In the steel manufacturing process heat-endurance deterioration of a ladle used to cause a big accident. In this paper, an infrared imaging system and image analyzing procedure are proposed for inspecting refractory bricks of a ladle. The proposed algorithm contains following three parts: two-stage image selection procedure, reference point detection, and analysis of heat-endurance deterioration. Experiments were conducted with real data from a steel plant and detailed configuration of infrared imaging system was presented.

In this paper, we propose an LTBC (Low Tension and Load Balance Control) scheme to improve a coiling shape control by reduction the tension fluctuation by the torque disturbance in the down coiler process of hot strip mills. The proposed controller is a combination of an LTC to control the overload at load-on in the mandrel and an LBC to regulate the load balance of the upper and bottom pinch roll. A tension calculation model is suggested with the concept of the tension deviation. The effectiveness of the proposed control scheme is verified from simulation under a disturbance of the pinch roll torque. Using a field test, we show that the performance of the shape and tension control is improved by the LTBC control.

In this study, an embedded ranging system based on a laser structured light image is developed. The distance measurement by the structured light image processing has efficient computation because the burdensome correspondence problem is avoidable. In order to achieve robustness against environmental illumination noise and real-time laser structured light image processing, a bandpass optical filter is adopted in this study. The proposed ranging system has an embedded image processor performing the whole image processing and distance measurement, and so reduces the computational burden in the main control system. A system calibration algorithm is presented to compensate for the lens distortion.

This paper describes the implemenation of localization and visualization scheme to find out an ultrasonic source caused by defects of a power distribution line equipment. To increase the fault detection performance, $2{\times}4$ sensor array is configured with MEMS ultrasonic sensors, and from the sensor signals aquired, the azimuth and elevation angles of the ultrasonic source is estimated based on the delay-sum beam forming method. Also, to visualize the estimated location, it is marked on the background image. Experimental results show applicability of the present technique.

This paper addresses a new algorithm for a stereo visual odometry to measure the ego-motion of a vehicle. The new algorithm introduces an inlier grouping method based on Delaunay triangulation and vanishing point computation. Most visual odometry algorithms rely on RANSAC in choosing inliers. Those algorithms fluctuate largely in processing time between images and have different accuracy depending on the iteration number and the level of outliers. On the other hand, the new approach reduces the fluctuation in the processing time while providing accuracy corresponding to the RANSAC-based approaches.

Approximately 23% of traffic accidents appear to be caused by drowsiness while driving. This fact shows that drowsy driving is a big factor in many traffic accidents. Therefore, the development of a drowsiness checking system is necessary to prevent drowsy driving. In this paper, we analyse the changes of the histogram of eye region images which are acquired using a CCD camera. We develop a drowsiness checking system using this histogram change information. The experimental results show that our proposed method enhances the accuracy of checking drowsiness by nearly 98%, and can be used to prevent vehicle accidents due to the drowsiness of a driver.

This paper proposes a balancing and driving control system for a Mecanum wheel ball robot which has a two axis structure and four motors. The inverted pendulum control method is adopted to maintain the balance of the ball robot while it is driving. For the balancing control, an anon-model-based controller has been designed to control the device simply without the need of a complex formula. All the gains of the controller are heuristically adjusted during the experiments. The tilt angle is measured by IMU sensors, which is used to generate the control input of the roll and pitch controller to make the tilt angle zero. For the driving control, the PID control algorithm has been adopted with angles of the wheels and the encoder data. The performance of the designed control system has been verified through the real experiments with the suggested ball robot.

This paper presents a two-wheel balancing mobile robot with linear workspace extension structures. The two-wheel mobile robot has two linear motions at the waist and shoulder to have extended workspace. The linear motion of the waist and shoulder provides some structural advantages. A dynamic equation of the simplified robot system is derived. Simulation studies of the position control of the robot system are performed based on the dynamic equations. The dynamic relationship between a two-wheel mobile system and linear extension mechanism is observed by simulation studies.

Underwater robots generally show better performances for tasks than humans under certain underwater constraints such as. high pressure, limited light, etc. To properly diagnose in an underwater environment using remotely operated underwater vehicles, it is important to keep autonomously its own position and orientation in order to avoid additional control efforts. In this paper, we propose an efficient method to assist in the operation for the various disturbances of a remotely operated vehicle for the diagnosis of underwater structures. The conventional AHRS-based bearing estimation system did not work well due to incorrect measurements caused by the hard-iron effect when the robot is approaching a ferromagnetic structure. To overcome this drawback, we propose a sensor fusion algorithm with the camera and AHRS for estimating the pose of the ROV. However, the image information in the underwater environment is often unreliable and blurred by turbidity or suspended solids. Thus, we suggest an efficient method for fusing the vision sensor and the AHRS with a criterion which is the amount of blur in the image. To evaluate the amount of blur, we adopt two methods: one is the quantification of high frequency components using the power spectrum density analysis of 2D discrete Fourier transformed image, and the other is identifying the blur parameter based on cepstrum analysis. We evaluate the performance of the robustness of the visual odometry and blur estimation methods according to the change of light and distance. We verify that the blur estimation method based on cepstrum analysis shows a better performance through the experiments.

In this paper, we design and implement a mobile robot with variable structure for tip-over prevention. The mobile robot is designed for the purpose of stable drive and work in outdoor terrain. The outdoor terrain is rough and uneven. In this terrain, the tip-over of the mobile robot can occur while driving and working. Therefore, the structure of the mobile robot must be designed in consideration of stable drive and work. The proposed structure is defined as an X-shape for overall balance of the mobile robot. The shape is designed by using a multi-level structure for reducing the size of the robot. To verify the effectiveness of the proposed design, we analyze the tip-over characteristics according to the height of gravitational center and the extension length of the robot. Finally, we develop a prototype of the mobile robot with variable structure, taking the results of the tip-over analysis into consideration.

In this paper, we propose a novel surveillance throwing robot which is compact, light-weight and has an efficient shock absorption mechanism. The throwing robot is designed in a spherical shape to be easily grabbed by a hand for throwing. Also, a motor-wheel linking mechanism is designed to be robustly protected from shocks upon landing. The proposed robot has a weight of 2.2kg and the diameter of its wheels is 150 mm. Through the field experiments, the designed robot is validated to withstand higher than 13Ns of impulse.

In this paper, a novel localization method for a monocular camera is proposed by using a feature-based probabilistic map. The localization of a camera is generally estimated from 3D-to-2D correspondences between a 3D map and an image plane through the PnP algorithm. In the computer vision communities, an accurate 3D map is generated by optimization using a large number of image dataset for camera pose estimation. In robotics communities, a camera pose is estimated by probabilistic approaches with lack of feature. Thus, it needs an extra system because the camera system cannot estimate a full state of the robot pose. Therefore, we propose an accurate localization method for a monocular camera using a probabilistic approach in the case of an insufficient image dataset without any extra system. In our system, features from a probabilistic map are projected into an image plane using linear approximation. By minimizing Mahalanobis distance between the projected features from the probabilistic map and extracted features from a query image, the accurate pose of the monocular camera is estimated from an initial pose obtained by the PnP algorithm. The proposed algorithm is demonstrated through simulations in a 3D space.

In this paper, the consideration factors that affect the actual driving of a rover wheel was examined based on the wheel-terrain model. For the evaluation of driving performance in a real environment, the test bed of the rover wheel consists of the driving part of the wheel and sensing part of the various parameters was designed and assembled. Using the test bed, the preliminary driving experiment concerning the slip ratio, sinkage, and friction force according to the rotational velocity and the shape of the wheel were carried out and evaluated. The wheel test bed and the experiment results are expected to contribute to finding the optimal result in the designing of the wheel shape and the planning of the driving conditions through further study.

Indoor localization is becoming one of the most important technologies for smart mobile applications with different requirements from conventional outdoor location estimation algorithms. Fingerprinting location estimation techniques based on neural networks have gained increasing attention from academia due to their good generalization properties. In this paper, we propose a novel location estimation algorithm based on an ensemble of multiple neural networks. The neural network ensemble has drawn much attention in various areas where one neural network fails to resolve and classify the given data due to its' inaccuracy, incompleteness, and ambiguity. To the best of our knowledge, this work is the first to enhance the location estimation accuracy in indoor wireless environments based on a neural network ensemble using fingerprinting training data. To evaluate the effectiveness of our proposed location estimation method, we conduct the numerical experiments using the TGn channel model that was developed by the 802.11n task group for evaluating high capacity WLAN technologies in indoor environments with multiple transmit and multiple receive antennas. The numerical results show that the proposed method based on the NNE technique outperforms the conventional methods and achieves very accurate estimation results even in environments with a low number of APs.

Quay cranes are considered core equipment for container terminal operation. However, unmanned operation systems have not as yet been announced due to the technological difficulties of implementation. In this paper, we developed a wireless controller to control a quay crane simulator remotely and conducted its performance test, a first step toward unmanned operation of quay cranes. The communication delay of a developed wireless controller was about 9.4ms on average while that of existing wired controllers was about 5.6ms. The same functions were implemented and tested on a smart phone where the average communication delay was 7.3ms. In addition, to apply the developed system into a real environment, we proposed a network architecture based on IEEE 802.11ac and carried out its performance evaluation. When the distance between two nodes was 50m apart, the throughputs of the TCP (Transmission Control Protocol) and UDP (User Datagram Protocol) were 57Mbps and 189Mbps, respectively. The communication delay of the control data was 9.1ms through the TCP channel. These results reveal the proper working of remote quay crane operation if we adopt the IEEE 802.11ac network.