Strain-sensing goniometers, systems, and recognition algorithms

• US 6,701,296 B1
• Filed: 12/27/1999
• Issued: 03/02/2004
• Est. Priority Date: 10/14/1988
• Status: Expired due to Fees

• Current Assignee: James F. Kramer, Peter Lindener, William R. George
• Original Assignee: James F. Kramer, Peter Lindener, William R. George
• Inventors: Kramer, James F., George, William R., Lindener, Peter
• Primary Examiner(s): ABEBE, DANIEL DEMELASH
• Application Number:
  US09/472,659
• Time in Patent Office: 1,527 Days
• Field of Search: 704/259, 704/270, 704/271, 704/243, 341/1, 345/156, 345/158
• US Class Current: 704/270
• CPC Class Codes: A61B 2562/0261 Strain gauges
• CPC Class Codes: A61B 5/1071 measuring angles, e.g. using goniometers A61B5/1123 takes precedence
• CPC Class Codes: A61B 5/6806 Gloves
• CPC Class Codes: A61B 5/7267 involving training the classification device
• CPC Class Codes: G06F 1/163 Wearable computers, e.g. on a belt
• CPC Class Codes: G06F 3/011 Arrangements for interaction with the human body, e.g. for user immersion in virtual reality blind teaching G09B21/00
• CPC Class Codes: G06F 3/014 Hand-worn input/output arrangements, e.g. data gloves
• CPC Class Codes: G06F 3/016 Input arrangements with force or tactile feedback as computer generated output to the user
• CPC Class Codes: G09B 21/009 Teaching or communicating with deaf persons G09B21/04 takes precedence; deaf and dumb persons G09B21/00
• CPC Class Codes: G09B 21/04 Devices for conversing with the deaf-blind
• CPC Class Codes: G16H 50/70 for mining of medical data, e.g. analysing previous cases of other patients

Abstract

Goniometers are provided having internal compensation employing two opposing variable resistance strain sensing elements separated by a flexible film. The goniometers may be used in sets for detecting complex hinge or joint movements, where patterns of hinge or joint positions may be used to define symbols. Algorithms are provided for parsing values from a system of goniometers in motion having information content.

Claims

1. An instrumented glove for use in an interface between a human and a machine, the instrumented glove comprising:

a cover material configured to fit on the hand of a wearer, and

a plurality of goniometers supported by said cover material and positioned to flex with movement of the hand, said cover material including guiding elements in which said goniometers are supported, each goniometer comprising a variable resistance strain sensing element mounted on a flexible support material, and a device electrically connected to said strain sensing elements operative to transmit changes in resistance of said plurality of strain sensing elements to circuitry of the machine.

2. An instrumented glove according to claim 1, wherein the goniometers are configured to follow an angle of bending to at least about 115 degrees.

3. An instrumented glove according to claim 1, wherein the machine includes a computer to receive signals based on the changes in resistance and generate an output signal related to the movement of the hand.

4. An instrumented glove according to claim 1, wherein the changes in resistance are used to control a graphic image.

5. An instrumented glove according to claim 4, wherein the graphic image is displayed in a virtual reality environment.

6. An instrumented glove according to claim 1, wherein the finger portion is one of a plurality of finger portions, the finger portions having open ends.

7. An instrumented glove according to claim 1, wherein the machine includes a computer configured to receive signals based on the changes in resistance, said computer including a pattern recognition procedure.

8. An instrumented glove according to claim 7, wherein the pattern recognition procedure is responsive to hand state vectors for recognizing hand position and orientation, said pattern recognition procedure incorporating a tree-structured neural network classifier.

9. A system comprising:

a sensor configured to generate an electrical signal indicative of a configuration of a body part fitted with a covering configured to fit on the body part;

a plurality of goniometers supported by said covering and positioned to flex with movement of at least portions of the body part, and

a computer configured to receive the electrical signal, said computer including pattern recognition procedure responsive to body part state vectors for recognizing body part position and orientation, and a first output circuit responsive to said computer providing an output recognized by said pattern recognition procedure, said pattern recognition procedure incorporating a tree-structured neural network classifier.

10. An instrumented interface glove comprising:

a cover material configured to fit on a portion of a hand of a wearer, the cover material including a finger portion into which a finger of the wearer may be inserted, the finger portion comprising an open end so that the tip of the finger may extend through the open end; and

a plurality of goniometers supported by said cover material and positioned to flex with movement of the hand and to generate signals related to movement of the hand, said cover material including guiding elements in which said goniometers are supported.

11. An instrumented interface glove according to claim 10, wherein each goniometer comprises a variable resistance strain sensing element mounted on a flexible support material.

12. An instrumented interface glove according to claim 11, further comprising means electrically connected to said goniometers for transmitting changes in resistance of said strain sensing elements to circuitry of a machine.

13. An instrumented interface glove according to claim 11, wherein the goniometers are configured to follow an angle of bending to at least about 115 degrees.

14. An instrumented interface glove according to claim 10, further comprising a computer to receive the signals and generate an output signal related to the movement of the hand.

15. An instrumented interface glove according to claim 14, wherein the output signal is used to control a graphic image.

16. An instrumented interface glove according to claim 14, wherein the output signal is used to control a graphic image in a virtual reality environment.

17. An instrumented interface glove according to claim 10, wherein the finger portion is one of a plurality of finger portions, the finger portions having open ends.

18. An instrumented interface glove according to claim 10, further comprising a computer configured to receive the signals, said computer including a pattern recognition procedure.

19. An instrumented interface glove according to claim 18, wherein the pattern recognition procedure is responsive to hand state vectors for recognizing hand position and orientation, said pattern recognition procedure incorporating a tree-structured neural network classifier.