PINO The Humanoid : A Basic Architecture
In this paper, we present a basic architecture and design principle behind Pino, a humanoid for RoboCup Humanoid League. Pino is designed to be a platform for research in robotics and AI. There are four major issues in Pino’s design; (1) high DOF system t
- PDF / 302,828 Bytes
- 10 Pages / 451 x 677.3 pts Page_size
- 6 Downloads / 185 Views
Fuminori Yamasaki1;2, Tatsuya Matsui1 , Takahiro Miyashita1, and Hiroaki Kitano1 1
Kitano Symbiotic Systems Project, ERATO, JST, [email protected], 2 Osaka University
Abstract. In this paper, we present a basic architecture and design principle behind Pino, a humanoid for RoboCup Humanoid League. Pino is designed to be a platform for research in robotics and AI. There are four major issues in Pino's design; (1) high DOF system to realize various behaviors, (2) exterior design, (3) cheap mechanical components, and (4) a basic behavioral control systems. These issues are speci cally addressed in this paper in order to illustrate basic architecture and components for humanoid platform that can be widely used for many RoboCup researchers in the world.
1 Introduction RoboCup Humanoid League [1], expected to start from 2002, is one of the most attractive research target, as well as potential major media attraction. We believe that the success of the humanoid league is critical for the future of RoboCup, and have major implications in robotics research and industries. Thus, we believe that it is important basic architectures for cheap and reliable research platform for humanoid to be quickly established, so that researchers in RoboCup community can initiative further investigation. In this paper, we present an example of basic architecture of humanoid for one of RoboCup humanoid league. There are three major issues addressed in this paper. First, humanoid should have a well designed exterior. As robot became everyday-life products, exterior designs plays major role in consumer choice. Since most existing research robots are functionally designed with minimal aesthetics, carefully designed robots are not yet exposed to general public, with exception of AIBO[2] and SIG [3]. We claim that "robot design" will be the major industrial design eld, and wish to present archetype of humanoid design through Pino. Second, the use of cheap, o -the-shelf components made humanoid more accessible for broad-range of researchers. It is a general impression that humanoid research is extremely expensive, thus it is beyond the capability of the most research group. This is partly true if we are to design all components from scratch aiming at Honda P3 [4] level humanoid. However, we believe that there is a room in the humanoid research that many interesting research can be done P. Stone, T. Balch, and G. Kraetzschmar (Eds.): RoboCup 2000, LNAI 2019, pp. 269-278, 2001. c Springer-Verlag Berlin Heidelberg 2001
270
Fuminori Yamasaki et al.
using cheap and o -the-shelf components a ordable to most research groups. The hidden name of our project is, in fact, "The Poorman's humanoid project". Third, we are working on possible modular and basic set of primitive behaviors and their control systems that are essential for most humanoids. While humanoid has very high DOF, some of primitive and basic behaviors may be de nable as a hopefully modular and primitive control sub-unit. If our attempt is successful, more complex behaviors can be b
Data Loading...
