• 제어로봇시스템학회:학술대회논문집
• /
• 2001.10a
• /
• pp.23.1-23
• /
• 2001

The unmanned vehicle is composed of three parts the front & side sensor system for keeping the lane and avoiding obstacles, the acceleration & brake control system for longitudinal motion control, and the steering control system for the lateral motion control. Each system helps the unmanned vehicle of which should take notice of its location and recognize obstacles around the place by itself and make a decision how much fast to proceed according to circumstances. During the operation, the control strategy that the vehicle can detect obstacles and avoid collision on the road involves with vehicle velocity very much. Therefore, We have to define a traction system which is powered by DC motor so that, unmanned vehicle can control its velocity accurately. In this study, we find mechanical and ...

• Journal of Information Processing Systems
• /
• v.19 no.1
• /
• pp.80-88
• /
• 2023

RGB-thermal (RGB-T) tracking using unmanned aerial vehicles (UAVs) involves challenges with regards to the similarity of objects, occlusion, fast motion, and motion blur, among other issues. In this study, we propose dynamic tracking aggregation (DTA) as a unified framework to perform object detection and data association. The proposed approach obtains fused features based a transformer model and an L1-norm strategy. To link the current frame with recent information, a dynamically updated embedding called dynamic tracking identification (DTID) is used to model the iterative tracking process. For object association, we designed a long short-term tracking aggregation module for dynamic feature propagation to match spatial and temporal embeddings. DTA achieved a highly competitive performance in an experimental evaluation on public benchmark datasets.

• Proceedings of the KSR Conference
• /
• 2011.10a
• /
• pp.1320-1326
• /
• 2011

The maximum speed of high-speed rail is restricted to various factors such as track condition including slope and radius, tunnel and dynamic stability of vehicle. Among the various factors, traction effort and resistance to motion is principal and basic factor. In addition, at high speed over 300km/h, aerodynamic drag amounts up to 80% of resistance to motion, that it can be said that aerodynamic drag is the most important factor to decide the maximum speed of high-speed rail system. This paper deals with a measure to increase the maximum speed of high-speed train by reducing aerodynamic drag. The traction effort curve and resistance to motion curve of existing high-speed train under development has been employed to set up the target of aerodynamic drag reduction to reach up to 500km/h without modification traction system. In addition, the contribution of various sources of aerodynamic drag to total value has been analyzed and the strategy for implementation of aerodynamic drag reduction has been discussed based on the aerodynamic simulation results around the train using computational fluid dynamics.

• 제어로봇시스템학회:학술대회논문집
• /
• 1997.10a
• /
• pp.1742-1745
• /
• 1997

We have developed a highly responsible probing system for inspection of electrical properties of assemble PCB$_{s}$ (printed circuit boards). However, as the duration of the impact occurring between a probe and a solder joint on PCB is very short, it is very difficult to control the harmful peak impact force and the slip motion of the probe to sufficient level only by its vorce feedback control with high gains. To overcome these disadvantages of the prototype, it needs ot obtain some information of the solder joint in advance before the contact. In addition, to guarantee the reliability of the probing task, the probing system is required to measure several points around the probale target point at high speed. There fore, to meet such requirements, we propose a new noncontaet sensor capable of detecting simultaneously position and normal vectors of the multiple points around the probable target point in real time. By using this information, we can prepare a control strategy for stable contact motion on impact. In this paper, we described measuring priniciple, design, and development of the sensor. The effectiveness of the proposed sensor is verified through a series of experiments.s.

• Journal of the Korean Society of Industry Convergence
• /
• v.17 no.2
• /
• pp.42-53
• /
• 2014

Robust voice recognition (RVR) is essential for a robot to communicate with people. One of the main problems with RVR for robots is that robots inevitably real environment noises. The noise is captured with strong power by the microphones, because the noise sources are closed to the microphones. The signal-to-noise ratio of input voice becomes quite low. However, it is possible to estimate the noise by using information on the robot's own motions and postures, because a type of motion/gesture produces almost the same pattern of noise every time it is performed. In this paper, we propose an RVR system which can robustly recognize voice by adults and children in noisy environments. We evaluate the RVR system in a communication robot placed in a real noisy environment. Voice is captured using a wireless microphone. Navigation Strategy is shown Obstacle detection and local map, Design of Goal-seeking Behavior and Avoidance Behavior, Fuzzy Decision Maker and Lower level controller. The final hypothesis is selected based on posterior probability. We then select the task in the motion task library. In the motion control, we also integrate the obstacle avoidance control using ultrasonic sensors. Those are powerful for detecting obstacle with simple algorithm.

• Journal of Korea Multimedia Society
• /
• v.21 no.8
• /
• pp.969-981
• /
• 2018

Recent advances in machine learning approaches such as deep neural network and reinforcement learning offer significant performance improvements in generating detailed and varied motions in physically simulated virtual environments. The optimization methods are highly attractive because it allows for less understanding of underlying physics or mechanisms even for high-dimensional subtle control problems. In this paper, we propose an efficient learning method for stochastic policy represented as deep neural networks so that agent can generate various energetic motions adaptively to the changes of tasks and states without losing interactivity and robustness. This strategy could be realized by our novel trajectory search method motivated by the trust region policy optimization method. Our value-based trajectory smoothing technique finds stably learnable trajectories without consulting neural network responses directly. This policy is set as a trust region of the artificial neural network, so that it can learn the desired motion quickly.

• The Journal of Korea Robotics Society
• /
• v.19 no.3
• /
• pp.236-243
• /
• 2024

This paper introduces a dual manipulator system designed to automate the packaging process of industrial coils, which exhibit higher variability than other structured industrial fields due to diverse commercial requirements. The conventional solution involves the direct-teaching method, where an operator instructs the robot on a target configuration. However, this method has distinct limitations, such as low flexibility in dealing with varied sizes and safety concerns for the operators handling large products. In this sense, this paper proposes a two-step approach for coil packaging: motion planning and assembly execution. The motion planning includes a Rapidly-exploring Random Tree algorithm and a smoothing method, allowing the robot to reach the target configuration. In the assembly execution, the packaging is considered a peg-in-hole assembly. Unlike typical peg-in-hole assembly handling two workpieces, the packaging includes three workpieces (e.g., coil, inner ring, side plate). To address this assembly, the paper suggests a suitable strategy for dual manipulation. Finally, the validity of the proposed system is demonstrated through experiments with three different sizes of coils, replicating real-world packaging situations.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.25 no.2
• /
• pp.168-173
• /
• 2015

The flight control of aircraft, which has nonlinear time-varying dynamic characteristics depending on the various and unexpected external conditions, can be performed on two motions: longitudinal motion and lateral motion. In the longitudinal motion control of aircraft, pitch and trust are major control parameters and roll and yaw are control ones in the lateral motion control. Until now, a number of efficient and reliable control schemes that can guarantee the stability and maneuverability of the aircraft have been developed. Recently, the intelligent flight control scheme, which differs from the conventional control strategy requiring the various and complicate procedures such as the wind tunnel and environmental experiments, has attracted attention. In this paper, an intelligent longitudinal control scheme has been proposed utilizing Interval Type-2 fuzzy logic which can be recognized as a representative intelligent control methodology. The results will be verified through computer simulation with a F-4 jet fighter.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• v.7 no.2
• /
• pp.138-142
• /
• 2007

This paper presents an algorithm which extends the rapidly-exploring random tree (RRT) framework to deal with change of the task environments. This algorithm called the Retrieval RRT Strategy (RRS) combines a support vector machine (SVM) and RRT and plans the robot motion in the presence of the change of the surrounding environment. This algorithm consists of two levels. At the first level, the SVM is built and selects a proper path from the bank of RRTs for a given environment. At the second level, a real path is planned by the RRT planners for the: given environment. The suggested method is applied to the control of $KUKA^{TM}$, a commercial 6 DOF robot manipulator, and its feasibility and efficiency are demonstrated via the cosimulatation of $MatLab^{TM}\;and\;RecurDyn^{TM}$.

• Journal of Korea Multimedia Society
• /
• v.19 no.2
• /
• pp.469-478
• /
• 2016

This paper designs an application for detecting various objects using a smart phone with camera sensor, then implements the application that detects the number of faces in front of a user by using the Face API provided by android and generates a speech to the user. For implementing the application, the GoF strategy pattern is applied to design the application. It provides some advantages; first, the algorithm development schedule can separate the whole application development schedule; next, it makes easier to add the algorithm. For example, another detecting algorithm for the other objects (character, motion detection) that may be developed in the future, or it may be replaced by a more high-performance algorithm. With the propose method, a general smart phone can make some advantages that can provide information of various objects (such as moving people and objects, and detected character from signboards) to the person who is visually impaired.