Vision-Based Control for Unmanned Rotorcraft
Christopher Jones, Jacques Heyder-Bruckner, Thomas Stuart Richardson, Chris Jones · AIAA Guidance, Navigation, and Control Conference and Exhibit · 2006
Removing the pilot from the cockpit of an aircraft leads to complex control challenges. An autonomous system must be capable of obtaining real-time position fixes for which some sensors are commercially available. For example, global positioning systems can give a definitive answer to the problem of knowing the current location. Problems can arise when using global positioning systems for navigation due to the availability of signals, the uncertainty in physical data or when tracking moving objects. Using visual sensors facilitates the tracking of moving targets within visual range. Rotorcraft are ideally suited to the tracking of targets, such as vehicles, which may be stationary for periods, due to their ability to hover in a fixed point in space for short periods. The ability to autonomously track and land on a target that is able to move in up to 6 degrees of freedom would have numerous applications, and would benefit from vision-based control. The work presented here is a first step toward achieving this aim through investigation of limited degree of freedom models in order to explore the capabilities of vision software as a control system sensor, and integration within control system architectures. In all, three experiments are presented; single degree of freedom pitch control using vision feedback as the main sensor; yaw control of an Ikarus ECO-8 model helicopter using inertial sensors and drift correction through visual control; and moving target tracking in 2 degrees of freedom incorporating a vision sensor alongside more standard sensor solutions. The initial work presented here shows that vision-based control of a rotary wing unmanned vehicle is a challenging yet feasible problem.