• Proceedings of the IEEK Conference
• /
• 2008.06a
• /
• pp.673-674
• /
• 2008

This paper presents a new navigation algorithm of an autonomous mobile robot with vision and IR sensors, Zigbee Sensor Network using fuzzy rules. We also show that the developed mobile robot with the proposed algorithm is navigating very well in complex unknown environments.

• 제어로봇시스템학회:학술대회논문집
• /
• 1991.10a
• /
• pp.990-995
• /
• 1991

The integration of intelligent robots into manufacturing systems should positively impact the product quality and productivity. A new theory of object location and recognition using the supporting plane is presented. The unknown supporting points are determined by image coordinates, known camera parameters, and joint coordinates of the robot manipulators. This is developed by using the geometrical interpretation of perspective projection and the geometrical constraints of industrial environments. This can be applied to solve typical robot vision problems such as determination of position, orientation, and recognition of objects.

• Proceedings of the IEEK Conference
• /
• 2002.07b
• /
• pp.1343-1345
• /
• 2002

In this paper, we introduce the MC-CDMA (Multi-Carrier CDMA) system with MD (multi-detector). Due to unknown functional form of noise in wireless channel environments, it is not easy to design the detector through estimating the functional form of noise. Instead, we design the MD, which is constructed based on DGT (Data Grouping Technique) and quantiles estimated through RMSA (Robbins-Monro Stochastic Approximation) algorithm.

• Proceedings of the KSPS conference
• /
• 2005.04a
• /
• pp.103-106
• /
• 2005

The goal of our research is to build a text independent speaker recognition system that can be used in any condition without any additional adaptation process. The performance of speaker recognition systems can be severally degraded in some unknown mismatched microphone and noise conditions. In this paper, we show that PCA(Principal component analysis) without dimension reduction can greatly increase the performance to a level close to matched condition. The error rate is reduced more by the proposed augmented PCA, which augment an axis to the feature vectors of the most confusable pairs of speakers before PCA

• 제어로봇시스템학회:학술대회논문집
• /
• 2000.10a
• /
• pp.41-41
• /
• 2000

biped robots are expected to robustly traverse terrain with various unknown surfaces. The robot will occasionally encounter the unexpected events in made-for human environments. The slipping is a very real and serious problem in the unexpected events. The robot system must respond to the unexpected slipping after it has occurred and before control is lost. This paper proposes a reflex control method for biped robots to recover from slipage. Computer simulations with the 6-DOF environment model which consists of nonlinear dampers, nonlinear springs, and linear springs, show that the proposed method is effective in preventing fall-down due to slippage.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.18 no.10
• /
• pp.2367-2374
• /
• 2014

This paper proposes a speech enhancement method which can be independently applied to different types of speech recognition systems. Feature compensation methods are well known to be effective as a front-end algorithm for robust speech recognition in noisy environments. The feature types and speech model employed by the feature compensation methods should be matched with ones of the speech recognition system for their effectiveness. However, they cannot be successfully employed by the speech recognition with "unknown" specification, such as a commercialized speech recognition engine. In this paper, a speech enhancement method is proposed, which is based on the PCGMM-based feature compensation method. The experimental results show that the proposed method significantly outperforms the conventional front-end algorithms for unknown speech recognition over various background noise conditions.

• 제어로봇시스템학회:학술대회논문집
• /
• 2003.10a
• /
• pp.1921-1926
• /
• 2003

We build a local minimum free motion planning for mobile robots considering dynamic environments by simple sensor fusion assuming that there are unknown obstacles which can be detected only partially at a time by proximity sensors and can be cleaned up or moved slowly (dynamic environments). Potential field is used as a basic platform for the motion planning. To clear local minimum problem, the partial information on the obstacles should be memorized and integrated effectively. Sets of linked line segments (SLLS) are proposed as the integration method. Then robot's target point is replaced by virtual target considering the integrated sensing information. As for the main proximity sensors, we use laser slit emission and simple web camera since the system gives more continuous data information. Also, we use ultrasonic sensors as the auxiliary sensors for simple sensor fusion considering the advantages in that they give exact information about the presence of any obstacle within certain range. By using this sensor fusion, the dynamic environments can be dealt easily. The performance of our algorithm is validated via simulations and experiments.

• The Journal of the Acoustical Society of Korea
• /
• v.15 no.5
• /
• pp.90-98
• /
• 1996

An auditory model is proposed for robust speech recognition in noisy environments. The model consists of cochlear bandpass filters and nonlinear stages, and represents frequency and intensity information efficiently even in noisy environments. Frequency information of the signal is obtained by zero-crossing intervals, and intensity information is also incorporated by peak detectors and saturating nonlinearities. Also, the robustness of the zero-crossings in estimating frequency is verified by the developed analytic relationship of the variance of the level-crossing interval perturbations as a function of the crossing level values. The proposed auditory model is computationally efficient and free from many unknown parameters compared with other auditory models. Speaker-independent speech recognition experiments demonstrate the robustness of the proposed method.

• Journal of Institute of Control, Robotics and Systems
• /
• v.12 no.6
• /
• pp.585-593
• /
• 2006

In this paper, we propose a vision-based simultaneous localization and map-building (SLAM) algorithm. SLAM problem asks the location of mobile robot in the unknown environments. Therefore, this problem is one of the most important processes of mobile robots in the outdoor operation. To solve this problem, Extended Kalman filter (EKF) is widely used. However, this filter requires computational power (${\sim}O(N)$, N is the dimension of state vector). To reduce the computational complexity, we applied compressed extended Kalman filter (CEKF) to stereo image sequence. Moreover, because the mobile robots operate in the outdoor environments, we should estimate full d.o.f.s of mobile robot. To evaluate proposed SLAM algorithm, we performed the outdoor experiments. The experiment was performed by using new wheeled type mobile robot, Robhaz-6W. The performance results of CEKF SLAM are presented.

• The Bulletin of The Korean Astronomical Society
• /
• v.43 no.1
• /
• pp.32.1-32.1
• /
• 2018

Searching for low surface brightness (LSB) dwarf galaxies in low density environments (isolated and group) can help us resolve the discrepancy between observation and theory known as the 'missing satellite' problem. They are also important to study the evolution of low mass galaxies in these environments. Although the number of dwarfs in such environments is rapidly increasing in many recent studies, it is still not easy to characterize their general properties. Motivated by this, we present preliminary results of our search for LSB dwarf galaxies around 60 nearby galaxies (D<50Mpc) using deep optical images. Imaging data from Maidanak Astronomical Observatory (MAO) in Uzbekistan as a part of Intensive Monitoring Survey of Nearby Galaxies (IMSNG; Im in prep.) and other archival data are used to find previously unknown LSB dwarf galaxies. Extended LSB sources (central surface brightness ${\mu}_0$ > $23mag/arcsec^2$) are first selected in the ${\mu}_0$ - magnitude plane (Rines & Geller 2008). The dwarf galaxy candidates are chosen by visual inspection. We discuss whether these candidates are actual satellite galaxies, by measuring the projected number densities in group environments and in the field. Also, their structural and photometric properties are compared with those of previously discovered dwarf galaxies in the literature.