Markerless Visual Servo Control of a Micro Helicopter with a Wireless Camera

Abstract

In this paper, the authors present a markerless vision-based estimation and control algorithm for a micro helicopter with a wireless camera. The camera looks downward, and it captures an image of the ground at each time step. The proposed algorithm consists of vision-based estimation and switched control. The 3D location and posture of the helicopter are estimated by using template matching with automatic reference generation. The proposed algorithm also detects noisy images that are sometimes captured by the camera. The control signals are produced by a set of PID controllers if the current captured image is noiseless, and otherwise by a set of integral controllers. Long-time hovering is achieved over a high contrast and planar ground. No specified markers or prior texture information are required. Yasushi IWATANI (Member)He received his B.S.

Indoor Hovering Flight of a Micro Helicopter by Markerless Visual Servo Control Based on Phase Correlation

“…A micro helicopter flights over a blue tiled carpet and a gray uniform carpet in this paper, while it flighted over a high contrast and colorful floor in [4]. The helicopter control system considered in this paper is same as [4].…”

“…A micro helicopter flights over a blue tiled carpet and a gray uniform carpet in this paper, while it flighted over a high contrast and colorful floor in [4]. The helicopter control system considered in this paper is same as [4]. The system consists of a helicopter with a wireless camera, a receiver, a computer with a video card and a DA converter, a signal converter, and a transmitter as shown in Fig.…”

“…Noisy images are sometimes obtained due to communication errors between the camera and the receiver, vibration behaviors of the helicopter and/or electromagnetic interference from motor devices. They are classified into two types, black line insertion and deformation/discoloration [4].…”

“…Vision-based control is also useful to autonomous takeoffs and landings, since precise position control is required at a neighborhood of the takeoff pad or the landing pad [3]. Vision-based control systems for helicopters may be separated into three groups based on sensor configurations as summarized in [4]. The first has combinations of cameras and some other sensors such as GPS, IMU and/or laser range finders.…”

“…The authors have proposed a markerless visual servo controller for a micro helicopter with an on-board monocular camera [4]. The camera is a single sensor for control of the helicopter, and it is a wireless device.…”