Method and system for remote assistance of an autonomous agent
A system 100 for remote assistance of an autonomous agent can include and/or interface with any or all of: a sensor suite 110 , a computing system 120 , a communication interface 130 , and/or any other suitable components. The system can further optionally include a set of infrastructure devices 140 , a teleoperator platform 150 , and/or any other suitable components. The system 100 functions to enable information to be exchanged between an autonomous agent and a tele-assist. Additionally or alternatively, the system 100 can function to operate the autonomous agent (e.g., based on remote inputs received from a teleoperator, indirectly, etc.) and/or can perform any other suitable functions.
1. A method for consideration of teleoperator input in the operation of an autonomous vehicle, the method comprising:
with a computing subsystem onboard the autonomous vehicle:
detecting satisfaction of a trigger condition;
receiving the teleoperator input, wherein the teleoperator input comprises a set of waypoints associated with the trigger condition;
based on the set of waypoints, determining a plurality of predefined autonomously electable policies, each comprising a set of rules for decision-making;
evaluating a set of aggregated decision options, the set of aggregated decision options comprising:
the set of waypoints;
the set of predefined autonomously electable policies;
selecting one of the set of aggregated decision options based on the evaluation, wherein the evaluation comprises simulating each of the set of predefined autonomously electable policies; and
with a control subsystem in communication with the computing subsystem, operating the autonomous vehicle in accordance with the selected decision option.
2. The method of claim 1 , wherein the trigger condition is associated with the autonomous vehicle's environment.
3. The method of claim 2 , wherein the trigger condition comprises exceeding a predetermined probability threshold.
4. The method of claim 3 , wherein the probability threshold is associated with a probability of the autonomous vehicle being stopped by an obstacle in the autonomous vehicle's environment.
5. The method of claim 1 , further comprising providing a set of input options to a teleoperator interface in response to detecting satisfaction of the trigger condition, wherein the teleoperator input is received in response to providing the set of input options.
6. The method of claim 5 , wherein the set of input options comprises a waypoint provision interface, wherein the set of waypoints is received at the waypoint provision interface.
7. The method of claim 6 , wherein the set of inputs options further comprises a set of teleoperator-electable policy options, wherein in an event that the teleoperator input comprises a selected teleoperator-electable policy option from the set of teleoperator-electable policy options, the set of aggregated decision options further comprises the selected teleoperator-electable policy option.
8. The method of claim 1 , wherein evaluating the set of aggregated decision options comprises performing a set of simulations.
9. The method of claim 8 , wherein the selected decision option is determined based on a set of parameter values produced from the set of simulations.
10. The method of claim 9 , wherein the set of parameters values comprises a score associated with the set of waypoints and a set of scores associated with each of the set of predefined autonomously electable policies.
11. A system for consideration of teleoperator input in the operation of an autonomous vehicle while navigating the autonomous vehicle along a target path, the system comprising:
a computing subsystem onboard the autonomous vehicle, wherein the computing subsystem is configured to:
detect satisfaction of a trigger condition;
receive the teleoperator input, wherein the teleoperator input comprises a set of waypoints associated with the trigger condition;
update the target path based on the set of waypoints;
evaluate a set of aggregated decision options, the set of aggregated decision options comprising:
the set of waypoints;
a set of autonomously electable policies, each comprising a set of rules for decision-making;
select one of the set of aggregated decision options based on the evaluation and the updated target path; and
a control subsystem in communication with the computing subsystem, wherein the control subsystem is configured to operate the autonomous vehicle in accordance with the selected decision option.
12. The system of claim 11 , wherein the trigger condition is associated with the autonomous vehicle's environment.
13. The system of claim 12 , wherein the trigger condition comprises exceeding a predetermined probability threshold.
14. The system of claim 13 , wherein the probability threshold is associated with a probability of the autonomous vehicle being stopped by an obstacle in the autonomous vehicle's environment.
15. The system of claim 11 , wherein the computing subsystem is further configured to provide a set of input options to a teleoperator interface in response to detecting satisfaction of the trigger condition, wherein the teleoperator input is received in response to providing the set of input options.
16. The system of claim 15 , wherein the set of input options comprises a waypoint provision interface, wherein the set of waypoints is received at the waypoint provision interface.
17. The system of claim 16 , wherein the set of inputs options further comprises a set of teleoperator-electable policy options, wherein in an event that the teleoperator input comprises a selected teleoperator-electable policy option from the set of teleoperator-electable policy options, the set of aggregated decision options further comprises the selected teleoperator-electable policy option.
18. The system of claim 11 , wherein the computing subsystem is further configured to, in evaluating the set of aggregated decision options, perform a plurality of simulations for each aggregated decision option of the set.
19. The system of claim 18 , wherein the selected decision option is determined based on a set of parameter values produced from the set of simulations.
20. The system of claim 19 , wherein the set of parameters values comprises a score associated with the set of waypoints and a set of scores associated with each of the set of autonomously electable policies.
21. The method of claim 1 , wherein the set of aggregated decision options comprises policies determined before satisfaction of the trigger condition and policies determined after satisfaction of the trigger condition.