Research into Simulator Realism Gaps using Machine and Causal Learning
Abstract
Problem: USAF in prior years indicated (1) simulating realistic flight dynamics and tests for more complex system behavior is increasingly difficult, and (2) avionics changes can now require an unacceptable two years of regression testing. More efficient testing while maintaining realism is imperative. The technical limitation rests in the inability to analyze/simulate avionics system behavior, conditioned by hundreds of parameters, to achieve realistic flight dynamics and early identification of issues.
Document Details
- Document Type
- Technical Report
- Publication Date
- Jun 13, 2022
- Accession Number
- AD1172647
Entities
People
- Robert W. Stoddard
Organizations
- Carnegie Mellon University