Statistical performance verification for an autonomous rotorcraft

Michael Elgersma, Subhabrata Ganguli, Vu Ha, Tariq Samad

Research output: Chapter in Book/Report/Conference proceedingConference contribution

9 Scopus citations

Abstract

We present an approach to verifying the performance of an intelligent control algorithm for which traditional, deterministic verification is not feasible. Our approach is based on statistical learning theory. We develop a classifier based on simulation data to partition the potential operating region of a system under control (here an autonomous helicopter) into acceptable and unacceptable subrogions. Statistical learning theory results can then be used to estimate the "generalization" performance of the classifier, providing rigorous bounds on the expected performance. A neural-network-based controller is used to demonstrate the methodology, the outcome of which is an analytical characterization of a "safe" set of maximum velocity and acceleration values under which particular helicopter maneuvers can be reliably executed with acceptable performance.

Original languageEnglish (US)
Title of host publicationProceedings of the 2004 IEEE International Symposium on Intelligent Control - 2004 ISIC
Pages7-12
Number of pages6
StatePublished - Dec 1 2004
EventProceedings of the 2004 IEEE International Symposium on Intelligent Control - 2004 ISIC - Taipei, Taiwan, Province of China
Duration: Sep 2 2004Sep 4 2004

Other

OtherProceedings of the 2004 IEEE International Symposium on Intelligent Control - 2004 ISIC
Country/TerritoryTaiwan, Province of China
CityTaipei
Period9/2/049/4/04

Fingerprint

Dive into the research topics of 'Statistical performance verification for an autonomous rotorcraft'. Together they form a unique fingerprint.

Cite this