The paper aims to investigate the effects of two genetic encodingmethods while developing a model helicopter pilot and realizing smooth trajectory in flying a simple maneuver - acceleration/deceleration maneuver. It ...
详细信息
ISBN:
(纸本)9781424481262
The paper aims to investigate the effects of two genetic encodingmethods while developing a model helicopter pilot and realizing smooth trajectory in flying a simple maneuver - acceleration/deceleration maneuver. It makes use of both inverse simulation and genetic algorithms to optimize the performance of the model pilot. The overall goal of is to define the maneuver and have the developed pilot find control settings that carry out the given task. Discrete and continuouscontrols encodingmethods were implemented, showing their effects on the development of the pilot in flying the maneuver. The helicopter pilot was formulated as a multi-objective optimization problem with four objectives imposed as penalties. A novel approach proposed in this work, termed maxPenalty, compared and returned the biggest of the four penalties in an attempt to maximize the fitness function, while minimizing the pilot's total workload.
暂无评论