• 제어로봇시스템학회:학술대회논문집
• /
• 2001.10a
• /
• pp.64.4-64
• /
• 2001

Localization is the key role in controlling the Mobile Robot. In this papers, a development of the sensor fusion algorithm for controling UTV(Unmanned Tracked Vehicle) is presented. The multi-sensocial dead-rocking subsystem is established based on the optimal filtering by first fusing heading angle reading from a magnetic compass, a rate-gyro and two encoders mouned on the robot wheels, thereby computing the deat-reckoned location. These data and the position data provoded by LBL system are fused together by means of an extended Kalman filter. This algorithm is proved by simulation studies.

• Journal of the Korea Institute of Military Science and Technology
• /
• v.8 no.4 s.23
• /
• pp.14-23
• /
• 2005

In this paper we propose a sensor fusion method for the navigation algorithm which can be used to estimate state vectors such as position and velocity for its motion control using multi-sensor output measurements. The output measurement we will use in estimating the state is a series of known multi-sensor asynchronous outputs with measurement noise. This paper investigates the Extended Kalman Filtering method to merge asynchronous heading, heading rate, velocity of DVL, and SSBL information to produce a single state vector. Different complexity of Kalman Filter, with. biases and measurement noise, are investigated with theoretically data from MOERI's SAUV. All levels of complexity of the Kalman Filters are shown to be much more close and smooth to real trajectories then the basic underwater acoustic navigation system commonly used aboard underwater vehicle.

• IEMEK Journal of Embedded Systems and Applications
• /
• v.4 no.2
• /
• pp.69-78
• /
• 2009

Localization is a very important technique for the mobile robot to navigate in outdoor environment. In this paper, the development of the sensor fusion algorithm for controlling mobile robots in outdoor environments is presented. The multi-sensorial dead-reckoning subsystem is established based on the optimal filtering by first fusing a heading angle reading data from a magnetic compass, a rate-gyro, and two encoders mounted on the robot wheels, thereby computing the dead-reckoned location. These data and the position data provided by a global sensing system are fused together by means of an extended Kalman filter. The proposed algorithm is proved by simulation studies of controlling a mobile robot controlled by a backstepping controller and a cascaded controller. Performances of each controller are compared.

• Smart Structures and Systems
• /
• v.16 no.2
• /
• pp.295-328
• /
• 2015

In recent years the monitoring of structural behavior through acquisition of vibrational data has become common practice. In addition, recent advances in sensor development have made the collection of diverse dynamic information feasible. Other than the commonly collected acceleration information, Global Position System (GPS) receivers and non-contact, optical techniques have also allowed for the synchronous collection of highly accurate displacement data. The fusion of this heterogeneous information is crucial for the successful monitoring and control of structural systems especially when aiming at real-time estimation. This task is not a straightforward one as measurements are inevitably corrupted with some percentage of noise, often leading to imprecise estimation. Quite commonly, the presence of noise in acceleration signals results in drifting estimates of displacement states, as a result of numerical integration. In this study, a new approach based on a time domain identification method, namely the Unscented Kalman Filter (UKF), is proposed for correcting the "drift effect" in displacement or rotation estimates in an online manner, i.e., on the fly as data is attained. The method relies on the introduction of artificial white noise (WN) observations into the filter equations, which is shown to achieve an online correction of the drift issue, thus yielding highly accurate motion data. The proposed approach is demonstrated for two cases; firstly, the illustrative example of a single degree of freedom linear oscillator is examined, where availability of acceleration measurements is exclusively assumed. Secondly, a field inspired implementation is presented for the torsional identification of a tall tower structure, where acceleration measurements are obtained at a high sampling rate and non-collocated GPS displacement measurements are assumed available at a lower sampling rate. A multi-rate Kalman Filter is incorporated into the analysis in order to successfully fuse data sampled at different rates.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.16 no.3
• /
• pp.115-127
• /
• 2006

The purpose of this paper is evaluation of various normalization methods and fusion algorithms in addition to pattern classification algorithms for multi-biometric systems. Experiments are performed using various normalization functions, fusion algorithms and pattern classification algorithms based on Biometric Scores Set-Releasel(BSSR1) provided by NIST. The performance results are presented by Half Total Error Rate (WTER). This study gives base data for the study on performance enhancement of multiple-biometric system by showing performance results using single database and metrics.

• Smart Structures and Systems
• /
• v.6 no.9
• /
• pp.1025-1039
• /
• 2010

Measuring displacement response for civil structures is very important for assessing their performance, safety and integrity. Recently, video-based techniques that utilize low-cost high-resolution digital cameras have been developed for such an application. These techniques however have relatively low sampling frequency and the results are usually contaminated with noises. In this study, an integrated visual-inertial measurement method that combines a monocular videogrammetric displacement measurement technique and a collocated accelerometer is proposed for displacement and velocity measurement of civil engineering structures. The monocular videogrammetric technique extracts three-dimensional translation and rotation of a planar target from an image sequence recorded by one camera. The obtained displacement is then fused with acceleration measured from a collocated accelerometer using a multi-rate Kalman filter with smoothing technique. This data fusion not only can improve the accuracy and the frequency bandwidth of displacement measurement but also provide estimate for velocity. The proposed measurement technique is illustrated by a shake table test and a pedestrian bridge test. Results show that the fusion of displacement and acceleration can mitigate their respective limitations and produce more accurate displacement and velocity responses with a broader frequency bandwidth.

• Journal of Information Processing Systems
• /
• v.17 no.2
• /
• pp.411-425
• /
• 2021

In this paper, a vehicle recognition algorithm based on deep convolutional neural network and compression dictionary is proposed. Firstly, the network structure of fine vehicle recognition based on convolutional neural network is introduced. Then, a vehicle recognition system based on multi-scale pyramid convolutional neural network is constructed. The contribution of different networks to the recognition results is adjusted by the adaptive fusion method that adjusts the network according to the recognition accuracy of a single network. The proportion of output in the network output of the entire multiscale network. Then, the compressed dictionary learning and the data dimension reduction are carried out using the effective block structure method combined with very sparse random projection matrix, which solves the computational complexity caused by high-dimensional features and shortens the dictionary learning time. Finally, the sparse representation classification method is used to realize vehicle type recognition. The experimental results show that the detection effect of the proposed algorithm is stable in sunny, cloudy and rainy weather, and it has strong adaptability to typical application scenarios such as occlusion and blurring, with an average recognition rate of more than 95%.

• 제어로봇시스템학회:학술대회논문집
• /
• 2001.10a
• /
• pp.123.2-123
• /
• 2001

It is difficult to determine the feeding rate of coagulant in the water treatment plant, due to nonlinearity, multivariables and slow response characteristics, etc. To deal with this difficulty, the neuro-fuzzy system and the genetic-fuzzy system were used in determining the feeding rate of the coagulant. The fuzzy system is excellently robust in multi-variables and nonlinear problems. Therefore it uses basic algorithm, but it is difficult to construct of the fuzzy parameter such as the rule table and the membership function, Therefore we made the neuro-fuzzy system and the genetic-fuzzy system with the fusion of learning algorithms and compared the performance of the two fuzzy systems. To apply these algorithms, we made the rule table, membership function from the actual operation data of the water treatment plant. We determined optimized feeding rate of coagulant using the fuzzy operation, and also compared ...

• Smart Structures and Systems
• /
• v.17 no.4
• /
• pp.647-667
• /
• 2016

In this paper, dynamic displacement is estimated with high accuracy by blending high-sampling rate acceleration data with low-sampling rate displacement measurement using a two-stage Kalman estimator. In Stage 1, the two-stage Kalman estimator first approximates dynamic displacement. Then, the estimator in Stage 2 estimates a bias with high accuracy and refines the displacement estimate from Stage 1. In the previous Kalman filter based displacement techniques, the estimation accuracy can deteriorate due to (1) the discontinuities produced when the estimate is adjusted by displacement measurement and (2) slow convergence at the beginning of estimation. To resolve these drawbacks, the previous techniques adopt smoothing techniques, which involve additional future measurements in the estimation. However, the smoothing techniques require more computational time and resources and hamper real-time estimation. The proposed technique addresses the drawbacks of the previous techniques without smoothing. The performance of the proposed technique is verified under various dynamic loading, sampling rate and noise level conditions via a series of numerical simulations and experiments. Its performance is also compared with those of the existing Kalman filter based techniques.

• 제어로봇시스템학회:학술대회논문집
• /
• 2000.10a
• /
• pp.175-175
• /
• 2000

In this Paper we propose a navigation algorithm which can be used to estimate state vectors such as position and velocity for its motion control using multi-sensor output measurements. The output measurement we will use in estimating the state is a series of known multi-sensor asynchronous outputs with measurement noise. This paper investigates the Extended Kalman Filtering method to merge asynchronous heading, heading rate, velocity of DVL, and SSBL information to produce a single state vector. Different complexity of Kalman Filter, with biases and measurement noise, are investigated with theoretically data from KRISO's AUV. All levels of complexity of the Kalman Filters are shown to be much more close and smooth to real trajectories then the basic underwater acoustic navigation system comment)'used aboard underwater vehicle.