Visual Servoing for Autonomous Aircraft Refueling
Abstract
The design and development of autonomous robotic systems for autonomous aircraft refueling is a major interest to the Air Force. The approach being undertaken is the integration of vision and robot technologies allowing visual information, regarding identification and location of an aerial refueling receptacle on an aircraft, to be fed back to a robot controller which develops trajectory information needed for compliant robot motion. The purpose of this thesis effort was to modify, develop, and evaluate existing visual processing algorithms to allow the AFIT PUMA-560 to visually acquire and track a half-scale mock-up UARRSI aerial refueling receptacle, and place a simulated refueling nozzle in the close proximity of the receptacle's slipway. This was accomplished by developing visual object recognition and robot serving algorithms which: analyzed images, recognizes and determined the position of the receptacle, and calculated proper PUMA joint angles for end-effector placement. Based on this approach, a static look-and-move robotic visual serving system (RVSS) was demonstrated which: identified, located, and served the PUMA's end-effector to the close proximity of the refueling receptacle. The RVSS provides the visual recognition and serving necessary so that when combined with a compliant motion controller completes the insertion task, thereby completely demonstrating the AFIT concept for robot refueling. In addition, the initial architecture for a dynamic look-and-move RVSS was developed based on parallel processing. Thesis.
Document Details
- Document Type
- Technical Report
- Publication Date
- Dec 14, 1989
- Accession Number
- ADA216042
Entities
People
- Richard P. Shipman
Organizations
- Air Force Institute of Technology