Copycat Hand - generation of imitative behavior by humanoid robot hand

摘要

The authors developed a method enabling to search similar images at high speed, with high accuracy, and in uniform processing time even in the case of use of a large-scale database, by clustering databases with about uniform numbers of data through self-organizing including self-multiplication and self-extinction, and by collating the input image with the data in the database by means of low-order amounts of characteristics of images, while narrowing the search space in accordance with the past history. By making estimation of continuous hand finger shape image string by using the method, we succeeded in realizing processing with an estimation error of joint angle within several degrees, at a processing time of 150 to 160 fps, and in an operating time without dispersion, in the case of use of a PC having a CPU clock frequency of 2.8 GHz and a memory capacity of 1GB. Because the image information and the joint angle information are paired in the database, the robot hand called as "Copycat hand" was able to reproduce the same motions as those of hand fingers of a human being, without any delay in time, by outputting the results of estimation at the robot hand.