Method and system for dynamically curating autonomous vehicle policies

Patent metadata

Field	Value
Publication number	US-11667306-B2
Application number	US-202217738462-A
Country	US
Kind code	B2
Filing date	May 6, 2022
Priority date	Jul 1, 2020
Publication date	Jun 6, 2023
Grant date	Jun 6, 2023

Abstract

A system for dynamic policy curation includes a computing system and interfaces with an autonomous agent. A method for dynamic policy curation includes collecting a set of inputs; processing the set of inputs; and determining a set of available policies based on processing the set of inputs. Additionally or alternatively, the method can include any or all of: selecting a policy; implementing a policy; and/or any other suitable processes.

First claim

We claim:

1. A method for dynamically determining a set of policies available to an autonomous vehicle, the method comprising:
collecting a set of sensor data;
determining a position of the autonomous vehicle based on the set of sensor data;
with a labeled map, wherein the labeled map prescribes multiple sets of potential policy assignments, determining the set of policies available to the autonomous vehicle and corresponding to the position, wherein the set of policies comprises a predetermined set of policies;
autonomously selecting a policy from the set of policies; and
maneuvering the autonomous vehicle according to the policy.

2. The method of claim 1 , wherein the labeled map is retrieved according to a fixed route associated with the vehicle.

3. The method of claim 1 , wherein the method is performed at each election step of an election cycle.

4. The method of claim 3 , wherein the election cycle is associated with a predetermined frequency.

5. The method of claim 1 , further comprising refining the set of policies based on supplementary information, wherein the policy is selected from the refined set of policies.

6. The method of claim 5 , wherein refining the set of policies based on supplementary information comprises eliminating a subset of the set of policies from consideration in selecting the policy.

7. The method of claim 5 , wherein the supplementary information is determined based on the set of sensor data.

8. The method of claim 7 , wherein the supplementary information comprises a characterization of a scenario of the autonomous vehicle within its environment.

9. The method of claim 7 , wherein the supplementary information comprises a determination of an available field of view associated with a set of sensors, wherein the set of sensor data is collected from the set of sensors.

10. The method of claim 9 , wherein refining the set of policies comprises eliminating a subset of the set of policies from consideration in selecting the policy in response to determining that the available field of view is below a threshold field of view.

11. The method of claim 1 , wherein selecting the policy comprises performing a set of multiple simulations, wherein the set of multiple simulations comprises a simulation for each policy of the set of policies.

12. A system for dynamically determining a set of policies available to an autonomous vehicle, the system comprising:
a set of sensors;
a labeled map, wherein the labeled map prescribes multiple sets of available predetermined policy assignments; and
a computer in communication with the set of sensors and the labeled map, wherein the computer:
collects a set of sensor data from the set of sensors;
determines a position of the vehicle based on the set of sensor data;
references the labeled map to determine a set of policies for the vehicle from the multiple sets of available predetermined policy assignments based on the position;
selects a policy from the set of policies; and
maneuvers the vehicle according to the policy.

13. The system of claim 12 , wherein each of the multiple sets of available predetermined policy assignments is assigned to a set of positions represented on the labeled map.

14. The system of claim 12 , wherein the labeled map is associated with a fixed route for the vehicle, wherein the sensor data is collected along the fixed route.

15. The system of claim 14 , further comprising an additional set of labeled maps, the additional set of labeled maps associated with an additional set of fixed routes.

16. The system of claim 12 , wherein the computer further refines the set of policies based on supplementary information, wherein the policy is selected from the refined set of policies.

17. The system of claim 12 , wherein refining the set of policies based on supplementary information comprises eliminating a subset of the set of policies from consideration in selecting the policy.

18. The system of claim 17 , wherein the supplementary information comprises a characterization of a scenario of the vehicle within its environment.

19. The system of claim 12 , wherein refining the set of policies based on supplementary information comprises adding a policy to the set of policies for consideration in selecting the policy.

20. The system of claim 19 , wherein the supplementary information comprises a set of inputs received from a remote operator.

Assignees

• May Mobility Inc

Inventors

• Fairley Stuart
• Ranjan Asheesh
• Kothbauer Melinda
• Patel Sajan
• Voorheis Tom
• Sterniak Jeff
• Olson Edwin B

Classifications

• B60W60/0011 Primary

  involving control alternatives for a single driving scenario, e.g. planning several paths to avoid obstacles · CPC title

• G06V20/56 Primary

  exterior to a vehicle by using sensors mounted on the vehicle · CPC title

• G06N20/10

  using kernel methods, e.g. support vector machines [SVM] · CPC title

• G06N20/00

  Machine learning · CPC title

• G06N3/04

  Architecture, e.g. interconnection topology · CPC title