Reconfigurable autonomous device networks

• US 20030005030A1
• Filed: 06/03/2002
• Published: 01/02/2003
• Est. Priority Date: 06/01/2001
• Status: Active Grant

• Current Assignee: The General Hospital Corporation (Mass General Brigham, Inc.)
• Original Assignee: The General Hospital Corporation (Mass General Brigham, Inc.)
• Inventors: Jamieson, Ian MacQueen Drummond, Sutton, Jeffrey P.
• Granted Patent: US 7,266,532 B2
• Time in Patent Office: Days
• US Class Current: 709/200
• CPC Class Codes: H04L 67/12 specially adapted for proprietary or special-purpose networking environments, e.g. medical networks, sensor networks, networks in vehicles or remote metering networks
• CPC Class Codes: H04L 69/329 in the application layer [OSI layer 7]
• CPC Class Codes: H04L 9/40 Network security protocols
• CPC Class Codes: H04W 40/00 Communication routing or communication path finding

Abstract

The present invention describes the use of autonomous devices, which can be arranged in networks, such as neural networks, to better identify, track, and acquire sources of signals present in an environment. The environment may be a physical environment, such as a battlefield, or a more abstract environment, such as a communication network. The devices may be mobile, in the form of vehicles with sensors, or may be information agents, and may also interact with one another, thus allowing for a great deal of flexibility in carrying out a task. In some cases, the devices may be in the form of autonomous vehicles which can collaboratively sense, identify, or classify a number of sources or targets concurrently. The autonomous devices may function as mobile agents or attractors in a network, such as a neural network. The devices may also be aggregated to form a network of networks and provide scalability to a system in which the autonomous devices are operating.

Claims

1. An autonomous device for collaboratively identifying objects in an environment, the autonomous device comprising:

a sensor unit adapted for sensing signals due to the objects;

a storage unit containing object template information corresponding to the objects;

a computation unit adapted for processing the sensed signals, wherein the computation unit can compute a match between the sensed signals and the object template information;

a communication unit adapted for communicating information relating to operation of the autonomous device with other devices; and

a control unit adapted for making a decision effecting a status of the autonomous device based at least on a result of the match, wherein the autonomous device operatively collaborates with other devices, similarly constructed, for identifying the objects in the environment.

2. The device of claim 1, further comprising a mobility unit, receiving instructions from the control unit, the mobility unit adapted for moving the device from one location to another.

3. The device of claim 1, further comprising a positioning unit adapted for determining the position of the device in the environment.

4. The device of claim 3, wherein the positioning unit comprises any one of:

a global positioning system (GPS), an inertial navigation system and a signal beacon guided system.

5. The device of claim 1, further comprising a learning unit which executes machine learning algorithms that improve an ability of the autonomous device to classify objects.

6. The device of claim 5, wherein the learning unit is adapted to execute new algorithms or use new data that was not initially loaded into the learning unit.

7. The device of claim 1, wherein the autonomous device is a member of a network of autonomous devices which can communicate over a communication channel.

8. The device of claim 1, wherein the storage unit comprises a database containing pre-programmed object template information.

9. The device of claim 8, wherein the storage unit can accept new information to modify the database.

10. The device of claim 1, wherein the autonomous device is a lead autonomous device and can coordinate the operation of at least one other device acting as a wing device that assists the lead autonomous device in identifying an object.

11. The device of claim 1, wherein the autonomous device is coupled over a communication channel to a central communication unit that centrally communicates with the autonomous device and other autonomous devices operating in the environment.

12. The device of claim 1, wherein the decision affecting the status of the autonomous device is a decision to transmit communication information to another autonomous device.

13. The device of claim 1, wherein the decision affecting the status of the autonomous device is a decision to move the autonomous device from one location to another.

14. The device of claim 1, wherein the decision affecting the status of the autonomous device is a decision to switch the autonomous device from one Mode 0f operation to another.

16. The method of claim 15, wherein the action comprises switching the autonomous device from one Mode 0f operation to another.

17. The method of claim 15, further comprising communicating information between the at least one autonomous device to a second autonomous device, the information being for collaborative identification of the object.

18. The method of claim 17, wherein the at least one autonomous device and the second device operate in a communication network.

20. The system of claim 19, further comprising an external controller that coordinates communication between the first and second autonomous devices.

21. The system of claim 19, wherein the first and second autonomous devices are elements in a first network of devices, and wherein the system further comprises a second network of devices, similar to the first network of devices and in communication with the first network.

15. A method for identifying objects in an environment, comprising:

providing at least one autonomous device for operation in the environment;

providing object template data, corresponding to the objects, in a database coupled to the autonomous device;

sensing a signal from an object using a sensor coupled to the autonomous device;

evaluating a match between an object template and the sensed signal; and

taking an action based at least on a result of the evaluation.

19. A system for identifying at least one object in an environment, comprising:

a first autonomous device which detects at least a first signal from the object;

a second autonomous device which detects at least a second signal from the object; and

a communication network which connects the first and second autonomous devices and passes information between said first and second autonomous devices;

wherein each of said first and second autonomous devices each comprises a control module, a sensor module, and a communications module;

wherein the first autonomous device can evaluate a first match between the first signal and a first reference object template;

wherein the second autonomous device can evaluate a second match between the second signal and a second reference object template; and

wherein said first and second matches being indicative of an identity of the at least one object in the environment.

22. A network, comprising:

a plurality of nodes;

a plurality of branches connecting said nodes; and

at least one autonomous agent capable of moving information from a first node to a second node;

wherein said at least one autonomous agent comprises a network condition sensor and can carry information pertaining to a network condition.

23. The network of claim 22, wherein said autonomous agent can move information from a first node to a second node by moving from the first note to the second node while carrying the information within the autonomous agent.

24. The network of claim 22, wherein said autonomous agent can move information from a first node to a second node by transmitting an information packet containing the information to said second node.

25. The network of claim 22, wherein said autonomous agent is a software agent and the information is data.

26. The network of claim 22, wherein said network condition corresponds to a communication signal travel time.

27. The network of claim 22, wherein said autonomous agent carries a representation of the network condition across the network in its entirety.

28. The network of claim 22, wherein said autonomous agent further comprises instructions for interpreting a model of the network representing some aspect of the network.

29. The network of claim 22, further comprising a system of autonomous agents in communication with one another.

30. A method for determining an optimum configuration of agents operating in an environment, the method comprising:

sensing, on a first agent in the environment, a first environmental signal;

forming a first representation of the first environmental signal;

sensing, on a second agent in the environment, a second environmental signal;

forming a second representation of the second environmental signal;

exchanging, between the first and second agents, the respective first and second representations;

computing a performance metric corresponding to a first configuration of the first and second agents; and

reconfiguring the first and second agents, based on the performance metric, to arrive at a new configuration of the first and second agents.

31. The method of claim 30, further comprising making a decision to include a third agent in the new configuration.

32. The method of claim 30, wherein the first and second agents are autonomous devices.

33. The method of claim 32, wherein the autonomous devices are mobile autonomous vehicles.

34. The method of claim 33, wherein the mobile autonomous vehicles are any of:

airborne vehicles, land vehicles and waterborne vehicles.

35. The method of claim 30, wherein the performance metric corresponds to an overlap between an environmental signal and a stored target template.

36. The method of claim 30, wherein the acts of the method are carried out as a simulation running on a machine executing programmed instructions.

37. The method of claim 30, wherein determination of the optimum configuration provides information regarding scalability of the system as the number and type of agents is varied.