Learning in lane-level route planner

1. A method for lane-level route planning, comprising:

obtaining lane-level information of a road,

wherein the road comprises a first lane and a second lane, and

wherein the lane-level information comprises first lane information related to the first lane and second lane information related to the second lane;

converting the lane-level information to probabilities for a state transition function;

obtaining a policy as a solution to a model that uses the state transition function,

wherein, given that a vehicle is on a first lane segment, the policy provides an action for controlling the vehicle with respect to moving to a second lane segment that neighbors the first lane segment,

wherein the model is a decision process that incorporates, into a cost function, a user preference for objectives including a first objective relating to comfort, a second objective relating to autonomy, and a third objective relating to urban lane segments, and a user input indicating a slack time for alternative routes to a destination relative to the user preference,

wherein the cost function represents an expected immediate cost of performing the action in a state,

wherein the first objective relating to comfort indicates a preference for lane segments where traffic moves at speeds that are within a threshold speed of speed limits on the lane segments,

wherein the second objective relating to autonomy indicates a preference for lane segments where an autonomous vehicle (AV) can be autonomously controlled as opposed to being manually controlled,

wherein the third objective relating to urban lane segments indicates whether to maximize selection of lane segments classified as urban over lane segments that are not classified as urban, and

wherein the slack time indicates an allowable deviation in travel time relative to the user preference;

receiving the destination; and

at time steps along a route to the destination, autonomously controlling the AV according to one or more respective actions obtained from the policy based on respective current lanes of the AV.

2. The method of claim 1 , wherein the lane-level information is obtained at a host vehicle.

3. The method of claim 1 , wherein the lane-level information is obtained from several vehicles.

4. The method of claim 1 , wherein the lane-level information comprises at least two of environment information, vehicle information, or human information.

5. The method of claim 4 , wherein the environment information comprises at least two of traffic patterns, pedestrian patterns, or traversal difficulties information of lane segments.

6. The method of claim 4 , wherein the vehicle information comprises preferred routes of a user and transfer of control requests by the user.

7. The method of claim 1 , wherein obtaining the lane-level information of the road comprises:

recording first times of automated traversal of the road with stop on the road;

recording second times of automated traversal of the road without stops on the road;

recording third times of manual traversal of the road with stop on the road; and

recording fourth times of manual traversal of the road without stops on the road.

8. The method of claim 1 , wherein obtaining the lane-level information of the road comprises:

recording successor lane segments during manual traversal.

9. The method of claim 1 , wherein obtaining the lane-level information of the road comprises:

recording overrides by a human of an automated travel control.

10. An apparatus for lane-level route planning, comprising:

a processor configured to:

obtain lane-level information of a road,

wherein the road comprises a first lane and a second lane, and

wherein the lane-level information comprises first lane information related to the first lane and second lane information related to the second lane;

convert the lane-level information to a state transition function;

obtain a policy as a solution to a model that uses the state transition function,

wherein, given that a vehicle is on a first lane segment, the policy provides an action for controlling the vehicle with respect to moving to a second lane segment that neighbors the first lane segment,

wherein the model incorporates, into a cost function, a user preference for objectives including at least a first objective relating to comfort and a second objective relating to urban lane segments, and a user input indicating a slack time for alternative routes to a destination relative to the user preference,

wherein the cost function represents an expected immediate cost of performing the action in a state,

wherein the first objective relating to comfort indicates a preference for lane segments where traffic moves at speeds that are within a threshold speed of speed limits on the lane segments,

wherein the second objective relating to urban lane segments indicates whether to maximize selection of lane segments classified as urban, and

wherein the slack time indicates an allowable deviation in travel time relative to the user preference;

receive the destination over lane segments that are not classified as urban; and

at time steps along a route to the destination, autonomously control an AV according to one or more respective actions obtained from the policy based on respective current lanes of the AV.

11. The apparatus of claim 10 , wherein the lane-level information is obtained from a host vehicle.

12. The apparatus of claim 10 , wherein the lane-level information is obtained from several vehicles.

13. The apparatus of claim 10 , wherein the lane-level information comprises at least two of environment information, vehicle information, or human information.

14. The apparatus of claim 13 , wherein the environment information comprises at least two of traffic patterns, pedestrian patterns, or traversal difficulties information of lane segments.

15. The apparatus of claim 13 , wherein the vehicle information comprises preferred routes of a user, transfer of control requests by the user.

16. The apparatus of claim 10 , wherein obtaining the lane-level information of the road comprises:

recording first times of automated traversal of the road with stop on the road;

recording second times of automated traversal of the road without stops on the road;

recording third times of manual traversal of the road with stop on the road; and

recording fourth times of manual traversal of the road without stops on the road.

17. The apparatus of claim 10 , wherein obtaining the lane-level information of the road comprises:

recording successor lane segments during manual traversal; and

recording overrides by a human of an automated travel control.

18. The apparatus of claim 10 , wherein the objectives further include a third objective relating to autonomy, wherein the third objective relating to autonomy indicates a preference for lane segments where an autonomous vehicle (AV) can be autonomously controlled as opposed to being manually controlled.

19. A non-transitory computer-readable storage medium, comprising executable instructions that, when executed by a processor, facilitate performance of operations comprising operations to:

receive from vehicles traversing a road respective lane-level information;

obtain a navigation map from lane-level information received from the vehicles, the navigation map comprising a state transition graph and a reward function, wherein the lane-level information comprises at least two of environment information, vehicle information, or human information;

transmit the navigation map to a vehicle, wherein the vehicle uses the navigation map to obtain lane-level routes;

obtain a policy as a solution to a model that uses the state transition function,

wherein, given that a vehicle is on a first lane segment, the policy provides an action for controlling the vehicle with respect to moving to a second lane segment that neighbors the first lane segment,

wherein the model incorporates, into a cost function, a user preference for objectives including a first objective relating to urban lane segments and a second objective relating to comfort, and a user input indicating a slack time for alternative routes to a destination relative to the user preference,

wherein the cost function represents an expected immediate cost of performing the action in a state,

wherein the first objective relating to urban lane segments indicates whether to maximize selection of lane segments classified as urban over lane segments that are not classified as urban,

wherein the second objective relating to comfort indicates a preference for lane segments where traffic moves at speeds that are within a threshold speed of speed limits on the lane segments, and

wherein the slack time indicates an allowable deviation in travel time relative to the user preference;

receive the destination; and

at time steps along the lane-level routes to the destination, autonomously control an AV according to one or more respective actions obtained from the policy based on respective current lanes of the AV.

20. The non-transitory computer-readable storage medium of claim 19 , wherein the objectives further include:

a third objective relating to autonomy that indicates a preference for lane segments where an autonomous vehicle (AV) can be autonomously controlled as opposed to being manually controlled.