Converting Motion between Different Types of Humanoid Robots Using Genetic Algorithms

Abstract

Abstract-The imitation between different types of robots remains an unsolved task for a long time. The assignment of the correct angles to each joint is critical for robot motion. However, different robots have different structures, thus this discrepancy causes a difficulty when converting a motion to another type of robot. For solving this problem, we propose a GA-based method that can find the conversion matrix needed to map joint angles of one robot to another. There are two objectives to consider when creating an imitation; reducing the difference between the ideal imitation and the converted imitation and keeping the stability. Three experiments were conducted; a stable experiment, an unstable experiment and a double learning experiment. As a result, the double experiment showed a high concordance rate of 93.5%, the highest stability and the fastest speed of all experiments. These results show great promise for the proposed method as a way to realize motion imitation between different types of robots.

Investigating the potential of redundant manipulators in narrow channels

“…Proceeding with this technique, Carmak and Mikhail 20 recently developed a navigation system for mobile robot in dynamic environment where objects in the proximity of robot are tracked by using laser scanner of simulated type. In the research domain of mobility, Nishiyama and Iba 21 proposed a conversion matrix using genetic algorithms (GA) for mapping of joint parameters of different robots with each other. The proposed algorithm is utilized to assign correct joint angles for distinct robot structures without any discrepancy.…”

Behaviour based navigational control of humanoid robot using genetic algorithm technique in cluttered environment

“…Singh et al [19][20][21] proposed navigational controllers for mobile robots by using the forward neural network in a real world dynamic environment. Nishiyama and Iba [22] analysed different robot motions using double learning experiments. Roberts et al [23] have described regarding smoothing the Zero Moment Point (ZMP) using two GA tunings and tested their approach through multiple simulations.…”