• Journal of Institute of Control, Robotics and Systems
• /
• v.19 no.2
• /
• pp.95-101
• /
• 2013

The paper investigates the geometric effect of landmarks to the navigation error in the landmark based 3D vision navigation and introduces the INS/Vision integrated navigation system considering its effect. The integrated system uses the vision navigation results taking into account the dilution of precision for landmark geometry. Also, the integrated system helps the vision navigation to consider it. An indirect filter with feedback structure is designed, in which the position and the attitude errors are measurements of the filter. Performance of the integrated system is evaluated through the computer simulations. Simulation results show that the proposed algorithm works well and that better performance can be expected when the error characteristics of vision navigation are considered.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.63 no.8
• /
• pp.1104-1110
• /
• 2014

This paper investigates geometric effect of landmarks on three-dimensional navigation error in landmark-based vision navigation systems. Dilution of precision is derived for landmark measurement error on the focal plane of the camera and separately expressed in position DOP and attitude DOP. Values of DOP are observed for various configurations of landmarks.

• Journal of Positioning, Navigation, and Timing
• /
• v.6 no.2
• /
• pp.59-70
• /
• 2017

Since GPS signals are vulnerable to interference and obstruction, many alternate aiding systems have been proposed to integrate with an inertial navigation system. Among these alternate systems, the vision-aided method has become more attractive due to its benefits in weight, cost and power consumption. This paper proposes a loosely-coupled vision/INS integrated navigation method which can work in GPS-denied environments. The proposed method improves the navigation accuracy by correcting INS navigation and sensor errors using position and attitude outputs of a landmark based vision navigation system. Furthermore, it has advantage to provide redundant navigation output regardless of INS output. Computer simulations and the van tests have been carried out in order to show validity of the proposed method. The results show that the proposed method works well and gives reliable navigation outputs with better performance.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.61 no.3
• /
• pp.479-484
• /
• 2012

Geometric effect of landmarks to the navigation error is investigated in the two-dimensional line-of-sight measurement based vision navigation system. DOP is derived between line-of-sight measurement error and navigation solution error. For cases of three landmarks in an area, variations of the DOP were observed through computer simulations. Vision navigation system experiments were performed for the cases. Simulation and experimental results show that navigation solution errors have similar trend to DOP values of the simulation.

• Journal of the Korean Society for Aeronautical & Space Sciences
• /
• v.45 no.8
• /
• pp.671-677
• /
• 2017

A new INS/Vision integrated navigation system by using multi-vision sensors is addressed in this paper. When the total number of landmark measured by the vision sensor is smaller than the allowable number, there is possibility that the navigation filter can diverge. To prevent this problem, multi-vision concept is applied to expend the field of view so that reliable number of landmarks are always guaranteed. In this work, the orientation of camera installed are 0, 120, and -120degree with respect to the body frame to improve the observability. Finally, the proposed technique is verified by using numerical simulation.

• KIPS Transactions on Software and Data Engineering
• /
• v.8 no.9
• /
• pp.379-390
• /
• 2019

In this paper, we propose a novel deep neural network model for Vision-and-Language Navigation (VLN) named LVLN (Landmark-based VLN). In addition to both visual features extracted from input images and linguistic features extracted from the natural language instructions, this model makes use of information about places and landmark objects detected from images. The model also applies a context-based attention mechanism in order to associate each entity mentioned in the instruction, the corresponding region of interest (ROI) in the image, and the corresponding place and landmark object detected from the image with each other. Moreover, in order to improve the success rate of arriving the target goal, the model adopts a progress monitor module for checking substantial approach to the target goal. Conducting experiments with the Matterport3D simulator and the Room-to-Room (R2R) benchmark dataset, we demonstrate high performance of the proposed model.

• Journal of Institute of Control, Robotics and Systems
• /
• v.16 no.4
• /
• pp.368-373
• /
• 2010

A new indoor mobile robot localization method is presented. Robot recognizes well designed single color landmarks on the ceiling by vision system, as reference to compute its precise position. The proposed likelihood prediction based method enables the robot to estimate its position based only on the orientation of landmark.The use of single color landmarks helps to reduce the complexity of the landmark structure and makes it easily detectable. Edge based optical flow is further used to compensate for some landmark recognition error. This technique is applicable for navigation in an unlimited sized indoor space. Prediction scheme and localization algorithm are proposed, and edge based optical flow and data fusing are presented. Experimental results show that the proposed method provides accurate estimation of the robot position with a localization error within a range of 5 cm and directional error less than 4 degrees.

• Journal of Institute of Control, Robotics and Systems
• /
• v.19 no.8
• /
• pp.667-675
• /
• 2013

This paper presents vision-based techniques for underwater landmark detection, map-based localization, and SLAM (Simultaneous Localization and Mapping) in structured underwater environments. A variety of underwater tasks require an underwater robot to be able to successfully perform autonomous navigation, but the available sensors for accurate localization are limited. A vision sensor among the available sensors is very useful for performing short range tasks, in spite of harsh underwater conditions including low visibility, noise, and large areas of featureless topography. To overcome these problems and to a utilize vision sensor for underwater localization, we propose a novel vision-based object detection technique to be applied to MCL (Monte Carlo Localization) and EKF (Extended Kalman Filter)-based SLAM algorithms. In the image processing step, a weighted correlation coefficient-based template matching and color-based image segmentation method are proposed to improve the conventional approach. In the localization step, in order to apply the landmark detection results to MCL and EKF-SLAM, dead-reckoning information and landmark detection results are used for prediction and update phases, respectively. The performance of the proposed technique is evaluated by experiments with an underwater robot platform in an indoor water tank and the results are discussed.

• Journal of the Korean Society of Industry Convergence
• /
• v.20 no.2
• /
• pp.89-95
• /
• 2017

In this paper, we suggest the method for a mobile robot to move safely from an initial position to a goal position in the wide environment like a building. There is a problem using odometry encoder sensor to estimate the position of a mobile robot in the wide environment like a building. Because of the phenomenon of wheel's slipping, a encoder sensor has the accumulated error of a sensor measurement as time. Therefore the error must be compensated with using other sensor. A vision sensor is used to compensate the position of a mobile robot as using the regularly attached light's panel on a building's ceiling. The method to create global path planning for a mobile robot model a building's map as a graph data type. Consequently, we can apply floyd's shortest path algorithm to find the path planning. The effectiveness of the method is verified through simulations and experiments.

• Journal of Institute of Control, Robotics and Systems
• /
• v.17 no.3
• /
• pp.206-210
• /
• 2011

Vision-based robot localization is challenging due to the vast amount of visual information available, requiring extensive storage and processing time. To deal with these challenges, we propose the use of features extracted from omni-directional panoramic images and present a method for localization of a mobile robot equipped with an omni-directional camera. The core of the proposed scheme may be summarized as follows : First, we utilize an omni-directional camera which can capture instantaneous $360^{\circ}$ panoramic images around a robot. Second, Nodes around the robot are extracted by the correlation coefficients of Circular Horizontal Line between the landmark and the current captured image. Third, the robot position is determined from the locations by the proposed correlation-based landmark image matching. To accelerate computations, we have assigned the node candidates using color information and the correlation values are calculated based on Fast Fourier Transforms. Experiments show that the proposed method is effective in global localization of mobile robots and robust to lighting variations.