George H Paul

US Patent:

6950534, Sep 27, 2005

Filed:

Jan 16, 2004

Appl. No.:

10/759459

Inventors:

Charles J. Cohen - Ann Arbor MI, US
Glenn Beach - Brooklyn MI, US
Brook Cavell - Ann Arbor MI, US
Gene Foulk - Ann Arbor MI, US
Charles J. Jacobus - Ann Arbor MI, US
Jay Obermark - Ann Arbor MI, US
George Paul - Bedford NH, US

Assignee:

Cybernet Systems Corporation - Ann Arbor MI

International Classification:

G06K009/00

US Classification:

382103, 382276

Abstract:

A gesture recognition interface for use in controlling self-service machines and other devices is disclosed. A gesture is defined as motions and kinematic poses generated by humans, animals, or machines. Specific body features are tracked, and static and motion gestures are interpreted. Motion gestures are defined as a family of parametrically delimited oscillatory motions, modeled as a linear-in-parameters dynamic system with added geometric constraints to allow for real-time recognition using a small amount of memory and processing time. A linear least squares method is preferably used to determine the parameters which represent each gesture. Feature position measure is used in conjunction with a bank of predictor bins seeded with the gesture parameters, and the system determines which bin best fits the observed motion. Recognizing static pose gestures is preferably performed by localizing the body/object from the rest of the image, describing that object, and identifying that description. The disclosure details methods for gesture recognition, as well as the overall architecture for using gesture recognition to control of devices, including self-service machines.

US Patent:

7460690, Dec 2, 2008

Filed:

Sep 14, 2005

Appl. No.:

11/226831

Inventors:

Charles J. Cohen - Ann Arbor MI, US
Glenn Beach - Ypsilanti MI, US
Brook Cavell - Ypsilanti MI, US
Gene Foulk - Ann Arbor MI, US
Charles J. Jacobus - Ann Arbor MI, US
Jay Obermark - Ann Arbor MI, US
George Paul - Bedford NH, US

Assignee:

Cybernet Systems Corporation - Ann Arbor MI

International Classification:

G06K 9/00
G06K 9/36
G06F 3/033

US Classification:

382103, 382276, 715863

Abstract:

A gesture recognition interface for use in controlling self-service machines and other devices is disclosed. A gesture is defined as motions and kinematic poses generated by humans, animals, or machines. Specific body features are tracked, and static and motion gestures are interpreted. Motion gestures are defined as a family of parametrically delimited oscillatory motions, modeled as a linear-in-parameters dynamic system with added geometric constraints to allow for real-time recognition using a small amount of memory and processing time. A linear least squares method is preferably used to determine the parameters which represent each gesture. Feature position measure is used in conjunction with a bank of predictor bins seeded with the gesture parameters, and the system determines which bin best fits the observed motion. Recognizing static pose gestures is preferably performed by localizing the body/object from the rest of the image, describing that object, and identifying that description. The disclosure details methods for gesture recognition, as well as the overall architecture for using gesture recognition to control of devices, including self-service machines.

US Patent:

20140074287, Mar 13, 2014

Filed:

Jan 25, 2013

Appl. No.:

14/001266

Inventors:

George Paul - Merrimack NH, US

Assignee:

Adept Technology, Inc. - Pleasanton CA

International Classification:

B25J 9/16

US Classification:

700253

Abstract:

Embodiments of the present invention provide methods and systems for ensuring that mobile robots are able to detect and avoid positive obstacles in a physical environment that are typically hard to detect because the obstacles do not exist in the same plane or planes as the mobile robot's horizontally-oriented obstacle detecting lasers. Embodiments of the present invention also help to ensure that mobile robots are able to detect and avoid driving into negative obstacles, such as gaps or holes in the floor, or a flight of stairs. Thus, the invention provides positive and negative obstacle avoidance systems for mobile robots.

US Patent:

20140350725, Nov 27, 2014

Filed:

Jan 25, 2013

Appl. No.:

14/370372

Inventors:

- Pleasanton CA, US
Matthew Vestal - Keene NH, US
George V. Paul - Merrimack NH, US

Assignee:

ADEPT TECHNOLOGY, INC. - Pleasanton CA

International Classification:

B25J 9/16
G05B 19/4061

US Classification:

700253, 901 1, 901 50, 901 46

Abstract:

An intelligent mobile robot having a robot base controller and an onboard navigation system that, in response to receiving a job assignment specifying a job location that is associated with one or more job operations, activates the onboard navigation system to automatically determine a path the mobile robot should use to drive to the job location, automatically determines that using an initially-selected path could cause the mobile robot to run into stationary or non-stationary obstacles, such as people or other mobile robots, in the physical environment, automatically determines a new path to avoid the stationary and non-stationary obstacles, and automatically drives the mobile robot to the job location using the new path, thereby avoiding contact or collisions with those obstacles. After the mobile robot arrives at the job location, it automatically performs said one or more job operations associated with that job location.