monotonically reduced as the digital road map 3 ages.
- step 150 If the actual behavior 2a is consistent with the target behavior 2b (truth value 1 in step 140), it is determined in step 150 that the digital road map 3 the visible from the given pose la actual conditions at least with respect to the features 3a , from which the target behavior 2b was determined, correctly reproduces.
- step 180 the digital road map 3 can be used for the behavior planning 180a of an at least partially automated vehicle 50 and/or a driver assistance system in a vehicle 50 .
- the vehicle can then be controlled in step 190 on the basis of this behavior plan 180a.
- step 161 If, on the other hand, the actual behavior 2a is not consistent with the target behavior 2b (truth value 0 in step 140), in step 161 several candidate changes la' of the specified pose la can be determined. In step 162, the digital road map 3 can then be checked again for each candidate change la' to determine the extent to which it correctly reproduces the actual conditions visible starting from the changed pose la.
- step 163 it can be checked whether an improvement is achieved here compared to the original pose la, which satisfies a predetermined criterion. If this is the case (truth value 1), it can be determined in step 164 that the determination of the specified pose la from the observations obtained by the sensor 51 is working incorrectly. Alternatively or in combination with this, in step 171 several candidate changes 3' of the digital road map 3 can be determined. The digital road map 3 modified in this way can be checked again in step 172 to determine the extent to which it correctly reproduces the actual conditions visible from the specified pose 1a.
- step 173 it can be checked whether the result of this new check satisfies a predetermined criterion, ie in particular represents an improvement compared to the check of the original digital road map 3 . If this is the case, in step 174 a modified digital road map 3 that best reflects the actual conditions can take the place of the previous digital road map 3 .
- an exemplary scenario 1 is outlined, in which a discrepancy occurs between the target behavior 2b and the actual behavior 2a of another road user 2.
- An expressway 11 has a right lane 11a and a left lane 11b. According to the observation lb of the scenery 1, a vehicle 2 is initially driving in the right lane 11a. On the basis of the digital map 3, which contains the expressway 11, it is therefore expected that the vehicle 2 will initially continue to drive there as a target behavior 2b. However, due to a short-term construction site 12, which is not shown on the digital road map 3, the vehicle 2 must show the actual behavior 2a of changing to the left lane 11b. In particular when this occurs for more vehicles 2, it can be derived from this discrepancy according to the method 100 described above that the right lane 11a is currently not usable.
Landscapes
- Engineering & Computer Science (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Automation & Control Theory (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Traffic Control Systems (AREA)
Abstract
Description
Claims
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
KR1020247012531A KR20240063148A (ko) | 2021-09-23 | 2022-09-13 | 로컬 타당성을 위한 디지털 로드맵 확인 |
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
DE102021210568.8 | 2021-09-23 | ||
DE102021210568.8A DE102021210568A1 (de) | 2021-09-23 | 2021-09-23 | Prüfung einer digitalen Straßenkarte auf lokale Plausibilität |
Publications (1)
Publication Number | Publication Date |
---|---|
WO2023046521A1 true WO2023046521A1 (de) | 2023-03-30 |
Family
ID=83507458
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/EP2022/075330 WO2023046521A1 (de) | 2021-09-23 | 2022-09-13 | PRÜFUNG EINER DIGITALEN STRAßENKARTE AUF LOKALE PLAUSIBILITÄT |
Country Status (3)
Country | Link |
---|---|
KR (1) | KR20240063148A (de) |
DE (1) | DE102021210568A1 (de) |
WO (1) | WO2023046521A1 (de) |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
DE102017211613A1 (de) * | 2017-07-07 | 2019-01-10 | Robert Bosch Gmbh | Verfahren zur Verifizierung einer digitalen Karte eines höher automatisierten Fahrzeugs (HAF), insbesondere eines hochautomatisierten Fahrzeugs |
WO2019038185A1 (de) | 2017-08-25 | 2019-02-28 | Robert Bosch Gmbh | Mobiles gerät, server und verfahren zum aktualisieren und bereitstellen einer hochgenauen karte |
US20200098135A1 (en) * | 2016-12-09 | 2020-03-26 | Tomtom Global Content B.V. | Method and System for Video-Based Positioning and Mapping |
-
2021
- 2021-09-23 DE DE102021210568.8A patent/DE102021210568A1/de active Pending
-
2022
- 2022-09-13 KR KR1020247012531A patent/KR20240063148A/ko unknown
- 2022-09-13 WO PCT/EP2022/075330 patent/WO2023046521A1/de active Application Filing
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20200098135A1 (en) * | 2016-12-09 | 2020-03-26 | Tomtom Global Content B.V. | Method and System for Video-Based Positioning and Mapping |
DE102017211613A1 (de) * | 2017-07-07 | 2019-01-10 | Robert Bosch Gmbh | Verfahren zur Verifizierung einer digitalen Karte eines höher automatisierten Fahrzeugs (HAF), insbesondere eines hochautomatisierten Fahrzeugs |
WO2019038185A1 (de) | 2017-08-25 | 2019-02-28 | Robert Bosch Gmbh | Mobiles gerät, server und verfahren zum aktualisieren und bereitstellen einer hochgenauen karte |
Also Published As
Publication number | Publication date |
---|---|
KR20240063148A (ko) | 2024-05-09 |
DE102021210568A1 (de) | 2023-03-23 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
DE102017215552A1 (de) | Plausibilisierung der Objekterkennung für Fahrassistenzsysteme | |
DE102018212733A1 (de) | Erkennung einer nachlassenden Leistungsfähigkeit eines Sensors | |
DE102009008959A1 (de) | Fahrzeugsystem zur Navigation und/oder Fahrerassistenz | |
DE102011010377A1 (de) | Verfahren zum Betreiben eines Kraftfahrzeugs und Kraftfahrzeug | |
WO2020212061A1 (de) | Verfahren zur prädiktion einer verkehrssituation für ein fahrzeug | |
EP4211529A1 (de) | Konzept zum unterstützen eines zumindest teilautomatisiert geführten kraftfahrzeugs | |
DE102015217371A1 (de) | Verfahren zum automatisierten Fahren mit Nutzung von Kartendaten | |
DE112018002533T5 (de) | Fahrzeuginformationsverarbeitungssystem | |
DE102008023242A1 (de) | Map matching für Sicherheitsanwendungen | |
WO2023046521A1 (de) | PRÜFUNG EINER DIGITALEN STRAßENKARTE AUF LOKALE PLAUSIBILITÄT | |
DE102020112899A1 (de) | Verfahren und System zur vollständig automatischen Führung eines Kraftfahrzeugs und Kraftfahrzeug | |
DE102019212829A1 (de) | Automatisierte Erkennung eines anormalen Verhaltens eines Verkehrsteilnehmers | |
DE102017219297B4 (de) | Verfahren zum Betreiben eines Fahrzeugs, Verfahren zum Betreiben eines Plausibilisierungssystems, Fahrzeug, Computerprogramm und Computerprogrammprodukt | |
DE102019220549A1 (de) | Training von neuronalen Netzen durch ein neuronales Netz | |
WO2023057014A1 (de) | Verfahren zur planung einer trajektorie eines fahrmanövers eines kraftfahrzeugs, computerprogrammprodukt, computerlesbares speichermedium sowie fahrzeug | |
DE102020213831B4 (de) | Verfahren zum Ermitteln einer Existenzwahrscheinlichkeit eines möglichen Elements in einer Umgebung eines Kraftfahrzeugs, Fahrerassistenzsystem und Kraftfahrzeug | |
DE102017212179A1 (de) | Korrektur eines gemessenen Positionswerts eines schienengebundenen Fahrzeugs | |
DE10337631B4 (de) | Verfahren zur Steuerung von Fahrzeugsystemen | |
EP3969846A1 (de) | Verfahren zum validieren einer kartenaktualität | |
DE102016211045A1 (de) | Aktualisierung einer digitalen Karte | |
WO2020224878A1 (de) | Verfahren und vorrichtung zum erstellen einer ersten karte | |
DE102019200145A1 (de) | Vorrichtung und Verfahren zum Verifizieren von elektronischen Horizonten | |
DE102019215099B4 (de) | Verfahren zum Bereitstellen einer aktuellen lokalen Umgebungszustandskarte für ein Kraftfahrzeug sowie Kraftfahrzeug zum Durchführen eines derartigen Verfahrens | |
DE102017204601A1 (de) | Verfahren und Vorrichtung zum Ermitteln zumindest eines wahrscheinlichsten Weges für ein Fahrzeug | |
DE102021102652B3 (de) | Verfahren und Steuergerät zum Ermitteln, ob ein Kraftfahrzeug auf einer in digitalem Kartenmaterial enthaltenen Straße gefahren ist |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
121 | Ep: the epo has been informed by wipo that ep was designated in this application |
Ref document number: 22782708 Country of ref document: EP Kind code of ref document: A1 |
|
ENP | Entry into the national phase |
Ref document number: 20247012531 Country of ref document: KR Kind code of ref document: A |
|
WWE | Wipo information: entry into national phase |
Ref document number: 2022782708 Country of ref document: EP |
|
NENP | Non-entry into the national phase |
Ref country code: DE |
|
ENP | Entry into the national phase |
Ref document number: 2022782708 Country of ref document: EP Effective date: 20240423 |