Methods and systems to aid autonomous vehicles driving through a lane merge
View Patent ↗Methods and devices for controlling a vehicle in an autonomous mode are disclosed. In one aspect, an example method is disclosed that includes obtaining, by a computer system, lane information that provides an estimated location of a lane of a road on which a vehicle is travelling, where the computer system is configured to control the vehicle in an autonomous mode. The example method further includes determining, by the computer system, that the lane information has become unavailable or unreliable and, in response to determining that the lane information has become unavailable or unreliable, the computer system analyzing trajectories of other vehicles to locate a potential merge point on the road and creating a new trajectory that follows the lane at the potential merge point.
1. A method comprising:
obtaining, by a computer system, lane information that provides an estimated location of a current lane of a road on which a vehicle is travelling, wherein the computer system is configured to control the vehicle in an autonomous mode;
identifying trajectories associated with other vehicles driving on or near the road;
determining, by the computer system, that the lane information has become unavailable or unreliable; and
in response to determining that the lane information has become unavailable or unreliable, the computer system creating a new trajectory based on the trajectories associated with other vehicles, comprising:
analyzing the trajectories to locate points of intersection among the trajectories representing a potential merge point on the road,
determining a location of a lane at the potential merge point,
creating a new trajectory that follows the lane at the potential merge point, and
controlling the vehicle to travel along the new trajectory.
2. The method of claim 1 , wherein the lane information is based on a predetermined map of the road.
3. The method of claim 2 , wherein determining that the lane information has become unavailable or unreliable comprises detecting that the lane information is not included in the predetermined map of the road.
4. The method of claim 2 , wherein determining that the lane information has become unavailable or unreliable comprises detecting that there is an error in the predetermined map.
5. The method of claim 1 , wherein identifying trajectories associated with other vehicles on or near the road comprises identifying vehicles in the same lane as the autonomous vehicle.
6. The method of claim 1 , wherein identifying trajectories associated with other vehicles on or near the road comprises identifying vehicles in a different lane than the autonomous vehicle.
7. The method of claim 1 , wherein analyzing the trajectories to locate points of intersection among the trajectories representing a potential merge point on the road comprises reviewing the trajectories associated with the other vehicles to find trajectories whose paths are initially separated by at least about a lane width and thereafter the separation between the paths decreases so that the paths either overlap or become separated by less than a lane width.
8. The method of claim 1 , wherein determining a location of a lane at the potential merge point further comprises:
measuring curvatures of the trajectories leading up to the potential merge point,
grouping the trajectories into a plurality of sets based on the measured curvatures,
averaging the curvatures for each set, and
selecting a set of trajectories that has less average curvature than the one or more other sets in the plurality of sets as trajectories that represent the location of the lane at the potential merge point.
9. The method of claim 1 , wherein creating a new trajectory that follows the lane at the potential merge point comprises providing for a lane change for the autonomous vehicle.
10. The method of claim 1 , wherein creating a new trajectory that follows the lane at the potential merge point comprises providing for the autonomous vehicle to remain in the current lane.
11. The method of claim 1 , further comprising:
obtaining information regarding a road condition at the potential merge point.
12. A vehicle comprising:
at least one processor; and
data storage comprising instructions executable by the at least one processor to cause a computer system to perform functions comprising:
obtaining lane information that provides an estimated location of a current lane of a road on which a vehicle is travelling, wherein the computer system is configured to control the vehicle in an autonomous mode;
identifying trajectories associated with other vehicles driving on or near the road;
determining, by the computer system, that the lane information has become unavailable or unreliable; and
in response to determining that the lane information has become unavailable or unreliable, the computer system:
analyzing the trajectories to locate points of intersection among the trajectories representing a potential merge point on the road,
determining a location of a lane at the potential merge point,
creating a new trajectory that follows the lane at the potential merge point, and
controlling the vehicle to travel along new trajectory.
13. The vehicle of claim 12 , wherein the lane information is based on a predetermined map of the road.
14. The vehicle of claim 12 , wherein determining that the lane information has become unavailable or unreliable comprises detecting that the lane information is not included in the predetermined map of the road.
15. The vehicle of claim 12 , wherein determining that the lane information has become unavailable or unreliable comprises detecting that there is an error in the predetermined map.
16. The vehicle of claim 12 , wherein identifying trajectories associated with other vehicles on or near the road comprises identifying vehicles in a different lane than the autonomous vehicle.
17. The vehicle of claim 12 , wherein functions further comprise:
measuring curvatures of the trajectories leading up to the potential merge point,
grouping the trajectories into a plurality of sets based on the measured curvatures,
averaging the curvatures for each set, and
selecting a set of trajectories that has less average curvature than the one or more other sets in the plurality of sets as the trajectories that represent the location of the lane at the potential merge point.
18. The vehicle of claim 12 , wherein analyzing the trajectories to locate points of intersection among the trajectories representing a potential merge point on the road comprises reviewing the trajectories associated with the other vehicles to find trajectories whose paths are initially separated by at least about a lane width and thereafter the separation between the paths decreases so that the paths either overlap or become separated by less than a lane width.
19. A non-transitory computer-readable medium having stored therein instructions executable by a computing device to cause the computing device to perform functions comprising:
obtaining lane information that provides an estimated location of a current lane of a road on which a vehicle is travelling, wherein the computer system is configured to control the vehicle in an autonomous mode;
identifying trajectories associated with other vehicles driving on or near the road;
determining, by the computer system, that the lane information has become unavailable or unreliable; and
in response to determining that the lane information has become unavailable or unreliable, the computer system:
analyzing the trajectories to locate points of intersection among the trajectories representing a potential merge point on the road,
determining a location of a lane at the potential merge point,
creating a new trajectory that follows the lane at the potential merge point, and
controlling the vehicle to travel along new trajectory.
20. The non-transitory computer-readable medium of claim 19 , wherein the lane information is based on a predetermined map of the road.