Methods and systems for generating a horizon for use in an advanced driver assistance system (ADAS)

Patent metadata

Field	Value
Publication number	US-11378404-B2
Application number	US-201715663931-A
Country	US
Kind code	B2
Filing date	Jul 31, 2017
Priority date	Nov 2, 2012
Publication date	Jul 5, 2022
Grant date	Jul 5, 2022

Abstract

A method of generating a horizon for use by an ADAS of a vehicle involves using digital location-based data, driver data and/or vehicle data to determine the likelihood that different outgoing paths are taken at a decision point along a currently traversed road segment, and deriving a probability that each path may be taken. The probability may be based on one or more of: an angle of the path relative to the incoming path, the road class of the path, a speed profile of the path, historical paths taken by vehicles at the decision point, and historical paths taken at the decision point by the individual driver or vehicle.

First claim

The invention claimed is:

1. A method of generating a horizon for use in an Advanced Driver Assistance System (ADAS) of a vehicle using stored digital map data, wherein the digital map data comprises a plurality of segments representative of roads of a road network, said method comprising:
determining a segment representing a road on which the vehicle is currently travelling based on an identified current location of the vehicle;
using the determined segment to identify an upcoming decision point of the road network from the digital map data;
determining an incoming path to the decision point with respect to which outgoing paths are to be defined;
identifying if the decision point is a roundabout from the digital map data, and, when the decision point is determined to be a roundabout, treating the roundabout as a single junction such that the outgoing paths of the decision point correspond to exits of the roundabout;
determining data indicative of a relative probability that each of a plurality of possible outgoing paths associated with the decision point will be taken by the vehicle using one or more of stored digital location-based data, vehicle data and driver data, wherein the relative probability for each outgoing path is a portion of a specified total probability value that is computed based on properties of that outgoing path, and wherein the relative probabilities for the outgoing paths for the decision point sum to the specified total probability value;
determining one or more predicted paths that the vehicle will be expected to travel in the immediate future at the decision point using the data indicative of a relative probability;
generating the horizon using the one or more predicted paths; and
providing data associated with the generated horizon to one or more applications, the data associated with the generated horizon configured to be used by the one or more applications when controlling corresponding vehicle subsystems.

2. The method of claim 1 , wherein each segment of the digital map data is associated with data indicative of one or more attributes of the road represented by the segment, and wherein the digital location-based data used to determine the data indicative of a relative probability comprises the attribute data.

3. The method of claim 2 , wherein the attribute data includes data indicative of: a geometry of the road; a gradient of the road; an angle of the road; a road class of the road; a speed limit associated with the road; vehicle flow data indicative of vehicle flow along the road; and vehicle speed profile data for the road.

4. The method of claim 1 , wherein the vehicle data is data indicative of one or more of: vehicle type, vehicle speed, and historical movements of the vehicle, optionally a turn history of the vehicle.

5. The method of claim 1 , further comprising using data indicative of a historical relative probability that each of the plurality of possible outgoing paths from the decision point has been taken in respect of the incoming path to determine the data indicative of the relative probability that each of the plurality of outgoing paths at a decision point will be taken by the vehicle.

6. The method of claim 1 , wherein the data indicative of the relative probability that each of the possible outgoing paths will be taken is determined based on data indicative of historical paths taken by the individual driver and/or vehicle at the decision point.

7. The method of claim 1 , further comprising ranking the plurality of possible outgoing paths according to the likelihood that the vehicle may be expected to travel along the paths and/or determining a probability factor in respect of each path indicative of the relative probability that the path will be taken.

8. The method of claim 1 , wherein generating the horizon comprises predicting a most probable outgoing path and at least one alternative outgoing path that the vehicle may be expected to travel in the immediate future at a decision point, wherein the stored digital location-based data, vehicle data and/or driver data is used in determining the most probable path and/or the at least one alternative path.

9. The method of claim 1 , wherein generating the horizon is carried out by a horizon generating subsystem of the ADAS, and wherein providing the data associated with the generated horizon to the one or more applications comprises the horizon generating subsystem providing the data associated with the generated horizon over a vehicle bus to one or more ADAS applications of the vehicle.

10. A method of generating a horizon for use in an Advanced Driver Assistance System (ADAS) of a vehicle using stored digital map data, wherein the digital map data comprises a plurality of segments representative of roads of a road network, said method comprising:
determining a segment representing a road on which the vehicle is currently travelling based on an identified current location of the vehicle;
using the segment to identify an upcoming decision point of the road network from the digital map data;
determining an incoming path to the decision point with respect to which outgoing paths are to be defined;
identifying if the decision point is a plural junction from the digital map data, and, when the decision point is determined to be a plural junction, treating the plural junction as a single junction such that the outgoing paths of the decision point correspond to outgoing paths of the plurality of proximate junctions forming the plural junction;
determining data indicative of a relative probability that each of a plurality of possible outgoing paths associated with the decision point will be taken by the vehicle using one or more of stored digital location-based data, vehicle data and driver data, wherein the relative probability for each outgoing path is a portion of a specified total probability value that is computed based on properties of that outgoing path, and wherein the relative probabilities for the outgoing paths for the decision point sum to the specified total probability value;
determining one or more predicted paths that the vehicle will be expected to travel in the immediate future at the decision point using the data indicative of a relative probability;
generating the horizon using the one or more predicted paths; and
providing data associated with the generated horizon to one or more applications, the data associated with the generated horizon configured to be used by the one or more applications when controlling corresponding vehicle subsystems.

11. The method of claim 10 , wherein each segment of the digital map data is associated with data indicative of one or more attributes of the road represented by the segment, and wherein the digital location-based data used to determine the data indicative of a relative probability comprises the attribute data.

12. The method of claim 11 , wherein the attribute data includes data indicative of: a geometry of the road; a gradient of the road; an angle of the road; a road class of the road; a speed limit associated with the road; vehicle flow data indicative of vehicle flow along the road; and vehicle speed profile data for the road.

13. The method of claim 10 , wherein the vehicle data is data indicative of one or more of: vehicle type, vehicle speed, and historical movements of the vehicle, optionally a turn history of the vehicle.

14. The method of claim 10 , further comprising using data indicative of a historical relative probability that each of the plurality of possible outgoing paths from the decision point has been taken in respect of the incoming path to determine the data ind

Assignees

• Tomtom Navigation Bv

Inventors

• Manoliu Adrian-Victor
• Serbanescu Alexandru
• Trofimov Sergey Yuryevich
• Raginsky Alexander
• Zheltov Stanislav
• Koponen Lauri
• Schaminee Johannes G M

Classifications

• B60T7/12

  for automatic initiation; for initiation not subject to will of driver or passenger {(limiting speed of vehicles other than rail vehicles B60K31/00)} · CPC title

• B60W2552/20

  Road profile, i.e. the change in elevation or curvature of a plurality of continuous road segments · CPC title

• B60W2556/50

  of positioning data, e.g. GPS [Global Positioning System] data · CPC title

• B60W30/18145

  Cornering · CPC title

• G01C21/3667

  Display of a road map (G01C21/3614 takes precedence; guidance using 3D or perspective road maps G01C21/3635) · CPC title