Transformational UUV A.I. (A Sixty-Day Study)

Abstract

Unmanned vehicles necessitate extreme autonomy by the nature of being unmanned. Onboard systems must sense, decide, and act with minimal or no human interaction. This manuscript elaborates the brief, sixty-day study of recent autonomy developments for unmanned underwater vehicles beginning with a rigorous review of very recent literature and culminating with initial efforts to create computer simulations in MATLAB/SIMULINK of the recent seminal publication of deterministic artificial intelligence. The methods were developed for highly nonlinear circuits and later extended to spacecraft guidance and control before recently being developed for unmanned underwater vehicles. Mathematical expressions of the governing physics are used to formulate self-awareness statements, where optimal learning is used to discern unknown or unknowable properties. Critical analysis and selection of discretization and differential equation solvers is offered using numerical precision as the key figure of merit for selection. Machine precision of the utilized software version was achieved invalidating simulations, where the simulation illustrated autonomous navigation without any kind of controller tuning. Recommendations are offered for future studies utilizing the developed simulation environment.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Jun 08, 2023
Accession Number
AD1224305

Entities

People

  • Timothy Sands

Organizations

  • Naval Postgraduate School

Tags

Readers

  • Adaptive Control and Estimation with Uncertainty in Dynamic Systems.
  • Theoretical Analysis.
  • Unmanned Aerial System (UAS) Autonomous Capabilities and Mission Reconnaissance.

Technology Areas

  • AI & ML
  • AI & ML - Autonomous Systems
  • AI & ML - DoD AI Strategy
  • AI & ML - Machine Learning Algorithms
  • Autonomy
  • Autonomy - Autonomous System Control
  • Space
  • Space - Spacecraft Maneuvers