CN115773743A - Method for providing data for creating digital map, method and system for creating digital map - Google Patents
Method for providing data for creating digital map, method and system for creating digital map Download PDFInfo
- Publication number
- CN115773743A CN115773743A CN202211084277.8A CN202211084277A CN115773743A CN 115773743 A CN115773743 A CN 115773743A CN 202211084277 A CN202211084277 A CN 202211084277A CN 115773743 A CN115773743 A CN 115773743A
- Authority
- CN
- China
- Prior art keywords
- data
- sensor
- digital map
- vehicle
- environmental data
- 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.)
- Pending
Links
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W4/00—Services specially adapted for wireless communication networks; Facilities therefor
- H04W4/30—Services specially adapted for particular environments, situations or purposes
- H04W4/40—Services specially adapted for particular environments, situations or purposes for vehicles, e.g. vehicle-to-pedestrians [V2P]
-
- 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
- G01C21/38—Electronic maps specially adapted for navigation; Updating thereof
- G01C21/3804—Creation or updating of map data
- G01C21/3807—Creation or updating of map data characterised by the type of data
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W4/00—Services specially adapted for wireless communication networks; Facilities therefor
- H04W4/30—Services specially adapted for particular environments, situations or purposes
- H04W4/38—Services specially adapted for particular environments, situations or purposes for collecting sensor information
Abstract
A method for providing data for creating a digital map (140), the method having the steps of: a) -sensor-wise detection of the environment of the parked vehicle (2), wherein a localization is performed for the parked vehicle (2); b) A process for defined merging of the sensor-detected environmental data (UD 2) of the parked vehicle (2); and c) transmitting the environmental data (UD 2) obtained in step b) to the database device (120) for storage.
Description
Technical Field
The invention relates to a method for providing data for creating a digital map. The invention also relates to a method for creating a digital map. The invention also relates to a system for creating a digital map. The invention also relates to a computer program product.
Background
An important component in achieving automated driving (SAE 3 to 5 levels) is the use of highly accurate digital HAD maps (highly automated driving). The vehicle pose estimated during localization can be used to detect information from the digital HAD map, for example about road topology and lane course of the vehicle relative to itself. This information can be used to implement automated driving functions.
For low level automation (level SAE 2/3), this may be cross-control within the lane to reach a preferred lane trajectory or assist lane change, and adjust the driving speed to the recommended speed on the map. In highly automated driving, trajectory planning may be based entirely on digital HAD maps. The digital HAD map contains different layers including one or more positioning layers with static environmental features and a planning layer for trajectory planning. The planning layer includes, for example, the topology and turning relationships of the lane, speed limit information or trafficability or usage information of different areas, etc.
In today's AD vehicles, various environmental sensors (e.g., video, radar, lidar, etc.) are used to detect environmental features during travel by way of the sensors and compare them to features of the map-located layer. Thereby, the posture (position and direction) of the current vehicle can be estimated. For example, a three-dimensional point cloud or semantic landmarks (road signs, traffic signs, light posts, etc.) may be used as the localization.
The positioning accuracy requirement is usually very high (the positioning error can reach 10cm at most relative to the map). The requirements on the map accuracy are correspondingly high. A system is provided for creating high-definition maps, typically using a measuring vehicle with expensive sensor devices to achieve the required accuracy of the map.
Although data collection is currently performed only for actual active vehicles, in recent years field application research in the fields of communication (network provisioning, etc.) and tracking (traffic density, parking space search, etc.) also considers parked vehicles (hereinafter referred to as passive vehicles). These can be considered as additional sensors and as a way to increase the network capacity.
DE 10 2015 222 A1 discloses a method for aggregating lane information to create and/or update a roadmap.
DE 10 2013 107 861 A1 relates to an autonomous and/or automated vehicle or self-propelled system and to a system for detecting and tracking objects in the vicinity of a vehicle using a laser distance meter.
EP 3 614 106 A1 discloses a system and method for navigating a host vehicle.
DE 10 2017 101 a 466 discloses a vehicle navigation system, in particular a vehicle navigation system which can be used when lane markings are worn, obscured or not present.
Disclosure of Invention
It is an object of the invention to provide an improved method for creating a digital map.
According to a first aspect, the object is achieved by a method for providing data for creating a digital map, having the following steps:
-sensor-wise detecting an environment of a parked vehicle, wherein a localization is performed for the parked vehicle;
-a defined combined processing of the sensor-detected environmental data of the parked vehicle; and
-transferring the environmental data found in step b) to a database means for saving.
In this way, the method advantageously provides collected data of the parked vehicle, which are then used supplementarily for map positioning and creation of a planning map for automated driving. This advantageously enables more data to be used on the one hand and other types of data to be used for creating the digital map on the other hand.
This is particularly advantageous because the sensing devices of the vehicle are typically consumer grade sensor devices that do not have as high performance capability as professional reference mapping vehicles. As a result, significantly greater data potentials can thus be used for creating digital maps. Due to the fact that parked vehicles are usually parked at the edge of the road, parked vehicles can be better positioned and can observe a specific environmental area for a certain period of time.
In this way, in contrast to a positive vehicle, it is possible to observe objects which are often only obscured and cannot be observed for a moving vehicle. As a result, the proposed method is used in this way to create digital maps for different layers, for example for a positioning layer, a planning layer, a semantic layer, etc. Thus, in this way, for example, traffic flows, pedestrian flows, etc. can be detected and displayed.
As a result, high accuracy of the map is thereby achieved by the crowdsourcing method. The fleet of vehicles send their data to the cloud where they are aggregated and merged into one map.
According to a second aspect, the task is solved with a method for creating a digital map, comprising the steps of:
a) Providing sensor-detected environmental data of at least one moving vehicle and processing the sensor-detected environmental data in a defined manner;
b) Providing sensor-detected environmental data of at least one parked vehicle and processing the sensor-detected environmental data in a defined manner; and
c) Creating a digital map from the environment data provided in steps a) and b).
As a result, this is performed in the cloud, thereby advantageously providing an improved way of creating digital maps with performance-capable computing. In this way, a map with a plurality of layers can advantageously be generated. Such an expanded map (Steckkarten) may be transmitted to a fleet of vehicles, for example.
According to a third aspect, the object is achieved with a system for creating a digital map, which is designed to carry out the proposed method.
According to a fourth aspect, the object is achieved with a computer program product having program code means for performing the proposed method when the method is run on an electronic device according to the proposed method or stored on a computer-readable data carrier.
An advantageous development of the proposed method can be achieved by the measures listed in the preferred embodiments.
An advantageous development of the method provides that in step b) the sensor-detected environmental data of the plurality of parked vehicles are processed in a defined manner, wherein in step c) the sensor-detected environmental data of the plurality of parked vehicles are transmitted to the database device.
In an advantageous embodiment of the method, the position of the object detected by the sensor is determined in step b) from the tracking data of the parked vehicle together with the positioning data. This enables a highly accurate position of the object in a parked or passive vehicle to be determined.
In a further advantageous embodiment of the method, provision is made for at least one object to be tracked on the basis of a measurement technique in step a) and for the trajectory of the object to be tracked on the basis of the measurement technique to be determined. It is possible to know where and thus be able to determine the trajectory.
In a further advantageous development of the method, provision is made for the data to be detected in step a) by at least one of the following sensors: video sensor, radar sensor, ultrasonic sensor, lidar sensor. In this way, a wide range of sensor devices of other traffic participants, pedestrians, landmarks, etc., can be used for the sensor detection and tracking. This advantageously takes place over a longer period of time, approximately corresponding to the parking duration of the parked vehicle.
A further advantageous development of the method provides that in step a), the sensor-like detection of the environment is carried out at a defined subsequent time after the start of the parking process of the parked vehicle. In this way, the vehicle battery of the parked vehicle is advantageously protected, wherein a defined data set of the environmental data is collected.
A further advantageous development of the method provides that, in step c), the data at the defined point in time are transmitted to the cloud. This can advantageously be carried out, for example, when the parked vehicle is started after parking has ended. As a result, the cloud is thereby transmitted with highly real-time data of the environment of the parked vehicle.
A further advantageous development of the method provides that, in step b), data of a defined size are collected. In this way, environmental data of a defined size can be transmitted to the cloud.
Drawings
The invention is described in detail below with reference to the several figures, together with additional features and advantages. All the described or illustrated features form the subject matter of the invention per se or in any combination, independently of their conclusion in the claims or their back-reference and independently of their representation or illustration in the description or the drawings.
The features and advantages of the disclosed method are derived in a similar manner from the disclosed features and advantages of the system, and vice versa.
Shown in the drawings are:
FIG. 1; a diagram of data collection for the method;
FIG. 2: a system diagram of the proposed system; and
FIG. 3: a schematic flow of one embodiment of the proposed method.
Detailed Description
A method is proposed in which the creation of a digital map can be improved. For this purpose, environmental data detecting the parked vehicles are also created for the map, so that these environmental data are not only "utilized in real time", but are subsequently used in the background for creating the digital map. Although the spatial section covered by the collected data is necessarily small, a passive or parked vehicle as a data collector has a series of advantages over an active, i.e. driving vehicle:
data relating to road edges can be collected better, more accurately or completely due to reduced occlusion and reduced distance;
self-positioning of parked vehicles is generally more accurate due to longer dwell times at the same location;
the ability to collect data at a particular location for an extended period of time. More targeted and more accurate long-term information about a specific site can thus be gathered, which information is not available even from very large fleets of vehicles. Some application scenarios that can improve map creation by using parked vehicles are listed below by way of example:
the parked vehicle can seek the trajectory of the active vehicle traveling past the parked vehicle and provide this data for map creation. These trajectories can also be used to derive road maps, in addition to crowd-sourced data from a fleet of active vehicles;
furthermore, it is also possible to find trajectories for further traffic participants, such as cyclists, pedestrians, etc., and to use these trajectories to supplement crowd-sourced data from a fleet of active vehicles. It is thus advantageously possible to identify the extension of the cycle path/sidewalk and the typical location where road crossing takes place, which results in an improved trajectory planning (e.g. matching speed, safe distance, etc.) in terms of automated driving functions;
the locating feature can also be detected by the parked vehicle and used supplementarily when creating the digital map. This supplementation enables a more accurate localization of map features in digital maps, precisely due to the long viewing time and the accurate self-localization of the mentioned features;
overall, it is possible to improve the targeted passage of data of parked vehicles at unsafe locations at selected locations in a map previously created purely on the basis of data of a fleet of active vehicles.
In the following, "data summarization" is understood to mean a defined comparative or combined processing of data from different or identical data sources, wherein the data may originate, for example, from GNSS measurements and/or may be odometry data or sensor data (e.g. video sensor data, radar sensor data). Here, for example, in the case of trajectory data, mutual alignment is performed on the data, and in the case of video data, for example, the same object detected is associated.
The proposed method uses different modules. First, objects are detected and classified in a parked vehicle, for example, by a camera. In a further process, the object is tracked on a measurement technique (english: gettrackt), and thus its position relative to the vehicle is tracked over a period of time. By simultaneously locating the own vehicle, the determination of the trajectory/position of the object in the global coordinate system can be achieved in this way. The mentioned data collection procedure is schematically shown in fig. 1.
Fig. 1 shows a principle data collection procedure for a parked or parked vehicle 2 (not shown). The detection of the object is performed in step 10. This is tracked in a measurement technique (gettrackt) in step 20, wherein the corresponding data together with the positioning data of the parked vehicle 2 determined in step 30 are used to determine the trajectory/position of the object, for example in the coordinates (e.g. longitude, latitude) of a defined coordinate system.
In this way, data of the parked vehicle 2 or all vehicles 2 of the parked vehicle fleet are transmitted into the cloud 100 (not shown) at defined points in time (which may be the vehicle still in a passive state or only thereafter in an active state, depending on requirements and possibilities). There, these data are managed separately from the data of the fleet of active vehicles. If a process for map creation is triggered, data is selected from the collection of active fleets and/or passive fleets as needed. The map creation can also be performed iteratively, i.e., the created digital map 140 can be evaluated according to different criteria and additional data from both data sources can be used as needed. Upon completion of the map creation process, the created digital map 140 is transmitted from the cloud 100 to the vehicle, where it can be used, for example, for vehicle regulation.
A systematic overview is schematically shown in fig. 2. It can be seen that a map is created in the cloud 100 based on data of both active and passive vehicle fleets.
The data of the first database 110 and the data of the second database 120 are fed to a map creation device 130, which generates a digital map 140 on the basis of the trigger events T1, T2. The trigger events T1, T2 are defined here, for example, as follows: in which case the digital map 140 should be created or the environment data UD1, UD2 used for the creation of the digital map 140 evaluated. This may be, for example, a point in time and/or a specific amount/type of data in the presence of which the map creation process is initiated.
As a result, the digital map 140 created in this way can be transmitted, for example, to the vehicle regulating device 1b of the aggressive vehicle 1, which is able to perform better on the basis of the highly accurate current digital map 140. For example, defined automated driving functions of the vehicle 1 can be activated using specific layers of the digital map 140, which are usually aligned with one another.
Pedestrian flow, traffic flow, etc. can be detected in this manner and used for planning layers of the digital map 140, for example. The data diversity for creating the digital map is advantageously increased in this way, as a result of which improved, highly accurate digital maps can be provided for the vehicle.
The method is therefore advantageously implemented as a software program that uses data of the parked vehicle 2 to create a digital map 140 in the cloud 100.
Fig. 3 shows a schematic flow of the proposed method, strongly schematically.
In step 200, the environment of the parked vehicle 2 is detected in a sensor-like manner, wherein a localization of the parked vehicle 2 is carried out.
In step 210, the sensor-detected environmental data UD2 of the parked vehicle 2 is processed in a defined manner.
In step 220, the environment data UD2 determined in step b) is transmitted to the database device 120 for storage.
The proposed method can advantageously be implemented as software, for example, running decentrally on a controller of the vehicle or running centrally in the cloud. In this way, a simple adaptation of the method is supported.
The proposed procedure can advantageously be executed in the cloud, wherein the calculations performed in the cloud are advantageously performed only once (for example until the next map update). The method is performed in the vehicle on each trip, since it is generally required to provide up-to-date map attributes in a high real-time.
The features of the invention are changed in an appropriate manner and/or combined with each other by the skilled person without departing from the essence of the invention.
Claims (15)
1. A method for providing data for creating a digital map (140), the method having the steps of:
a) -sensor-wise detection of the environment of a parked vehicle (2), wherein a localization is performed for the parked vehicle (2);
b) -a defined processing of the sensorwise detected environmental data (UD 2) of the parked vehicle (2); and
c) The environmental data (UD 2) determined in step b) are transmitted to a database device (120) for storage.
2. Method according to claim 1, wherein in step b) the sensor-detected environmental data of a plurality of parked vehicles (2) are processed in a defined manner, wherein in step c) the sensor-detected environmental data of a plurality of parked vehicles (2) are transmitted to the database device (120).
3. Method according to claim 1 or 2, wherein in step b) the position of the sensor-detected object is determined from the tracking data of the parked vehicle (2) together with the positioning data.
4. Method according to any of the preceding claims, wherein in step a) at least one object is tracked over a measurement technique and the trajectory of the object tracked with the measurement technique is found.
5. Method according to any of the preceding claims, wherein in step a) the data is detected by at least one of the following sensors: video sensor, radar sensor, ultrasonic sensor, lidar sensor.
6. Method according to any of the preceding claims, wherein in step a) sensor-wise detection of the environment is performed at a defined subsequent time after the start of the parking process of the parked vehicle (2).
7. The method according to any of the preceding claims, wherein in step c) data at a defined point in time is sent to the cloud (100).
8. The method according to any of the preceding claims, wherein in step b) data is collected having a defined scale.
9. A method for creating a digital map (140), the method comprising the steps of:
a) Providing sensor-detected environmental data (UD 1) of at least one moving vehicle (2) and performing a defined combination of said sensor-detected environmental data;
b) Providing sensor-detected environmental data (UD 2) of at least one parked vehicle (2) and performing a defined combined processing of the sensor-detected environmental data; and
c) Creating a digital map (140) from the environment data (UD 1, UD 2) provided in said steps a) and b).
10. The method according to claim 9, wherein the creation of the digital map (140) is triggered by means of at least one defined trigger event (TR 1, TR 2).
11. The method of claim 10, wherein the creation of the digital map (140) is performed in a defined time-triggered manner and/or in a defined event-triggered manner.
12. The method according to any one of claims 9 to 11, wherein the digital map (140) is created for a defined geographical region.
13. The method according to any one of claims 9 to 12, wherein the data of the digital map (140) are transmitted to at least one moving vehicle (1).
14. A system (100) for creating a digital map, the system being configured for performing the method according to any one of claims 9 to 13.
15. A computer program product having program code means for performing the method according to any one of claims 8 to 12 when the method is run on a system (100) according to claim 14 or stored on a computer-readable data carrier.
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
DE102021209783.9 | 2021-09-06 | ||
DE102021209783.9A DE102021209783A1 (en) | 2021-09-06 | 2021-09-06 | Method for providing data to create a digital map |
Publications (1)
Publication Number | Publication Date |
---|---|
CN115773743A true CN115773743A (en) | 2023-03-10 |
Family
ID=85226698
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202211084277.8A Pending CN115773743A (en) | 2021-09-06 | 2022-09-06 | Method for providing data for creating digital map, method and system for creating digital map |
Country Status (2)
Country | Link |
---|---|
CN (1) | CN115773743A (en) |
DE (1) | DE102021209783A1 (en) |
Family Cites Families (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US9255989B2 (en) | 2012-07-24 | 2016-02-09 | Toyota Motor Engineering & Manufacturing North America, Inc. | Tracking on-road vehicles with sensors of different modalities |
DE102013011824A1 (en) | 2013-07-15 | 2015-01-15 | Audi Ag | Method for determining and updating a debit card in a parking area |
DE102014015073B4 (en) | 2014-10-11 | 2021-02-25 | Audi Ag | Method for updating and / or expanding a map data set in a limited environment |
DE102015222962A1 (en) | 2015-11-20 | 2017-05-24 | Robert Bosch Gmbh | Method for aggregating lane information for digital map services |
US9707961B1 (en) | 2016-01-29 | 2017-07-18 | Ford Global Technologies, Llc | Tracking objects within a dynamic environment for improved localization |
KR20230017365A (en) | 2016-06-27 | 2023-02-03 | 모빌아이 비젼 테크놀로지스 엘티디. | controlling host vehicle based on detected spacing between stationary vehicles |
US10078790B2 (en) | 2017-02-16 | 2018-09-18 | Honda Motor Co., Ltd. | Systems for generating parking maps and methods thereof |
DE102017206311A1 (en) | 2017-04-12 | 2018-10-18 | Ford Global Technologies, Llc | Method and device for supporting the search for available parking spaces |
GB2568264B (en) | 2017-11-09 | 2020-09-16 | Jaguar Land Rover Ltd | Vehicle parking assistance |
DE102018201111B4 (en) | 2018-01-24 | 2020-06-18 | Audi Ag | Method for monitoring at least one parking space for availability and system for performing the method |
JP7393128B2 (en) | 2019-03-20 | 2023-12-06 | フォルシアクラリオン・エレクトロニクス株式会社 | In-vehicle processing equipment, mobility support system |
-
2021
- 2021-09-06 DE DE102021209783.9A patent/DE102021209783A1/en active Pending
-
2022
- 2022-09-06 CN CN202211084277.8A patent/CN115773743A/en active Pending
Also Published As
Publication number | Publication date |
---|---|
DE102021209783A1 (en) | 2023-03-09 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Suhr et al. | Sensor fusion-based low-cost vehicle localization system for complex urban environments | |
Spangenberg et al. | Pole-based localization for autonomous vehicles in urban scenarios | |
EP3032221B1 (en) | Method and system for improving accuracy of digital map data utilized by a vehicle | |
Schreiber et al. | Laneloc: Lane marking based localization using highly accurate maps | |
US10369993B2 (en) | Method and device for monitoring a setpoint trajectory to be traveled by a vehicle for being collision free | |
US10553117B1 (en) | System and method for determining lane occupancy of surrounding vehicles | |
US10699565B2 (en) | Systems and methods for inferring lane obstructions | |
JP2019532292A (en) | Autonomous vehicle with vehicle location | |
JP7245084B2 (en) | Autonomous driving system | |
US20210389133A1 (en) | Systems and methods for deriving path-prior data using collected trajectories | |
CN113330279A (en) | Method and system for determining the position of a vehicle | |
CN108961811A (en) | Parking lot vehicle positioning method, system, mobile terminal and storage medium | |
US11555705B2 (en) | Localization using dynamic landmarks | |
US11023753B2 (en) | System and method for determining a lane change of a preceding vehicle | |
US11754415B2 (en) | Sensor localization from external source data | |
CN114485619A (en) | Multi-robot positioning and navigation method and device based on air-ground cooperation | |
CN112394725A (en) | Predictive and reactive view-based planning for autonomous driving | |
Gläser et al. | Environment perception for inner-city driver assistance and highly-automated driving | |
JP6507841B2 (en) | Preceding vehicle estimation device and program | |
US11499833B2 (en) | Inferring lane boundaries via high speed vehicle telemetry | |
WO2018090661A1 (en) | Path planning for autonomous vehicle using bidirectional search | |
US20210158696A1 (en) | Systems and methods for mitigating anomalies in lane change detection | |
CN114127738A (en) | Automatic mapping and positioning | |
Raaijmakers et al. | In-vehicle roundabout perception supported by a priori map data | |
US11885640B2 (en) | Map generation device and map generation method |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication |