大学院情報理工学系研究科電子情報学専攻
Graduate School of Information Science and Technology Department of Information and Communication Engineering The University of Tokyo
Abstract
Recently, many areas of research on humanoid robots have been studied, such as motion control, man-machine interfaces, artificial intelligence (AI), and so on. Among them many research projects have tried to create artist robots, with the common objective of exploring new sensing, artificial intelligence, and manipulation techniques. The research described in this paper explores new vision and manipulation techniques through painting tasks. The ultimate goal is to create a robot painter that has capabilities similar to those of human artists. Regarding vision, the key problems of 2D/3D object segmentation, color perception, orientation mapping, and geometric edge processing are directly addressed by our method. This research focuses, first, on an effective 2D segmentation scheme using local and global classifiers. Our proposed method can effectively deal with a foreground cut, multiple cuts, and cut before matting. Then it is shown how to exploit normal stereo cameras to roughly extract the object automatically, based on 3D background subtraction and other vision techniques, and how to use our 2D segmentation to extract the object area correctly. The robot must analyze color distribution of the object to select the best set of colors to use. Normally, clustering colors face the tendency to produce colors with low contrast. We solve this problem by incorporating two clustering methods: maximum distance clustering and K-means. Then, in order to draw brush strokes meaningfully, the robot senses the orientation of the object. To smooth the orientation of the whole object, we apply global orientation that exploits the radial basis function to generate a style similar to Van Gogh, for instance, for the entire object. Furthermore, some human artists usually use edges to enhance their paintings. Technically, many researchers use gradient information to represent edges of objects. However, this would be affected by the color information on the surface. Hence, we decided to use 3D geometric edges as an input. We then extract 2D edges from the 3D model. Finally, the 2D edges are processed into brush strokes. We show how to apply these methods to high-level manipulation using a robot platform that consists of two arms and multi-fingered hands. The robot also has a stereo vision system. Based on the derived information, the robot then performs a visual feedback drawing. First, it detects a brush and grabs it using cameras and force sensors. Second, it calculates the position of the brush tip using principal component analysis (PCA). Third, it then draws and compares the canvas with the picture produced by the stereo cameras. Finally, as the trajectories planned by the robot may not be realized on the real robot platform because of its physical limitations, this research presents a method to filter and optimize trajectories targeting offline and online applications. All physical attributes, namely angle, collision, velocity, and dynamic force, are considered as a set of constraints to be met and represented as B-spline coefficients, making the limits guaranteed. The proposed method will be shown to outperform the current methods in the sense of correctness and minimal user interaction, and it does so in a reasonable computation time.
発行年
2008-03
日本十進分類法
548
学位名
博士(情報理工学)
学位
doctoral
学位分野
Information Science and Technology (情報理工学)
学位授与機関
University of Tokyo (東京大学)
研究科・専攻
Department of Information and Communication Engineering, Graduate School of Information Science and Technology (情報理工学系研究科電子情報学専攻)
学位授与年月日
2008-03-24
学位授与番号
甲第23947号
学位記番号
博情第192号
アイテムへのリンクの際はタイトル右肩にある「Permalink」をご利用ください！
Please use "Permalink" at the top right of the title when linking to items!
Robot Painter : High-Level Planning Based on Visual Perception
48057414.pdf
(5.83MB)
