Method and system for dynamically curating autonomous vehicle policies
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.
1. A system for operation of an autonomous vehicle, the system comprising:
a teleoperator interface configured to receive an input from a teleoperator;
a computing subsystem onboard the autonomous vehicle, wherein the computing subsystem:
identifies a predetermined set of behavioral policies available for selection by the autonomous vehicle;
receives the input from the teleoperator;
determines a dynamic set of behavioral policies available for selection by the autonomous vehicle based on the input, wherein the dynamic set of behavioral policies comprises a behavioral policy not available for selection by the autonomous agent prior to receiving the input from the teleoperator;
evaluates each of an aggregated set of behavioral policies, the aggregated set of behavioral policies comprising the predetermined set of behavioral policies and the dynamic set of behavioral policies, to select a behavioral policy from the aggregated set for the autonomous vehicle to implement; and
a control subsystem, wherein the control subsystem maneuvers the autonomous vehicle according to the selected behavioral policy.
2. The system of claim 1 , wherein the predetermined set of behavioral policies available for selection by the autonomous vehicle is identified based on at least one of: a position, a speed, or a heading of the autonomous vehicle.
3. The system of claim 2 , wherein at least a portion of the predetermined set of behavioral policies is retrieved from a lookup table.
4. The system of claim 2 , wherein the predetermined set of behavioral policies is identified absent of the input from the teleoperator.
5. The system of claim 1 , wherein the selected behavioral policy is one of the predetermined set of behavioral policies.
6. The system of claim 1 , wherein evaluating each of the aggregated set of behavioral policies comprises calculating a parameter value associated with each of the aggregated set of behavioral policies, wherein the selected behavioral policy is selected based on its parameter value.
7. The system of claim 6 , wherein the parameter value is a score.
8. The system of claim 6 , wherein the parameter value associated with each of the aggregated set of behavioral policies is determined based on the performance of a set of simulations.
9. The system of claim 1 , wherein the input from the teleoperator comprises a type of policy, wherein the dynamic set of behavioral policies comprises the type of policy.
10. The system of claim 9 , wherein the type of policy is not present in the predetermined set of behavioral policies.
11. A method for operation of an autonomous vehicle, the method comprising:
with a computing subsystem onboard the autonomous vehicle:
identifying a predetermined set of behavioral policies available to the autonomous vehicle;
receiving an input from a teleoperator interface in communication with the computing subsystem;
determining a dynamic set of behavioral policies available to the autonomous vehicle based on the input, wherein the dynamic set of behavioral policies comprises a behavioral policy not available to the autonomous vehicle prior to receiving the input from the teleoperator interface;
evaluating each of an aggregated set of behavioral policies, the aggregated set of behavioral policies comprising the predetermined set of behavioral policies and the dynamic set of behavioral policies, to select a behavioral policy from the aggregated set for the autonomous vehicle to implement; and
maneuvering the autonomous vehicle according to the selected behavioral policy.
12. The method of claim 11 , wherein the predetermined set of behavioral policies available to the autonomous vehicle is identified based on at least one of: a position, a speed, or a heading of the autonomous vehicle.
13. The method of claim 12 , wherein at least a portion of the predetermined set of behavioral policies is retrieved from a lookup table.
14. The method of claim 12 , wherein the predetermined set of behavioral policies is identified absent of the input from the teleoperator interface.
15. The method of claim 14 , wherein the selected behavioral policy is one of the predetermined set of behavioral policies.
16. The method of claim 11 , wherein evaluating each of the aggregated set of behavioral policies comprises calculating a parameter value associated with each of the aggregated set of behavioral policies, wherein the selected behavioral policy is selected based on its parameter value.
17. The method of claim 16 , wherein the parameter value is a score.
18. The method of claim 16 , further comprising performing a set of simulations, wherein the parameter value associated with each of the aggregated set of behavioral policies is determined based on the set of simulations.
19. The method of claim 11 , wherein the input from the teleoperator comprises a type of policy, wherein the dynamic set of behavioral policies comprises the type of policy.
20. The method of claim 19 , wherein the type of policy is not present in the predetermined set of behavioral policies.