ClipBot：遺伝的アルゴリズムで歩行を学習する教育用身体障害ロボット
ClipBot: an educational, physically impaired robot that learns to walk via genetic algorithm optimization
クリップ2つで作った低コストDIYロボットが、遺伝的アルゴリズムにより20回未満の試行で前進歩行を学習する教育事例を報告した。
著者: Diego Ulisse Pizzagalli, Ilaria Arini, Mauro Prevostini
分類: cs.RO, cs.AI
原文アブストラクト
Educational robots allow experimenting with a variety of principles from mechanics, electronics, and informatics. Here we propose ClipBot, a low-cost, do-it-yourself, robot whose skeleton is made of two paper clips. An Arduino nano microcontroller actuates two servo motors that move the paper clips. However, such mechanical configuration confers physical impairments to movement. This creates the need for and allows experimenting with artificial intelligence methods to overcome hardware limitations. We report our experience in the usage of this robot during the study week 'fascinating informatics', organized by the Swiss Foundation Schweizer Jugend Forscht (www.sjf.ch). Students at the high school level were asked to implement a genetic algorithm to optimize the movements of the robot until it learned to walk. Such a methodology allowed the robot to learn the motor actuation scheme yielding straight movement in the forward direction using less than 20 iterations.