世界初の糊付けまで可能な折紙ロボットの開発

抄録

Creating complex spatial objects from a flat sheet of material using origami-folding techniques has attracted attention in science and engineering. It is extremely difficult to introduce highly versatile automation using machines to handle deformable objects such as a flat sheet of paper. This work proposes two machines for paper manipulations based on Lego NXT technology that use feedback error learning (FEL) with holographic neural networks (HNN) to perform precise and smooth manipulations of the paper. The first machine makes simple zigzag folding and the second machine glues the generated zigzag folded paper to generate complex 3D shapes. A new spring-back compensation algorithm is proposed to deal with paper's thickness increase after multiples folding and the change in gluing positions due to the paper spring-back phenomenon. The results demonstrate that proposed compensation approximates the generated motion trajectories to real paper fluctuations in the machines. Examples of round shapes and honeycomb patterns are shown.