• Journal of Institute of Control, Robotics and Systems
• /
• v.7 no.1
• /
• pp.1187-1195
• /
• 2001

This paper presents a sweeping path planning algorithm for an autonomous smearing robot. An automatic planner generates a sweeping path pattern by proposed five basic procedures. This algorithm rocog-nizes obstacle on the architectural CAD draft and generates subgoals as tracking points which executes the area filling task based on heuristic approach. A sweeping path is planned by sequentially connecting the track-ing points in such a way that(1) the connected line segments should not be crossed, (2) the total tracking points should be as short as possible, and (3) the tracking line should not pass through the obstacle, Feasibility of the developed techniques has been demonstrated on a real architectural CAD draft.

• International Journal of Control, Automation, and Systems
• /
• v.1 no.1
• /
• pp.35-42
• /
• 2003

This paper proposes a simple, robust, nonlinear controller based on Lyapunov stability for tracking the reference welding path and velocity of a two-wheeled welding mobile robot (WMR). The system has three degrees of freedom including two wheels and one torch slider. Torch slider motion is used for faster tracking because the welding speed is very slow. Control law is obtained from the Lyapunov control function to ensure the asymptotical stability of the system. The controller has three free parameters for adjusting the performance of the controlled system. A simple way of measuring the errors using two potentiometers is introduced. The effectiveness of the proposed controller is shown through simulation results.

• Journal of Institute of Control, Robotics and Systems
• /
• v.5 no.1
• /
• pp.95-104
• /
• 1999

In this paper we propose a fast and precise control algorithm for a mobile robot, which aims at the self-tuning control applying two multi-layered neural networks to the structure of computed torque method. Through this algorithm, the nonlinear terms of external disturbance caused by variable task environments and dynamic model errors are estimated and compensated in real time by a long term neural network which has long learning period to extract the non-linearity globally. A short term neural network which has short teaming period is also used for determining optimal gains of PID compensator in order to come over the high frequency disturbance which is not known a priori, as well as to maintain the stability. To justify the global effectiveness of this algorithm where each of the long term and short term neural networks has its own functions, simulations are peformed. This algorithm can also be utilized to come over the serious shortcoming of neural networks, i.e., inefficiency in real time.

• Journal of Institute of Control, Robotics and Systems
• /
• v.10 no.5
• /
• pp.464-474
• /
• 2004

This paper proposes a middleware structure for the module-based personal robot, which can run on heterogeneous network interfaces and provides users easy interface-method regardless of underlying heterogeneous interfaces and convenient exchange of modules. The proposed middleware is divided into three layers of a streaming layer (SL), a network adaptation layer (NAL) and a network interface layer (NIL). The streaming layer manages application transactions using middleware services and provides user a uniform interfaces to the proposed middleware. The network adaptation layer manages a message-routing and provides naming service and it is a core of the proposed middleware. And the network interfaces layer manages dependent parts of heterogeneous network interfaces such as IEEE1394, USB, Ethernet, and CAN (Control Area Network). This paper implements the proposed middleware structure, where 3 types of interfaces of IEEE 1394, USB and Ethernet are used, and measures response times among those interfaces.

• Journal of Institute of Control, Robotics and Systems
• /
• v.9 no.11
• /
• pp.937-942
• /
• 2003

We present a self-localization method for mobile robots using vertical line features of indoor environment. When a 2D map including feature points and color information is given, a mobile robot moves to the destination, and acquires images from the surroundings having vertical line edges by one camera. From the image, vertical line edges are detected, and pattern vectors meaning averaged color values of the left and right regions of the each line are computed by using the properties of the line and a region growing method. The pattern vectors are matched with the feature points of the map by comparing the color information and the geometrical relationship. From the perspective transformation and rigid transformation of the corresponded points, nonlinear equations are derived. Localization is carried out from solving the equations by using Newton's method. Experimental results show that the proposed method using mono view is simple and applicable to indoor environment.

• Journal of Institute of Control, Robotics and Systems
• /
• v.9 no.11
• /
• pp.943-951
• /
• 2003

A strategy for fault-tolerant gaits of autonomous legged robots is proposed. A legged robot is considered to be fault tolerant with respect to a given failure if it is guaranteed to be capable of walking maintaining its static stability after the occurrence of the failure. The failure concerned in this paper is a locked joint failure for which a joint in a leg cannot move and is locked in place. If a failed joint is locked, the workspace of the resulting leg is constrained, but legged robots have fault tolerance capability to continue static walking. An algorithm for generating fault-tolerant gaits is described and, especially, periodic gaits are presented for forward walking of a hexapod robot with a locked joint failure. The leg sequence and the formula of the stride length are analytically driven based on gait study and robot kinematics. The transition procedure from a normal gait to the proposed fault-tolerant gait is shown to demonstrate the applicability of the proposed scheme.

• Journal of Institute of Control, Robotics and Systems
• /
• v.5 no.4
• /
• pp.437-445
• /
• 1999

Most autonomous mobile robots view only things in front of then, and as a result, they may collide with objects moving from the side or behind. To overcome this problem, an active omni-directional range sensor system has been built that can obtain an omni-directional depth map through the use of a laser conic plane and a conic mirror. In the navigation of the mobile robot, the proposed sensor system produces a laser conic plane by rotating the laser point source at high speed: this creates a two-dimensional depth map, in real time, once an image is captured. The results obtained from experiment show that the proposed sensor system is very efficient, and can be utilized for navigation of mobile robot in an unknown environment.

• Journal of Institute of Control, Robotics and Systems
• /
• v.7 no.1
• /
• pp.1171-1177
• /
• 2001

This paper provides a guideline for specifying the operational compliance characteristics considering the location of compliance center and the grasp points in assembly tasks using robot hands. Through various assembly tasks, we analyze the conditions of the achievable operational stiffness matrix with respect to the location of compliance center and the grasp points. Also, we show that some of coupling stiffness elements in the operational space cannot be planned arbitrarily. As a result it is concluded that the location of compliance center on the grasped object and the grasp points play important roles for successful assembly tasks and also the operational stiffness matrix should be carefully specified by considering those conditions.

• 제어로봇시스템학회:학술대회논문집
• /
• 2003.10a
• /
• pp.2057-2062
• /
• 2003

Chained form mobile robots have been studied from the viewpoint of the control and analysis of nonholonomic mechanical systems in literature. However, researches for the detailed closed form kinematic modeling are rarely progressed. Nothing that a chained form mobile robot can be considered as a parallel system including several chains and wheels, the transfer method using augmented generalized coordinates is applied to obtain inverse and forward kinematic models of chained form mobile robots. Various numerical simulations are conducted to verify the effectiveness of the suggested kinematic model.

• Journal of Institute of Control, Robotics and Systems
• /
• v.21 no.6
• /
• pp.565-570
• /
• 2015

Supervised machine learning has become popular in discovering context descriptions from sensor data. However, collecting a large amount of labeled training data in order to guarantee good performance requires a great deal of expense and time. For this reason, semi-supervised learning has recently been developed due to its superior performance despite using only a small number of labeled data. In the existing semi-supervised learning algorithms, unlabeled data are used to build a graph Laplacian in order to represent an intrinsic data geometry. In this paper, we represent the unlabeled data as the spatial-temporal dataset by considering smoothly moving objects over time and space. The developed algorithm is evaluated for position estimation of a smartphone-based robot. In comparison with other state-of-art semi-supervised learning, our algorithm performs more accurate location estimates.