• 한국정밀공학회:학술대회논문집
• /
• 한국정밀공학회 2008년도 춘계학술대회 논문집
• /
• pp.477-478
• /
• 2008

• 한국인터넷방송통신학회논문지
• /
• 제9권5호
• /
• pp.101-107
• /
• 2009

본 논문은 감시카메라 영상으로부터 응급상황을 탐지하는 방법과 응급상황의 정밀 탐색 및 서비스를 위한 이동로봇 추적 시스템 개발에 대하여 기술한다. 건물 곳곳에 설치된 카메라로부터 얻어지는 일련의 영상들을 분석하여 처리함으로써 사람의 행동을 인식할 수 있으며, 이 중 응급상황이 탐지된 경우 준비된 이동로봇을 이용해 응급상황 발생지점의 정밀 탐색이 가능하다. 감시 카메라 영상을 통하여 사람의 행동들을 인식하기 위해서는 인간의 모습이라고 가정되는 영역들을 추적하고 관리해야 한다. 한 영상에서 가우시안 혼합 모델(MOG)을 이용하여 배경과 분리된 관심 영역들을 추출하고, 각 영역들을 외관 모델을 이용하여 지속적으로 추적한다. 그리고 각 영역의 실루엣 정보를 이용한 움직임 누적 영상(MHI)을 생성하여 행동을 모델링하고 신경망을 이용하여 응급 상황을 최종 인식한다. 또한 응급상황에 처한 사람과 이동로봇의 위치정보를 계산해 이동로봇이 사람에게 접근하는 기술을 구현한다.

• 한국멀티미디어학회논문지
• /
• 제17권7호
• /
• pp.787-796
• /
• 2014

Many mobile robot navigation methods utilize laser scanners, ultrasonic sensors, vision camera, and so on for detecting obstacles and path following. However, human utilizes only vision(e.g. eye) information for navigation. In this paper, we study a mobile robot control method based on only the camera vision. The Gaussian Mixture Model and a shadow removal technology are used to divide the foreground and the background from the camera image. The mobile robot uses a combined CAMSHIFT and KLT feature tracker algorithms based on the information of the foreground to follow a person. The algorithm is verified by experiments where a person is tracked and followed by a robot in a hallway.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2004년도 ICCAS
• /
• pp.1419-1423
• /
• 2004

In this paper, we propose an algorithm for planning an optimal path to capture a moving object by a mobile robot in real-time. The direction and rotational angular velocity of the moving object are estimated using the Kalman filter, a state estimator. It is demonstrated that the moving object is tracked by using a 2-DOF active camera mounted on the mobile robot and then captured by a mobile manipulator. The optimal path to capture the moving object is dependent on the initial conditions of the mobile robot, and the real-time planning of the robot trajectory is definitely required for the successful capturing of the moving object. Therefore the algorithm that determines the optimal path to capture a moving object depending on the initial conditions of the mobile robot and the conditions of a moving object is proposed in this paper. For real-time implementation, the optimal representative blocks have been utilized for the experiments to show the effectiveness of the proposed algorithm.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2003년도 ICCAS
• /
• pp.186-190
• /
• 2003

In this paper, we propose an algorithm for planning an optimal path to capture a moving object by a mobile robot in real-time. The direction and rotational angular velocity of the moving object are estimated using the Kalman filter, a state estimator. It is demonstrated that the moving object is tracked by using a 2-DOF active camera mounted on the mobile robot and then captured by a mobile manipulator. The optimal path to capture the moving object is dependent on the initial conditions of the mobile robot, and the real-time planning of the robot trajectory is definitely required for the successful capturing of the moving object. Therefore the algorithm that determines the optimal path to capture a moving object depending on the initial conditions of the mobile robot and the conditions of a moving object is proposed in this paper. For real-time implementation, the optimal representative blocks have been utilized for the experiments to show the effectiveness of the proposed algorithm.

• 로봇학회논문지
• /
• 제13권2호
• /
• pp.121-128
• /
• 2018

Obstacle avoidance is one of the most important parts of autonomous mobile robot. In this study, we proposed safe and efficient local path planning of robot for obstacle avoidance. The proposed method detects and tracks obstacles using the 3D depth information of an RGB-D sensor for path prediction. Based on the tracked information of obstacles, the paths of the obstacles are predicted with probability circle-based spatial search (PCSS) method and Gaussian modeling is performed to reduce uncertainty and to create the cost function of caution. The possibility of collision with the robot is considered through the predicted path of the obstacles, and a local path is generated. This enables safe and efficient navigation of the robot. The results in various experiments show that the proposed method enables robots to navigate safely and effectively.

• 한국정밀공학회:학술대회논문집
• /
• 한국정밀공학회 1995년도 춘계학술대회 논문집
• /
• pp.490-496
• /
• 1995

A four-legged mobile robot can move on the plain terrain with mobility and stability, but if there exist any obstacles on the terrain of the motion direction, it takes extra times for a mobile robot to cross those obstacles and the stability should be considered during motion. The main objevtive is the study of a quadruped which can cross obstacles with better mobility, stability and fuel economy than any other wheeled or tracked vehicles. Vertical step, isolated wall and ditch are the basic obstacles and by understanding those three cases perfectly, a quadruped can move on any mixed rough terrain as 4-legged animal moves. Each leg of a determine the crossing capability in a static analysis. A quadruped can be simplified with links and joints. By applying the research method, a quadruped can determine the control procedures as soon as it receives the terrain informations from scanner and finally can be moved as animals move with mobility and stability.

• 로봇학회논문지
• /
• 제5권3호
• /
• pp.270-277
• /
• 2010

Various robot platforms have been designed and developed to perform given tasks in a hazardous environment for the purpose of surveillance, reconnaissance, search and rescue, and etc. We have considered a terrain adaptive hybrid robot platform which is equipped with rapid navigation on flat floors and good performance on overcoming stairs or obstacles. Since our special consideration is posed to its flexibility for real application, we devised a design of a transformable robot structure which consists of an ordinary wheeled structure to navigate fast on flat floor and a variable tracked structure to climb stairs effectively. Especially, track arms installed in front side, rear side, and mid side are used for navigation mode transition between flatland navigation and stairs climbing. The mode transition is determined and implemented by adaptive driving mode control of mobile robot. The wheel and track hybrid mobile platform apparatus applied off-road driving mechanism for various professional service robots is verified through experiments for navigation performance in real and test-bed environment.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2001년도 ICCAS
• /
• pp.64.4-64
• /
• 2001

Localization is the key role in controlling the Mobile Robot. In this papers, a development of the sensor fusion algorithm for controling UTV(Unmanned Tracked Vehicle) is presented. The multi-sensocial dead-rocking subsystem is established based on the optimal filtering by first fusing heading angle reading from a magnetic compass, a rate-gyro and two encoders mouned on the robot wheels, thereby computing the deat-reckoned location. These data and the position data provoded by LBL system are fused together by means of an extended Kalman filter. This algorithm is proved by simulation studies.

• 로봇학회논문지
• /
• 제4권2호
• /
• pp.105-111
• /
• 2009

In this paper, we provide experimental results and verification for obstacle avoidance algorithm 'ELA(Emergency Level Around)', which is applicable to rescue robots. ELA is a low level intelligence-based obstacle avoidance algorithm, so can be used in fast mobile robots requiringhigh speed in operation with little computational load. Constructed system for experiments consist of laptop, sensors, peripheral devices and mobile robot platform VSTR(Variable Single-tracked Robot) to realize predetermined scenarios. Finally, experiment was conducted in indoor surroundings including miscellaneous things as well as dark environment to show fitness and robustness of ELA for rescue, and it is shown that VSTR navigates endowed area well with real-time obstacle avoidance based on ELA. Therefore, it is concluded that ELA can be a candidate algorithm to increase mobility of rescue robots in real situation.