Systems and methods for deweighting veering margins based on crossing time
This document discloses system, method, and computer program product embodiments for operating a vehicle. For example, the method includes: obtaining a vehicle trajectory for the vehicle and a possible object trajectory for a moving object; analyzing the vehicle trajectory and the possible object trajectory to identify a time interval in which a footprint of the vehicle overlaps laterally with a footprint of the object; generating a mover raw margin in the time interval by shifting the footprint of the vehicle laterally until contact is made with the footprint of the object; obtaining a crossing time associated with each point in the mover raw margin; and generating a mover strong boundary by laterally shifting point(s) of the mover raw margin in the direction towards the vehicle when the crossing time(s) associated with the point(s) is(are) equal to or less than a threshold time.
1. A method for operating a vehicle, comprising:
obtaining, by a computing device, a vehicle trajectory for the vehicle and a possible object trajectory for a moving object;
analyzing, by the computing device, the vehicle trajectory and the possible object trajectory to identify a time interval in which a footprint of the vehicle overlaps laterally with a footprint of the moving object, wherein the footprint of the vehicle does not overlap with the footprint of the moving object longitudinally during the time interval;
generating, by the computing device, a mover raw margin in the time interval by shifting the footprint of the vehicle laterally until contact is made with the footprint of the object;
obtaining, by the computing device, a crossing time associated with each point of a plurality of points in the mover raw margin;
generating, by the computing device, a mover strong boundary by laterally shifting at least one point of the mover raw margin in the direction towards the vehicle when the crossing time associated with said at least one point is equal to or less than a threshold time;
generating a lateral vehicle trajectory for the vehicle to follow based on at least the mover strong boundary; and
controlling the vehicle to follow the lateral vehicle trajectory.
2. The method of claim 1 , wherein controlling the vehicle to follow the lateral vehicle trajectory comprises steering the vehicle laterally toward the moving object while a center of gravity of the vehicle does not cross the mover strong boundary.
3. The method according to claim 1 , wherein the crossing time comprises a time at which the vehicle is lateral to the moving object at a location of a respective point of the plurality of points in the mover raw margin.
4. The method according to claim 1 , wherein a constant weight is assigned to the mover strong boundary which reflects an incentive to avoid reaching a minimum distance from the object.
5. The method according to claim 1 , further comprising:
expanding, by the computing device, the mover raw margin in time and distance to generate a vehicle veering margin; and
generating, by the computing device, a mover weak boundary by laterally shifting the vehicle veering margin in a direction towards the vehicle by a first amount that is greater than a second amount by which said point of the mover raw margin is laterally shifted to generate the mover strong boundary.
6. The method according to claim 5 , further comprising computing, by the computing device, crossing times for a plurality of points in the vehicle veering margin based on the mover raw margin.
7. The method according to claim 6 , wherein the crossing time for each one of the plurality of points in the vehicle veering margin, which is located before a start point of the mover raw margin, is set equal to a time associated with the start point of the mover raw margin.
8. The method according to claim 6 , wherein the crossing time for each one of the plurality of points in the vehicle veering margin, which is located after an end point of the mover raw margin, is set equal to a time associated with the end point of the mover raw margin.
9. The method according to claim 6 , further comprising using the crossing times associated with the vehicle veering margin to scale weights for the mover weak boundary.
10. The method according to claim 9 , wherein the weights for the mover weak boundary reflect an incentive for the vehicle to react to the mover weak boundary.
11. A system, comprising:
a memory; and
at least one processor coupled to the memory and configured to:
obtain a vehicle trajectory for the vehicle and a possible object trajectory for a moving object;
analyze the vehicle trajectory and the possible object trajectory to identify a time interval in which a footprint of the vehicle overlaps laterally with a footprint of the moving object;
generate a mover raw margin in the time interval by shifting the footprint of the vehicle laterally until contact is made with the footprint of the object;
obtain a crossing time associated with each point of a plurality of points in the mover raw margin;
generate a mover strong boundary by laterally shifting at least one point of the mover raw margin in the direction towards the vehicle when the crossing time associated with said at least one point is equal to or less than a threshold time;
generate a lateral vehicle trajectory for the vehicle to follow based on at least the mover strong boundary; and
control the vehicle to follow the lateral vehicle trajectory.
12. The system of claim 11 , wherein the footprint of the vehicle does not overlap with the footprint of the moving object longitudinally during the time interval, and controlling the vehicle to follow the lateral vehicle trajectory comprises steering the vehicle laterally toward the mover strong boundary while a center of gravity of the vehicle does not cross the mover strong boundary.
13. The system according to claim 11 , wherein the crossing time comprises a time at which the vehicle is lateral to the moving object at a location of a respective point of the plurality of points in the mover raw margin.
14. The system according to claim 11 , wherein a constant weight is assigned to the mover strong boundary which reflects an incentive to avoid reaching a minimum distance from the object.
15. The system according to claim 11 , wherein the at least one processor is further configured to:
expand the mover raw margin in time and distance to generate a vehicle veering margin; and
generate a mover weak boundary by laterally shifting the vehicle veering margin in a direction towards the vehicle by a first amount that is greater than a second amount by which said point of the mover raw margin is laterally shifted to generate the mover strong boundary.
16. The system according to claim 15 , wherein the at least one processor is further configured to compute crossing times for a plurality of points in the vehicle veering margin based on the mover raw margin.
17. The system according to claim 16 , wherein the crossing time for each one of the plurality of points in the vehicle veering margin, which is located before a start point of the mover raw margin, is set equal to a time associated with the start point of the mover raw margin.
18. The system according to claim 16 , wherein the crossing time for each one of the plurality of points in the vehicle veering margin, which is located after an end point of the mover raw margin, is set equal to a time associated with the end point of the mover raw margin.
19. The system according to claim 16 , wherein the at least one processor is further configured to use the crossing times associated with the vehicle veering margin to scale weights for the mover weak boundary.
20. A non-transitory computer-readable medium that stores instructions that is configured to, when executed by at least one computing device, cause the at least one computing device to perform operations comprising:
obtaining a vehicle trajectory for the vehicle and a possible object trajectory for a moving object;
analyzing the vehicle trajectory and the possible object trajectory to identify a time interval in which a footprint of the vehicle overlaps laterally with a footprint of the object;
generating a mover raw margin in the time interval by shifting the footprint of the vehicle laterally until contact is made with the footprint of the object;
obtaining a crossing time associated with each point of a plurality of points in the mover raw margin;
generating a mover strong boundary by laterally shifting at least one point of the mover raw margin in the direction towards the vehicle when the crossing time associated with said at least one point is equal to or less than a time;
generating a lateral vehicle trajectory for the vehicle to follow based on at least the mover strong boundary; and
controlling the vehicle to follow the lateral vehicle trajectory.