• 대한기계학회논문집A
• /
• 제34권8호
• /
• pp.953-964
• /
• 2010

이 연구에서는 다 개체 로봇에 의해 하나의 로봇을 자율적으로 포획하는 협업제어에 관한 연구를 제안한다. 제안된 방안은 각 로봇에 대한 작업역할을 지정하는 역할 분류기, 단일 로봇의 행동 선택기 그리고 복잡한 상황을 대처하는 협업관리기로 구성되어 있다. 이 연구에서는 주변의 다개체 로봇의 다양한 행동을 통하여 단위 로봇을 특정지역으로 몰아가는 결과를 시뮬레이션을 통하여 그 적절성을 검증하였다.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2001년도 합동 추계학술대회 논문집 정보 및 제어부문
• /
• pp.428-430
• /
• 2001

다수의 자율이동로봇으로 구성되는 다개체 시스템에서의 협조행동을 위해서 각 개체는 주변환경의 인식뿐만 아니라 환경변화에 적응할 수 있는 추론능력이 요구된다. 이에 본 논문에서는 강화학습을 이용하여 동적으로 변화하는 환경 하에서 개체들이 스스로 학습하고 대처할 수 있는 협조행동 방법을 제시한다. 제안한 방법을 먹이와 포식자 문제에 적용하여 포식자 로봇간의 협조행동을 구현하였다. 여러 대로 구성된 포식자 로봇은 회피가 목적인 먹이로봇을 추적하여 포획하는 것이 임무이며 포식자 로봇들 간의 협조행동을 위해 각 상태에 따른 최적의 행동방식을 찾는데 강화학습을 이용한다.

• 한국정밀공학회:학술대회논문집
• /
• 한국정밀공학회 2011년도 춘계학술대회 논문집
• /
• pp.291-292
• /
• 2011

• 제어로봇시스템학회논문지
• /
• 제10권8호
• /
• pp.696-702
• /
• 2004

An optimal trajectory generation algorithm for capturing a moving object by a mobile robot in real-time is proposed in this paper. The linear and rotational velocities of the moving object are estimated using the Kalman filter, as a state estimator. For the estimation, the moving object is tracked by a 2-DOF active camera mounted on the mobile robot, which enables a mobile manipulator to track the mobile robot until the capturing moment. The optimal trajectory for capturing the moving object is dependent on the initial conditions of the mobile robot as well as the moving object. Therefore, real-time trajectory planning for the mobile robot is definitely required for the successful capturing of the moving object. The performance of proposed algorithm is verified through the real experiments and the superiority is demonstrated by comparing to other algorithms.

• 제어로봇시스템학회논문지
• /
• 제7권9호
• /
• pp.741-748
• /
• 2001

In this paper, we propose a method of tracking and capturing a moving object by a mobile robot. The position of the moving object is acquired from the relation through color-based image information from a 2-DOF active camera mounted on the mobile robot. The direction and rotational angular velocity of the moving object are estimated using a state estimator. A Kalman fiber is used as the state estimator for taking characteristics of robustness against noises and uncertainties included in the input data. After estimating the trajectory of the moving object, we decide on the optimal trajectory and plan the motion of the mobile robot to capture the target object within the shortest distance and time. The effectiveness of the proposed method is demonstrated by the simulations and experiments.

• 한국해양공학회지
• /
• 제30권2호
• /
• pp.141-149
• /
• 2016

In this technical note, the issues and challenges for the launch and recovery systems (LARS) and related techniques for the operation of an underwater robot from a manned platform are considered. Various types of LARS fitted to specific manned platforms, surface or sub-surface, are surveyed and categorized. The current UUV launch and recovery systems from surface ships and submarines utilize time consuming processes. As underwater robot technologies evolve and their roles are defined, safe and effective launch and recovery methods should be developed capable of reliable and efficient operations, particularly at a high sea state. To improve the existing underwater robot capabilities, LARS technology maturation is required in the near term, leading to the ability to incorporate autonomous LARS for an underwater robot on a manned platform. In the near term, particular emphasis should be placed on UUV LARS, which are surface ship based, with submarine based systems in the long term. Furthermore, for a dedicated LARS ship, independent of the existing host ship type, particular emphasis should be given to fully utilizing the capabilities of underwater robots.

• 제어로봇시스템학회논문지
• /
• 제12권2호
• /
• pp.145-153
• /
• 2006

An optimal capturing trajectory for a moving object is proposed in this paper based on the observation that a single-curvature path is more accurate than double-or triple-curvature paths. Moving distance, moving time, and trajectory error are major factors considered in deciding an optimal path for capturing the moving object. That is, the moving time and distance are minimized while the trajectory error is maintained as small as possible. The three major factors are compared for the single and the double curvature trajectories to show superiority of the single curvature trajectory. Based upon the single curvature trajectory, a kinematics model of a mobile robot is proposed to follow and capture the moving object, in this paper. A capturing scenario can be summarized as follows: 1. Motion of the moving object has been captured by a CCD camera., 2. Position of the moving object has been estimated using the image frames, and 3. The mobile robot tries to follow the moving object along the single curvature trajectory which matches positions and orientations of the moving object and the mobile robot at the final moment. Effectiveness of the single curvature trajectory modeling and capturing algorithm has been proved, through simulations and real experiments using a 2-DOF wheel-based mobile robot.