• 제어로봇시스템학회논문지
• /
• 제5권8호
• /
• pp.961-968
• /
• 1999

In this paper we handle a system that transform sensor data to sensor information. Sensor informations from redundant accelerometers are manipulated to represent the configuration of objects carrying sensors. Basic sensor unit of the proposed systme is composed of 3 accelerometers that are aligned along x-y-z coordination axes of motion. To refine the sensor information, at first the sensor data are fused by geometrical optimization to reduce the variance of sensor information. To overcome the error caused from inexact alignment of each sensor to the coordination system, we propose a calibration technique that identifies the transformation between the coordinate axes and real sensor axes. The calibration technique make the sensor information approach real value. Also, we propose a technique that decomposes the accelerometer data into motion acceleration component and gravity acceleration component so that we can get more exact configuration of objects than in the case of raw sensor data. A set of experimental results are given to show the usefulness of the proposed method as well as the experiments in which the proposed techniques are applied to human body motion capture.

• 한국항해항만학회:학술대회논문집
• /
• 한국항해항만학회 2002년도 추계공동학술대회논문집
• /
• pp.127-132
• /
• 2002

This paper proposes a sensor-fusion technique where the data sets for the previous moments are properly transformed and fused into the current data sets to enable accurate measurement, such as, distance to an obstacle and location of the service robot itself. In the conventional fusion schemes, the measurement is dependent on the current data sets. As the results, more of sensors are required to measure a certain physical parameter or to improve the accuracy of the measurement. However, in this approach, instead of adding more sensors to the system the temporal sequence of the data sets are stored and utilized for the measurement improvement. Theoretical basis is illustrated by examples and the effectiveness is proved through the simulations. finally, the new space and time sensor fusion (STSF) scheme is applied to the control of a mobile robot in an unstructured environment as well as structured environment.

• 한국측량학회지
• /
• 제39권5호
• /
• pp.289-295
• /
• 2021

Recently, owing to the development of autonomous vehicles, research on precisely determining the position of a moving object has been actively conducted. Previous research mainly used the fusion of GNSS/IMU (Global Positioning System / Inertial Navigation System) and sensors attached to the vehicle through a Kalman filter. However, in recent years, new technologies have been used to determine the location of a moving object owing to the improvement in computing power and the advent of deep learning. Various techniques using RNN (Recurrent Neural Network), LSTM (Long Short-Term Memory), and NARX (Nonlinear Auto-Regressive eXogenous model) exist for such learning-based positioning methods. The purpose of this study is to compare the precision of existing filter-based sensor fusion technology and the NARX-based method in case of GNSS signal blockages using simulation data. When the filter-based sensor integration technology was used, an average horizontal position error of 112.8 m occurred during 60 seconds of GNSS signal outages. The same experiment was performed 100 times using the NARX. Among them, an improvement in precision was confirmed in approximately 20% of the experimental results. The horizontal position accuracy was 22.65 m, which was confirmed to be better than that of the filter-based fusion technique.

• Smart Structures and Systems
• /
• 제7권3호
• /
• pp.229-240
• /
• 2011

Recent developments in Smart Structures with very large scale embedded sensors and actuators have introduced new challenges in terms of data processing and sensor fusion. These smart structures are dynamically classified as a large-scale system with thousands of sensors and actuators that form the musculoskeletal of the structure, analogous to human body. In order to develop structural health monitoring and diagnostics with data provided by thousands of sensors, new sensor informatics has to be developed. The focus of our on-going research is to develop techniques and algorithms that would utilize this musculoskeletal system effectively; thus creating the intelligence for such a large-scale autonomous structure. To achieve this level of intelligence, three major research tasks are being conducted: development of a Bio-Inspired data analysis and information extraction from thousands of sensors; development of an analytical technique for Optimal Sensory System using Structural Observability; and creation of a bio-inspired decision-making and control system. This paper is focused on the results of our effort on the first task, namely development of a Neuro-Morphic Engineering approach, using a neuro-symbolic data manipulation, inspired by the understanding of human information processing architecture, for sensor fusion and structural diagnostics.

• 대한원격탐사학회:학술대회논문집
• /
• 대한원격탐사학회 2003년도 Proceedings of ACRS 2003 ISRS
• /
• pp.107-109
• /
• 2003

Optical sensor-based land cover categories produce spectral signature confusion along with degraded classification accuracy. In the classification tasks, the goal of fusing data from different sensors is to reduce the classification error rate obtained by single source classification. This paper describes the result of land cover/land use classification derived from solely of Landsat TM (TM) and multisensor image fusion between JERS 1 SAR (JERS) and TM data. The best radar data manipulation is fused with TM through various techniques. Classification results are relatively good. The highest Kappa Coefficient is derived from classification using principal component analysis-high pass filtering (PCA+HPF) technique with the Overall Accuracy significantly high.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2002년도 ICCAS
• /
• pp.104.2-104
• /
• 2002

This paper proposes a sensor-fusion technique where the data sets for the previous moments are properly transformed and fused into the current data sets to enable accurate measurement, such as, distance to an obstacle and location of the service robot itself. In the conventional fusion schemes, the measurement is dependent on the current data sets. As the results, more of sensors are required to measure a certain physical parameter or to improve the accuracy of the measurement. However, in this approach, instead of adding more sensors to the system , the temporal sequence of the data sets are stored and utilized for the measurement improvement. Theoretical basis is il lustrated by examples and...

• International Journal of Ocean System Engineering
• /
• 제1권2호
• /
• pp.102-109
• /
• 2011

This paper describes the implementation of a precise underwater navigation solution using a multiple sensor fusion technique based on USBL, GPS, DVL and AHRS measurements for the operation of a remotely operated mine disposal vehicle (MDV). The estimation of accurate 6DOF positions and attitudes is the key factor in executing dangerous and complicated missions. To implement the precise underwater navigation, two strategies are chosen in this paper. Firstly, the sensor frame alignment to the body frame is conducted to enhance the performance of a standalone dead-reckoning algorithm. Secondly, absolute position data measured by USBL is fused to prevent cumulative integration error. The heading alignment error is identified by comparing the measured absolute positions with the DR algorithm results. The performance of the developed approach is evaluated with the experimental data acquired by MDV in the South-sea trial.

• 한국해양공학회지
• /
• 제24권3호
• /
• pp.46-51
• /
• 2010

This paper describes the implementation of a precise underwater navigation solution using a multi-sensor fusion technique based on USBL, DVL, and IMU measurements. To implement this precise underwater navigation solution, three strategies are chosen. The first involves heading alignment angle identification to enhance the performance of a standalone dead-reckoning algorithm. In the second, the absolute position is found quickly to prevent the accumulation of integration error. The third one is the introduction of an effective outlier rejection algorithm. The performance of the developed algorithm was verified with experimental data acquired by the deep-sea ROV, Hemire, in the East-sea during a survey of a methane gas seepage area at a 1,500 m depth.

• 전자공학회논문지
• /
• 제52권5호
• /
• pp.190-196
• /
• 2015

본 논문은 항법장치 위치보정을 위해 칼만필터를 적용한 GPS/INS융합의 다중보정방법을 제안한다. 연구에서는 관성항법장치를 구현하기 위해 9축 항법장치로 보정알고리즘을 적용하여 위치오차를 감소시킨 방법을 적용했다. 일반적으로 GPS/INS는 위치정보를 얻어낼 수 있지만 위치정보를 구하는 과정에서 오차 또한 더불어 커지게 되기에 이를 보정하기 위한 강인한 오차 보정 알고리즘이 필요하다. 본 논문에서는 9축 관성센서(mpu-9150)의 외란에 대한 강인성 향상을 위해 가속도계 보정 알고리즘을 사용하여 tilt보정을 수행했으며, 제어 대상체의 정확한 방위를 파악할 수 있도록 Yaw각 재정의 알고리즘을 적용하였다. 최종적으로 GPS/INS와 칼만 필터를 함께 결합한 통합시스템을 구현하였다.

• 한국측량학회지
• /
• 제30권1호
• /
• pp.75-86
• /
• 2012

SAR는 기상상태와 태양고도 제약을 받지 않고 영상을 취득할 수 있는 장점을 갖지만 광학영상에 비해 시각적 가독성이 떨어지는 단점을 갖는다. 광학영상의 다중분광정보를 융합하여 SAR 영상의 가독성을 향상시키기 위한 다중센서 융합기술에 대한 관심이 증대되고 있다. 본 연구에서는 고속 퓨리에 변환을 통한 고주파 정보 추출 및 이상치 제거과정을 통해 SAR 영상의 공간적 세밀함과 다중분광영상의 분광정보를 유지할 수 있는 새로운 다중센서 융합기술을 제안하였다. 실험데이터로는 KOMPSAT-5호와 동일한 고해상도 X-band SAR 시스템을 장착한 TerraSAR-X 영상과 KOMPSAT-2호의 다중분광영상을 사용하였다. 제안기법의 효용성을 평가하기 위해 기존에 위성영상융합에 많이 사용된 융합기법과의 시각적/정량적 비교평가를 수행하였다. 실험 결과 기존 영상융합알고리즘에 비해 분광정보 보존측면에서 보다 향상된 결과를 보임을 확인할 수 있었다.