Encoding junction information in map data
Embodiments of the present disclosure relate to encoding of junction area information in map data. In particular, the encoding may include organizing vehicle paths that traverse through a junction area according to path groups and organizing contentions that influence behavior of vehicles traveling along the vehicle paths according to contention groups. In addition, the encoding may include generating direction data structures that associate respective path groups with one or more of the contention groups. In these or other embodiments, the map data that corresponds to the junction area may be updated with direction data structures.
1. A method comprising:
performing, by an autonomous or semi-autonomous machine, one or more navigation, localization, or control operations for one or more of steering, braking, or accelerating the autonomous or semi-autonomous machine based at least on map data of an area that has been updated at least by:
identifying, in the map data, a junction area that corresponds to one or more potential yield scenarios associated with a corresponding geographical area represented by the map data;
organizing one or more paths that traverse through the junction area according to one or more path groups based at least on directionality of the one or more paths through the junction area;
organizing one or more contentions that influence behavior of objects traveling along the paths according to one or more contention groups based at least on object behavior influenced by the contentions;
associating, using one or more direction data structures, the one or more path groups with at least one contention group of the one or more contention groups; and
updating at least a portion of the map data that corresponds to the junction area with the one or more direction data structures.
2. The method of claim 1 , further comprising obtaining one or more respective direction rules with respect to the one or more direction data structures, at least one direction rule of the one or more direction rules corresponding to a particular contention group and a particular path group of a particular direction data structure of the one or more direction data structures and defining one or more object behaviors that correspond to the particular contention group and the particular path group.
3. The method of claim 2 , wherein the particular direction data structure associates the at least one direction rule with the particular contention group and the particular path group.
4. The method of claim 2 , wherein:
the at least one direction rule is obtained from a rule library that indicates an association between the particular contention group and the particular path group.
5. The method of claim 1 , wherein the one or more contentions include one or more of:
merging paths;
intersecting paths;
a traffic signal;
a pedestrian area;
a railroad crossing area; or
a driveway area.
6. The method of claim 1 , further comprising identifying one or more of the contentions based at least on identified intersections between the paths and the one or more contentions.
7. The method of claim 1 , wherein the contentions include traffic signals and organizing the contentions includes organizing the traffic signals into signal groups further based at least on directionality of the traffic signals.
8. The method of claim 1 , further comprising determining a yield behavior for the machine based at least on the map data as updated.
9. One or more processors comprising:
one or more circuits to:
identify, in map data of an area, a junction area that corresponds to one or more potential yield scenarios associated with a corresponding geographical area represented by the map data;
organize one or more paths that traverse through the junction area according to one or more path groups based at least on directionality of the paths through the junction area;
organize one or more contentions that influence behavior of objects traveling along the paths according to one or more contention groups based at least on behavior influenced by the contentions;
generate one or more direction data structures that respectively associate the one or more path groups with at least one of the one or more contention groups; and
update the map data that corresponds to the junction area with the one or more direction data structures, wherein the map data as updated is used by one or more autonomous or semi-autonomous machines to perform one or more navigation, localization, or control operations for autonomous or semi-autonomous maneuvering that includes one or more of steering, braking, or accelerating the one or more autonomous or semi-autonomous machines.
10. The one or more processors of claim 9 , wherein:
the one or more circuits are further to obtain one or more respective direction rules with respect to the one or more direction data structures, at least one direction rule of the one or more direction rules corresponding to a particular contention group and a particular path group of a particular direction data structure of the one or more direction data structures and defining one or more object behaviors that correspond to the particular contention group and the particular path group; and
the particular direction data structure associates the at least one direction rule with the particular contention group and the particular path group.
11. The one or more processors of claim 10 , wherein:
the at least one direction rule is obtained from a rule library that indicates an association between the particular contention group and the particular path group.
12. The one or more processors of claim 9 , wherein the contentions include one or more of:
merging paths;
intersecting paths;
a traffic signal;
a pedestrian area;
a railroad crossing area; or
a driveway area.
13. The one or more processors of claim 9 , wherein the one or more circuits are further to identify one or more of the contentions based at least on identified intersections between the paths and the one or more contentions.
14. The one or more processors of claim 9 , wherein the contentions include traffic signals and organizing the contentions includes organizing the traffic signals into signal groups further based at least on directionality of the traffic signals.
15. A system comprising:
one or more processing units to cause one or more autonomous or semi-autonomous machines to perform one or more navigation, localization, or control operations for autonomous or semi-autonomous maneuvering that includes one or more of steering, braking, or accelerating the one or more autonomous or semi-autonomous machines, the one or more navigation, localization, or control operations being based at least on map data that has been updated at least by:
organizing one or more paths that traverse through a junction area according to one or more path groups based at least on directionality of the paths through the junction area, the junction area corresponding to one or more potential yield scenarios associated with a geographical area;
organizing one or more contentions that influence behavior of objects traveling along the paths according to one or more contention groups based at least on path entry points and path exit points with respect to the junction area;
obtaining one or more direction rules, at least one direction rule of the one or more direction rules corresponding to a particular contention group and a particular path group and defining one or more object behaviors that correspond to the particular contention group and the particular path group;
generating one or more direction data structures that respectively associate two or more of: the one or more path groups, the one or more contention groups, and the one or more direction rules; and
updating at least a portion of the map data that corresponds to the junction area with the one or more direction data structures.
16. The system of claim 15 , wherein the contentions include one or more of:
merging paths;
intersecting paths;
a traffic signal;
a pedestrian area;
a railroad crossing area; or
a driveway area.
17. The system of claim 15 , wherein the updating of the map data further includes identifying one or more of the contentions based at least on identified intersections between the paths and the one or more contentions.
18. The system of claim 15 , wherein the contentions include traffic signals and organizing the contentions includes organizing the traffic signals into signal groups further based at least on directionality of the traffic signals.
19. The system of claim 15 , wherein the one or more processing units are further to:
determine a yield behavior based at least on the map data as updated; and
perform the one or more navigation, localization, or control operations based at least on the yield behavior.
20. The system of claim 15 , wherein the one or more processing units are further to define the junction area using a polygon in which the path entry points and the path exit points correspond to borders of the polygon.