No abstract

This paper addresses vision-based tracking and landing of a micro-aerial vehicle (MAV) on a ground vehicle (GV). The camera onboard the MAV is mounted so that the optical axis is aligned with the downward-facing axis of the body-fixed frame. A novel supervised learning vision algorithm is proposed as the method to detect the ground vehicle in the image frame. A feedback linearization technique is developed for the MAV to fly over and track the GV so that visibility with the tracked target is maintained with certain guarantees. The efficacy of the visual detection algorithm, and of the tracking and landing controller is demonstrated in simulations and experiments with static and mobile GV.

No abstract

No abstract