Learning to Fly: Modeling Human Control Strategies in an Aerial Vehicle

Much work has been done in recent years to abstract computational models of human controlcomputational models of human control strategy (HCS) that are capable of accurately emulating dynamic human control behaviors. Land-based autonomous vehicles, both in simulation and on real roads, have made successful use of this modeling formalism. Little work has been done, however, in attempting such skill transfer from humans to aerial robotic vehicles. Although control of an aerial vehicle is quite different from that of ground vehicles, we contend that human pilots can potentially serve as excellent guides in the development of intelligent autonomous aerial vehicles. As a first step in modeling human control strategies in aerial vehicles, we are developing a robotic airplane (Figure 1) as an experimental platform for studying human-tomachine skill transfer in aerial vehicles. This paper describes the configuration of this airplane, the results of early experiments, and future planned experiments.