Robust uninhabited air vehicle active missions

• US 7,194,397 B1
• Filed: 11/27/2001
• Issued: 03/20/2007
• Est. Priority Date: 11/27/2001
• Status: Active Grant

• Current Assignee: Lockheed Martin Corporation (Martin Marietta Corporation)
• Original Assignee: Lockheed Martin Corporation (Martin Marietta Corporation)
• Inventors: Bush, Stephen Francis
• Primary Examiner(s): FERRIS III, FRED O
• Application Number:
  US09/994,447
• Publication Number:
  US 20070061116A1
• Time in Patent Office: 1,939 Days
• Field of Search: 703/8, 703/6, 703/22, 703/7, 701/3, 701/23, 701/1, 701/2, 701/14
• US Class Current: 703/8
• CPC Class Codes: B64U 2201/10 autonomous, i.e. by navigating independently from ground or air stations, e.g. by using inertial navigation systems [INS]
• CPC Class Codes: G01C 23/00 Combined instruments indicating more than one navigational value, e.g. for aircraft; Combined measuring devices for measuring two or more variables of movement, e.g. distance, speed or acceleration
• CPC Class Codes: G05D 1/0088 characterized by the autonomous decision making process, e.g. artificial intelligence, predefined behaviours using knowledge based models G06N5/00

Abstract

A command sequence for an autonomous UAV mission is optimized by simulating the performance of a mission in a model environment. Using a genetic algorithm, neural net, or other suitable technique this command sequence is then optimized, to improve the outcome of the mission. A factor in selecting an optimal command sequence will be its compressability. A set of one or more optimal command sequences is compiled. Each optimal command sequence is encoded into an algorithmic active packet of minimum size for uploaded to the UAV, which then executes the mission. To track the UAV in its performance of the mission without compromising its location, the active packets are executed in the simulated environment. The simulated environment is continually updated with the most current available information. The simulation results are an approximation of the current state of the UAV.

Claims

1. A method of optimizing a command sequence for a UAV to accomplish mission objectives, comprising the steps of:

(a) simulating the performance of an initial command sequence by a UAV in a simulated environment, resulting in a simulated mission outcome;

(b) modifying the command sequence of said mission;

(c) simulating the performance of said modified command sequence by a UAV in said simulated environment, resulting in another simulated mission outcome;

(d) iteratively performing steps (b) and (c) to optimize the simulated mission outcome;

(e) selecting the one or more command sequences based in part upon which command sequences produce an optimal simulated mission outcome; and

(f) encoding each selected command sequence into an algorithmic active packet.

2. The method of optimizing a command sequence for a UAV according to claim 1, wherein modifying the command sequence comprises using one of a genetic algorithm technique and a neural network technique.

3. The method of optimizing a command sequence for a UAV according to claim 2, wherein modifying the command sequence comprises using a genetic algorithm technique, and further wherein said genetic algorithm comprises a fitness function which measures the simulated outcome against mission objectives.

4. The method of optimizing a command sequence for a UAV according to claim 1, wherein the criteria for an optimal mission outcome include the compressibility of the command sequence.

5. The method of optimizing a command sequence for a UAV according to claim 4, wherein the compressibility of the command sequence is measured according to the Minimum Data Length theorem.

6. The method of optimizing a command sequence for a UAV according to claim 1, wherein step of encoding a command sequence includes representing the commands as an algorithm supplemented by data.

7. The method of optimizing a command sequence for a UAV according to claim 6, wherein the encoded command sequence achieves an optimal compression as measured by the Minimum Data Length theorem.