Objective-based reasoning in autonomous vehicle decision-making
An autonomous vehicle traverses a vehicle transportation network using a multi-objective policy based on a model for specific scenarios. The multi-objective policy includes a topographical map that shows a relationship between at least two objectives. The autonomous vehicle receives a candidate vehicle control action associated with each of the at least two objectives. The autonomous vehicle selects a vehicle control action based on a buffer value that is associated with the at least two objectives. The autonomous vehicle traverses a portion of the vehicle transportation network in accordance with the selected vehicle control action.
1. A method for use in traversing a vehicle transportation network, the method comprising:
traversing the vehicle transportation network, by an autonomous vehicle, wherein traversing the vehicle transportation network includes:
operating a scenario-specific operational control evaluation module instance, wherein the scenario-specific operational control evaluation module instance includes an instance of a scenario-specific operational control evaluation model of a distinct vehicle operational scenario, and wherein operating the scenario-specific operational control evaluation module instance includes identifying a multi-objective policy for the scenario-specific operational control evaluation model, wherein the multi-objective policy includes at least a first objective, a second objective, and a topological graph that shows a relationship between the first objective and the second objective;
receiving, from the multi-objective policy for the scenario-specific operational control evaluation module instance, a candidate vehicle control action associated with the first objective and a candidate vehicle control action associated with the second objective;
determining a buffer value associated with the first objective and the second objective;
determining a probability of success of each of the first objective and the second objective based on a competence measure that is incorporated into a partially observable Markov decision process (POMDP) state transition to obtain a restricted number of available actions;
selecting a vehicle control action from the restricted number of available actions based on the buffer value, wherein the selected vehicle control action is the candidate vehicle control action associated with the first objective or the candidate vehicle control action associated with the second objective; and
traversing a portion of the vehicle transportation network by performing the selected vehicle control action.
2. The method of claim 1 , wherein the first objective is based on a behavior preference, a time to complete the selected vehicle control action, or a risk value.
3. The method of claim 1 , wherein the candidate vehicle control action associated with the first objective is stop, edge, or go.
4. The method of claim 1 , wherein the second objective is based on a behavior preference, a time to complete the selected vehicle control action, or a risk value.
5. The method of claim 1 , wherein the candidate vehicle control action associated with the second objective is stop, edge, or go.
6. The method of claim 1 , wherein the first objective is based on a behavior preference and the second objective is based on a time to complete the selected vehicle control action, and when the buffer value indicates a high-risk behavior preference, selecting the candidate vehicle control action associated with the first objective.
7. The method of claim 1 , wherein the first objective is based on a behavior preference and the second objective is based on a time to complete the selected vehicle control action, and when the buffer value indicates a low-risk behavior preference, selecting the candidate vehicle control action associated with the second objective.
8. The method of claim 1 , wherein the buffer value is a configurable value based on a behavior preference.
9. The method of claim 1 , wherein the buffer value is a constraint value relating the first objective and the second objective.
10. An autonomous vehicle comprising:
a processor configured to execute instructions stored on a non-transitory computer readable medium to:
operate a scenario-specific operational control evaluation module instance, wherein the scenario-specific operational control evaluation module instance includes an instance of a scenario-specific operational control evaluation model of a distinct vehicle operational scenario, and wherein operating the scenario-specific operational control evaluation module instance includes identifying a multi-objective policy for the scenario-specific operational control evaluation model, wherein the multi-objective policy includes at least a first objective, a second objective, and a topological graph that shows a relationship between the first objective and the second objective;
receive, from the multi-objective policy for the scenario-specific operational control evaluation module instance, a candidate vehicle control action associated with the first objective and a candidate vehicle control action associated with the second objective;
determine a buffer value associated with the first objective and the second objective;
determine a probability of success of each of the first objective and the second objective based on a competence measure that is incorporated into a partially observable Markov decision process (POMDP) state transition to obtain a restricted number of available actions
select a vehicle control action from the restricted number of available actions based on the buffer value, wherein the selected vehicle control action is the candidate vehicle control action associated with the first objective or the candidate vehicle control action associated with the second objective; and
cause the autonomous vehicle to perform the selected vehicle control action to traverse a portion of a vehicle transportation network.
11. The autonomous vehicle of claim 10 , wherein the first objective is based on a behavior preference, a time to complete the selected vehicle control action, or a risk value.
12. The autonomous vehicle of claim 10 , wherein the candidate vehicle control action associated with the first objective is stop, edge, or go.
13. The autonomous vehicle of claim 10 , wherein the second objective is based on a behavior preference, a time to complete the selected vehicle control action, or a risk value.
14. The autonomous vehicle of claim 10 , wherein the candidate vehicle control action associated with the second objective is stop, edge, or go.
15. The autonomous vehicle of claim 10 , wherein the first objective is based on a behavior preference and the second objective is based on a time to complete the selected vehicle control action, and when the buffer value indicates a high-risk behavior preference, selecting the candidate vehicle control action associated with the first objective.
16. The autonomous vehicle of claim 10 , wherein the first objective is based on a behavior preference and the second objective is based on a time to complete the selected vehicle control action, and when the buffer value indicates a low-risk behavior preference, selecting the candidate vehicle control action associated with the second objective.
17. The autonomous vehicle of claim 10 , wherein the buffer value is a configurable value based on a behavior preference.
18. The autonomous vehicle of claim 10 , wherein the buffer value is a constraint value relating the first objective and the second objective.
19. A method for use in traversing a vehicle transportation network, the method comprising:
traversing the vehicle transportation network, by an autonomous vehicle, wherein traversing the vehicle transportation network includes:
operating a scenario-specific operational control evaluation module instance, wherein the scenario-specific operational control evaluation module instance includes an instance of a scenario-specific operational control evaluation model of a distinct vehicle operational scenario, and wherein operating the scenario-specific operational control evaluation module instance includes identifying a multi-objective policy for the scenario-specific operational control evaluation model, wherein the multi-objective policy includes a topological graph that shows a relationship between at least two objectives;
receiving, from the multi-objective policy for the scenario-specific operational control evaluation module instance, candidate vehicle control actions associated with each of the at least two objectives;
determining a probability of success of each of the at least two objectives based on a competence measure that is incorporated into a partially observable Markov decision process (POMDP) state transition to obtain a restricted number of available actions;
selecting a vehicle control action from the restricted number of available actions based on a buffer value, wherein the selected vehicle control action is one of the candidate vehicle control actions; and
traversing a portion of the vehicle transportation network by performing the selected vehicle control action.
20. The method of claim 19 , wherein the buffer value is a constraint value relating the at least two objectives.