• 로봇학회논문지
• /
• 제15권2호
• /
• pp.169-176
• /
• 2020

This paper studied the collision detection of robot manipulators for safe collaboration in human-robot interaction. Based on sensor-based collision detection, external torque is detached from subtracting robot dynamics. To detect collision using joint torque sensor data, a comparative study was conducted using data-based machine learning algorithm. Data was collected from the actual 3 degree-of-freedom (DOF) robot manipulator, and the data was labeled by threshold and handwork. Using support vector machine (SVM), decision tree and k-nearest neighbors KNN method, we derive the optimal parameters of each algorithm and compare the collision classification performance. The simulation results are analyzed for each method, and we confirmed that by an optimal collision status detection model with high prediction accuracy.

• 방송공학회논문지
• /
• 제25권6호
• /
• pp.870-881
• /
• 2020

본 논문에서는 5G NR (new radio) 시스템에서 PSS/SSS (primary synchronization signal/secondary synchronization signal)를 이용한 cell ID (cell identity) 검출 방법들을 제시하고 성능을 평가한다. 시간 영역에서 PSS를 먼저 검출한 후 검출된 PSS 정보를 이용하여 채널 추정 및 SSS의 시퀀스 검출에 사용하는 2단계(2-stage) 검출 방법과 PSS와 SSS 시퀀스를 결합하여 동시에 검출하는 결합 검출(joint detection) 방법을 사용한다. 또한, 추정한 채널 이득을 이용하여 주어진 PSS 및 SSS의 전체 시퀀스 길이의 상관(correlation) 값을 계산하는 coherent 방법과 시퀀스의 전체 길이를 여러 개의 그룹으로 나누어 각 그룹 내에서는 coherent 상관을 계산하고, 이들을 결합하여 전체 그룹의 상관 값을 계산하는 non-coherent combining 방법을 제시한다. 본 논문에서 고려한 검출 방법들에 대해 전산 실험을 통하여 PSS 및 SSS의 개별 검출 에러율과 전체 cell ID 검출 에러율 성능을 비교한다. 전산 실험 결과는 가산 백색 가우시안 잡음환경과 고정 및 이동 환경에서 non-coherent combining 방법이 coherent 방법에 비해 우수한 검출 성능을 보이며, 결합 검출 방법은 2단계 검출 방법에 비해 우수한 성능을 보이나 계산 복잡도 측면에서는 2단계 검출 방법이 보다 낮은 복잡도를 갖는다는 것을 보여준다.

• 제어로봇시스템학회논문지
• /
• 제17권10호
• /
• pp.1044-1050
• /
• 2011

The quality of brazing joints is one of the most important factors that have an effect on the performance of the brazing joint-based heat exchangers with the growing use in industry recently. Therefore, it is necessary to inspect the brazing joints in order to guarantee the performance of the heat exchangers. This paper presents a non-destructive method to inspect the brazing joints of the heat exchangers using X-ray. Firstly, X-ray cross-sectional images of the brazing joints are obtained by using CT (Computerized Tomography) technology. Cross-sectional image from CT is more useful to detect the inner defects than the traditional transmitted X-ray image. Secondly, the acquired images are processed by an algorithm proposed for the defect detection of brazing joint. Finally, two types of brazing joint are examined in a series of experiments to detect the defects in brazing joints. The experimental results show that the proposed algorithm is effective for defect detection of the brazing joints in heat exchangers.

• 한국멀티미디어학회논문지
• /
• 제19권12호
• /
• pp.1909-1918
• /
• 2016

This paper presents a unified framework for joint Convolutional Neural Network (CNN) based vehicle detection by leveraging multi-spectral image pairs. With the observation that under challenging environments such as night vision and limited light source, vehicle detection in a single color image can be more tractable by using additional far-infrared (FIR) image, we design joint CNN architecture for both RGB and FIR image pairs. We assume that a score map from joint CNN applied to overall image can be considered as confidence of vehicle existence. To deal with various scale ratios of vehicle candidates, multi-scale images are first generated scaling an image according to possible scale ratio of vehicles. The vehicle candidates are then detected on local maximal on each score maps. The generation of overlapped candidates is prevented with non-maximal suppression on multi-scale score maps. The experimental results show that our framework have superior performance than conventional methods with a joint framework of multi-spectral image pairs reducing false positive generated by conventional vehicle detection framework using only single color image.

• 터널과지하공간
• /
• 제19권1호
• /
• pp.1-10
• /
• 2009

암반 내 구조물을 시공하는 경우 역학적 안정성을 평가하기 위하여 암반의 특성을 조사한다. 이 경우 암반의 특성은 주로 암반 내 절리의 특성에 의하여 좌우된다. 지금까지는 암반 내 절리의 특성을 조사하기 위하여 암반이 노출된 사면이나 노두에 접근하고 육안으로 직접 관찰하였다. 이때 급사면과 같은 곳에서 접근의 문제, 작업의 안전 문제, 많은 시판이 걸리는 문제, 조사시간에 비하여 얻은 정보량의 부족, 정보의 재현 문제, 측정 오차 문제 등의 제한이 있었다. 따라서 이와 같은 문제를 개선하기 위하여 LIDAR (light detection and ranging)로 암반을 스캔하여 얻은 포인트 클라우드(point cloud)글 Split-FX 소프트웨어로 처리한 결과 절기의 방향과 간격 및 절리면의 거칠기 등 절리의 특성을 정확하고 효율적으로 분석할 수 있었다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제13권4호
• /
• pp.1795-1811
• /
• 2019

In order to achieve rapid and accurate detection of vehicle objects in complex traffic conditions, we propose a novel vehicle detection method. Firstly, more contextual and small-object vehicle information can be obtained by our Joint Feature Network (JFN). Secondly, our Evolved Region Proposal Network (EPRN) generates initial anchor boxes by adding an improved version of the region proposal network in this network, and at the same time filters out a large number of false vehicle boxes by soft-Non Maximum Suppression (NMS). Then, our Mask Network (MaskN) generates an example that includes the vehicle occlusion, the generator and discriminator can learn from each other in order to further improve the vehicle object detection capability. Finally, these candidate vehicle detection boxes are optimized to obtain the final vehicle detection boxes by the Fine-Tuning Network(FTN). Through the evaluation experiment on the DETRAC benchmark dataset, we find that in terms of mAP, our method exceeds Faster-RCNN by 11.15%, YOLO by 11.88%, and EB by 1.64%. Besides, our algorithm also has achieved top2 comaring with MS-CNN, YOLO-v3, RefineNet, RetinaNet, Faster-rcnn, DSSD and YOLO-v2 of vehicle category in KITTI dataset.

• 로봇학회논문지
• /
• 제13권3호
• /
• pp.157-163
• /
• 2018

This paper deals with the development and application of control algorithms for series elastic relief robots for rescue operations in harsh environment like disasters or battlefield. The joint controller applied in this paper has a cascade structure combining inner loop for torque control and outer loop for position control. The torque loop contains feedforward and feedback controller and disturbance observer for independent, decentralized joint control. The effect of the elastic component and motor dynamics are treated as the nonlinear disturbance and compensated with the disturbance observer of torque controller. For the collision detection, Band Designed Disturbance Observer is configured to recognize/respond to external disturbance robustly in the continuously changing environment. The controller is applied to a 7-dof series elastic manipulator to evaluate the torque tracking and collision detection/response performance.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제8권2호
• /
• pp.601-617
• /
• 2014

In digital radio broadcasting systems, long delays are incurred in service start time when tuning to a particular frequency because several synchronization steps, such as symbol timing synchronization, frame synchronization, and carrier frequency offset and sampling frequency offset compensation are necessary. Therefore, the operation of the synchronization blocks causes delays ranging from several hundred milliseconds to a few seconds until the start of the radio service after frequency tuning. Furthermore, if spectrum inversed signals are transmitted in digital radio broadcasting systems, the receivers are unable to decode them, even though most receivers can demodulate the spectral inversed signals in analog radio broadcasting systems. Accordingly, fast synchronization techniques and a method for spectral inversion detection are required in digital radio broadcasting systems that are to replace the analog radio systems. This paper presents a joint detection method of frame, integer carrier frequency offset, and spectrum inversion for DRM Plus digital broadcasting systems. The proposed scheme can detect the frame and determine whether the signal is normal or spectral inversed without any carrier frequency offset and sampling frequency offset compensation, enabling fast frame synchronization. The proposed method shows outstanding performance in environments where symbol timing offsets and sampling frequency offsets exist.

• ETRI Journal
• /
• 제26권5호
• /
• pp.384-390
• /
• 2004

We propose a new bandwidth-efficient technique that achieves high data rates over a wideband wireless channel. This new scheme is targeted for a multiple-input multiple- output orthogonal frequency-division multiplexing (MIMO-OFDM) system that achieves transmit diversity through a space frequency block code and capacity enhancement through the iterative joint processing of zero-forcing detection and maximum a posteriori (MAP) decoding. Furthermore, the proposed scheme is compared to the coded Bell Labs Layered Space-Time OFDM (BLAST-OFDM) scheme.

• 대한전자공학회논문지TC
• /
• 제45권11호
• /
• pp.1-8
• /
• 2008

본 논문은 순방향 다중 안테나 다중 반송파-부호 분할 다중 접속 (MC-CDMA: multicarrier code division multiple access) 시스템에서 maximum likelihood (ML)를 기준으로 한 합동 검파 방식의 심벌 오류 확률을 분석한다. 심벌 오류 확률의 분석은 상향 바운드 (bound)의 형태로 주어지며, 주어진 바운드는 레일리 페이딩 채널 환경에서 다중 안테나 MC-CDMA 시스템의 심벌 오류 확률에 근사한 값을 나타낸다. 또한, 본 논문에서는 주어진 시스템에서 획득 가능한 다이버시티의 차수를 유도한다. 이 다이버시티의 차수는 시스템의 성능에 확산 계수, 코드의 수, 그리고 송수신 안테나의 수가 미치는 영향을 보여준다. 다이버시티 차수의 분석으로부터, loading되는 코드의 수가 확산 계수보다 작은 경우에, 주어진 시스템이 수신 안테나 다이버시티 외에 추가적인 다이버시티를 얻는다는 것을 알 수 있다. 오류 확률과 다이버시티의 분석은 모의실험과 비교하여 검증하였다.