Summaries - Research
Back Advancing the Science of Test via Simulation Experiments
|Division||Graduate School of Operational & Information Sciences|
Sanchez, Susan M.
Lucas, Thomas W.
|Sponsor||Air Force Institute of Technology (Air Force)|
|Summary||This project continuous previous research on simulation methodologies suitable for the test and evaluation (T&E) of autonomous systems, as well as other uses of simulation experiments to support T&E activities. Test and evaluation of autonomous systems presents challenges when applying methodologies used to test manned systems, typically related to the decision process. Autonomous systems, by definition, are intended to require no human intervention to perform their designated functions, because they are able to perceive their environment, understand their state and the state of the environment, and identify the correct action to express in the environment. Errors in any of these three main functions can result in erroneous behavior from the autonomous system. Measurement of system metrics associated with these three functions is made more challenging due to the variety of environmental conditions autonomous systems must be evaluated under, as well as the use of adaptive decision-making algorithms. This research will examine the issues associated with the systematic test and evaluation of autonomous systems, by exploring the behavior of several adaptive algorithms in a simulation environment. It will also lead to new design of experiments suitable for conducting large-scale simulation experiments.|
|Keywords||Simulation data farming design of experiments test & evaluation unmanned systems|
|Publications||Publications, theses (not shown) and data repositories will be added to the portal record when information is available in FAIRS and brought back to the portal|
|Data||Publications, theses (not shown) and data repositories will be added to the portal record when information is available in FAIRS and brought back to the portal|