Predictive planning

1. A computer-implemented method comprising:

acquiring, by a computing system, data regarding historical movement of a lead obstacle and one or more obstacles in front of the lead obstacle;

predicting, by the computing system, movement of at least the lead obstacle based at least in part on the data;

applying, by the computing system, the predicted movement of the lead obstacle to an optimizable function associated with movement of an ego vehicle, the optimizable function based at least in part on a combination of a safety term and a traffic term, wherein the safety term is weighted by a constant value and the traffic term is weighted by a value inversely related to a headway distance;

generating, by the computing system, a plan for movement of the ego vehicle based on minimization of the optimizable function; and

moving, by the computing system, the ego vehicle based on the plan.

2. The computer-implemented method of claim 1 , wherein the predicted movement of the lead obstacle includes predicted speed of the lead obstacle.

3. The computer-implemented method of claim 1 , wherein the predicting is based on a model that generates at least a speed profile of the lead obstacle.

4. The computer-implemented method of claim 3 , wherein the model assumes that the lead obstacle and the one or more obstacles in front of the lead obstacle have the same velocity at the same location.

5. The computer-implemented method of claim 3 , wherein the data includes distances and velocities of the lead obstacle and distances and velocities of the one or more obstacles in front of the lead obstacle over a duration of time, and the model is a learning based algorithm that is trained based on the data.

6. The computer-implemented method of claim 5 , wherein the predicted movement of the lead obstacle is based on a function determined by the data, the predicted movement associated with a time following the duration of time.

7. The computer-implemented method of claim 1 , wherein the safety term is based at least in part on a difference between a preferred following distance and an obstacle distance and the traffic term is based at least in part on a difference between a velocity of the ego vehicle and a traffic target speed.

8. The computer-implemented method of claim 1 , wherein the lead obstacle and the one or more obstacles in front of the lead obstacle are vehicles traveling in an ego lane.

9. A system comprising:

at least one processor; and

a memory storing instructions that, when executed by the at least one processor, cause the system to perform operations comprising:

acquiring data regarding historical movement of a lead obstacle and one or more obstacles in front of the lead obstacle;

predicting movement of at least the lead obstacle based at least in part on the data;

applying the predicted movement of the lead obstacle to an optimizable function associated with movement of an ego vehicle, the optimizable function based at least in part on a combination of a safety term and a traffic term, wherein the safety term is weighted by a constant value and the traffic term is weighted by a value inversely related to a headway distance;

generating a plan for movement of the ego vehicle based on minimization of the optimizable function; and

moving the ego vehicle based on the plan.

10. The system of claim 9 , wherein the predicted movement of the lead obstacle includes predicted speed of the lead obstacle.

11. The system of claim 9 , wherein the predicting is based on a model that generates at least a speed profile of the lead obstacle.

12. The system of claim 11 , wherein the model assumes that the lead obstacle and the one or more obstacles in front of the lead obstacle have the same velocity at the same location.

13. The system of claim 11 , wherein the data includes distances and velocities of the lead obstacle and distances and velocities of the one or more obstacles in front of the lead obstacle over a duration of time, and the model is a learning based algorithm that is trained based on the data.

14. The system of claim 13 , wherein the predicted movement of the lead obstacle is based on a function determined by the data, the predicted movement associated with a time following the duration of time.

15. A non-transitory computer-readable storage medium including instructions that, when executed by at least one processor of a computing system, cause the computing system to perform operations comprising:

acquiring data regarding historical movement of a lead obstacle and one or more obstacles in front of the lead obstacle;

predicting movement of at least the lead obstacle based at least in part on the data; and

applying the predicted movement of the lead obstacle to an optimizable function associated with movement of an ego vehicle, the optimizable function based at least in part on a combination of a safety term and a traffic term, wherein the safety term is weighted by a constant value and the traffic term is weighted by a value inversely related to a headway distance;

generating a plan for movement of the ego vehicle based on minimization of the optimizable function; and

moving the ego vehicle based on the plan.

16. The non-transitory computer-readable storage medium of claim 15 , wherein the predicted movement of the lead obstacle includes predicted speed of the lead obstacle.

17. The non-transitory computer-readable storage medium of claim 15 , wherein the predicting is based on a model that generates at least a speed profile of the lead obstacle.

18. The non-transitory computer-readable storage medium of claim 17 , wherein the model assumes that the lead obstacle and the one or more obstacles in front of the lead obstacle have the same velocity at the same location.

19. The non-transitory computer-readable storage medium of claim 17 , wherein the data includes distances and velocities of the lead obstacle and distances and velocities of the one or more obstacles in front of the lead obstacle over a duration of time, and the model is a learning based algorithm that is trained based on the data.

20. The non-transitory computer-readable storage medium of claim 19 , wherein the predicted movement of the lead obstacle is based on a function determined by the data, the predicted movement associated with a time following the duration of time.