Context-Aware Hybrid Learning for Real-Time Estimation of Uncertain Systems

Abstract

Sub-second real-time estimation of uncertain systems will enable critical applications, such as hypersonic system guidance and post-ballistic impact maneuvers. State estimation of these systems is typically conducted offline or on a time scale that does not allow sub-second applications. This is attributed to the large complexities under consideration. In this research, a context-aware hybrid learning method for real-time estimation and prediction of uncertain high-dimensional systems will be developed. The method consists of a machine learning tool that produces fast state estimations through the injection of physical knowledge. The advantage of the proposed method is a fast convergence towards physically meaningful parameters enabling decision making. Collaboration will be conducted with the AFRL-RW to obtain expert feedback and access to key experimental data in demonstrating the applicability of the method to the Air Force challenge

Document Details

Document Type
DoD Grant Award
Publication Date
Feb 22, 2024
Source ID
FA95502310033

Entities

People

  • Simon Laflamme

Organizations

  • Air Force Office of Scientific Research
  • Iowa State University
  • United States Air Force

Tags

Fields of Study

  • Computer science

Readers

  • Agent-Based Social Robotics and Mobile-Assisted Learning in Virtual Environments.
  • Computer Vision.
  • Robotics and Automation.

Technology Areas

  • AI & ML
  • AI & ML - Bayesian Inference
  • AI & ML - Machine Learning Algorithms
  • Hypersonics