Date of Award
2017
Document Type
Dissertation
Degree Name
Doctor of Philosophy (PhD)
Department
Computer Science : Modeling and Simulation
Committee Chair
Mikel D. Petty
Committee Member
Letha H. Etzkorn
Committee Member
Sampson Gholston
Committee Member
Daniel M. Rochowiak
Committee Member
Patrick A. Tobbe
Subject(s)
Computer software--Testing, Drone aircraft--Manufacturing processes, Remotely piloted vehicles--Testing
Abstract
Autonomous systems must successfully operate in complex time-varying spatial environments even when dealing with system faults that may occur during a mission. Consequently, evaluating the robustness, or ability to operate correctly under unexpected conditions, of autonomous vehicle control software is an increasingly important issue in software testing. New methods to automatically generate test cases for robustness testing of autonomous vehicle control software in closed-loop simulation are needed. Search-based testing techniques were used to automatically generate test cases, consisting of initial conditions and fault occurrence times, intended to challenge the control software more than test cases generated using current methods. Two different search-based testing methods, genetic algorithms and surrogate-based optimization, were developed and applied to automated test case generation. Hybrid algorithms were also developed that combined aspects of both genetic algorithms and surrogate-based optimization. The effectiveness of the search-based methods in generating challenging test cases was compared to the method most commonly used today (Monte Carlo testing) for two different test scenarios involving unmanned aerial vehicles (UAVs). The first test scenario consisted of a UAV flying through an entryway. The second test scenario involved a UAV autolanding on an aircraft carrier. In both scenarios, the search-based testing techniques demonstrated statistically significant improvements in performance relative to Monte Carlo testing for the two primary test case generation performance metrics: (1) finding the single most challenging test case, and (2) finding the set of fifty test cases with the highest mean degree of challenge.
Recommended Citation
Betts, Kevin Michael, "Search-based automated robustness testing of autonomous vehicle control software" (2017). Dissertations. 126.
https://louis.uah.edu/uah-dissertations/126
