• 한국정보통신학회논문지
• /
• 제6권8호
• /
• pp.1365-1373
• /
• 2002

본 논문에서는 자율 이동로봇이 장애물을 회피하며 목표하는 지점까지의 경로를 구성하여 찾아가는 알고 리즘을 제안하고자 한다. 시스템의 구성은 로봇에 탑재된 CCD카메라로부터 획득한 영상신호를 RF 무선 모듈을 이용하여 PC로 보내고 PC에서 영상 처리 과정을 거친 후, 장애물로 인식되는 지역을 회피하도록 제어 신호를 이동로봇으로 전송하는 것이다. 이동로봇에 탑재된 CCD카메라에서 획득한 영상 정보는 매 샘플링 시간마다 캡쳐하여 PC로 전송하고 호스트는 화면에서 장애물의 유무를 판별한 후 좌 혹은 우로 회전하여 장애물을 피해 나가도록 하며 로봇이 이동한 거리를 PC로 전송하는 시스템을 구현하여 초기에 지정한 목표지점까지 로봇이 갈 수 있도록 간략한 경로를 계획하여 추적해 나가도록 한다. 먼저 로봇으로부터 전송되어진 영상은 호스트PC에서 다음과 같은 영상처리과정을 거치도록 한다. 먼저 Original영상을 입력받아서 3X3 mask Sobel 연산자를 사용한다. 그리하면 윤곽선이 추출된다. 여기서 추출된 윤곽정보는 처리가 용이하도록 NOR Converter를 거치도록 한다 마지막으로 이 영상의 경계값을 찾는다. 처음에 획득한 영상은 깨끗한 환경에서 얻어진 것이 아니라 주변에 여러 가지 기구나 명암대비가 뚜렷하지 못한 조건들로 되어 있다. 어떤 장애물이라도 가까이서 획득한 영상으로 보게 되면 색상이 단일한 색상으로 나타난다. 즉, 멀리 있는 영상정보나 장애물이 없는 영상 정보 쪽에 히스토그램이 넓게 분포되기 마련이다. 이런 이유로 마지막에 Convert를 처리한 영상의 경계치를 229로 둔다. 그러면 거의 흰색에 가까우면서도 약간의 그레이 레벨만 가진다 하더라도 흑백 대비를 뚜렷하게 만들어 준다. 즉, 불순 성분을 받아들이기 위하여 경계값을 높이는 것이다. 다음으로 처리된 영상의 좌표를 (0, 0)에서 (0, 197)까지의 히스토그램 분포를 스캔한다. 그러면 장애물이 있는 부분의 히스토그램의 분포는 거의 변동이 없이 나타난다. 이러한 특성을 이용하여 장애물이 있는 곳을 찾아내고 이것을 회피하기 위한 알고리즘을 세웠다

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2004년도 ICCAS
• /
• pp.1550-1554
• /
• 2004

This paper deals with an unmanned vehicle system configuration using all terrain vehicle. Many research institutes and university study and develop unmanned vehicle system and control algorithm. Now a day, they try to apply unmanned vehicle to use military device and explore space and deep sea. These unmanned vehicles can help us to work is difficult task and approach. In the previous research of unmanned vehicle in our lab, we used 1/10 scale radio control vehicle and composed the unmanned vehicle system using ultrasonic sensors, CCD camera and kinds of sensor for vehicle's motion control. We designed lane detecting algorithm using vision system and obstacle detecting and avoidance algorithm using ultrasonic sensor and infrared ray sensor. As the system is increased, it is hard to compose the system on the 1/10 scale RC car. So we have to choose a new vehicle is bigger than 1/10 scale RC car but it is smaller than real size vehicle. ATV(all terrain vehicle) and real size vehicle have similar structure and its size is smaller. In this research, we make unmanned vehicle using ATV and explain control theory of each component

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2000년도 하계학술대회 논문집 D
• /
• pp.2784-2786
• /
• 2000

Mobile robots include control modules for autonomous obstacle avoidance and navigation. They are range modules to detect and avoid obstacles. motor control modules to operate two wheels. and encoder modules for localization. There is needed an appropriate controller for each modules. In this paper. a control system. including 18 channels for Sonar sensors. 4 channels for PWM modules. and 4 channels for encoder modules. is proposed using TMS320C32 DSP adopted with CAN. The board communicates with other modules by CAN. so that mobile robots can perform several tasks in real time. So we can realize on autonomous mobile robot with basic functions such as obstacle avoidance by using the developed controller. Especially. this controller has 100 msec scan time for 16 sonar sensors and can detect closer objects comparing with standard sonar sensors.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 1993년도 한국자동제어학술회의논문집(국내학술편); Seoul National University, Seoul; 20-22 Oct. 1993
• /
• pp.94-99
• /
• 1993

In this paper, the method for navigation and obstacle avoidance of an autonomous mobile robot is proposed. It is based on the fuzzy inference system which enables to deal with imprecise and uncertain information, and on the neural network which enables to learn input and output pattern data obtained from ultrasonic sensors. For autonomous navigation, the wall-following navigation utilizing input and output data by an expert's control action is constructed. An approach by the neural network is developed for the obstacle avoidance because of the redundant input data. For an autonomous navigation, the fuzzy control and the control of the neural network are integrated and its feasibility is demonstrated by means of experiment.

• 제어로봇시스템학회논문지
• /
• 제16권4호
• /
• pp.361-367
• /
• 2010

This paper reports the development of a mobile robot for patrol using a single laser range finder. A Laser range finder is useful for outdoor environment regardless of illumination change or various weather conditions. In this paper we combined the motion control of the mobile robot and the algorithm for detecting the outdoor environment. For obstacle avoidance, we adopted the Vector Field Histogram algorithm. A laser range finder is mounted on the mobile robot and looking down the road with a small tilt angle. We propose an algorithm for detecting the surface of the road. The outdoor patrol robot platform is equipped with a DGPS system, a gyro-compass sensor, and a laser range finder. The proposed obstacle avoidance and road detection algorithms were experimentally tested in success.

• 제어로봇시스템학회논문지
• /
• 제15권1호
• /
• pp.105-110
• /
• 2009

In this paper, we proposed a navigation algorithm of the mobile robot for obstacle avoidance using a circular path planning method. The proposed method makes circular paths in order to avoid obstacles in the front side of the mobile robot. An optimal path for approaching to the target is selected and the linear and angular speeds for stable moving of the mobile robot are controlled. Obstacles are detected by image processing which reduce image data obtained from a web camera. Performance of the proposed algorithm is shown by experiments with application to the Pioneer-2DX mobile robot.

• 대한전기학회논문지:시스템및제어부문D
• /
• 제52권8호
• /
• pp.471-481
• /
• 2003

The acts of biological immune system are similar to the navigation for autonomous mobile robots under dynamically changing environments. In recent years, many researchers have studied navigation algorithms using artificial immune networks. Conventional artificial immune algorithms consist of an obstacle-avoidance behavior and a goal-reaching behavior. To select a proper action, the navigation algorithm should combine the obstacle-avoidance behavior with the goal-reaching behavior. In this paper, the neural network is employed to combine the behaviors. The neural network is trained with the surrounding information. the outputs of the neural network are proper combinational weights of the behaviors in real-time. Also, a velocity control algorithm is constructed with the artificial immune network. Through a simulation study and experimental results for a autonomous mobile robot, we have shown the validity of the proposed navigation algorithm.

• 한국컴퓨터정보학회:학술대회논문집
• /
• 한국컴퓨터정보학회 2019년도 제59차 동계학술대회논문집 27권1호
• /
• pp.59-60
• /
• 2019

WCS에서 AGV의 스케줄링과 동적, 정적 장애물 인식 및 충돌 회피문제는 오래전부터 다뤄져 온 중요한 문제이다. 본 논문에서는 위의 문제를 해결하기 위해 Lidar 센서를 중심으로 다양한 데이터를 기반으로 한 강화학습 시스템을 제안한다. 제안하는 시스템은 기본의 명시적인 알고리즘에 비해 다양하고 유동적인 환경에서 경로 계획과 동적 정적 장애물을 인식하고 안정적으로 회피하는 것을 확인하였으며 산업 현장에 도입 가능성을 확인하였다. 또한 강화학습의 적용 범위, 적용 방안과 한계에 대해서 시사한다.

• 전기학회논문지
• /
• 제57권7호
• /
• pp.1260-1272
• /
• 2008

This paper proposes object detection algorithm using laser scanner and vision system for the path planning of autonomous mobile agents. As the scanner-based method can observe the obstacles in only two dimensions, it is hard to detect the shape and the number of obstacles. On the other hand, vision-based method is sensitive to the environment and has its difficulty in the accurate distance measurement. Thus, we combine these two methods based on K-means algorithm such that the obstacle avoidance and optimal path planning of autonomous mobile agents can be achieved.

• 대한전기학회논문지:시스템및제어부문D
• /
• 제51권5호
• /
• pp.182-189
• /
• 2002

This paper presents a framework of hybrid dynamic control systems for the motion control of wheeled mobile robot systems with nonholonomic constraints. The hybrid control system has the 3-layered hierarchical structure: digital automata for the higher process, mobile robot system for the lower process, and the interface as the interaction process between the continuous dynamics and the discrete dynamics. In the hybrid control architecture of mobile robot, the continuous dynamics of mobile robots are modeled by the switched systems. The abstract model and digital automata for the motion control are developed. In high level, the discrete states are defined by using the sensor-based search windows and the reference motions of a mobile robot in low level are specified in the abstracted motions. The mobile robots can perform both the motion planning and autonomous maneuvering with obstacle avoidance in indoor navigation problem. Simulation and experimental results show that hybrid system approach is an effective method for the autonomous maneuvering in indoor environments