System and method for transforming mission models from plan goal graph to Bayesian network for autonomous system control

1. A method for control of an autonomous or unmanned system comprising:

obtaining a mission model, wherein the mission model comprises a goal and one or more assets that are used to accomplish the goal;

producing by a first hardware processor, a plan goal graph (PGG) model based on the mission model, wherein the PGG comprises the goal represented as a first parent node and one or more alternative plans to achieve the goal utilizing the one or more assets represented as one or more first child nodes to the first parent node, wherein the first parent node is connected to each of the one or more first child nodes by one or more first directed arcs;

transforming, by a second hardware processor, the PGG model into a Bayesian Network (BN) model;

computing a feasibility to execute a plan and an achievability of accomplishing the goal; and

providing control instructions to the one or more assets to be used to accomplish the goal.

2. The method of claim 1 , wherein the one or more assets comprise an autonomous or unmanned system.

3. The method of claim 1 , wherein the BN model comprises one or more alternative plans using the one or more assets represented as one or more second parent nodes and the goal represented as a second child node to the one or more second parent nodes, wherein the one or more second parent nodes are connected to the second child node by one or more second directed arcs.

4. The method of claim 3 , wherein the transforming comprises changing a first direction of the first directed arcs to a second direction of the second directed arcs and adding a decision node to the second child node.

5. The method of claim 4 , further comprising defining one or more achievability variables for one or more goal nodes, defining one or more feasibility variables for one or more plan nodes, and a relationship between the one or more feasibility variables for the one or more plan nodes and the one or more achievability variables for the one or more goal nodes.

6. The method of claim 4 , further comprising generating a conditional probability table for each node of the BN model that reflects a conditional probability distribution over one or more states of a node given different combinations of one or more states of each second parent nodes.

7. The method of claim 4 , further comprising adding a risk factor and a scaling factor in the computing the feasibility and the achievability.

8. The method of claim 1 , wherein the BN model and a computation method of computing an achievability of a goal node and one or more feasibility variables for one or more plan nodes are embedded in a mission reasoning component of an autonomous or semi-autonomous system to provide reasoning and decisions based on computed best course of actions.

9. The method of claim 1 , wherein the first hardware processor and the second hardware processor are different processors.

10. The method of claim 1 , wherein the one or more assets comprise a robot equipped with wired or wireless communication, anthropomorphic hands and limbs, and a vision system.

11. The method of claim 1 , wherein the one or more assets comprise an autonomous air system, autonomous water system, or autonomous ground system.

12. The method of claim 1 , wherein the one or more assets comprise one or more of: a wireless communication system, a cargo stowage unit, a material handling equipment unit, a vision system, or a global positioning system.

13. A computing system comprising:

at least one hardware processor;

a non-transitory computer-readable medium storing instruction, that when executed by the at least one hardware processor, perform a method for control of an autonomous or unmanned system, the method comprising:

obtaining a mission model, wherein the mission model comprises a goal and one or more assets that are used to accomplish the goal;

producing a plan goal graph (PGG) model based on the mission model, wherein the PGG ( 100 ) comprises the goal represented as a first parent node and one or more alternative plans to achieve the goal utilizing the one or more assets represented as one or more first child nodes to the first parent node, wherein the first parent node is connected to each of the one or more first child nodes by one or more first directed arcs;

transforming the PGG model into a Bayesian Network (BN) model;

computing a feasibility to execute a plan and an achievability of accomplishing the goal; and

providing control instructions to the one or more assets to be used to accomplish the goal.

14. The computing system of claim 13 , wherein the one or more assets comprise an autonomous or unmanned system.

15. The computing system of claim 13 , wherein the BN model comprises one or more alternative plans using the one or more assets represented as one or more second parent nodes and the goal represented as a second child node to the one or more second parent nodes, wherein the one or more second parent nodes are connected to the second child node by one or more second directed arcs.

16. The computing system of claim 15 , wherein the transforming comprises changing a first direction of the first directed arcs to a second direction of the second directed arcs and adding a decision node to the second child node.

17. The computing system of claim 16 , wherein the at least one hardware processor is operable to perform the method further comprising defining one or more achievability variables for one or more goal nodes, defining one or more feasibility variables for one or more plan nodes, and a relationship between the one or more feasibility variables for the one or more plan nodes and the one or more achievability variables for the one or more goal nodes.

18. The computing system of claim 16 , wherein the at least one hardware processor is operable to perform the method further comprising generating a conditional probability table for each node of the BN model that reflects a conditional probability distribution over one or more states of a node given different combinations of one or more states of each second parent nodes.

19. The computing system of claim 13 , wherein the BN model and a computation method of computing an achievability of a goal node and one or more feasibility variables for one or more plan nodes are embedded in a mission reasoning component of an autonomous or semi-autonomous system to provide reasoning and decisions based on computed best course of actions.

20. The computing system of claim 13 , wherein the computing system comprises the autonomous or the unmanned system.

21. The computing system of claim 13 , wherein the computing system is a system that is separate from the autonomous or the unmanned system.