• 한국공작기계학회:학술대회논문집
• /
• 한국공작기계학회 1997년도 추계학술대회 논문집
• /
• pp.82-87
• /
• 1997

This paper presents a new approach to the design of cruise control system of a mobile robot with two drive wheel. The proposed control scheme uses a Gaussian function as a unit function in the fuzzy-neural network, and back propagation algorithm to train the fuzzy-neural network controller in the framework of the specialized learning architecture. It is proposed a learning controller consisting of two neural network-fuzzy based on independent reasoning and a connection net with fixed weights to simply the neural networks-fuzzy. The performance of the proposed controller is shown by performing the computer simulation for trajectory tracking of the speed and azimuth of a mobile robot driven by two independent wheels.

• 한국공작기계학회:학술대회논문집
• /
• 한국공작기계학회 2001년도 춘계학술대회 논문집(한국공작기계학회)
• /
• pp.250-254
• /
• 2001

This paper presents a new approach to the design of cruise control system of a mobile robot with two drive wheel. The proposed control scheme uses a Gaussian function as a unit function in the fuzzy-neural network, and back propagation algorithm to train the fuzzy-neural network controller in the framework of the specialized learning architecture. It is proposed a learning controller consisting of two neural network-fuzzy based on independent reasoning and a connection net with fixed weights to simply the neural networks-fuzzy. The performance of the proposed controller is shown by performing the computer simulation for trajectory tracking of the speed and azimuth of a mobile robot driven by two independent wheels.

• 한국공작기계학회:학술대회논문집
• /
• 한국공작기계학회 2000년도 춘계학술대회논문집 - 한국공작기계학회
• /
• pp.199-203
• /
• 2000

This paper presents a new approach to the design of cruise control system of a mobile robot with two drive wheel. The proposed control scheme uses a Gaussian function as a unit function in the fuzzy-neural network, and back propagation algorithm to train the fuzzy-neural network controller in the framework of the specialized learning architecture. It is proposed a learning controller consisting of two neural network-fuzzy based on independent reasoning and a connection net with fixed weights to simply the neural networks-fuzzy. The performance of the proposed controller is shown by performing the computer simulation for trajectory tracking of the speed and azimuth of a mobile robot driven by two independent wheels.

• 한국공작기계학회:학술대회논문집
• /
• 한국공작기계학회 2000년도 추계학술대회논문집 - 한국공작기계학회
• /
• pp.130-134
• /
• 2000

This paper presents a new approach to the design of cruise control system of a mobile robot with two drive wheel. The proposed control scheme uses a Gaussian function as a unit function in the fuzzy-neural network, and back propagation algorithm to train the fuzzy-neural network controller in the framework of the specialized learning architecture. It is proposed a learning controller consisting of two neural network-fuzzy based on independent reasoning and a connection net with fixed weights to simply the neural networks-fuzzy. The performance of the proposed controller is shown by performing the computer simulation for trajectory tracking of the speed and azimuth of a mobile robot driven by two independent wheels.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2001년도 ICCAS
• /
• pp.69.3-69
• /
• 2001

This paper presents a new approach to the design of cruise control system of a mobile robot with two drive wheel. The proposed control scheme uses a Gaussian function as a unit function in the fuzzy-neural network, and back propagation algorithm to train the fuzzy-neural network controller in the framework of the specialized learning architecture. It is proposed a learning controller consisting of two neural network-fuzzy based on independent reasoning and a connection net with fixed weights to simply the neural networks-fuzzy. The performance of the proposed controller is shown by performing the computer simulation for trajectory tracking of the speed and azimuth of a mobile robot driven by two independent wheels.

• 제어로봇시스템학회논문지
• /
• 제20권9호
• /
• pp.895-899
• /
• 2014

This paper presents the balancing control of a unicycle robot using air power. Since the robot has one wheel to move forward and backward, the balancing control is quite challenging. To control the balancing angle, the accurate angle estimation by a tilt and a gyro sensor is required a priori. A complementary filter is implemented to eliminate the defects of two sensors and to fuse together to estimate an accurate balancing angle. The optimal design of air ducts is found empirically. Experimental studies of the balancing control of a unicycle robot confirm that the robot is well regulated without falling down.

• 한국컴퓨터정보학회논문지
• /
• 제16권7호
• /
• pp.157-163
• /
• 2011

본 논문에서는 ARS(Attitude Refrence System)를 이용하여 모바일 역진자 로봇의 수평유지와 주행을 위한 자세 제어를 연구하였다. 현재 미국 및 여러 나라에서는 모바일 역진자 로봇에 대한 많은 연구가 진행되고 있으며 이를 이용한 세그 웨이 등을 개발하고 있다. 이러한 2자유도를 이용한 모바일 역진자 로봇은 다양한 모드로 움직일 수 있다. 모바일 역진자 로봇이 2바퀴로 수직 자세를 취하면 시스템이 안정을 취하기 위하여 항상 앞, 또는 뒤로 넘어지려는 성질을 가진다. 현재 자이로센서와 가속도센서를 혼합하는 알고리즘은 칼만필터가 일반적으로 이용되고있으며 많은 연구가 진행되고 있다. 본 연구에서 ARS는 2축의 자이로 각(roll, pitch)과 3축의 가속도계 값(x, y, z)값으로 자세를 계산하도록 하였다. 본 논문은 자율주행시스템인 2발 로봇 시스템으로 간단하지만 원하는 성능을 발휘할 수 있는 ARS와 PID 알고리즘을 이용한 자세 제어를 실현하였다.

• 로봇학회논문지
• /
• 제8권4호
• /
• pp.229-237
• /
• 2013

In this paper, we report a self-balancing robot wheelchair which has the capability of keeping upright posture regardless of the terrain inclination in terms of the three dimensional balancing motion. It has the mobility of five degrees of freedom, where pitching, yawing, and forward motions are generated by the two-wheeled inverted pendulum mechanism and the rolling and vertical motions are implemented by the movement of the tilting mechanism. Several design considerations are suggested for the sliding type vehicle body, wheel actuator module, tilting actuator module, power and control system, and the riding module.

• 대한전기학회논문지:시스템및제어부문D
• /
• 제55권2호
• /
• pp.65-67
• /
• 2006

To make the autonomous mobile robot move in the unknown space, we have to know the information of current location of the robot. So far, the location information that was obtained using Encoder always includes Dead Reckoning Error, which is accumulated continuously and gets bigger as the distance of movement increases. In this paper, we analyse the effect of the size of the two wheels of the mobile robot and the wheel track of them among the factors of Dead Reckoning Error. And after this, we compensate this Dead Reckoning Error by Kalman filter using Gyro Sensors. To accomplish this, we develop the controller to analyse the error components of Gyro Sensor and to minimize the error values. We employ the numerical approach to analyse the error components by linearizing them because each error component is nonlinear. And we compare the improved result through simulation.

• 제어로봇시스템학회논문지
• /
• 제18권2호
• /
• pp.118-125
• /
• 2012

Based on recent advances in technology, many robots are developed and they are used in a hazardous environment such as military operation, fire, and building collapse and so on. Among them, reconnaissance robot should be able to perform various missions which people can not do. So it needs the capability of moving with hiding its position on rough terrain, overcoming obstacles, and guaranteeing its efficiency of reconnaissance. For this reason there are in progress of researching biomimetic robots. Therefore in this paper we proposed robot mechanism, two modules based on the screw and wheel mechanism which mimic snake, and the spiral climbing method was considered for overcoming the situation when moving on the trees.