System and method of a two-step object data processing by a vehicle and a server database for generating, updating and delivering a precision road property database

• US 10,970,317 B2
• Filed: 07/28/2016
• Issued: 04/06/2021
• Est. Priority Date: 08/11/2015
• Status: Active Grant

• Current Assignee: Continental Automotive GmbH (Continental AG)
• Original Assignee: Continental Automotive GmbH (Continental AG)
• Inventors: Thiel, Christian, Barnard, Paul, Herbst, James, Lenninger, Ralf Johannes, Foersterling, Frank
• Primary Examiner(s): Boccio, Vincent F
• Application Number:
  US15/751,850
• Publication Number:
  US 20180246907A1
• Time in Patent Office: 1,713 Days
• Field of Search: 707724
• CPC Class Codes: G06F 16/29 Geographical information databases
• CPC Class Codes: G06V 20/58 Recognition of moving objects or obstacles, e.g. vehicles or pedestrians; Recognition of traffic objects, e.g. traffic signs, traffic lights or roads
• CPC Class Codes: H04W 4/44 for communication between vehicles and infrastructures, e.g. vehicle-to-cloud [V2C] or vehicle-to-home [V2H]

Abstract

A method and a system of a two-step object data processing by a vehicle and a database for generating and updating a digital road description database containing object-based information about road objects is disclosed. First, the server database comprises fourth data sets and generates and forwards first data sets to the vehicle, which are related to the area of interest of the vehicle. The vehicle is collecting a plurality of ambient data sets at least along a specific section of its path. It is performing the first step of object data processing by evaluating a selection of the plurality of ambient data sets and generating at least one second data set comprising at least location information and detailed object-based information. It further generates third data sets containing differences between the object-based information of the second data sets and the object-based information of the first data sets and forwards the third data sets to the server database. The server database performs the second step of object data processing comprising at least statistical evaluation and post processing to update the fourth data sets in the server database based on the third data sets.

Claims

1. A method for generating and updating a precision road property database that includes information about driving-relevant objects, the method comprising:

a) with a computer of a server database, operably connected with a tangible storage of the server database that contains pre-stored data sets with driving-relevant object data including location information and object-based information about at least one of said driving-relevant objects including at least one of a road object, a road furniture object, and a geographical object,

generating first data sets from said pre-stored data sets, each first data set comprising said driving-relevant object data;

b) either with a computer of a vehicle, requesting information about a location from the computer of the server database to have the computer of the server database transfer the first data sets containing the driving-relevant object data concerning the location to the computer of the vehicle,

or

with the computer of the server database, initiating a data transfer to the computer of said vehicle and forwarding said first data sets containing the driving-relevant object data concerning the location to the computer of the vehicle;

c) with the computer of the vehicle, storing the first data sets in a vehicle database;

d) based at least on said location information contained in the first data sets or transferred to the computer of the vehicle separately, collecting ambient data sets at the vehicle with the use of at least one vehicular sensor under at least one of the following conditions;

(d1) along path sections, of a vehicle path that includes said location; and

(d2) at a specific time or time interval; and

(d3) about a driving-relevant object,

said ambient data sets characterizing said at least one of the driving-relevant objects,

e) with the computer of the vehicle,

acquiring said ambient data sets from the at least one sensor of the vehicle,

evaluating the ambient data sets to form an evaluation result, and

generating second data sets based on the evaluation result, each second data set comprising driving-relevant object data,

f) with the computer of the vehicle, generating third data sets that contains at least one of;

(f1) differences between the object-based information of the second data sets and the object-based information of the respectively corresponding first data sets related to the path sections, and

(f2) the object-based information of the second data sets related to the path sections,

g) with the computer of the vehicle, forwarding the third data sets to the computer of the server database via a communication network,

h) with the computer of the server database, identifying a plurality of said path sections that at least partially overlap with one another and storing a selection of the third data sets corresponding to said plurality of said path sections,

i) for each of said path sections from said plurality, with the use of the computer of the server database;

(i1) grouping together related objects identified in such path sections that at least partially overlap each other to generate at least one group of objects, and

(i2) performing at least one of;

matching location information of said at least one group of objects with location information of groups of objects comprising the same related objects of other data sets from said selection, and

matching the path sections from said plurality by aligning the groups of objects between the path sections,

j) with the computer of the server database, performing at least statistical evaluation and post processing of j1) the third data sets from said selection of the third data sets corresponding to the plurality of the path sections that at least partially overlap with one another and j2) corresponding pre-stored data sets, and

k) with the computer of the server database, modifying the pre-stored data sets in the tangible storage of the server database based on results of said performing.

2. The method according to claim 1, wherein said generating second data sets based on the evaluation result includes generating at least partial object data of at least parts of the driving-relevant objects based on said acquiring the ambient data sets from the at least one sensor of the vehicle.

3. The method according to claim 1, wherein said modifying the pre-stored data sets in the tangible storage of the server database includes forming modified pre-stored data sets representing a consolidated model of the road network that provides driving relevant information.

4. The method according to claim 1, wherein grouping together related objects identified in such path sections to generate at least one group of objects includes generating said at least one group of objects that includes a road object and at least one of a road furniture object and a geographic object.

5. The method according to claim 1, comprising:

with the computer of the server database;

having initiated data transfer to the computer of the vehicle and forwarded said first data sets to the computer of the vehicle, transferring to the computer of the vehicle a sampling request specifying time at which said collecting of the ambient data sets with the use of at least one vehicular sensor should be carried out.

6. The method according to claim 1, wherein the at least one of the first data sets and the third data sets includes auxiliary data that contain a statistical parameter, wherein said statistical parameter defines at least one of an average value and a standard deviation characterizing object data in a respective data set.

7. The method according to claim 6, wherein said generating third data sets, with the computer of the vehicle, includes selecting at least one specific path section based said auxiliary data such that the at least one specific path section that has been selected is characterized by at least one of a low confidence level, a large standard deviation, and no data available in the corresponding auxiliary data.

8. The method according to claim 6, comprising:

with the computer of the server database, supplying at least part of the auxiliary data as part of the first data sets to the computer of the vehicle, wherein said at least part of the auxiliary data includes a confidence level generated by the computer of the server database.

9. The method according to claim 8, comprising:

when a first data set transferred to the computer of the vehicle contains data about the location that is represented by the confidence level that is low, increasing a number of vehicles passing the location, each of said vehicles performing said collecting the ambient data sets to thereby increase an amount of overall collected data and forwarding the third data sets to the computer of the server database to thereby increase the confidence level during said modifying the pre-stored data sets.

10. The method according to claim 8, comprising:

when a first data set transferred to the computer of the vehicle contains data about the location that is represented by the confidence level that is low, triggering a rescan of objects at said location with the at least one of the vehicular sensors to thereby form the third data sets that includes auxiliary data with increased confidence level.

11. The method according to claim 8, comprising:

when a first data set transferred to the computer of the vehicle contains data about the location that is represented by the confidence level that is high, decreasing occurrence of said collecting ambient data sets to thereby decrease network traffic and processing power required at the vehicle and the server database.

12. The method according to claim 1, wherein said generating third data sets, with the computer of the vehicle, includes generating auxiliary data that contain a confidence level characterizing object data in the third data sets, wherein said confidence level has been determined by the computer of the vehicle based on at least one of:

equipment of the vehicle, a travelling speed of the vehicle, a number of measurements performed during said collecting the ambient data sets at the vehicle with the use of at least one vehicular sensor, a number of images formed as a result of said collecting, and a signal to noise ratio of said measurements.

13. The method according to claim 10, wherein said confidence level has been determined based on at least one of:

weather condition during said collecting, visibility conditions during said collecting, light conditions during said collecting, shadows, and blinding.

14. The method according to claim 1, wherein said server database is hosted by at least one stationary server or by a cloud-based infrastructure or a combination of said at least one stationary sever and the cloud-based infrastructure, each of which is external to the vehicle.

15. The method according to claim 1, wherein said collecting ambient data sets at the vehicle with the use of at least one vehicular sensor includes using at least one of a CCD sensor, an infrared sensor, a laser scanner, an ultrasound transducer, a radar sensor, a radiofrequency (RF) channel, and an auxiliary environmental sensor.

16. The method according to claim 1, comprising:

with the use of the server database and prior to said modifying the pre-stored data sets in the tangible storage of the server database, correlating the location information in the stored data with at least one of satellite image information and precision position information available for at least one of the road objects specified by the driving-relevant object data.

17. A server database comprising:

a tangible storage that contains pre-stored data sets with driving-relevant object data including location information and object-based information about at least one of said driving-relevant objects including at least one of a road object, a road furniture object, and a geographical object;

a computer of the server database, said computer configured

to generate first data sets from said pre-stored data sets, wherein the first data sets are sub-sets of the pre-stored data sets and represent at least one of a path section of a vehicle path that includes a corresponding location, a specific time or time interval pre-determined for collection of ambient data with a sensor of the a vehicle, and wherein each of the first data sets includes driving-relevant object data, wherein the sub-sets include driving-relevant object data and

to identify a plurality of path sections of the vehicle path that at least partially overlap with one another;

means for transferring the first data sets to a vehicle;

the server database configured to store a selection of output data sets, wherein output the data sets have been generated at the vehicle and received by the server database and include at least differences between the object-based information contained in the ambient data collected along said path sections that at least partially overlap with one another;

the server database configured to generate at least one group of objects in each of said path sections that at least partially overlap with one another by grouping together related objects identified in such path sections, to perform matching location information of the at least one group of objects with location information of groups of objects comprising the same related objects of other output data sets from the selection, and to match said path sections that at least partially overlap with one another by aligning the groups of object between the path sections;

the server database having means for statistical evaluation and post-processing of the output data sets and the pre-stored data sets and modifying the pre-stored data sets in the tangible data storage based on results of evaluation and processing.

18. A vehicle comprising:

means for transferring information about at least one of an area of interest and a vehicle path to a remote server database and for receiving first data sets comprising driving-relevant object data, such driving-relevant object data further comprising at least location information and detailed object-based information characterizing at least one of a road object, a road furniture object and a geographic object under at least one of the following conditions;

a) within the at least one of the area of interest and the vehicle path;

at a specific time or time interval; and

c) with respect to a specific object;

the vehicle having at least one sensor configured to collect, in operation of the vehicle, at least one ambient data set under said at least one of conditions including i) along path sections, of the vehicle path that includes a location corresponding to said location information, ii) at the specific time or time interval, and iii) with respect to the specific object, the ambient data sets characterizing at least one of the road object, the road furniture object, and the geographic object,

the vehicle having a computer of the vehicle configured

to acquire said ambient data sets from the at least one sensor of the vehicle,

to evaluate the ambient data sets to form an evaluation result,

to generate second data sets based on the evaluation result, each second data set comprising driving-relevant object data,

to generate third data sets that contains at least one of;

differences between the object-based information of the second data sets and the object-based information of the respectively corresponding first data sets related to the path sections that at least partially overlap with one another, and

the object-based information of the second data sets related to the path sections that at least partially overlap with one another, and

means for forwarding the third data sets to an external database.