• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.12 no.4
• /
• pp.1786-1795
• /
• 2011

The trajectory control for omni-directional mobile robot is not easy. Especially, the tracking control which system uncertainty problem is included is much more difficult. This paper develops trajectory controller of 3-wheels omni-directional mobile robot using fuzzy multi-layered algorithm. The fuzzy control method is able to solve the problems of classical adaptive controller and conventional fuzzy adaptive controllers. It explains the architecture of a fuzzy adaptive controller using the robust property of a fuzzy controller. The basic idea of new adaptive control scheme is that an adaptive controller can be constructed with parallel combination of robust controllers. This new adaptive controller uses a fuzzy multi-layered architecture which has several independent fuzzy controllers in parallel, each with different robust stability area. Out of several independent fuzzy controllers, the most suited one is selected by a system identifier which observes variations in the controlled system parameter. This paper proposes a design procedure which can be carried out mathematically and systematically from the model of a controlled system; related mathematical theorems and their proofs are also given. Finally, the good performance of the developed mobile robot is confirmed through live tests of path control task.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.20 no.2
• /
• pp.228-234
• /
• 2019

This study was conducted to evaluate the usability of serious-game apps for robots that are being developed for hospitals to add familiarity to hospital life for hospitalized patients. We conducted a usability test of 10 experts and 12 elementary school students with inpatient experience. The usability evaluation of the developed apps was based on the professional (MARS) evaluation tool and the user (uMARS) evaluation tool. The results of the usability test of the serious game robot app were $3.67{\pm}0.342$ for professionals and $3.68{\pm}0.592$ for children. The expert group obtained the highest score in the aesthetics category, and the user group obtained the highest score in the functionality category. In the subjective comments, the experts pointed out the game layout and the consistency of the style. According to the children, the methods were easy to learn, and the screen movement was mainly described. Both groups received low ratings in terms of engagement through participation. This study will provide useful reference material when the functional game app is actually installed in the robot and the usability test is conducted again after the results obtained in this study are considered.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.19 no.12
• /
• pp.47-53
• /
• 2018

Various types of robotic arms are being used for industrial purposes, particularly with the small production of multi-products, and the importance of the gripper, which can be used in industrial fields, is increasing. This study evaluated a variable stiffness mechanism gripper that can change the stiffness using the nonlinearity of a flexible material. A prototype of the gripper was fabricated and examined to confirm the change in stiffness. The previous gripper was unable to grip objects in some situations with three variable stiffness mechanism. In addition, these mechanisms were not balanced and rarely rotated when the object was gripped. Therefore, a new type of gripper was needed to solve this problem. Inspired by the movements of the human palm and Venus Flytrap, a new type of a variable stiffness soft robot hand was designed. The possibility of grasping could be increased by interlocking the palm folding mechanism by pulling the tendon attached to the variable stiffness mechanism. The soft robotic hand was used to grasp objects of various shapes and weights more stably than the previous variable stiffness mechanism gripper. This new variable stiffness soft robot hand can be used selectively depending on the application and environment to be used.

• Proceedings of the KAIS Fall Conference
• /
• 2010.11a
• /
• pp.344-348
• /
• 2010

The intent of this paper is to describe a neural network structure called multi dynamic neural network(MDNN), and examine how it can be used in developing a learning scheme for computing robot inverse kinematic transformations. The architecture and learning algorithm of the proposed dynamic neural network structure, the MDNN, are described. Computer simulations are demonstrate the effectiveness of the proposed learning using the MDNN.

• Proceedings of the KAIS Fall Conference
• /
• 2010.11a
• /
• pp.332-336
• /
• 2010

The intent of this paper is to describe a neural network structure called multi dynamic neural network(MDNN), and examine how it can be used in developing a learning scheme for computing robot inverse kinematic transformations. The architecture and learning algorithm of the proposed dynamic neural network structure, the MDNN, are described. Computer simulations are demonstrate the effectiveness of the proposed learning using the MDNN.

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 2010.05a
• /
• pp.77-78
• /
• 2010

• Proceedings of the KAIS Fall Conference
• /
• 2007.05a
• /
• pp.150-153
• /
• 2007

The intent of this paper is to describe a neural network structure called multi dynamic neural network(MDNN), and examine how it can be used in developing a learning scheme for computing robot inverse kinematic transformations. The architecture and learning algorithm of the proposed dynamic neural network structure, the MDNN, are described. Computer simulations are demonstrate the effectiveness of the proposed learning using the MDNN.

• Proceedings of the KAIS Fall Conference
• /
• 2011.05a
• /
• pp.109-112
• /
• 2011

본 논문에서는 13가지 생각하는 도구와 로봇교육의 결합을 다루고 있다. 21세기의 새로운 경쟁력이 되고 있는 창의력과 훌륭한 교구로써의 역할을 지니고 있는 교육용 교구로봇을 연계함으로써 낼 수 있는 시너지 효과에 대하여 서술하려 한다.

• Proceedings of the KAIS Fall Conference
• /
• 2009.05a
• /
• pp.454-457
• /
• 2009

The intent of this paper is to describe a neural network structure called multi dynamic neural network(MDNN), and examine how it can be used in developing a learning scheme for computing robot inverse kinematic transformations. The architecture and learning algorithm of the proposed dynamic neural network structure, the MDNN, are described. Computer simulations are demonstrate the effectiveness of the proposed learning using the MDNN.

• 제어로봇시스템학회:학술대회논문집
• /
• 1998.10a
• /
• pp.190-194
• /
• 1998

In this paper, we introduce the micro robot soccer playing system as a standard test bench for the study on the multiple agent system. Our method is based on following viewpoints. They are (1) any complex behavior such as cooperation among agents must be completed by sequential basic actions of concerned agents. (2) those basic actions can be well defined, but (3) how to organize those actions in current time point so as to result in a new stale beneficial to the end aim ought to be achieved by a kind of self-learning self-organization strategy.