• The Journal of Korea Robotics Society
• /
• v.17 no.3
• /
• pp.273-281
• /
• 2022

In this paper, we propose a robot sound recognition system that detects various sound events. The proposed system is designed to detect various sound events in real-time by using a microphone on a robot. To get real-time performance, we use a VGG11 model which includes several convolutional neural networks with real-time normalization scheme. The VGG11 model is trained on augmented DB through 24 kinds of various environments (12 reverberation times and 2 signal to noise ratios). Additionally, based on random forest algorithm, a decision logic is also designed to generate event signals for robot applications. This logic can be used for specific classes of acoustic events with better performance than just using outputs of network model. With some experimental results, the performance of proposed sound recognition system is shown on real-time device for robots.

• Journal of Institute of Control, Robotics and Systems
• /
• v.13 no.11
• /
• pp.1082-1091
• /
• 2007

In this paper, we developed a new hybrid mobile robot which can climb stairs and go over thresholds by crawl gait with embedded real-time control software. This robot is also categorized into hybrid robot that has advantages of wheeled mobile robot and legged mobile robot, but adopts gait feature of crocodile named belly crawl. We imitated the belly crawl using four legs of 2 DOF, four omni-directional wheels, and embedded control software which controls legs and wheels. This software is developed using RTAI/Linux, real-time drivers. As a result, the new hybrid mobile robot has crawl gait. Using this feature, the new hybrid mobile robot can climb stairs and go over thresholds just by path planning of each leg with size of stairs and thresholds, and computing the movement distance of robot body center without considering stability. The performance of our new hybrid mobile robot is verified via experiments.

• Proceedings of the KIEE Conference
• /
• 2007.04a
• /
• pp.337-339
• /
• 2007

This paper proposes a new paradigm for cooperation of multi-robot system for home service. For localization of each robot. the master robot collects information of location of each robot based on communication of RFID tag on the floor and RFID reader attached on the bottom of the robot. The Master robot communicates with slave robots via wireless LAN to check the motion of robots and command to them based on the information from slave robots. The operator may send command to slave robots based on the HRI(Human-Robot Interaction) screened on masted robot using information from slave robots. The cooperation of multiple robots will enhance the performance comparing with single robot.

• The Journal of Korea Robotics Society
• /
• v.7 no.3
• /
• pp.216-221
• /
• 2012

Recently, although the need of marine robots being raised in extreme areas, the basis is very deficient. Fortunately, as the robot competition is vitalizing and the need of the robot education is increasing, it is desirable to establish the basis of the R&D and industrialization of marine robots and to train professionals through the development and diffusion of marine robot kits. However, in conventional case, there is no remotely operated aerial robot-kit based on the balloon for the marine robot competition, which has the abilities of the airborne locomotion and obstacle avoidance. To solve this problem, an aerial robot-kit which has the abilities of the airborne locomotion and remote control, is developed. To verify the performance of the developed kit, test and evaluation such as surge, yaw and pitch is performed. The test and evaluation results show that the possibility of the real applications of the developed kit.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.16 no.4
• /
• pp.2370-2378
• /
• 2015

This paper proposes an algorithm using Lagrange interpolation method to realize trajectory planning for torque minimization of robot manipulators. For the algorithm, position constraints of robot manipulators should be given and the stability of robot manipulators should be satisfied. In order to avoid Runge's phenomenon, we set up time interpolation points using Chebyshev interpolation points. After that, we found suitable angle which corresponds to the points and then we got trajectories of joint's angle, velocity, acceleration using Lagrange interpolation method. We selected performance index for torque consumption optimization of robot manipulator. The method went through repetitive computation process to have minimum value of the performance index by calculated trajectory. Through the process, we could get optimized trajectory to minimize torque and performance index and guarantee safety of the motion for manipulator performance.

• Journal of the Korean Society for Precision Engineering
• /
• v.28 no.9
• /
• pp.1025-1031
• /
• 2011

Take-out robots used for handling of the plastic parts manufactured with the injection mold are usually the gantry type that consists of long and thin links, The performance of the take-out robot is determined by the speed of the motion and the positioning accuracy to grab the part out of the mold, As the speed of the robot increases the flexure in the links of the take-out robot becomes more significant and it results in more residual vibration, The residual vibration deteriorates the positioning accuracy and compels the operator to slow down the motion of the robot. The typical method to reduce the vibration in the robot requires stiffening the links and/or slowing down the robot, Vibration control could achieve the desired performance without increasing the manufacturing cost or the operation cost that would be incurred otherwise, Considering the point-to-point nature of the task to be performed by the take-out robot the time-delay command (or input) shaping filter approach would be the most effective control method to be adopted among a few available control schemes. In this paper a direct adaptive command shaping filter (ACSF) algorithm has been modified and applied to design the optimal command shaping filters for various configuration of the take-out robot. Optimal filters designed by ACSF algorithm have been implemented on a take-out robot and the effectiveness of the designed filters in terms of vibration suppression has been verified for multiple positions of the robot.

• 제어로봇시스템학회:학술대회논문집
• /
• 1997.10a
• /
• pp.756-759
• /
• 1997

Multi-arm cooperation robot system is required for more specific and dextrous jobs such as transferring very large or heavy objects, or grasping work piece while processing on it. There is little research on 3-dimensional multi-arm robot. Here we propose two performance indices presenting isotropy of end-effector's acceleration and velocity capabilities with constraints of joint torques, that is Isotropic Acceleration Radius [IAR] and Isotropic Velocity Radius [IVRI. Also the procedure to find 3-dimensional IAR, IVR is proposed, where available acceleration set concept is used. The case of 3-dimensional two 3 joint robot system was simulated and the distributions of IAR, IVR was studied.

• The Transactions of the Korean Institute of Electrical Engineers P
• /
• v.60 no.4
• /
• pp.172-174
• /
• 2011

This paper is presented for robot vacuum cleaners using BLDC motors. Recently, BLDC motors which require smaller size, lower sound noise and higher efficiency have been placed in high value-added products including robot vacuum cleaners, vehicle cars and other industry applications. The DC motors have higher sound noise, higher height of the size and lower efficiency due to electro-magnetic structure using the brushes and the commutators. The proposed BLDC motors are appropriate for the motors adequate in regards to higher efficiency, longer life cycle time, and smaller height of the size when robot vacuum cleaners go to some lower height of the space like under sleeping beds and because it's power source is batteries. The paper shows the performance of the BLDC motors designed by the Finite Element Analysis(FEA) of the electro-magnetic field. This paper shows the mechanical structure and the prototype of the motor with the impeller. The performance characteristics of the BLDC motors with the hall sensor controller are verified by the experimental results.

• Transactions of the Korean Society of Mechanical Engineers
• /
• v.19 no.1
• /
• pp.99-110
• /
• 1995

An industrial robot needs a simple and robust control algorithm obtaining high precision control performance in spite of disturbance and parameter's change. In this paper, for solving this problem, a new sliding mode control algorithm is proposed and applied to the trajectory control of a SCARA type robot. The proposed algorithm has diminished the chattering occurring in sliding mode by setting a dead band along the switching line on the phase plane. It shows that we can easily obtain a simple switching control input satisfying sliding mode in spite of regarding nonlinear terms of a manipulator and servo system as disturbance. A guideline for selection of dead-band width is determined by optimal value of cost function presenting magnitudes of chattering and error. By this algorithm, we can expect the high performance of the trajectory tracking of an industrial robot which needs a robust and simple algorithm.

• 제어로봇시스템학회:학술대회논문집
• /
• 1991.10a
• /
• pp.280-285
• /
• 1991

Neural network control has many innovative potentials for fast, accurate and intelligent adaptive control. In this paper, a learning control architecture for the dynamic control of a robot manipulator is developed using inverse dynamic neurocontroller and linear neurocontroher. The inverse dynamic neurocontrouer consists of a MLP (multi-layer perceptron) and the linear neurocontroller consists of SLPs (single layer perceptron). Compared with the previous type of neurocontroller which is using an inverse dynamic neurocontroller and a fixed PD gain controller, proposed architecture shows the superior performance over the previous type of neurocontroller because linear neurocontroller can adapt its gain according to the applied task. This superior performance is tested and verified through the control of PUMA 560. Without any knowledge on the dynamic model, its parameters of a robot , (The robot is treated as a complete black box), the neurocontroller, through practice, gradually and implicitly learns the robot's dynamic properties which is essential for fast and accurate control.