Traffic object intent estimation
A method comprises periodically monitoring, by a processor, lateral position and velocity of vehicle within a predetermined distance from an autonomous vehicle, the vehicle moving in a direction having at least one common attribute with the autonomous vehicle; executing, by the processor, a computer model using the monitored lateral position and velocity of the vehicle, to predict whether a trajectory for the vehicle; and when a current trajectory of the autonomous has a likelihood of collision with the predicted trajectory of the vehicle that satisfies a threshold, determining, by the processor, an alternative trajectory for the autonomous vehicle.
1. A method comprising:
periodically monitoring, by a processor, lateral position and velocity of a vehicle within a predetermined distance from a lane line representing a boundary of a lane of an autonomous vehicle, the vehicle is moving in a same direction as the autonomous vehicle;
executing, by the processor, a computer model using the monitored lateral position and velocity of the vehicle, to predict a path and a velocity of the vehicle;
determining, by the processor, an intent of the vehicle i) to exit the lane of the autonomous vehicle, or ii) to enter into the lane of the autonomous vehicle, based at least in part on a lateral velocity of the vehicle, wherein the lateral velocity is determined based on the path and the velocity;
determining, by the processor, whether a predicted trajectory for the vehicle has a likelihood of collision with the autonomous vehicle within a time threshold, based on time to collision between the autonomous vehicle and the vehicle determined at least in part based on the path and the velocity of the vehicle;
in response to the vehicle having a threshold distance from the lane line and in response to a current trajectory of the autonomous vehicle having the likelihood of collision with the predicted trajectory of the vehicle satisfying a threshold, determining, by the processor, an alternative trajectory for the autonomous vehicle; and
controlling operation of the autonomous vehicle to travel according to the alternative trajectory.
2. The method of claim 1 , wherein the alternative trajectory comprises a reduction in a velocity of the autonomous vehicle.
3. The method of claim 1 , wherein the alternative trajectory comprises a lane change.
4. The method of claim 1 , wherein the alternative trajectory comprises activating a horn of the autonomous vehicle.
5. The method of claim 1 , wherein the alternative trajectory comprises exiting a current path of the autonomous vehicle.
6. The method of claim 1 , further comprising:
when the likelihood of collision does not satisfy the threshold, reverting, by the processor, the autonomous vehicle to the current trajectory.
7. The method of claim 1 , further comprising:
transmitting, by the processor, a notification indicating that the likelihood of collision satisfies the threshold.
8. The method of claim 1 , wherein the vehicle is in an adjacent lane to the autonomous vehicle.
9. A system comprising:
a non-transitory computer-readable storage medium that contains instructions configured to be executed by at least one processor to:
periodically monitor lateral position and velocity of a vehicle within a predetermined distance from a lane line representing a boundary of a lane of an autonomous vehicle, the vehicle is moving in a same direction as the autonomous vehicle;
execute a computer model using the monitored lateral position and velocity of the vehicle, to predict a path and a velocity of the vehicle;
determine, by the at least one processor, an intent of the vehicle i) to exit the lane of the autonomous vehicle, or ii) to enter into the lane of the autonomous vehicle, based at least in part on a lateral velocity of the vehicle, wherein the lateral velocity is determined based on the path and the velocity;
determine, by the at least one processor, whether a predicted trajectory for the vehicle has a likelihood of collision with the autonomous vehicle within a time threshold, based on time to collision between the autonomous vehicle and the vehicle determined at least in part based on the path and the velocity of the vehicle;
in response to the vehicle having a threshold distance from the lane line and in response to a current trajectory of the autonomous vehicle having the likelihood of collision with the predicted trajectory of the vehicle satisfying a threshold, determine an alternative trajectory for the autonomous vehicle; and
control operation of the autonomous vehicle to travel according to the alternative trajectory.
10. The system of claim 9 , wherein the alternative trajectory comprises a reduction in a velocity of the autonomous vehicle.
11. The system of claim 9 , wherein the alternative trajectory comprises a lane change.
12. The system of claim 9 , wherein the alternative trajectory comprises activating a horn of the autonomous vehicle.
13. The system of claim 9 , wherein the alternative trajectory comprises exiting a current path of the autonomous vehicle.
14. The system of claim 9 , wherein the at least one processor is further configured to:
when the likelihood of collision does not satisfy the threshold, revert the autonomous vehicle to the current trajectory.
15. The system of claim 9 , wherein the at least one processor is further configured to:
transmit a notification indicating that the likelihood of collision satisfies the threshold.
16. The system of claim 9 , wherein the vehicle is in an adjacent lane to the autonomous vehicle.