D201 ロボットコンバインの穀粒排出作業自動化のための画像処理技術の応用(OS14 農業機械の運動と制御1)

概要

論文の詳細を見る
In Japan, less and less workers are engaged in agriculture and they are aging rapidly. Moreover, opening up the country to trade is being inevitable year by year. Therefore, it is thought that Japan's agriculture will face a labor shortage and be exposed to harsher global competition in future. Development of automated agricultural machinery is a way to overcome the difficult circumstances. Thus we are now trying to develop a robot combined harvester. Attempt has been made to develop automated combined harvester. Although a few prototypes can run and automatically harvest rice and wheat, unloading work, in which grains are unloaded through harvester's auger to a truck attached with a grain container, has not yet been automated. This study presents a new method for positioning an auger at an appropriate position using marker detection algorithms and investigates the accuracy of positioning. SURF (Speeded-Up Robust Features) and ARToolKit are utilized for marker detection. A few types of markers are laid on the roof of a truck. Images are taken with USB camera attached to the auger. Our auger are modeled as a two-degree-of-freedom manipulator and controlled by calculated angles. The controlled positions are measured with a total station and compared to calculated positions. Experimental results indicate that this method has the sufficient accuracy in actual use.
2011-06-28