• Korean Journal of Artificial Intelligence
• /
• v.11 no.4
• /
• pp.15-20
• /
• 2023

Machine learning is comprised of supervised learning, unsupervised learning and reinforcement learning as the type of data and processing mechanism. In this paper, as input and output are unclear and it is difficult to apply the concrete modeling mathematically, reinforcement learning method are applied for crawling robot in this paper. Especially, Q-Learning is the most effective learning technique in model free reinforcement learning. This paper presents a method to implement a crawling robot that is operated by finding the most optimal crawling method through trial and error in a dynamic environment using a Q-learning algorithm. The goal is to perform reinforcement learning to find the optimal two motor angle for the best performance, and finally to maintain the most mature and stable motion about EV3 Crawling robot. In this paper, for the production of the crawling robot, it was produced using Lego Mindstorms with two motors, an ultrasonic sensor, a brick and switches, and EV3 Classroom SW are used for this implementation. By repeating 3 times learning, total 60 data are acquired, and two motor angles vs. crawling distance graph are plotted for the more understanding. Applying the Q-learning reinforcement learning algorithm, it was confirmed that the crawling robot found the optimal motor angle and operated with trained learning, and learn to know the direction for the future research.

• Proceedings of the KIEE Conference
• /
• 1992.07a
• /
• pp.381-385
• /
• 1992

In this paper, dynamic modeling and adaptive control problems for a space robot system are discussed. The space robot consist of a robot manipulator mounted on a free-floating base where no attitude control is applied. Using an extended robot model, the entire space robot can be viewed as an under-actuated robot system. Based on nonlinear control theory, the extended space robot model can then be decomposed into two subsystems: one is input-output exactly linearizable, and the other is unlinearizable and represents an internal dynamics. With this decomposition, a normal form-augmentation approach and an augmented state-feedback control are proposed to facilitate the design of adaptive control for the space robot system against parameter uncertainty, unknown dynamics and unmodeled payload in space applications. We demonstrate that under certain conditions, the entire space robot can be represented as a full-actuated robot system to avoid the inclusion of internal dynamics. Based on the dynamic model, we propose an adaptive control scheme using Cartesian space representation and demonstrate its validity and design procedure by a simulation study.

• Transactions of the Korean Society of Mechanical Engineers A
• /
• v.39 no.3
• /
• pp.275-282
• /
• 2015

Recently, Vecna BEAR type robot to save injured individuals from inaccessible areas has been developed to minimize the loss of life. Because this robot is driven on rough terrain, there is a risk of rollover and vibration, which could impact the injured. In order to guarantee its stability, an algorithm is required that can estimate the speed limits for various environments in real time. Therefore, a dynamic model for real-time analysis is needed for this algorithm. Because the tracks used as the driving component of Vecna BEAR type robot consist of many parts, it is impossible to analyze the multibody tracks in real time. Thus, a lumped track model that satisfies the requirements of a short computation time and adequate accuracy is required. This study performed lumped track modeling, and the traction force was verified using RecurDyn, which is a dynamic commercial program.

• Journal of Institute of Control, Robotics and Systems
• /
• v.9 no.11
• /
• pp.906-916
• /
• 2003

A multi-robot control algorithm using Petri-Net is proposed for 5vs5 robot soccer. The dynamic environment of robot soccer is modeled by defining the place and transition of each robot and converting it into Petri-Net diagram. Once all the places and transitions of robots are represented by the Petri-Net model, their actions can be chosen according to the roles of robots and position of the ball in soccer game, e.g., offensive, defensive and goalie robot. The proposed modeling method is implemented for soccer robot system. The efficiency and applicability of the proposed multiple-robot control algorithm using Petri-Net are demonstrated through 5vs5 Middle League SimuroSot soccer game.

• 제어로봇시스템학회:학술대회논문집
• /
• 2000.10a
• /
• pp.330-330
• /
• 2000

In this paper, as an entertainment robot the implementation of boxing robot system is presented for mechatronics education. In order for students to learn robot as a mechatronics system, boxing robot is a good model. The boxing robot consists of three parts: two link arms for punching, controller for actuating wheeled mobile robot, infrared rays sensors for the detection of he other robot and ring. The strategic algorithm for playing boxing is presented as wel as simple game rules.

• Journal of Institute of Control, Robotics and Systems
• /
• v.20 no.6
• /
• pp.599-605
• /
• 2014

This paper presents the interactive behavior modeling method based on POMDP (Partially Observable Markov Decision Process) for HRI (Human-Robot Interaction). HRI seems similar to conversational interaction in point of interaction between human and a robot. The POMDP has been popularly used in conversational interaction system. The POMDP can efficiently handle uncertainty of observable variables in conversational interaction system. In this paper, the input variables of the proposed conversational HRI system in POMDP are the input information of sensors and the log of used service. The output variables of system are the name of robot behaviors. The robot behavior presents the motion occurred from LED, LCD, Motor, sound. The suggested conversational POMDP-based HRI system was applied to an emotional robot KIBOT. In the result of human-KIBOT interaction, this system shows the flexible robot behavior in real world.

• 제어로봇시스템학회:학술대회논문집
• /
• 2001.10a
• /
• pp.161.4-161
• /
• 2001

This paper presents adaptive control of robot manipulator using neuro-fuzzy controller Fuzzy logic is control incorrect system without correct mathematical modeling. And, neural network has learning ability, error interpolation ability of information distributed data processing, robustness for distortion and adaptive ability. To reduce the number of fuzzy rules of the FLS(fuzzy logic system), we consider the properties of robot dynamic. In fuzzy logic, speciality and optimization of rule-base creation using learning ability of neural network. This paper presents control of robot manipulator using neuro-fuzzy controller. In proposed controller, fuzzy input is trajectory following error and trajectory following error differential ...

• Proceedings of the Korean Society of Machine Tool Engineers Conference
• /
• 1999.10a
• /
• pp.565-570
• /
• 1999

In this paper, we developed a windows 95 version Off-Line Programming system which can simulate a Robot model in 3D Graphics space. 4axes SCARA Robot (especially FARA SM5) was adopted as an objective model. Forward kinematics, inverse kinematics and robot dynamics modeling were included in the developed program. The interface between users and the OLP system in the Windows 95's GUI environment was also studied. The developing language is Microsoft Visual C++. Graphic libraries, OpenGL, by silicon Graphics, Inc. were utilized for 3D Graphics.

• Proceedings of the KIEE Conference
• /
• 2000.11d
• /
• pp.765-768
• /
• 2000

Linearization of the biped dynamic equations and design of linear controller for the linearized equations are studied in this paper. The biped robot with inverted pendulum type trunk, used to stabilize the dynamic balancing of the biped robot during dynamic walking period, is modelled with 14 DOF and simulated. Despite of well defined linear control theories so far, the linear control methods was limited to the applications for a walking robot, because they have been inherently strong nonlinear properties, such as a modeling parameter uncertainties, external forces as noise, inertial and Coriolis terms by three dimensional modeling and so on. To linearize the nonlinear equations of motion of biped robot on MIMO and time varying linear equations of motion, 1st order Taylor series is used to formulate the linear equation. And a 2nd order numerical perturbation method Is used to approximate partial differential equations. Using the linearized equations of motion, a linear controller is designed by pole placement method with feed forward compensation. Using the obtained linearized equations and linear controller, the continuous walking simulation is performed.

• Transactions of the Korean Society of Mechanical Engineers A
• /
• v.30 no.3 s.246
• /
• pp.287-294
• /
• 2006

In recent years, capsule endoscope is highlighted for the patient's convenience and the possibility of the application in the small intestine. However, the capsule endoscope has some limitations to get the image of the digestive organ because its movement only depends on the peristaltic motion. In order to solve these problems, locomotion of capsule endoscope is necessary. In this paper, we analyze the locomotive mechanism of earthworm-like robot proposed as locomotive device of capsule endoscope and derive the condition which can Judge the possibility of its mobility using theoretical analysis. Based on a biomechanical modeling and simulation, the critical stroke, that is minimum stroke of the earthworm-like robot to perform motion inside small intestine, is obtained. Also, this derived critical stroke can be validated by the moving test of fabricated earthworm-like robot. Consequently, it is expected that this study can supply useful information to design of earthworm-like robot for mobility of capsule endoscope.