Simulation of Dynamic Coastal Scenes for Semantic Autonomy
Abstract
BYU PI: Joshua Mangelson ONR Program Manager: Marc Steinberg (Code 351) Recent research into semantic high-level autonomy has great potential, but has yet to be tested and applied at scale to dynamic coastal scenes. In large part this is due to the lack of a robotics simulator capable of simulating semantics and dynamics of marine vehicles, sensors, and environments. As a first step towards this goal, we have developed an open source simulator entitled HoloOcean with the goal of lowering the barrier of entry for marine robotics research. In this project, we propose to extend HoloOcean with the ability to generate semantic data and simulate dynamic natural environments common to the marine litoral environment. Our goal in doing this is to enable application and extension of current research focused on semantic mapping and high-level intelligent autonomy to the litoral domain. Specific tasks to be carried out through this grant include 1) Extension of HoloOcean to enable extraction of semantic labels (in sonar and camera) 2) Automatic generation of simulation environments from user configurable parameters/specifications; 3) Simulation of marine dynamic effects including tide, waves, and current; and 4) High-fidelity simulation of underwater camera imagery. Expected outcomes include research dissemination in tier-one robotics journals and conferences, release of the developed simulation tools as updates to the open-source HoloOcean simulator, 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
- Nov 08, 2024
- Source ID
- N000142412503
Entities
People
- Joshua G. Mangelson
Organizations
- Brigham Young University
- Office of Naval Research
- United States Navy