Research Results | Verification and Validation of Adaptive Systems


	Search:	Advanced Search

Test Analysis < Verification & Validation < Results Home

Click here to complete a short survey. The results of this survey will be used to help us improve the research program and this website.

Click here to view research projects that had new research results added in the last 90 days.

Verification and Validation of Adaptive Systems
Point of Contact	Bojan Cukic cukic@csee.wvu.edu
Dates	October 2001 - December 2005
Problem	Artificial Neural Networks (ANN) play an increasing role in flight control and navigation, two focus areas for NASA. What makes them appealing for NASA is that they are very useful in application domains that arise routinely within NASA's practice areas, where autonomy and adaptability are important features. A major obstacle precludes, however, the widespread use of ANN's in NASA (and elsewhere). Most of the certification standards that NASA and other federal agencies (such as FAA) impose on such life-critical and mission-critical applications cannot be met with today's technology. No existing software V&V method/ technique can be applied to systems, which contain on-line (nor off-line) learning artificial neural networks.
Objective	The objective of this proposal is to attempt to fill the gap identified in the problem statement, by producing a framework for reasoning about adaptive systems. In the short term, this objective involves the following goals: Derive a computational model for adaptive systems. Validate the proposed model against existing adaptive algorithms, to show its relevance. Validate the proposed model within existing application areas, to show its applicability. Investigate how this model can be used to derive methods for the verification/certification of adaptive systems. In the medium term, we intend to derive engineering techniques for the verification of adaptive systems, and to investigate how these techniques can be used to meet predefined certification standards.
Results	OSMA SAS 2002 Presentation.ppt Validate the Model for Relevance.doc Validate Developed models for Applicability.pdf Progress report on data sniffing experiments.pdf Flight Simulation Capabilities for V&V of adaptive systems.zip Technical Report Define a Computational Model of Adaptive Systems.pdf SAS 05 Executive Presentation.ppt SAS 06 Executive Presentation.ppt SAS 05 Technical Presentation.ppt Decompose and Combine - A Fast Training Algorithm for SVDD.pdf Validity Index in Dynamic Cell Structures.pdf SAS 06 Technical Presentation.ppt Final project report.pdf Integrating novelty detection techniques with Lyapunov online monitoring.pdf
Keywords	flight control, adaptive systems, fault tolerance, DCS networks
Categories	Software Reliability Software Safety Domain-Specific Analysis Formal Methods Test Analysis

Curator: Josh Stonestreet
NASA Official: Lisa Montgomery

NASA Privacy, Security, Notices