Automated learning system for improved pickup/dropoff maneuver

1. A method for pickup/drop-off at a location, comprising:

providing, to an autonomous vehicle (AV), a parameter value of a parameter associated with the pickup/drop-off, wherein the parameter comprises a lateral offset, the lateral offset being a distance between a a center line of an outermost lane closest to the location of the pickup/drop-off and a final longitudinal axis of the AV when the AV is parked at the location to perform the pickup/drop-off;

executing, by the AV, the pickup/drop-off according to the parameter value;

receiving a customer feedback related to the parameter;

receiving a tele-operator feedback related to the parameter;

identifying other world objects at the location; and

generating an optimized parameter value for executing the pickup/drop-off,

wherein generating the optimized parameter value uses the parameter value, the customer feedback, the tele-operator feedback, and the other world objects.

2. The method of claim 1 , wherein the optimized parameter value is optimized for at least one of a time of day, weather conditions, neighborhood type of the location, or road speed limit at the location.

3. The method of claim 1 , wherein the parameter further comprises an approach speed profile.

4. The method of claim 1 , wherein the parameter further comprises a departure speed profile.

5. The method of claim 1 , wherein the AV is a first AV, further comprising:

executing, by a second AV, a second pickup/drop-off at the location according to the optimized parameter value of the parameter.

6. The method of claim 1 , wherein executing, by the AV, the pickup/drop-off according to the parameter value comprising:

selecting a maneuver for the pickup/drop-off;

receiving, by the AV, the parameter value; and

planning a path for the maneuver using the parameter value.

7. The method of claim 1 , wherein the parameter value is associated with a type of the location.

8. A system for pickup/drop-off at a location, comprising:

a processor, configured to:

provide, to a first autonomous vehicle (AV), a parameter value of a parameter associated with the pickup/drop-off, wherein the parameter comprises a lateral offset that is a distance between a center line of an outermost lane closest to the location of the pickup/drop-off and a final longitudinal axis of the first AV when the first AV is parked at the location to perform the pickup/drop-off;

receive, subsequent to the first AV executing the pickup/drop-off according to the parameter value, feedback related to the parameter;

generate an optimized parameter value for executing the pickup/drop-off,

wherein to generate the optimized parameter value uses the parameter value and the feedback related to the parameter; and

in response to a request from a second AV for the parameter, provide, to the second AV, the optimized parameter value.

9. The system of claim 8 , wherein to receive the feedback related to the parameter comprises to:

receive, subsequent to the first AV executing the pickup/drop-off according to the parameter value, a customer feedback related to the parameter; and

receive, from a tele-operator, a tele-operator feedback related to the parameter.

10. The system of claim 9 , wherein the processor is further configured to:

identify other world objects at the location; and

identify respective risks for at least some of the other world objects, wherein the respective risks are associated with the first AV executing the pickup/drop-off according to the parameter value.

11. The system of claim 10 , wherein to generate the optimized parameter value further uses the respective risks.

12. The system of claim 8 , wherein the processor is further configured to:

provide, to a third AV, another parameter value of another parameter associated with another pickup/drop-off at another location, wherein the another location is at least one of a cul-de-sac or an airport taxi lane.

13. The system of claim 8 , wherein the parameter further comprises an approach speed profile.

14. The system of claim 8 , wherein the parameter further comprises a departure speed profile.

15. A method for a pickup/drop-off at a location, comprising:

providing, to a first autonomous vehicle (AV), a parameter value of a parameter associated with the pickup/drop-off, wherein the location of the pickup/drop-off is a straight curb and the parameter comprises a lateral offset that defines how far a longitudinal axis of the AV is to be from a center of a lane closest to the straight curb when the AV performs a pull-over maneuver for the pick-up/drop-off;

receiving, subsequent to the first AV executing the pickup/drop-off according to the parameter value, feedback related to the parameter;

generating an optimized parameter value for executing the pickup/drop-off, wherein to generate the optimized parameter value uses the parameter value and the feedback related to the parameter; and

in response to a request from a second AV for the parameter, providing, to the second AV, the optimized parameter value.

16. The method of claim 15 , wherein receiving the feedback related to the parameter comprises:

receiving, subsequent to the first AV executing the pickup/drop-off according to the parameter value, a customer feedback related to the parameter; and

receiving, from a tele-operator, a tele-operator feedback related to the parameter.

17. The method of claim 16 , further comprising:

identifying other world objects at the location; and

identifying respective risks for at least some of the other world objects, wherein the respective risks are associated with the first AV executing the pickup/drop-off according to the parameter value.

18. The method of claim 17 , wherein generating the optimized parameter value further uses the respective risks.

19. The method of claim 16 , further comprising:

displaying, to the tele-operator, an augmented view of the location, wherein a representation of the AV is displayed on the augmented view, and wherein the tele-operator provides the tele-operator feedback by manipulating the augmented view.

20. The method of claim 15 , wherein the parameter further comprises at least one of an approach speed profile or departure speed profile.