• Journal of Institute of Control, Robotics and Systems
• /
• v.16 no.11
• /
• pp.1060-1067
• /
• 2010

In this paper, we present a new type of spherical robot having two arms. This robot, called KisBot, mechanically consists of three parts, a wheel-shaped body and two rotating semi-spheres. In side of each semi-sphere, there exists an arm which is designed based on slider-crank mechanism for space efficiency. KisBot has hybrid types of driving mode: rolling and wheeling. In the rolling mode, the robot folds its arms through inside of itself and uses them as pendulum, then the robot works like a pendulum-driven robot. In the wheeling mode, two arms are extended from inside of the robot and are contacted to the ground, then the robot works like a one-wheel car. The Robot arms can be used as a brake during rolling mode and add friction to the robot for climbing a slope during wheeling mode. We developed a remote controlled type robot for experiment. It contains two DC motors which are located in the center of each semi-sphere for main propulsion, two RC motors for each arm operation, speed controllers for each semi-sphere, batteries for main power source, and other mechanical components. Experiments for the rolling and wheeling mode verify the hybrid driving ability and efficiency of the our proposed spherical robot.

• 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.

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 2010.11a
• /
• pp.43-44
• /
• 2010

• Journal of the Korean Society for Precision Engineering
• /
• v.27 no.9
• /
• pp.34-42
• /
• 2010

Agricultural automation has become more and more important by environmental change. The automation demands the highest technology due to the ever changing various conditions in agriculture system. In the paper, semi-autonomous pesticide spray robot system has been developed for rose farming in the glass house. The robot is in autonomous mode during pesticide spraying process driven on pipe rail. The robot is manually driven while moving from a rail to the next rail. The drive platform and autonomous operation control system are developed based on IT fusion technology. The pesticide spray system is also developed with nozzles and booms for precision mist spray system. Experimental data of nozzle test is also included.

• 제어로봇시스템학회:학술대회논문집
• /
• 2005.06a
• /
• pp.963-968
• /
• 2005

For worm robots applied to pipe inspection and colonoscopy, earthworm-like robots that have a locomotion pattern in backward wave or green caterpillar-like robots that have a locomotion pattern in forward wave have been studied widely. Note however that a method using a single and fixed locomotion pattern is not desirable in the sense of mobility cost, if there are various changes in pipe diameter. In this paper, locomotion patterns are considered for a semi-looper-like robot, which adopts a locomotion pattern of green caterpillars as the basic motion and sometimes can realize a locomotion pattern of looper, whose motion approximately consists of two rhythms or relatively low rhythm.

• Proceedings of the Korea Institute of Convergence Signal Processing
• /
• 2000.08a
• /
• pp.113-116
• /
• 2000

This paper analyzes the singularity of an anthropomorphic robot associated with joint and operational stiffness generation from muscle stiffness. The singularity analysis is made simply based on the signs of the actual and the desired coupling joint stiffness. First, the relationships of the muscle stiffness and the actual joint stiffness, and the operational stiffness and the desired joint stiffness are examined. Second, according to the sign restriction on the actual coupling joint stiffness, the operational space is divided into the semi-singular(SS), the regular(R), and the semi-regular(SR) regions. Third, from the sign comparison of tile actual and the desired coupling joint stiffness, the sufficient condition for the semi-singularity in operational stiffness generation is derived. The limitation on the allowable operational stiffness when a task point belongs to SS, R, and SR regions is also discussed. Simulation results are given.

• Proceedings of the KIEE Conference
• /
• 2007.04a
• /
• pp.349-351
• /
• 2007

A concept of the semi-autonomous tele-weeding-system which performs weeding tasks through co-operation of human and machine intelligence is proposed. The tele-weeding system consists of weeding robot, communication networks and operating server. The images of plants taken by the weeding robot are transferred through the communication networks to the human operator. Positions of the weeds are indicated at the operating host by the operator and transferred back to the weeding robot. Such position informations are converted to the world space and the weeding is done based on the robot intelligence. Feasibility of such concept has been tested through development of a laboratory model of the system.

• 제어로봇시스템학회:학술대회논문집
• /
• 1988.10a
• /
• pp.528-533
• /
• 1988

Recently the needs for industrial robot system of high speed continuous path motion such as sealing application have been increasing. To apply to this kinds of work, dynamic analysis for Hyundai 8601 robot has been carried out by experiment. For the good design of high performance robot manipulator, accurate analysis of dynamic characteristics is important especially for current semi-closed loop control type industrial robots.

• The Journal of Korea Robotics Society
• /
• v.5 no.2
• /
• pp.127-134
• /
• 2010

In this paper, a hybrid semi-3D path planning algorithm combining Virtual Tangential Vector(VTV) and fuzzy control is proposed. 3D dynamic environmental factors are reflected to the 2D path planning model, VTV. As a result, the robot can control direction from 2D path planning algorithm VTV and speed as well depending on the fuzzy inputs such as the distance between the robot and obstacle, roughness and slope. Performances and feasibilities of the suggested method are demonstrated by using Matlab simulations. Simulation results show that fuzzy rules and obstacle avoidance methods are working properly toward virtual 3D environments. The proposed hybrid semi-3D path planning is expected to be well applicable to a real life environment, considering its simplicity and realistic nature of the dynamic factors included.

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 2009.10a
• /
• pp.333-334
• /
• 2009