• Journal of the Korean Institute of Intelligent Systems
• /
• v.15 no.1
• /
• pp.59-64
• /
• 2005

In the paper, we propose an intelligent walking algorithm of biped robot on the uneven ground and a posture stabilization algorithm against external forces. At first, the mechanics and the control system of biped robot that can walk on the uneven ground and stand external forces are designed. We propose obstacle hurdling, incline walking. and going-up stairs algorithm by using infrared sensors and FSR sensors. Also, posture stabilization algorithm against external forces is designed using FSR sensors. Infrared sensors ate used to detect the obstacles in the working environment and FSR sensors are used to obtain the ZMP of biped robot. The developed biped robot can be controlled by the remote control system using vision system and RF module. The experimental results show that the biped robot Performs obstacle avoidance, obstacle hurdling, walking on the inclined plane, and going up stairs using the proposed walking and stabilization algorithm.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.19 no.4
• /
• pp.532-537
• /
• 2009

The necessity of intelligent surveillance system is gradually considered seriously from the space where the security is important. In this paper, we embodied unmanned intelligent system by developing embedded mobile robot based on images and sounds tracking. For objects tracking, we used block-matching algorithm and for sound source tracking, we calculated time differences and magnitude dissimilarities of sound. And we demonstrated the superiority of intruder tracking algorithm through the embodiment of Pan-Tilt camera and sound source tracking module using system, Network camera and mobile robot using system and mobile robot using system. By linking security system, the suggested system can provide some interfacing functions for the security service of the public facilities as well as that of home.

• Journal of Internet Computing and Services
• /
• v.10 no.5
• /
• pp.117-125
• /
• 2009

Early in 21st century, researches about intelligent service robot that provide various services for a human out of the industrial robot only has simple pattern repetition. It concentrates in the research regarding the URC(Ubiquitous Robotic Companion) robot which connects the network in the intelligent service. This paper proposes the robot system based on network to guide a way. The robot has made by lego brick and used ultrasonic sensor, rotation sensor and RFID tag to recognize external environment. Also, it includes a PDA to process the data between robot and server. The network server transmits information to robot controller by bluetooth and it controls the course movement and evasion of the robot. In this research, the robot system based on network to guide a way is easy to expand service and is able to process a data in real time due to data processing in the server as a part of intelligent robot. And it can reduce the cost to build a robot thank to use cheaper sensor equipment.

• The Journal of the Korea Contents Association
• /
• v.18 no.9
• /
• pp.116-124
• /
• 2018

This study aimed to interpreting the view of current media by artificial intelligence(AI) with the case of a TV show Person of Interest, which was broadcasted until 2016 in US. In this study, we first attempted to find how AI reflects the three laws of robotics, which often appear in Science Fictions. In addition, we paid attention to how the society looks according to the change of the manipulator of the AI, and as a result we derived the distinguishes of the show from other content dealing with robots or AI in terms of narrative. Through this study, we classified the messages in accordance of AI into three categories- importance of data sovereignty, potential of intelligence explosion, and blind faith in high technology. This study suggested that the show emphasizes the consciousness and attitude that should be possessed as a citizen who meets the era of AI prior to raising issue of 'what artificial intelligence is should be developed for our convenience?'

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2005.11a
• /
• pp.305-308
• /
• 2005

시각 센서를 이용한 환경 및 상황 인식은 로봇의 자동화된 행동을 위해서 매우 중요하다. 실제 환경에서 사람은 주위를 인식할 때 여러 단계의 인식과정을 거친다. 효율적이고 정확한 환경 인식을 위해서는 지능형 로봇의 인식 또한 사람의 인식과정과 같이 다단계로 이루어져야 한다. 또한 실제 환경은 유동적이며 많은 불확실성을 가지고 있으므로 불확실한 상황에 강인한 인식 방법이 필요하다. 이러한 불확실성을 내포한 환경 및 상황 인식에는 베이지안 네트워크를 이용한 인식이 강인하나 복잡한 환경을 하나의 베이지안 네트워크로 인식하는 것은 어렵다. 이 논문에서는 복잡하고 불확실한 환경 인식을 위한 여러 베이지안 네트워크를 사람의 인식과 같은 다단계의 인식 과정으로 구성된 행동 네트워크 기반으로 결합하는 앙상블 기법을 제안한다. 불확실한 상황을 적용한 환경 실험과 로봇 시뮬레이터를 이용한 로봇 실험으로 베이지안 네트워크 앙상블 기법이 환경 인식에 효과적인 것을 확인할 수 있었다.

• Proceedings of the KAIS Fall Conference
• /
• 2009.12a
• /
• pp.293-294
• /
• 2009

시스템 통합(System Integration) 패러다임의 변화와 MEMS, 네트워크 기술의 발달로 사람, 컴퓨터 그리고 사물이 유기적으로 연계되어 다양하고 편리한 서비스를 제공해 주는 컴퓨팅 기술에 대한 연구들이 진행 되고 있다. 이와 관련하여 지능형 로봇 시스템 환경은 중앙집중 환경에서 분산 환경과 웹이융합된 새로운 환경으로 변화하고 있다. 이를 적용하기 위해서 다양한 연구기관의 개발자 들은 이를 지원할 수 있는 미들웨어의 개발에 많은 노력을 기울이고 있다. 로봇 미들웨어는 다양한 통신 프로토콜, 하드웨어, 운영체제 그리고 프로그래밍 언어의 통합, 통신 오버헤드 그리고 소프트웨어 개발 방법론 등 많은 문제점을 가지고 있다. 본 논문에서는 통합성, 통신 오버헤드, 유연성을 기준으로 기존 미들웨어의 단점을 제시하고 해당 문제점을 해결하기 위한 지능형 로봇을 위한 효율적 미들웨어를 제안한다.

• Journal of Internet Computing and Services
• /
• v.8 no.2
• /
• pp.137-146
• /
• 2007

This paper presents a way to integrate a task planner with a plan executive for efficient control of intelligent robots. For this purpose, it first surveys several types of the existing task planners and plan executives. And then it introduces a new approach that combines a BDI-based executive with an on-demand task planner, and it explains a control architecture of intelligent robots based upon this integrating paradigm. Finally it analyzes the flexibility and robustness of both the proposed integrating paradigm and the control architecture through implementation of a demo system using AIBO robots.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2000.05a
• /
• pp.175-178
• /
• 2000

생명체는 자신을 이루고 있는 단순한 구성 요소들이 적은 수의 근본 규칙들에 의하여 국부적 상호작용을 함으로써 복잡한 생명 현상을 보이고있다 이 연구에서는 생명 현상을 보이고 있는 개체가 많은 수의 단순한 구성 요소들의 집합으로 이루어져 있으며 그러한 구성 요소들이 적은 수의 근본 규칙들에 의하여 서로 국부적인 상호작용을 함으로써 복잡한 행동패턴들을 나타낸다는 가정 아래, 여러 대의 자율이동로봇(autonomous mobile robot)들의 군지능을 나타낼 수 있는 적은 수의 근본 규칙을 찾아내고 찾아진 근본규칙들을 퍼지규칙으로 표현하는 것을 목표로 한다. 각 자율이동로봇은 기능이 매우 제한되어 있으며, 자신만의 독특한 신호를 발생한다. 이 신호를 "heartbeat"이라 부르며 이를 이용하여 대략적으로 자신의 위치와 현재상태를 다른 개체에게 알리는 역할을 한다 이 논문에서는 "heartbeat"을 이용한 로봇간의 통신과 자재반송이라는 군행동을 퍼지시스템으로 구현하고 이를 평가한다.

• Electronics and Telecommunications Trends
• /
• v.36 no.1
• /
• pp.12-21
• /
• 2021

This article presents the future vision and core technologies of the "Life Companion Robot," which is one of the 12 future concepts introduced in the ETRI Technology Roadmap published in November 2020. Assistant robots, care robots, and life support robots were proposed as the development stages of life companion robots. Further, core technologies for each of the ten major roles that must be directly or indirectly performed by life companion robots are introduced. Finally, this article describes in detail three major artificial intelligence technologies for autonomous robots.

• KIPS Transactions on Software and Data Engineering
• /
• v.11 no.9
• /
• pp.363-370
• /
• 2022

Grasping a target object among clutter objects without collision requires machine intelligence. Machine intelligence includes environment recognition, target & obstacle recognition, collision-free path planning, and object grasping intelligence of robot hands. In this work, we implement such system in simulation and hardware to grasp a target object without collision. We use a RGB-D image sensor to recognize the environment and objects. Various path-finding algorithms been implemented and tested to find collision-free paths. Finally for an anthropomorphic robot hand, object grasping intelligence is learned through deep reinforcement learning. In our simulation environment, grasping a target out of five clutter objects, showed an average success rate of 78.8%and a collision rate of 34% without path planning. Whereas our system combined with path planning showed an average success rate of 94% and an average collision rate of 20%. In our hardware environment grasping a target out of three clutter objects showed an average success rate of 30% and a collision rate of 97% without path planning whereas our system combined with path planning showed an average success rate of 90% and an average collision rate of 23%. Our results show that grasping a target object in clutter is feasible with vision intelligence, path planning, and deep RL.