This paper proposes an algorithm capable of extracting corresponding points between a pair of stereo images based on dynamic programming. The purpose of extracting the corresponding points is to provide the stereo disparity data to a road-slope estimation algorithm with high accuracy and in real-time. As the road-slope estimation algorithm does not require dense disparity data, the proposed stereo matching algorithm aims at extracting corresponding points accurately and quickly. In order to realize this contradictory goal, this paper exploits dynamic programming, and minimizes matching candidates using vertical components of color edges. Furthermore, the typical occlusion problem in stereo vision is solved. The proposed algorithm is proven to be effective through experiments with various images captured on the roads.

This paper presents a hierarchical trajectory planning method which can handle a collision-free of the planned path in complex and dynamic environments. A PV (Path & Velocity profile) planning method minimizes a sharp change of orientation and waiting time to avoid a collision with moving obstacle through detour path. The path generation problem is solved by three steps. In the first step, a smooth global path is generated using $A^*$ algorithm. The second step sets up the velocity profile for the optimization problem considering the maximum velocity and acceleration. In the third step, the velocity profile for obtaining the shortest path is optimized using the fuzzy and genetic algorithm. To show the validity and effectiveness of the proposed method, realistic simulations are performed.

The scale of wind turbines has continuously increased over the last decade. Especially, the rapid growth of the rotor diameter has brought about the increase of the tower height and the load on the rotor blade, as can be seen in the case of a 5MW class wind turbine with 126m rotor diameter. This trend means the increasing possibility of system failure. In addition to that, it is impossible for human operators to stay and manage all the turbines in the case of a large-scale wind farm. For these reasons, the operation and maintenance technology is getting more importance. In this paper, we present an unmanned remote monitoring system for MW class wind turbines and its application to YeungHeung wind test bed.

This paper suggests a judgement method for an inclined plane before entrance of it and the detection of obstacle position. Main idea is started from the assumption that obstacle is always on the bottom plane, and corner appears at this position. The process to detect the obstacle consists of three steps. First the 3D data using stereo matching is acquired to detect an obstacle. Second a bottom plane is extracted by using limit condition. Last the obstacle position is found by using Harris corner detection. Obstacle position detection on an inclined plane was verified by outdoor and indoor experiment. In error analysis, it is confirmed that an average error of obstacle detection in outdoor was larger than the error in indoor but the error are within about 0.030 m. This method will be applied to unmanned vehicles to navigate under various environment.

This paper presents a sensor fusion-based estimation of heading and a Bezier curve-based motion planning for unmanned ground vehicle. For the vehicle to drive itself autonomously and safely, it should estimate its pose with sufficient accuracy in reasonable processing time. The vehicle should also have a path planning algorithm that enables to adapt to various situations on the road, especially at intersections. First, we address a sensor fusion-based estimation of the heading of the vehicle. Based on extended Kalman filter, the algorithm estimates the heading using the GPS, IMU, and wheel encoders considering the reliability of each sensor measurement. Then, we propose a Bezier curve-based path planner that creates several number of path candidates which are described as Bezier curves with adaptive control points, and selects the best path among them that has the maximum probability of passing through waypoints or arriving at target points. Experiments under various outdoor conditions including at intersections, verify the reliability of our algorithm.

Recognition of structures in urban environments is a fundamental ability for unmanned ground vehicles. In this paper we propose the geometrical featured voxel which has not only 3-D coordinates but also the type of geometrical properties of point cloud. Instead of dealing with a huge amount of point cloud collected by range sensors in urban, the proposed voxel can efficiently represent and save 3-D urban structures without loss of geometrical properties. We also provide an urban structure classification algorithm by using the proposed voxel and machine learning techniques. The proposed method enables to recognize urban environments around unmanned ground vehicles quickly. In order to evaluate an ability of the proposed map representation and the urban structure classification algorithm, our vehicle equipped with the sensor system collected range data and pose data in campus and experimental results have been shown in this paper.

Environmental change, labor shortage, and international trade politics make agricultural automation ever more important. The automation demands the highest technology due to the nature of agriculture. In this paper, autonomous pesticide spray robot system has been developed for rose farming in the glass house. We developed drive platform, navigation/localization system, atomization spray system, autonomous, remote, and manual operation system, and monitoring system. The robot will be a great contribution to automation of hazardous labor-demanding chore of pesticide control in glass houses.

Fundamentally, there are 5 systems are needed for autonomous navigation of unmanned ground vehicle: Localization, environment perception, path planning, motion planning and vehicle control. Path planning and motion planning are accomplished based on result of the environment perception process. Thus, high reliability of localization and the environment perception will be a criterion that makes a judgment overall autonomous navigation. In this paper, via map matching using vehicle dynamic model and LIDAR sensors, replace high price localization system to new one, and have researched an algorithm that lead to robust autonomous navigation. Finally, all results are verified via actual unmanned ground vehicle tests.

This paper presents a dynamic workspace control method of underwater manipulator considering a floating ROV (Remotely Operated vehicle) motion caused by sea wave. This method is necessary for the underwater work required linear motion control of a manipulator's end-effector mounted on a floating ROV in undersea. In the proposed method, the motion of ROV is modeled as nonlinear first-order differential equation excluded dynamic elements. For online manipulator control achievement, we develop the position tracking method based on sensor data and EKF (Extended Kalman Filter) and the input velocity compensation method. The dynamic workspace control method is established by applying these methods to differential inverse kinematics solution. For verification of the proposed method, experimental data based test of ROV position tracking and simulation of the proposed control method are performed, which is based on the specification of the KORDI deep-sea ROV Hemire.

This UGV (Unmanned Ground Vehicle) is not only widely used in various practical applications but is also currently being researched in many disciplines. In particular, obstacle avoidance is considered one of the most important technologies in the navigation of an unmanned vehicle. In this paper, we introduce a simple algorithm for path planning in order to reach a destination while avoiding a polygonal-shaped static obstacle. To effectively avoid such an obstacle, a path planned near the obstacle is much shorter than a path planned far from the obstacle, on the condition that both paths guarantee that the robot will not collide with the obstacle. So, to generate a path near the obstacle, we have developed an algorithm that combines an edge detection method and a limit-cycle navigation method. The edge detection method, based on Hough Transform and IR sensors, finds an obstacle's edge, and the limit-cycle navigation method generates a path that is smooth enough to reach a detected obstacle's edge. And we proposed novel algorithm to solve local minima using the virtual wall in the local vision. Finally, we verify performances of the proposed algorithm through simulations and experiments.

The automation of production process is actively expanding for the purpose of the cost reduction and quality assurance. Among these, automatic tracking of the product along the whole process of the production is also important topic. Typically this is done by adopting OCR technology. Conventional OCR technology operates well on the rather good quality of the image like as printed characters on the paper. In industrial application, IDs are marked on the metal surface, and this cause the height difference between background material and character. Illumination systems that guarantee an image with good quality may be a solution, but it is rather difficult to design such an illumination system. This paper proposes an algorithm for the recognition of vehicle's ID characters using edge projection and PCA (Principal Component Analysis). Proposed algorithm robustly operates under illumination change using the same parameters. Experimental results show the feasibility of the proposed algorithm.

Some patients can't use their hands because of inherent and acquired paralysis of their fingers. Their fingers can recover with rehabilitative training, and the extent of rehabilitation can be judged by grasping a cylindrical-object with their fingers. At present, the cylindrical-object used in hospitals is only a cylinder which cannot measure grasping force of the fingers. Therefore, doctors must judge the extent of rehabilitation by watching patients' fingers as they grasp the cylinder. A cylindrical-type finger force measuring system which can measure the grasping force of patients' fingers should be developed. This paper looks at the development of a cylindrical-type finger force measuring system with two-axis force/moment sensor which can measure grasping force. The two-axis force/moment sensor was designed and fabricated, and the high-speed force measuring device was designed and manufactured by using DSP (digital signal processing). Also, cylindrical-type finger force measuring system was developed using the developed two-axis force/moment sensor and the high-speed force measuring device, and the grasping force tests of men were performed using the developed system. The tests confirm that the average finger forces of right and left hands for men were about 186N and 172N respectively.

In this paper, we present a two-stage vision-based approach to detect multi views of pedestrian in road scene images. The first stage is HG (Hypothesis Generation), in which potential pedestrian are hypothesized. During the hypothesis generation step, we use a vertical, horizontal edge map, and different colors between road background and pedestrian's clothes to determine the leg position of pedestrian, then a novel symmetry peaks processing is performed to define how many pedestrians is covered in one potential candidate region. Finally, the real candidate region where pedestrian exists will be constructed. The second stage is HV (Hypothesis Verification). In this stage, all hypotheses are verified by Support Vector Machine for classification, which is robust for multi views of pedestrian detection and recognition problems.

In this paper, we suggest a method for discretized frequency modulations of ultrasonic signals. A continuous sweep of frequency modulation signals can be modelled with fine levels of discretization. If the ultrasound signals are modulated with monotonically decreasing frequencies, then the cross-correlation between an emitted signal and received signal can be used to identify the distance of multiple target objects. For the discretized frequency synthesis, CF ultrasounds with different frequencies are serially ordered. The auto-correlation test with the signal shows effective results for distance estimation. The discretized frequency syntheses have better distance resolution than CF ultrasound signals and the resolution depends on the number of the combined ultrasound frequencies.

In this paper, we have developed an automatic velocity control system of a small-sized commercial treadmill (belt length of 1.2 m and width of 0.5 m) which is widely used at home and health centers. The control objective is to automatically adjust the treadmill velocity so that the subject's position is maintained within the track when the subject walks at a variable velocity. The subject's position with respect to a reference point is measured by a low-cost sonar sensor located on the back of the subject. Based on an encoder sensor measurement at the treadmill motor, a state feedback control algorithm with Kalman filter was implemented to determine the velocity of the treadmill. In order to reduce the unnatural inertia force felt by the subject, a predefined acceleration limit was applied, which generated smooth velocity trajectories. The experimental results demonstrate the effectiveness of the proposed method in providing successful velocity changes in response to variable velocity walking without causing significant inertia force to the subject. In the pilot study with three subjects, users could change their walking velocity easily and naturally with small deviations during slow, medium, and fast walking. The proposed automatic velocity control algorithm can potentially be applied to any locomotion interface in an economical way without having to use sophisticated and expensive sensors and larger treadmills.