Pseudo-genetic meta-knowledge artificial intelligence systems and methods

• US 8,447,419 B1
• Filed: 05/02/2012
• Issued: 05/21/2013
• Est. Priority Date: 05/02/2012
• Status: Active Grant

• Current Assignee: Ether Dynamics Corporation
• Original Assignee: Ether Dynamics Corporation
• Inventors: de Anda Fast, Dominic
• Primary Examiner(s): Ali, Mohammad
• Assistant Examiner(s): Sivanesan, Sivalingam
• Application Number:
  US13/462,683
• Time in Patent Office: 384 Days
• Field of Search: 700/83, 706/13
• US Class Current: 700/83
• CPC Class Codes: G05B 13/0265 the criterion being a learning criterion
• CPC Class Codes: G06N 20/00 Machine learning
• CPC Class Codes: G06N 3/126 Evolutionary algorithms, e.g. genetic algorithms or genetic programming

Abstract

Systems and methods for artificially intelligent physical and virtual actors including pseudo-genetic information and configured to retain meta-knowledge are described. The actors are adapted with unique behavioral and physical attributes which may independently evolve over time. The attributes may include reproduction based attributes which direct how, when, and with whom the actor reproduces and may be subject to mutation and reproductive forces. The attributes may include evaluation attributes which dictate when and how each actor evaluates their performance. The evaluation attributes may also be subject to mutation and reproductive forces. The attributes may consider meta-knowledge which is a reflection of information gathered by an actor. What and how much meta-knowledge is collected may also be expressed as one or more evolvable attributes.

Claims

1. A method of generating a control sequence for an autonomous actor, the method comprising:

receiving one or more control sequences from a plurality of autonomous actors;

identifying portions of control sequences from said received control sequences that will contribute to said control sequence for said autonomous actor, said identification based at least in part on a portion of said received control sequences, said identified portions of said received control sequences including a pseudo-gene having one or more values indicating which actors of the plurality of autonomous actors will contribute and a contribution from each of the indicated actors, said identified portions of said received control sequences comprising;

a selection attribute indicating which control sequences will be selected;

a mutation characteristic indicating an amount and a type of alteration applied to said one or more received control sequences; and

a synthesizer indicating in what manner said selected control sequences will be combined to generate said control sequence for said autonomous actor; and

generating a control sequence for said autonomous actor based on at least said identified control sequences.

2. The method of claim 1, wherein identifying control sequences is based at least in part on information received by said autonomous actor.

3. The method of claim 1, further comprising altering the control sequence for said autonomous actor based at least in part on the generated control sequence.

4. The method of claim 3, wherein altering said control sequence comprises at least one of changing a value included in said control sequence and removing a value included in said control sequence.

5. The method of claim 1, wherein said control sequence comprises a first portion controlling a physical attribute of said autonomous actor and a second portion controlling a behavioral attribute of said autonomous actor, the physical attribute associated with a physical interaction of the apparatus with the environment.

6. The method of claim 5, wherein said physical attribute comprises one or more of a height, a width, a weight, a total surface area, a speed, an armor thickness, an engine output, a battery life, color, and a property indicating how the actor interacts with the environment.

7. The method of claim 5, wherein said behavioral attribute comprises an action to take in response to information detected by said autonomous actor.

8. The method of claim 5, wherein said behavior attribute comprises an evaluation function identifying at least one or more information elements detected by said autonomous actor and a relationship between the elements.

9. The method of claim 5, wherein said behavior attribute comprises a reproduction function identifying in what manner, when, and with whom said autonomous actor may share at least one of a physical attribute, a behavioral attribute, and detected information.

10. A tangible computer-readable storage medium comprising instructions executable by a processor of an apparatus to cause the apparatus to:

receive one or more control sequences from a plurality of autonomous actors;

identify portions of control sequences from said received control sequences that will contribute to said control sequence for an autonomous actor based on at least a portion of said received control sequences, said identified portions of said received control sequences including a pseudo-gene having one or more values indicating which actors of the plurality of autonomous actors will contribute and a contribution from each of the indicated actors, said identified portions of said received control sequences comprising;

a selection attribute indicating which control sequences will be selected;

a mutation characteristic indicating an amount and a type of alteration applied to said one or more received control sequences; and

a synthesizer indicating in what manner said selected control sequences will be combined to generate said control sequence for said autonomous actor; and

generate a control sequence for said autonomous actor based on at least said identified control sequences.

11. A computing device comprising:

a processor configured to execute instructions in order to cause the computing device to;

receive one or more control sequences from a plurality of autonomous actors;

identify portions of control sequences from said received control sequences that will contribute to said control sequence for an autonomous actor, said identification based at least in part on a portion of said received control sequences, said identified portions of said received control sequences including a pseudo-gene having one or more values indicating which actors of the plurality of autonomous actors will contribute and a contribution from each of the indicated actors, said identified portions of said received control sequences comprising;

a selection attribute indicating which control sequences will be selected;

a mutation characteristic indicating an amount and a type of alteration applied to said one or more received control sequences; and

a synthesizer indicating in what manner said selected control sequences will be combined to generate said control sequence for said autonomous actor; and

generate a control sequence for said autonomous actor based on at least said identified control sequences.