G3.5 Learning to break things: adaptive testing of intelligent controllers

Autonomous vehicles require sophisticated software controllers to maintain vehicle performance in the presence of vehicle faults. The test and evaluation of complex software controllers is a challenging task. The goal of this effort is to apply machine learning techniques to the general problem of evaluating an intelligent controller for an autonomous vehicle. The approach involves subjecting a controller to an adaptively chosen set of fault scenarios within a vehicle simulator, and searching for combinations of faults that produce noteworthy performance by the vehicle controller. The search employs a genetic algorithm. The evidence suggests that this approach is an effective supplement to manual and other forms of automated testing of sophisticated software controllers. Several intelligent controllers were tested in this project using several different genetic algorithm-based learning programs. Over the course of this research, the representation, evaluation function, genetic operator..