Youngsu Park

Improving position estimation on RFID tag floor localization using RFID reader transmission power control

Localization of indoor mobile robot is one of main issues on service robot area. Various sensor systems like odometry, INS, ultra sonic, laser lange finder (LRF), RF range systems such as UWB and chirp spread-spectrum (CSS), and vision have been applied to solve localization problem. RFID system can be a solution due to the low cost and scalability. A RFID system used to localize mobile robot in distributed tags on the floor is called RFID Tag floor localization system. RFID tag floor localization system generally uses fixed tag recognition range or probability model. In this paper, RFID reader transmission power control is introduced to change the tag recognition range to get more information about distances of tags. Using RFID power control, the performance of a position estimation was improved in simulation. The experimental results also showed improvement.

Development of Real-time Defect Detection Algorithm for High-speed Steel Bar in Coil(BIC)

In steel manufacturing industry, as many advanced technologies increase manufacturing speed, fast and exact products inspection gets more important. This paper deals with a real-time defect detection algorithm for high-speed steel bar in coil (BIC). To get good performance, this algorithm has to solve several difficult problems such as cylindrical shape of a BIC, influence of light, many kinds of defects. Additionally, it should process quickly the large volumes of image for real-time processing since a steel bar moves at high speed. Therefore defect detection algorithm should satisfy two conflicting requirements of reducing the processing time and improving the efficiency of defect detection. This paper proposes an effective real-time defect detection algorithm that can solve above problems. And the algorithm is implemented by a high speed image processing system and will be applied to a practical manufacturing line. Finally, the performance of the proposed algorithm is demonstrated by experiment results

On-Load Motor Parameter Identification Using Univariate Dynamic Encoding Algorithm for Searches

Parameter identification of an induction motor has long been studied either for vector control or fault diagnosis. This paper addresses parameter identification of an induction motor under on-load operation. For estimating electrical and mechanical parameters in the motor model from the on-load data, unmeasured initial states and load torque profile have to be also estimated for state evaluation. Since gradient of cost function for the auxiliary variables are hard to be derived, direct optimization methods that rely on computational capability should be employed. In this paper, the univariate dynamic encoding algorithm for searches (uDEAS), recently developed by the authors, is applied to the identification of whole unknown variables with measured voltage, current, and velocity data. Profiles of motor parameters estimated with uDEAS are reasonable, and estimation time is 2 s on average, which is quite fast as compared with other direct optimization methods.

Mathematical formulation of RFID tag floor based localization and performance analysis for tag placement

A radio-frequency identification (RFID) tag floor based localization is recently proposed indoor mobile robot localization method that utilizes super-distributed RFID tag infrastructure (SDRI) installed on a working area. An RFID tag floor localization (RTFL) method is easy to scale up the working area and the number of robots and is reliable in the position estimation. There have been several researches for practical applications of the RTFL, however, the investigation on performance and properties of the localization method is still insufficient. This paper propose a mathematical formulations of the RTFL and its performance index based on an RFID position estimation error variance. This paper also presents simulation results of the RTFL performances and analysis. These results can be used for optimal installation of the RFID tag floor.

Vision-based AGV Parking System

This paper proposes an efficient method to locate the automated guided vehicle (AGV) into a specific parking position using artificial visual landmark and vision-based algorithm. The landmark has comer features and a HSI color arrangement for robustness against illuminant variation. The landmark is attached to left of a parking spot under a crane. For parking, an AGV detects the landmark with CCD camera fixed to the AGV using Harris comer detector and matching descriptors of the comer features. After detecting the landmark, the AGV tracks the landmark using pyramidal Lucas-Kanade feature tracker and a refinement process. Then, the AGV decreases its speed and aligns its longitudinal position with the center of the landmark. The experiments showed the AGV parked accurately at the parking spot with small standard deviation of error under bright illumination and dark illumination.

AGV parking system using artificial visual landmark

This paper proposes an efficient method to locate the automated guided vehicle (AGV) into the parking position using artificial visual landmark. For automated transshipment system in container terminals, the port AGV is used to transport containers autonomously and efficiently. To co-operate with the transfer crane, accurate guiding and positioning system is required. Using computer vision algorithms that detect and track the object from the video streams, we extract the exact position and relative distance with respect to the parking position. The artificial landmark is designed for effective detection based on corner feature and color information. After detection phase finds the position of the landmark in the captured image, tracking phase follows the trace of the landmark in the successive image sequences. Tracking phase consists of two stages, estimation and refinement steps. Optical flow vector around the detected point in the current image is calculated by pyramidal Lucas-Kanade feature tracker, and it is used to estimate the current position of the landmark. Then, the refinement step uses some features of the landmark as references to correct the estimated position of the object. Whole process is performed in HSI color space so that the system can be robust to illuminant variation. Experiments show reliable results of parking movement of the AGV. Our approach is simple, effective and robust.

Support Vector Machine Parameter tuning using Dynamic Encoding algorithm for handwritten digit recognition

In this paper, we propose a support vector machine parameter tuning algorithm using dynamic encoding algorithm for handwritten digit recognition. This method uses dynamic encoding algorithm for search (DEAS) which is recently proposed optimization algorithm based on variable binary encoding length. The radius/margin bound is used for the estimation of the support vector machine generalization performance. When the radius/margin bound is not convex form or different from real error rate for test data set, n-poled validation error rate can be used for parameter tuning. The proposed method can be applied to the case which is hard to find gradient information of radius/margin bound. Moreover, the proposed method is a more efficient algorithm compared with GA algorithm and grid search in computation time

Improving Position Estimation of the RFID Tag Floor Localization with Multiple Recognition Ranges

This chapter introduces the RFID tag floor localization method with multiple recognition ranges and its mathematical formulation to improve position estimation accuracy. Using the multiple recognition ranges of RFID reader, the reader can obtain more information about the distances to the tags on the tag floor. The information is used to improve the position estimation performance. At first, this chapter reviews the RFID tag floor localization methodwith single recognition range formobile robots(Park et al., 2010) and The performance measure based on the position estimation error variance for the localization method. For the second, this paper extends the mathematical formulation of the localization method and the performance measure for the case of multiple recognition ranges. This work is related to the previous work(Park et al., 2009) that used multiple powers to improve position estimation performance. However, previous work lacks analysis and mathematical formulation of general RFID tag recognition models. We extend the mathematical formulation and the analysis of the single recognition range RFID tag floor localizationmethod (Park et al., 2010) to the multiple recognition range case. Then the minimum error variance of multiple recognition range is introduced as a lower bound of position estimation error variance. Finally, it presents performance improvement of proposed localization method via the Monte-Carlo simulation and simple experiments. The analysis for the simulation and experimental results and the consideration for real application will be given. This chapter is organized as follows; This section discusses sensor systems used in the mobile robot localization. Then the advantages of the RFID systems as sensor systems for localization are discussed and the researches on the systems are reviewed. Section 2 introduces the RFID tag floor localization, its mathematical formulation and its performance index. Section 3 represents the motivation of introducing the use of multiple recognition ranges for the RFID tag floor localizationmethod, and extend themathematical formulation and the error variance for the multiple recognition range case. Section 4 conducts the Monte-Carlo simulation to show the improvement of the position estimation performance when the multiple recognition range is used. Section 5 represents experimental results that support the simulation results. In Section 6, the minimum error variance(Park et al., 2010) as a lower bound of error variance is extended to the multiple recognition range case. Section 7 gives the conclusions, discussions and tasks for the further researches. Youngsu Park, Je Won Lee, Daehyun Kim, Sang-woo Kim Electronic and Electric Engineering department, POSTECH Korea, South Improving Position Estimation of the RFID Tag Floor Localization with Multiple Recognition Ranges 10

Model-based iterative position estimation algorithm for RFID tag floor localization

The RFID tag floor localization method is one of the recently proposed localization methods for mobile platforms based on the RFID system. The method utilizes an RFID tag grid on a work area and RFID readers under the mobile platforms for localization. There have been several researches to improve the accuracy of the position estimation from the information of detected tags. However, the accuracy of position estimation is limited by the density of the RFID tag grid. However, with the recognition model of tags and readers, the position estimation accuracy can be improved more. For instance, localization of RFID tags with virtual reference tags (L-VIRT) algorithm utilizes model information to improve the position estimation accuracy, but it requires numerous model evaluations for localization. This paper proposes a more accurate and efficient model-based iterative localization algorithm for the RFID tag floor localization. The performance improvement is verified by simulations.

AGV parking system based on tracking landmark

This paper presents an efficient method that locates the automated guided vehicle (AGV) into a specific position using vision-based system. For an automated transshipment system in the container terminal, it is necessary for the AGV to recognize the current position of the transfer crane, so that the port AGV locates itself into the working area of the crane. Using an artificially designed landmark attached on the crane, the vehicle detects and tracks the position of the landmark from the video stream through CCD camera fixed to the vehicle. The AGV calculates its position from the position of landmark in the image and control the velocity to align with the crane. The detection method is based on the local features of the landmark such as edges, corners, and color information. After detecting the landmark the vehicle tracks the trace of the target using Condensation algorithm and refinement stage. Detecting and tracking steps are performed in HSI color space to reduce the effect of illumination. Experiment shows reasonable results.