Method and system for context-aware decision making of an autonomous agent
A system for context-aware decision making of an autonomous agent includes a computing system having a context selector and a map. A method for context-aware decision making of an autonomous agent includes receiving a set of inputs, determining a context associated with an autonomous agent based on the set of inputs, and optionally any or all of: labeling a map; selecting a learning module (context-specific learning module) based on the context; defining an action space based on the learning module; selecting an action from the action space; planning a trajectory based on the action S 260 ; and/or any other suitable processes.
1. A method for decision making of an autonomous agent, the method comprising:
receiving a set of inputs from a sensor subsystem of the autonomous agent;
determining a context for the autonomous agent based on the set of inputs;
selecting a model from a set of models based on the context;
with the model, determining an action for the autonomous agent;
determining a trajectory for the autonomous agent based on the action; and
operating the autonomous agent according to the trajectory.
2. The method of claim 1 , further comprising detecting a second context for the autonomous agent based on a second set of inputs from the sensor subsystem.
3. The method of claim 2 , further comprising operating the autonomous agent according to a second trajectory, wherein the second trajectory is determined based on the second context.
4. The method of claim 3 , wherein each of the first and second contexts is predetermined based on a route of the autonomous agent.
5. The method of claim 1 , wherein the set of inputs comprises location information associated with the autonomous agent.
6. The method of claim 5 , wherein the location information comprises a set of poses of the autonomous agent.
7. The method of claim 1 , wherein the context is a predetermined context.
8. The method of claim 7 , wherein the predetermined context is further determined based on a map.
9. The method of claim 8 , wherein at least a portion of the map is manually labeled.
10. The method, wherein the map prescribes the predetermined context based at least in part on a fixed route associated with the autonomous agent.
11. The method of claim 1 , wherein determining the context comprises selecting the context from a set of contexts.
12. The method of claim 11 , wherein the set of contexts is mapped to the set of models in a 1:1 fashion.
13. A system for decision making of an autonomous agent, the system comprising:
a sensor system; and
a computing system in communication with the sensor system, wherein the computing system:
receives a set of inputs from the sensor system;
determines a context for the autonomous agent based on the set of inputs;
selects a model from a set of context-aware learning models based on the context;
determines an action for the autonomous agent based on the model;
determines a trajectory for the autonomous agent based on the action; and
operates the autonomous agent based on the trajectory.
14. The system of claim 13 , further comprising a map, wherein the map prescribes a set of contexts for the autonomous agent.
15. The system of claim 14 , wherein the set of contexts is predetermined.
16. The system of claim 15 , wherein the map is manually labeled based at least in part on a set of fixed routes associated with the autonomous agent.
17. The system of claim 14 , wherein the set of contexts is dynamically determined.
18. The system of claim 13 , wherein the set of inputs from the sensor system comprises a set of poses of the autonomous agent.
19. The system of claim 13 , wherein determining the context comprises selecting the context from a set of contexts.
20. The system of claim 19 , wherein the set of contexts is mapped to the set of models in a 1:1 fashion.