System and method for the creation and utilization of multi-agent dynamic situational awareness models

• US 10,046,457 B2
• Filed: 10/31/2014
• Issued: 08/14/2018
• Est. Priority Date: 10/31/2014
• Status: Active Grant

• Current Assignee: General Electric Company
• Original Assignee: General Electric Company
• Inventors: McHugh, Justin, Aggour, Kareem Sherif, Lizzi, John Michael, Theurer, Charles Burton
• Primary Examiner(s): Kiswanto, Nicholas
• Application Number:
  US14/530,399
• Publication Number:
  US 20160121483A1
• Time in Patent Office: 1,383 Days
• CPC Class Codes: B25J 9/163 learning, adaptive, model based, rule based expert control
• CPC Class Codes: G05B 2219/39146 Swarm, multiagent, distributed multitask fusion, cooperation multi robots
• CPC Class Codes: G05B 2219/40323 Modeling robot environment for sensor based robot system

Abstract

A method, system, and non-transitory computer-readable medium, the method including receiving notifications from a plurality of agents, the notifications being associated with the plurality of agents sensing aspects of an environment; determining, based at least in part on the received notifications from the plurality of agents, a situational model of the environment from the notifications; determining a status of the environment based on the situational model; and reporting the status of the environment to at least one of the plurality of agents.

Claims

1. A computer-implemented method, the method comprising:

receiving, by a processor, notifications from a plurality of agents, the notifications being associated with respective individual agents of the plurality of agents and one or more different sensors of each of the respective individual agents which, independently of the other individual agents, monitor one or more parameters and process sensor data from their one or more sensors;

generating, by the processor and based at least in part on a processing of a combination of a totality of the received notifications from the plurality of agents, a shared situational model of a situation of a global environment relating to the notifications, the situation of the global environment being defined by a totality of the notifications received and a transformation of data related to the notifications that occurs within the global environment as the sensor data changes over a period of time, where the global environment relates to one or more physical spaces monitored by the plurality of agents;

determining, by the processor, a status of the global environment from the shared situational model;

reporting the status of the global environment to at least one agent of the plurality of agents; and

processing and using, by the at least one agent of the plurality of agents, the determined and reported status of the global environment as a basis of a decision-making and an action by the at least one agent.

2. The method of claim 1, wherein the determining of a status of the global environment comprises representing the calculated status at a certain level of abstraction, prior to the reporting, and involves a request for a reporting of the status.

3. The method of claim 1, wherein a notification received from one of the plurality of agents is used in at least one of generating the status of the global environment and transmitted to at least one other agent of the plurality of agents for use thereby.

4. The method of claim 1, wherein at least two of the plurality of agents provides notifications relate to disjoint tasks.

5. The method of claim 1, wherein peer activity between the plurality of agents can be performed without coordination of the processor.

6. The method of claim 1, wherein the plurality of agents are logically grouped into a hierarchy of ranked categories, facilitating various patterns of control of information, both to and from the processor, allowing for differing levels of abstraction to be utilized at different ranks.

7. The method of claim 1, wherein the determining of the shared situational model of the related global environment is dynamically updated based, at least in part, on the notifications received from the plurality of agents over the period of time without disruption of notification processing by the plurality of agents.

8. A non-transitory computer-readable medium having executable instructions stored thereon, the medium comprising:

instructions to receive notifications from a plurality of agents, the notifications being associated with respective individual agents of the plurality of agents and one or more different sensors of each of the respective individual agents which, independently of the other individual agents, monitor one or more parameters and process sensor data from their one or more sensors;

instructions to generate, based at least in part on a processing of a combination of a totality of the received notifications from the plurality of agents, a shared situational model of a situation of a global environment relating to the notifications, the situation of the global environment being defined by a totality of the notifications received and a transformation of data related to the notifications that occurs within the global environment as the sensor data changes over time, where the global environment relates to one or more physical spaces monitored by the plurality of agents;

instructions to determine a status of the global environment from the shared situational model; and

instructions to report the status of the global environment to at least one agent of the plurality of agents, the at least one agent of the plurality of agents to process and use the determined and reported status of the global environment as a basis of a decision-making and an action of the at least one agent.

9. The medium of claim 8, wherein the determining of a status of the global environment comprises representing the calculated status at a certain level of abstraction, prior to the reporting, and involves a request for a reporting of the status based on a mutable collection of profiles, potentially supplied at runtime, to determine applicable levels of abstraction for a given report.

10. The medium of claim 8, wherein a notification received from one of the plurality of agents is used in at least one of generating the status of the global environment and transmitted to at least one other agent of the plurality of agents for use thereby.

11. The medium of claim 8, wherein at least two of the plurality of agents provides notifications related to disjoint tasks.

12. The medium of claim 8, wherein each of the plurality of agents performs local processing to achieve individual objectives of each respective agent.

13. The medium of claim 8, wherein the plurality of agents are logically grouped into a hierarchy of ranked categories, facilitating various patterns of control of information, both to and from the processor, allowing for differing levels of abstraction to be utilized at different ranks.

14. The medium of claim 8, wherein the determining of the shared situational model of the related global environment is dynamically updated based, at least in part, on the notifications received from the plurality of agents over the period of time without disruption of notification processing by the plurality of agents.

15. A system comprising:

a storage device;

a processor in communication with the storage device and operable to;

receive notifications from a plurality of agents, the notifications being associated with respective individual agents of the plurality of agents and the respective individual agent'"'"'s one or more different sensors of each of the respective individual agents which, independently of the other individual agents, monitor one or more parameters and process sensor data from their one or more sensors;

generate, based at least in part on a processing of a combination of a totality of the received notifications from the plurality of agents, a shared situational model of a situation of a global environment relating to the notifications, the situation of the global environment being defined by a totality of the notifications received and a transformation of data related to the notifications that occurs within the global environment as the sensor data changes over a period of time where the global environment relates to one or more physical spaces monitored by the plurality of agents;

determine a status of the global environment from the shared situational model;

report the status of the global environment to at least one of the plurality of agents; and

the at least one agent of the plurality of agents processing and using the determined and reported status of the global environment as a basis of a decision-making and an action by the at least one agent.

16. The system of claim 15, wherein the determining of a status of the global environment comprises representing the calculated status at a certain level of abstraction, prior to the reporting, and involves a request for a reporting of the status.

17. The system of claim 15, wherein a notification received from one of the plurality of agents is used in at least one of generating the status of the global environment and transmitted to at least one other agent of the plurality of agents for use thereby.

18. The system of claim 15, wherein at least two of the plurality of agents provides notifications related to disjoint tasks.

19. The medium of claim 15, wherein the plurality of agents are logically grouped into a hierarchy of ranked categories, facilitating various patterns of control of information, both to and from the processor, allowing for differing levels of abstraction to be utilized at different ranks.

20. The medium of claim 15, wherein the determining of the shared situational model of the related global environment is dynamically updated based, at least in part, on the notifications received from the plurality of agents over the period of time without disruption of notification processing by the plurality of agents.