Drift Improvement with Reinforcement Training - Inertial Sensors - Year 2

Abstract

This report is a follow-on to TR-3267, the technical report titled Drift Improvement with Reinforcement Training - Inertial - Year 1 that described the work and results from the first year of the Drift Improvement with Reinforcement Training Inertial (DIRT-I) project. This report covers the work and results completed under the second year of this project, which focused on the use of several different inertial sensors with a wide range of performances. The overall goal was to show that the DIRT-I system could be used with any inertial sensor, and to determine the effectiveness of the DIRT-I system with lower quality inertial sensors. This report shows that there is potential to use the DIRT-I system to improve the positional error of inertial sensors without access to corrections from external sensors such as GNSS. However, several changes to the system and much more research into the effectiveness of the RL algorithm(s) used, would be required.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Nov 01, 2022
Accession Number
AD1185841

Entities

People

  • Eric Bozeman
  • Jeffrey Onners
  • Minhdao Nguyen
  • Mohammad Alam

Organizations

  • Naval Information Warfare Center Pacific

Tags

Communities of Interest

  • Sensors

DTIC Thesaurus Topics

  • Algorithms
  • Data Sets
  • Engineering
  • Global Navigation Satellite Systems
  • Global Positioning Systems
  • Governments
  • Gyroscopes
  • Inertial Measurement Units
  • Inertial Navigation
  • Inertial Navigation Systems
  • Information Warfare
  • Kalman Filters
  • Measurement
  • Microelectromechanical Systems
  • Navigation
  • Navigation Satellites
  • Standards
  • Training
  • United States
  • United States Government

Readers

  • Positioning, Navigation, and Timing (PNT) Technology.
  • Sensor Fusion and Tracking Systems.
  • Technical Research and Report Writing.