• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.13 no.6
• /
• pp.470-476
• /
• 2020

In this paper, we present the design of modular replaceable AI server for image deep learning that separates the server from the Edge Device so as to drive the AI block and the method of data transmission and reception. The modular replaceable AI server for image deep learning can reduce the dependency between social robots and edge devices where the robot's platform will be operated to improve drive stability. When a user requests a function from an AI server for interaction with a social robot, modular functions can be used to return only the results. Modular functions in AI servers can be easily maintained and changed by each module by the server manager. Compared to existing server systems, modular replaceable AI servers produce more efficient performance in terms of server maintenance and scale differences in the programs performed. Through this, more diverse image deep learning can be included in robot scenarios that allow human-robot interaction, and more efficient performance can be achieved when applied to AI servers for image deep learning in addition to robot platforms.

• 제어로봇시스템학회:학술대회논문집
• /
• 1996.10a
• /
• pp.99-102
• /
• 1996

A novel iterative learning control scheme comprising a unique feedforward learning controller and a disturbance observer is proposed. Disturbance observer compensates disturbance due to parameter variations, mechanical nonlinearities, unmodeled dynamics and external disturbances. The convergence and robustness of the proposed controller is proved by the method based on Lyapunov stability theorem. The results of numerical simulation are shown to verify the effectiveness of the proposed control scheme.

• 제어로봇시스템학회:학술대회논문집
• /
• 1996.10a
• /
• pp.133-136
• /
• 1996

The nozzle dam task is essentially needed to maintain and repair nuclear power plants. For this task, an 8-dof redundant robot is studied with a local path-planning method[l] which is effective to find the optimal joint path in the constrained environment. In this paper, the method[l] is improved practically with the weight matrix and efficient algorithm to find working set. The effectiveness of the proposed method is demonstrated by simulation and animation.

• 제어로봇시스템학회:학술대회논문집
• /
• 1997.10a
• /
• pp.720-723
• /
• 1997

This paper presents a cooperative control method for multiple robots. This method is based on local sensors. The proposed method integrates all information obtained by local perception through a set of sensors and generates commands without logical conflicts in designing control logic. To control multiple robots effectively, a global control strategy is proposed. These methods are constructed by using AND/OR logic and transition firing sequences in Petri nets. To evaluate these methods, the object-searching task is introduced. This task is to search an object like a box by two robots and consists of two sub-tasks, i.e., a wall tracking task and a robot tracking task. Simulation results for the object-searching task and the wall tracking task are presented to show the effectiveness of the method.

• 제어로봇시스템학회:학술대회논문집
• /
• 1997.10a
• /
• pp.1704-1707
• /
• 1997

In this work, position and vibratiion control of a two-link manipulator with one flexible link, which an unkoun but bounded payload mass and two pair of artificial muscle-type penumatic actuators, are investgated. A flexible link robot has advantages over a figid link robot in the sense that it is much safer when it cones into contact with its environment, including humans. Furthermore, for the sake of safety, it would be more desirabel if an actuator could deliver required force while maintaining proper compliance. An artificial muscle-type penumatic actuator is adequate for such cases. In this study, a controller based on singular perturbation method, adaptive and sliding mode contro, and .mu.-synthesis is developed. The effectiveness of the proposed control scheme is confirmed through simulations and experiments.

• 제어로봇시스템학회:학술대회논문집
• /
• 1997.10a
• /
• pp.1714-1717
• /
• 1997

A human operator is able to perform some tasks smoothly with force feedvack for the teleoperation or a virtual device in a the virtual environments. This paper describes a virtual force generation method with which operator can feel the interactive force between virtula robot and artificial environments. A virtual force generation algortihm is applied to generate the contact force at the arbitrary point of virtual robot, and the virtual force is displayed to the human operator via a tendon master arm consisted with 3 motors. Some experiments has beencarried out to verify the effectiveness of the force generation algorithm and usefulness of the developed backdrivable master arm.

• 제어로봇시스템학회:학술대회논문집
• /
• 1997.10a
• /
• pp.1738-1741
• /
• 1997

This paper addresses the issue fo target classification and localization with a SONAR for mobiler robot indoor navigation. In particular, multiple refetions of SONAR sound are used actively and interntionally. As for the SONAR sensor, the multiple reflection has been generally considered as one of the noisy phenomena, which is inevitable in the indoor environments. However, these multiple reflections can be a clue for classifying and localizing targets in the indoor environment if those can be controlled and used well. This paper develops a new SONAR sensor module with a reflection plane which can actively create the multiple refection. This paper also intends to suggest a new target classification emthod which uses the multiple refectiions. We approximate the world as being two dimensional and assume that the targets consisting of the indoor environment are pland, corner, and edge. Multiple reflection paths of an acoustic bean by a SONAR are analyzed, by simulations and the patterns of the TOPs (Time Of Flight) and angles of multiple reflections from each target are also analyzed. In addition, a new algorithm for target classification and localization is proposed.

• 제어로봇시스템학회:학술대회논문집
• /
• 1997.10a
• /
• pp.1820-1823
• /
• 1997

For the Cartesian space position controlled robot, it is required to have the accurate mapping from the Cartesian space to the joint space in order to command the desired joint trajectories correctly. since the actual mapping from Cartesian space to joint space is obtained at the joint coordinate not at the actuator coordinate, uncertainty in Jacobian can be present. In this paper, two feasible neural network schemes are proposed to compensate for the kinematic Jacobian uncertainties. Uncertainties in Jacobian can be compensated by identifying either actuator Jacobian off-line or the inverse of that in on-line fashion. the case study of the stenciling robot is examined.

• 제어로봇시스템학회:학술대회논문집
• /
• 1997.10a
• /
• pp.819-824
• /
• 1997

This paper presents a cell-based motion control strategy for soccer playing mobile robots. In the central robot motion planner, the planar ground is divided into rectangular cells with variable sizes and motion indices to which direction the mobile robot should move. At every time the multiple objects-the goal gate, ball, and robots-detected, integer values of motion indices are assigned to the cells occupied by mobile robots. Once the indices being calculated, the most desirable state-action pair is chosen from the state and action sets to achieve successful soccer game strategy. The proposed strategy is computationally simple enough to be used for fast robotic soccer system.

• 제어로봇시스템학회:학술대회논문집
• /
• 2004.08a
• /
• pp.1153-1157
• /
• 2004

The report of the Korean National Statistics Office shows that Korea has been emerging as an elderly society rapidly, and it will burden the Korean society with excessive social welfare cost for the aged in the near future. If we can help the aged to live healthy in some ways, the social burden for the health care of the aged will be lessened. In order to help physical and mental health of the elderly person, we have developed an exercise apparatus called intelligent arm wrestling machine system. This paper presents the mechanism and scenario of the proposed intelligent arm wrestling machine system. The proposed mechanism and scenario are peculiar. In particular, the proposed scenario determines randomly who will win between the man and the robot and generates a game process that the arm-wrestler cannot predict in advance.