Wheeled robot control for catching up flying objects using RGB-D sensors

This work is proposed to actualize a wheeled robot system for catching up flying objects. The landing site of the flying objects is estimated by an image recognition system with capacity of processing the location of a flying object in terms of depth, which is measured by an RGB-D sensor. And according to the depth of the object and the XY coordinates of image pixels, the system will convert the measured data to a three-dimensional spatial coordinate with respect to the frame of the RGB-D sensor. Then an algorithm is proposed to predict the flying path and the landing point of the object in real time. The algorithm can predict the direction of the flying object and its landing point according to, respectively, the first two and the first three measured data of the object position very effectively. Finally, several experiments are carried out for catching up flying objects of different shapes, colors and sizes.