Advanced Cross-Modality Localization and Mapping
Abstract
Successful deployment of unmanned underwater vehicles (UUVs) depends on the capability to localize (determine accurate local/globalposition) and perceive/map their environment (automatically interpret sensor data). These capabilities present significant challenges in the underwater environment. Moreover, these challenges are magnified by the fact that different UUV systems often utilize various different types of sensors including side scan sonar, imaging/forward-looking sonar, bathymetric multibeam sonar, and optical cameras.In this project, we propose to investigate techniques for localization and mapping that leverage unique combinations of these various sensing modalities. We will explicitly focus this research on the use case where multiple UUVs operate in coordination with one another to complete complex search tasks requiring localization and reacquire capabilities involving multiple vehicles with different motion and sensing capabilities. To ensure grounding of the research, we will conduct regular infield testing and data collection operations to validate the proposed ideas in situ.Specific research to be carried out through this grant include 1) The development of novel cross-sensor-modality localization techniques that enable teams of agents to localize against maps created with differing sensor modalities; 2) The development of novel cross-modality mapping techniques that fuse information from multiple vehicles/sensors in a single map; and 3) The development of novel techniques that merge Synthetic-Aperture-Sonar (SAS) and Simultaneous Localization and Mapping (SLAM).Expected outcomes include research dissemination in tier-one robotics journals and conferences, demonstrations of the proposed techniques both via in-field testing and post-processing of real-world data, and training of multiple graduate and undergraduate students in fields relevant to the US Navy research enterprise.Approved for Public Release.
Document Details
- Document Type
- DoD Grant Award
- Publication Date
- Apr 11, 2024
- Source ID
- N000142412272
Entities
People
- Michael Kaess
Organizations
- Carnegie Mellon University
- Office of Naval Research
- United States Navy