Monocular Unmanned Leader-Follower (MULE-F) System

Award Information
Agency:
Department of Defense
Branch:
Army
Amount:
$738,300.00
Award Year:
2012
Program:
STTR
Phase:
Phase II
Contract:
W56HZV-12-C-0049
Agency Tracking Number:
A2-4529
Solicitation Year:
2010
Solicitation Topic Code:
A10a-T030
Solicitation Number:
2010.A
Small Business Information
Charles River Analytics Inc.
MA, Cambridge, MA, 02138-4555
Hubzone Owned:
N
Socially and Economically Disadvantaged:
N
Woman Owned:
N
Duns:
115243701
Principal Investigator
 Camille Monnier
 Camille Monnier
 (617) 491-3474
 cmonnier@cra.com
Business Contact
 Mark Felix
Title: Contracts Manager
Phone: (617) 491-3474
Email: mfelix@cra.com
Research Institution
 Boston University
 John F Imbergamo
 Office of Sponsored Programs
25 Buick Street
Boston, MA, 02215-
 (617) 353-4365
 Nonprofit college or university
Abstract
The Army has a clear need for an unmanned ground vehicle (UGV) capable of autonomously accompanying a single soldier or vehicle. Such a UGV would help solve both logistical problems of soldiers needing to transport more equipment and supplies than they can carry in a backpack, and tactical problems of scouting unsafe areas. Multiple designs for such UGVs exist; however, they require active remote control or teleoperation, even for mundane tasks such as long-distance travel. Teleoperation is undesirable for these types of situations, as it requires"heads down"attention from the soldier, which reduces situational awareness and causes fatigue. We propose a Monocular Unmanned Leader-Follower (MULE-F) system for the autonomous tracking and following of a designated soldier or vehicle. The proposed system enables a UGV to autonomously follow a soldier or vehicle at operational following distances and speeds, using a single lightweight UGV-mounted video camera and requiring no modifications to the leader"s equipment. The system is specifically designed to operate in the presence of multiple visually-similar soldiers or vehicles by integrating the designated leader"s tracked kinematics with a learned appearance model, and may be controlled at a distance using intuitive arm/hand gestures.

* information listed above is at the time of submission.

Agency Micro-sites

US Flag An Official Website of the United States Government