Jae-Uk Shin

The displacement estimation error back-propagation (DEEP) method for a multiple structural displacement monitoring system

Visually servoed paired structured light system (ViSP) has been found to be useful in estimating 6-DOF relative displacement. The system is composed of two screens facing each other, each with one or two lasers, a 2-DOF manipulator and a camera. The displacement between two sides is estimated by observing positions of the projected laser beams and rotation angles of the manipulators. To apply the system to massive structures, the whole area should be partitioned and each ViSP module is placed in each partition in a cascaded manner. The estimated displacement between adjoining ViSPs is combined with the next partition so that the entire movement of the structure can be estimated. The multiple ViSPs, however, have a major problem that the error is propagated through the partitions. Therefore, a displacement estimation error back-propagation (DEEP) method which uses Newton–Raphson or gradient descent formulation inspired by the error back-propagation algorithm is proposed. In this method, the estimated displacement from the ViSP is updated using the error back-propagated from a fixed position. To validate the performance of the proposed method, various simulations and experiments have been performed. The results show that the proposed method significantly reduces the propagation error throughout the multiple modules.

Micro aerial vehicle type wall-climbing robot mechanism

Nowadays, as the building structures are getting taller and taller, the importance of maintenance or inspection of these structures is being increased. However, it has some problems due to the lack of professional manpower and there is a risk in maintaining those areas that are hard to reach, besides the high maintenance cost. The unmanned wall-climbing robots for the areas hard to reach have been researched to solve the problems. The infrastructure-based wall-climbing robots have high payload and safety but the robots need the infrastructure that should be installed on the target structure. The infrastructure is not preferred by the architects since it can be harmful to the exterior of the structure. For this reason, wall-climbing robots that do not need any infrastructure are being researched. Nevertheless, most of the non-infrastructure-based wall-climbing robots are in the laboratory level since the payload, safety and maneuverability are not satisfactory. To overcome these problems, a flight-possible wall-climbing robot mechanism is proposed in this paper. The robot is based on the quadrotor system that is a well-known aerial vehicle using four rotors. It uses thrust forces induced by the four rotors not only to fly but also to stick on the wall. The flight capability makes its maneuverability and safety greatly enhanced. The feasibility of the mechanism is shown through simulations and experiments with a prototype.

Experimental Tests of Autonomous Jellyfish Removal Robot System JEROS

Recently, the increase in population of jellyfish is becoming a great menace to the oceans ecosystem, which leads to drastic damage to the fishery industries. To overcome this problem, a jellyfish removal system with trawl boats equipped with the jellyfish removal net has been suggested by NFRDI. However, the system needs large ships which need to be operated by a lot of human operators. Thus, this paper represents the design and implementation of an autonomous jellyfish removal robot system, called JEROS. The JEROS consists of an autonomous surface vehicle (ASV), a grid for jellyfish removal, and an autonomous navigation system. Once jellyfish are detected using a camera, the jellyfish removal scenario is started with generating efficient path to remove the jellyfish. Finally, the jellyfish is sliced up with the grid installed underneath the JEROS by following the generated path. The prototype of the system was implemented, and its feasibility was demonstrated through outdoor experiments and field tests.

Experimental Validation of Visually Servoed Paired Structured Light System (ViSP) for Structural Displacement Monitoring

Structural displacement is considered an important indicator to assess structural conditions. To directly measure the displacement in the time domain, a visually servoed paired structured light system was proposed. The system is composed of two sides facing each other, each with one or two lasers that are controlled by a visually servoed two-DOF manipulator, a camera, and a screen. The relative six-DOF displacement between the two sides can be estimated by calculating the positions of the projected laser beams on the screens and the rotation angles of manipulators. To verify the performance of the proposed system, two kinds of field tests were carried out. A prototype of the system was built and installed on a steel frame building structure and a railway bridge, respectively. The estimated displacements were compared with the reconstructed displacement from an accelerometer. The test results verify the performance of the system and its applicability to real structures.

Micro-aerial vehicle type wall-climbing robot mechanism for structural health monitoring

Currently, the maintenance or inspection of large structures is labor-intensive, so it has a problem of the large cost due to the staffing professionals and the risk for hard to reach areas. To solve the problem, the needs of wall-climbing robot are emerged. Infra-based wall-climbing robots to maintain an outer wall of building have high payload and safety. However, the infrastructure for the robot must be equipped on the target structure and the infrastructure isn’t preferred by the architects since it can injure the exterior of the structure. These are the reasons of why the infra-based wall-climbing robot is avoided. In case of the non-infra-based wall-climbing robot, it is researched to overcome the aforementioned problems. However, most of the technologies are in the laboratory level since the payload, safety and maneuverability are not satisfactory. For this reason, aerial vehicle type wall-climbing robot is researched. It is a flying possible wallclimbing robot based on a quadrotor. It is a famous aerial vehicle robot using four rotors to make a thrust for flying. This wall-climbing robot can stick to a vertical wall using the thrust. After sticking to the wall, it can move with four wheels installed on the robot. As a result, it has high maneuverability and safety since it can restore the position to the wall even if it is detached from the wall by unexpected disturbance while climbing the wall. The feasibility of the main concept was verified through simulations and experiments using a prototype.

Development of jellyfish removal robot system JEROS

This paper represents a novel autonomous jellyfish removal robot system, called JEROS (Jellyfish Elimination RObotic Swarm). The JEROS consists of an autonomous surface vehicle (ASV), a grid for jellyfish removal, and an autonomous navigation system. Once jellyfish are detected using a camera, efficient path to remove the jellyfish is generated. Then, the jellyfish are sliced up with the grid installed underneath the JEROS by following the path. The prototype was implemented, and its feasibility was demonstrated through field tests.

Mechanism and system design of MAV(Micro Aerial Vehicle)-type wall-climbing robot for inspection of wind blades and non-flat surfaces

Wind turbines need annual inspections to investigate their states which may have damages, such as cracks, erosion, bonding defects, cavities and delamination. Wind blades inspection, however, is a difficult process which needs specialized equipment and well-trained technicians to perform it manually. In addition, most approaches to inspect require pre-installed infrastructures like ropes or other platforms, so they are not appropriate for a close investigation and has a low preference. To overcome these problems, the need for a wall-climbing robot has emerged. In this paper, we suggest a MAV (Micro Aerial Vehicle) type wall-climbing robot that has four rotors to make thrust force for flying and four wheels for wall-climbing so that it can fly, stick, and move on a vertical and non-flat surface. The overall inspection process has two parts; macro and micro inspections. The main concept was verified throughout simulations.

Path Planning for Multi-agent Jellyfish Removal Robot System JEROS and Experimental Tests

Over the recent years, the increasing influence of climate change has given rise to an uncontrolled proliferation of jellyfish in marine habitats, which has visibly damaged many ecosystems, industries, and human health. To resolve this issue, our team developed a robotic system to successfully and efficiently remove jellyfishes, named JEROS (Jellyfish Elimination RObotic Swarm). The JEROS consists of multiple USVs (Unmanned Surface Vehicles) that freely move in a marine environment to scavenge for and eliminate jellyfishes. In this paper, we propose a constrained formation control algorithm that enhances the efficiency of jellyfish removal. Our formation control algorithm is designed in consideration of the characteristic features of JEROS. It is designed to effectively work with the simple leader-follower algorithm. The leader-follower formation control does not work well if a reference path of the leader is generated without considering a minimum turning radius. In order to overcome such a limitation, a new path planning method—angular rate-constrained path planning—is proposed in this paper. The performance of the jellyfish removal function was tested at Masan Bay in the Southern coast of South Korea and formation control tests were conducted at Bang-dong Reservoir in Daejeon, South Korea.

Image-Based Monitoring of Jellyfish Using Deep Learning Architecture

Jellyfish blooms have caused great damage to the fishery industry. In efforts to solve this problem, various systems to remove jellyfish have been proposed. This letter presents preliminary results of applying an image-based jellyfish distribution recognition algorithm to increase the efficiency of an existing jellyfish removal system. By using a convolutional neural network and dedicated image processing techniques, the experimental results show reasonable performance for real-world application.

Dynamics Analysis and Controller Design of a Quadrotor-based Wall-climbing Robot for Structural Health Monitoring

The modern situation that infrastructures are getting taller and massive makes the maintenance or inspection of large vertical structures more important; nevertheless, the lack of professional manpower, the high cost due to labor-intensive tasks, and high risk of the areas that are hard to reach are problems. There have been many attempts to solve the problems with a wall-climbing robot. As a result, various robots are researched and tested but most of the robots are not practical in the real field. In the previous study, the wall-climbing robots were classified into two types; an infrastructure-based wall-climbing robot and a non-infrastructure-based wall-climbing robot. The first one is not preferred by the architects due to the necessity of the infrastructures installed in a building and the size that is too huge to carry it to another building, even though it has high payload and safety. The second one needs no infrastructures, but most of the robots are laboratory level owing to a danger of falling or limited maneuverability. In the previous research, to supplement the weakness, a quadrotor-based wall-climbing robot mechanism was proposed, and the feasibility was verified through simple simulations and experiments. Through the quadrotor-based mechanism, the robot is not only possible to fly but also can stick on the vertical wall using just only four thrust forces. It makes the maneuverability of the wall-climbing robot extremely enhanced. In this paper, more advanced and additional researches are conducted. The dynamics of the robot is analyzed when it is in flying state or pose transformation state, and then the controllers are designed based on the dynamics. Especially, a pose transformation controller is designed to avoid the slipping and falling accidents when the robot transforms the pose from flying mode to stick mode. Similar to the previous work, the feasibility is verified through the simulations and tests. As a result, it is shown that the proposed robot can be used for the structural health monitoring with some additional equipment such as a camera. doi: 10.12783/SHM2015/161