Method and system for localizing a vehicle

Patent metadata

Field	Value
Publication number	US-11092445-B2
Application number	US-201716342469-A
Country	US
Kind code	B2
Filing date	Aug 28, 2017
Priority date	Oct 17, 2016
Publication date	Aug 17, 2021
Grant date	Aug 17, 2021

Abstract

A method and a corresponding system for localizing a vehicle using a digital map are described. In accordance with the method, the digital map assigns to the features one or a plurality of predetermined attributes, which are provided for characterizing possibly occurring actual changes in the features comparison to the digital map existing at the moment. On the basis of the assigned attributes, probabilities relative to the changes are also determined, and the vehicle is localized in consideration of the determined probabilities.

First claim

What is claimed is:

1. A method for localizing a vehicle using a digital map that describes one or more features, the method comprising:
for a respective one of the one or more features, causing the digital map to assign at least one predetermined attribute to the respective feature, wherein the at least one predetermined attribute characterizes an actual change made to the digital map regarding the respective feature;
determining a corresponding probability for a further change based on the assigned at least one predetermined attribute; and
localizing the vehicle in consideration of the determined probability.

2. The method as recited in claim 1 , wherein the respective feature is of an environment of a vehicle.

3. The method as recited in claim 1 , wherein the at least one predetermined attribute includes a value that is specified in accordance with a particular type of the respective feature.

4. The method as recited in claim 1 , wherein the at least one predetermined attribute includes information about one of a cycle time and a change rate, and includes information about a point in time of a most recent change of the respective feature.

5. The method as recited in claim 1 , wherein the one or more features include a plurality of features, and wherein the at least one predetermined attribute includes a plurality of attributes, the method further comprising:
recording a version of the respective feature in a driving environment of the vehicle using a driving environment sensor system;
comparing the recorded version of the respective feature to a version of the feature in the digital map; and
when the comparing yields an ambivalence, at least one of prioritizing and weighting the respective feature based on a respective probable availability or updatedness determined from the attributes.

6. The method as recited in claim 5 , wherein, responsive to an updating of the digital map, the attributes assigned to the respective feature are adapted accordingly.

7. The method as recited in claim 1 , wherein the at least one predetermined attribute identifies when the actual change was made.

8. The method as recited in claim 1 , wherein the at least one predetermined attribute indicates an expected time the further change is expected to occur.

9. The method as recited in claim 1 , wherein the at least one predetermined attribute identified when the actual change was made and an expected period of time from when the actual change was made to when the further change is expected to occur.

10. A method for localizing a vehicle using a digital map that describes a feature, the method comprising:
causing the digital map to assign at least one predetermined attribute to the feature, wherein the at least one predetermined attribute characterizes the feature changing relative to the digital map;
determining, based on the at least one predetermined attribute, a model for a progression over time of a probability of the changing of the feature; and
localizing the vehicle based on the probability.

11. The method as recited in claim 10 , wherein the model is formed as at least one of a periodic superlinerality curve and a piecewise superlinearly rising sawtooth-like curve.

12. A system of a vehicle for localizing the vehicle using a digital map that describes one or more features to a respective one of which is assigned at least one predetermined attribute that characterizes an actual change made to the digital map regarding the respective feature, the system comprising:
a localization unit, wherein the localization unit is configured to:
determine a probability for a further change based on the assigned at least one predetermined attribute; and
localize the vehicle based on the determined probability.

13. The system as recited in claim 12 , wherein the respective feature is of an environment of the vehicle.

14. The system as recited in claim 12 , wherein the localization unit is further configured to:
read and record the at least one predetermined attribute, the localization unit being connected to a memory for the digital map; and
update the at least one predetermined attribute in response to an updating of map data.

15. The system as recited in claim 12 , wherein the one or more features include features created or influenced by people, including lane markings, bridges, buildings, a number of lanes or sign gantries, and/or road signs.

16. A vehicle, comprising:
a control unit, wherein the control unit is configured to perform a method that uses a digital map that describes one or more features to a respective one of which is assigned at least one predetermined attribute that characterizes an actual change made to the digital map regarding the respective feature, the method comprising
determining a probability for a further change based on the assigned at least one predetermined attribute; and
localizing the vehicle based on the determined probability.

17. The vehicle as recited in claim 16 , wherein the vehicle is an autonomously driving vehicle.

18. A non-transitory computer-readable medium on which are stored instructions that are executable by a processor of a vehicle and that, when executed by the processor, causes the processor to perform a method for localizing the vehicle using a digital map that describes one or more features, the method comprising:
for a respective one of the one or more features, causing the digital map to assign at least one predetermined attribute to the respective feature, wherein the at least one predetermined attribute characterizes an actual change made to the digital map regarding the respective feature;
determining a corresponding probability for a further change based on the assigned at least one predetermined attribute; and
localizing the vehicle in consideration of the determined probability.

Assignees

• Bosch Gmbh Robert

Inventors

• Hasberg Carsten
• Schroeder Christoph
• Hiendriana Danny
• Pink Oliver
• Rasp Philipp

Classifications

• G01C21/3837 Primary

  Data obtained from a single source · CPC title

• G01C21/30

  Map- or contour-matching · CPC title

• G05D2201/0213

  Physics · mapped topic

• G05D1/0088

  characterized by the autonomous decision making process, e.g. artificial intelligence, predefined behaviours (using knowledge based models G06N5/00) · CPC title

• G05D1/0274

  using mapping information stored in a memory device (navigation using map-matching G01C21/30) · CPC title