Accession Number : AD1020297

Title :   A Framework for Evidence-Based Licensure of Adaptive Autonomous Systems: Technical Areas

Descriptive Note : Technical Report,01 Jan 2016,01 Mar 2016

Corporate Author : Institute for Defense Analyses Alexandria

Personal Author(s) : Tate,David M ; Grier,Rebecca A ; Martin,Christopher A ; Moses,Franklin L ; Sparrow,David A

Full Text : https://apps.dtic.mil/dtic/tr/fulltext/u2/1020297.pdf

Report Date : 01 Mar 2016

Pagination or Media Count : 65

Abstract : Adaptive autonomous systems of interest to DoD have great potential to complement human performance in a wide range of missions. This particularly is true for adaptive systems that learn those whose behavior on a given set of inputs may change over time, even after the system has been fielded. However, such adaptation makes exhaustive testing, certification, and licensure of the final system impossible.

Descriptors :   unmanned vehicles , probabilistic models , unmanned aerial vehicles , autonomous systems , software testing , system software , algorithms , command and control , operating systems , probability , life cycles

Distribution Statement : APPROVED FOR PUBLIC RELEASE