• The Journal of Korea Robotics Society
• /
• v.17 no.2
• /
• pp.142-151
• /
• 2022

With the advent of the 4th industrial revolution, autonomous driving technology is being commercialized in various industries. However, research on autonomous driving so far has focused on platforms with wheel-type platform. Research on a tracked platform is at a relatively inadequate step. Since the tracked platform has a different driving and steering method from the wheel-type platform, the existing research cannot be applied as it is. Therefore, a path-tracking algorithm suitable for a tracked platform is required. In this paper, we studied a path-tracking algorithm for a tracked platform based on a GPS sensor. The existing Pure Pursuit algorithm was applied in consideration of the characteristics of the tracked platform. And to compensate for "Cutting Corner", which is a disadvantage of the existing Pure Pursuit algorithm, an algorithm that changes the LAD according to the curvature of the path was developed. In the existing pure pursuit algorithm that used a tracked platform to drive a path including a right-angle turn, the RMS path error in the straight section was 0.1034 m and the RMS error in the turning section was measured to be 0.2787 m. On the other hand, in the variable LAD algorithm, the RMS path error in the straight section was 0.0987 m, and the RMS path error in the turning section was measured to be 0.1396 m. In the turning section, the RMS path error was reduced by 48.8971%. The validity of the algorithm was verified by measuring the path error by tracking the path using a tracked robot platform.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2008.10a
• /
• pp.768-771
• /
• 2008

This paper presents an algorithm for generating inverse element over finite fields $GF(3^m)$, and constructing method of inverse element generator based on inverse element generating algorithm. The method need to compute inverse of an element eve. $GF(3^m)$ which corresponds to a polynomial eve. $GF(3^m)$ with order less than equal to m-1. Here, the computation is based on multiplication, square and cube method derived from the mathematics properties over finite fields.

• Proceedings of the Korean Operations and Management Science Society Conference
• /
• 2006.11a
• /
• pp.147-157
• /
• 2006

In this paper we consider alternate m machine scheduling problem in which each job having at most two eligible machines should be assigned with the objective of makespan minimization. For this problem, we propose a $O(m2^m)$ time rounding algorithm with performance ratio at most 1.5. For a little general problem where each job can be processed at most three machines, we prove that there cannot exist a polynomial time algorithm with performance ratio less than 1.5.

• Journal of Institute of Control, Robotics and Systems
• /
• v.9 no.1
• /
• pp.50-56
• /
• 2003

In electrical impedance tomography(EIT), various image reconstruction algorithms have been used in order to compute the internal resistivity distribution of the unknown object with its electric potential data at the boundary. Mathematically the EIT image reconstruction algorithm is a nonlinear ill-posed inverse problem. This paper presents a new combined method based on genetic algorithm(GA) and modified Newton-Raphson(mNR) algorithm via two-step approach for the solution of the static EIT inverse problem. In the first step, each mesh is classified into three mesh groups: target, background, and temporary groups. The mNR algorithm can be used to determine the region of group. In the second step, the values of these resistivities are determined using genetic algorithm. Computer simulations with the 32 channels synthetic data show that the spatial resolution of reconstructed images by the proposed scheme is improved compared to that of the mNR algorithm at the expense of increased computational burden.

• Proceedings of the IEEK Conference
• /
• 1998.10a
• /
• pp.731-734
• /
• 1998

A scalable parallel algorithm is proposed for efficient image component labeling with local operatos on a mesh connected SIMD computer. In contrast to the conventional parallel labeling algorithms, where a single pixel is assigned to each PE, the algorithm presented here is scalable and can assign m$\times$m pixel set to each PE according to the input image size. The assigned pixel set is converted to a single pixel that has representative value, and the amount of the required memory and processing time can be highly reduced. For N$\times$N image, if m$\times$m pixel set is assigned to each PE of P$\times$P mesh, where P=N/m, the time complexity due to the communication of each PE and the computation complexity are reduced to O(PlogP) bit operations and O(P) bit operations, respectively, which is 1/m of each of the conventional method. This method also diminishes the amount of memory in each PE to O(P), and can decrease the number of PE to O(P2) =Θ(N2/m2) as compared to O(N2) of conventional method. Because the proposed parallel labeling algorithm is scalable, we can adapt to the increase of image size without the hardware change of the given mesh connected SIMD computer.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.18 no.6
• /
• pp.681-691
• /
• 2017

In the clutter environment, it is necessary to update the target tracking filter by detecting the target signal among many measured value data obtained via the radar system, the track does not diverge, and tracking performance is maintained. The method of associating the measurement most relevant to the target track among numerous measurement values is referred to as data association. PSNF and PSNF-m are data association methods of SN-series. In this paper, we provide an IPSNF-m(Integrated Probabilistic Strongest Neighbor Filter-m) algorithm with a track management method based on the track existence probability in PSNF-m algorithm. This algorithm considers not only the presence of the target but also the case where the target is present but not detected. Calculating the probability of each caseenables efficient management. In order to verify the performance of the proposed IPSNF-m, the track existence probability of the IPSNF algorithm applying the track management technique to PSNF, which is known to have similar performance to PSNF-m, is derived. Through simulation in the same environment, we compare and analyze the proposed algorithm with RMSE, Confirmed True Track, and Track Existence Probability that show better performance in terms of track retention and estimation than the existing PSNF-m and IPSNF algorithms.

• Proceedings of the IEEK Conference
• /
• 2003.07c
• /
• pp.2617-2620
• /
• 2003

This paper presents the construction algorithm of the irreducible polynomial which needs to multiply over GF(2$\^$m/) and the flow chart representing the proposed algorithm has been proposed. And also, we get the degree from the value of xm＋k formation to the value of k = 7 using the proposed flow chart. The multiplier circuit has been implemented by using the proposed irreducible polynomial generation(IPG) algorithm in this paper, and we compared the proposed circuit with the conventional one. In the case of k = 7, one AND gate and five Ex-or gates are needed as the delay time for the irreducible polynomial in the proposed algorithm, but seven AND gates and sever Ex-or gates in the conventional one. As a result, the proposed algorithm shows the improved performance on the delay time.

• Journal of Korea Multimedia Society
• /
• v.16 no.11
• /
• pp.1338-1347
• /
• 2013

Face recognition is a science of automatically identifying individuals based their unique facial features. In order to avoid overfitting and reduce the computational reduce the computational burden, a new face recognition algorithm using PCA-fisher linear discriminant (PCA-FLD) and fuzzy radial basis function neural network (RBFNN) is proposed in this paper. First, face features are extracted by the principal component analysis (PCA) method. Then, the extracted features are further processed by the Fisher's linear discriminant technique to acquire lower-dimensional discriminant patterns, the processed features will be considered as the input of the fuzzy RBFNN. As a widely applied algorithm in fuzzy RBF neural network, BP learning algorithm has the low rate of convergence, therefore, an improved learning algorithm based on Levenberg-Marquart (L-M) for fuzzy RBF neural network is introduced in this paper, which combined the Gradient Descent algorithm with the Gauss-Newton algorithm. Experimental results on the ORL face database demonstrate that the proposed algorithm has satisfactory performance and high recognition rate.

• Journal of Auto-vehicle Safety Association
• /
• v.14 no.4
• /
• pp.6-15
• /
• 2022

In this study, a traffic light recognition algorithm was implemented and validated for low-speed special purpose vehicles in an urban environment. Real-time image data using a camera and YOLO algorithm were applied. Two methods were presented to increase the accuracy of the traffic light recognition algorithm, and it was confirmed that the second method had the higher accuracy according to the traffic light type. In addition, it was confirmed that the optimal YOLO algorithm was YOLO v5m, which has over 98% mAP values and higher efficiency. In the future, it is thought that the traffic light recognition algorithm can be used as a dual system to secure the platform safety in the traffic information error of C-ITS.

• 제어로봇시스템학회:학술대회논문집
• /
• 2004.08a
• /
• pp.444-447
• /
• 2004

A new approach to compute the control moves in Extended Dynamic Matrix Control (EDMC) is presented. In this approach, the number of variables, determined in the inner loop of the control algorithm using iterative methods, is reduced from P , the prediction horizon to M , the control horizon. Since M is usually much smaller than P , this modifies the control algorithm from computational point of view. To justify the modification, the computational requirements are compared to those of the existing EDMC algorithm.