Cross-Modality Localization and Mapping
Abstract
The Office of Naval Research (ONR) has been investing in fundamental research in feature-based navigation (FBN) with an eye toward improved accuracy of autonomous navigation in the noncomplex and complex areas of a ship during ship-hull searches performed by a Hovering Autonomous Underwater Vehicle (HAUV).We believe that by extending our work to include side-scan sonar and synthetic aperture sonar (SAS) data we can look at fundamental problems associated with new challenges in cross-modalitylocalization and mapping, moving beyond inspection of ships to more general and complex marine structures such as harbors. Using side-scan sonar or SAS, a conventional AUV can quickly coverlarge open spaces and also capture parts of complex areas such as pilings under a pier. Looking behind obstructions to fill in the gaps or acting on objects perceived in the side-scan sonar map would then be up to a hovering AUV, or alternatively, a human diver with a hand-held device.To accomplish this, we propose new and continued work in advanced capabilities and extensions of the HAUV navigation and perception systems, to be carried out in collaboration between Carnegie Mellon University (CMU) and Brigham Young University (BYU), over a period of three years. These advanced capabilities build upon our foundational work in FBN and planning for ship inspection capabilities, and seek to yield integrated methods for cross-modality operation with heterogeneous vehicles.
Document Details
- Document Type
- DoD Grant Award
- Publication Date
- Aug 05, 2021
- Source ID
- N000142112482
Entities
People
- Michael Kaess
Organizations
- Carnegie Mellon University
- Office of Naval Research
- United States Navy