Systems, methods and computer program products for collaborative agent control
View Patent ↗Systems, methods and unmanned agents for collaboratively controlling agents in a collaborative network by one or more agents continuously simulating numeric models of one or more other agents in the network to dramatically reduce the computational bandwidth required between agents, and improve the quality of shared estimates of the agent locations as well as the locations and characteristics of other objects of interest, e.g. targets. Bandwidth is reduced by using the models to intelligently filter data before communicating.
1. A method for controlling multiple unmanned, autonomous vehicles during a mission, comprising:
executing in each of the multiple unmanned, autonomous vehicles a dynamic mission model that outputs one or more mission parameters comprising reducing the communication bandwidth needed to maintain a selected quality of shared estimate of system state;
wherein each of the multiple unmanned, autonomous vehicles continuously simulate the dynamic mission model of the multiple unmanned, autonomous vehicles in the mission;
wherein one or more of the multiple unmanned, autonomous vehicles changes its mission operation control based on the output one or more mission parameters;
wherein the mission parameter further comprises a new state estimate through collaborative data fusion in the absence of GPS or other low uncertainty localization sensors;
wherein the dynamic mission model further comprises a model-based bandwidth efficient communications protocol that exchanges reduced bandwidth for increased distributed computation; and
wherein the dynamic mission model further comprises a collaborative target identification and localization process that fuses sensor data from the two or more unmanned, autonomous vehicles to identify and locate a target.
2. The method of claim 1 , wherein the dynamic mission model further comprises a collaborative state estimation process that fuses data from the two or more unmanned, autonomous vehicles of the multiple unmanned, autonomous vehicles to reduce uncorrelated errors in autonomous vehicle location estimates.
3. The method of claim 1 , wherein the dynamic mission model further comprises an automated task generation process that enables two or more unmanned, autonomous vehicles of the multiple unmanned, autonomous vehicles to generate a new task.
4. The method of claim 3 , wherein the new task is bringing particular sensors to bear on potential targets to improve shared model target identification.
5. An unmanned, autonomous vehicle system, comprising: two or more unmanned, autonomous vehicles, each of the two or more unmanned, autonomous vehicles comprising a processor for executing instructions that outputs one or more mission parameters to one or more other unmanned, autonomous vehicles based on a dynamic mission model of the unmanned, autonomous vehicle system operating on each of the two or more unmanned, autonomous vehicles, the outputs comprising reducing the communication bandwidth needed to maintain a selected quality of shared estimate of system state;
wherein the two or more unmanned, autonomous vehicles each continuously simulate the dynamic mission model of the two or more unmanned, autonomous vehicles in an assigned mission;
wherein one or more of the multiple unmanned, autonomous vehicles changes its mission operation control based on the output one or more mission parameters;
wherein the mission parameter further comprises a new state estimate through collaborative data fusion in the absence of GPS or other low uncertainty localization sensors;
wherein the dynamic model further comprises a model-based bandwidth efficient communications protocol that exchanges reduced bandwidth for increased distributed computation; and
wherein the dynamic model further comprises a collaborative target identification and localization process that fuses sensor data from the two or more unmanned, autonomous vehicles to identify and locate a target.
6. The unmanned, autonomous vehicle system of claim 5 , wherein the dynamic mission model further comprises a collaborative state estimation process that fuses data from the two or more unmanned, autonomous vehicles to reduce uncorrelated errors in autonomous vehicle location estimates.
7. The unmanned, autonomous vehicle system of claim 5 , wherein the dynamic mission model further comprises an automated task generation process that enables the two or more unmanned, autonomous vehicles to generate a new task.
8. The unmanned, autonomous vehicle system of claim 7 , wherein the new task is bringing particular sensors to bear on potential targets to improve shared model target identification.
9. The unmanned, autonomous vehicle system of claim 5 , wherein the unmanned, autonomous vehicle is an unmanned, autonomous air vehicle.
10. A system, comprising:
an operator command and control station;
a communications network linked to the operator command and control station;
two or more unmanned, autonomous vehicles that receive mission instructions from the operator command and control station via the communications network;
wherein the two or more unmanned, autonomous vehicles each comprise a processor for executing instructions that outputs one or more mission parameters to one or more other unmanned, autonomous vehicles based on a dynamic mission model of the system operating on each of the two or more unmanned, autonomous vehicles, the outputs comprising reducing the communication bandwidth needed to maintain a selected quality of shared estimate of system state;
wherein the two or more unmanned, autonomous vehicles continuously simulate the dynamic mission model of the two or more unmanned, autonomous vehicles in the mission;
wherein one or more of the multiple unmanned, autonomous vehicles changes its mission operation control based on the output one or more mission parameters;
wherein the mission parameter further comprises a new state estimate through collaborative data fusion in the absence of GPS or other low uncertainty localization sensors;
wherein the dynamic mission model further comprises a model-based bandwidth efficient communications protocol that exchanges reduced bandwidth for increased distributed computation; and
wherein the dynamic mission model further comprises a collaborative target identification and localization process that fuses sensor data from the two or more unmanned, autonomous vehicles to identify and locate a target.
11. The system of claim 10 , wherein the dynamic mission model further comprises a collaborative state estimation process that fuses data from the two or more unmanned, autonomous vehicles to reduce uncorrelated errors in autonomous vehicle location estimates.
12. The system of claim 10 , wherein the dynamic mission model further comprises an automated task generation process that enables the two or more unmanned, autonomous vehicles to generate a new task.
13. The system of claim 12 , wherein the new task is bringing particular sensors to bear on potential targets to improve shared model target identification.
14. The system of claim 10 , wherein the two or more unmanned, autonomous vehicles are unmanned, autonomous air vehicles.