to break things: adaptive testing of intelligent controllers,”
In Handbook on Evolutionary Computation , G3.5, IOP Publishing
Ltd. and Oxford Press, 1997.
are likely to require sophisticated software controllers to
maintain vehicle performance in the presence of vehicle faults.
The test and evaluation of complex software controllers is
expected to be a challenging task. The goal of this effort
is to apply machine learning techniques from the field of
artificial intelligence 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.
We illustrate the approach by evaluating the performance of
a subsumption-based controller for an autonomous vehicle.
The preliminary evidence suggests that this approach is an
effective alternative to manual testing of sophisticated software
and Evaluation by Genetic Algorithms," IEEE Expert 8(5),
9-14, October 1993,
Testing of Controllers for Autonomous Vehicles,"
Proceedings of the Symposium on Autonomous Underwater Vehicles
Technology, Washington DC, 158-164, IEEE Press, June 2-3,
Navy Policy prohibits lists of authors names on this page, however, the links above will download the full papers, whch do contain the authors names.
"Material contained herein is made available for the purpose of peer review and discussion and does not necessarily reflect the views of the Department of the Navy or the Department of Defense."