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