• Corrosion Science and Technology
• /
• 제18권6호
• /
• pp.253-257
• /
• 2019

A deep learning based real-time painting surface inspection algorithm is proposed herein, designed for developing an autonomous inspection drone. The painting surface inspection is usually conducted manually. However, the manual inspection has a limitation in obtaining accurate data for correct judgement on the surface because of human error and deviation of individual inspection experiences. The best method to replace manual surface inspection is the vision-based inspection method with a camera, using various image processing algorithms. Nevertheless, the visual inspection is difficult to apply to surface inspection due to diverse appearances of material, hue, and lightning effects. To overcome technical limitations, a deep learning-based pattern recognition algorithm is proposed, which is specialized for painting surface inspections. The proposed algorithm functions in real time on the embedded board mounted on an autonomous inspection drone. The inspection results data are stored in the database and used for training the deep learning algorithm to improve performance. The various experiments for pre-inspection of painting processes are performed to verify real-time performance of the proposed deep learning algorithm.

• 전자공학회논문지SC
• /
• 제45권6호
• /
• pp.10-15
• /
• 2008

무인차량의 자율주행성능을 예측하고 분석하기 위해서는 실 환경에서 다양한 주행시험을 수행하여야 한다. 하지만, 무인체계의 특성상 시험안전성과 재현성, 다양한 시험환경의 인위적 제공의 어려움 등 많은 제약이 있다. 따라서, 본 논문에서는 실차량에 적용전에 자율주행성능을 분석하기위한 가상시험환경을 구축하고 감지센서신호를 모의하는 기법을 제안하였다. 또한, 제안된 기법의 타당성을 보이기위해 새롭게 개발된 자율주행 알고리즘에 대한 가상환경 및 센서 모델을 이용한 시뮬레이션을 수행한 결과 그 타당성을 입증하였다.

• 한국중재학회지:중재연구
• /
• 제31권4호
• /
• pp.119-136
• /
• 2021

Due to the restriction of movement caused by the Corona epidemic and the expansion of the "big face" through human distance, the "unmanned system" based on artificial intelligence and the Internet of Things has been widely used in modern life. "Self-driving," one of the transportation systems based on artificial technology, has taken the initiative in the transportation system as the spread of Corona has begun. Self-driving technology eliminates unnecessary contact and saves time and manpower, which can significantly impact current and future transportation. Accidents may occur, however, due to the performance of self-driving technology during transportation albeit the U.S. allows ordinary people to drive automatically through experimental operations, and the product liability law will resolve the dispute. Self-driving has become popular in the U.S. after the experimental stage, and in the event of a self-driving accident, product liability should be applied to protect drivers from complicated self-driving disputes. The purpose of this paper is to investigate whether disputes caused by defects in ordinary cars can be resolved through arbitration through U.S. precedents and to investigate whether disputes caused by defects in autonomous cars can be arbitrated.

• 한국군사과학기술학회지
• /
• 제18권3호
• /
• pp.226-233
• /
• 2015

Pose estimation is an important operation for many vision tasks. This paper presents a method of estimating the camera pose, using a known landmark for the purpose of autonomous vertical takeoff and landing(VTOL) unmanned aerial vehicle(UAV) landing. The proposed method uses a distinctive methodology to solve the pose estimation problem. We propose to combine extrinsic parameters from known and unknown 3-D(three-dimensional) feature points, and inertial estimation of camera 6-DOF(Degree Of Freedom) into one linear inhomogeneous equation. This allows us to use singular value decomposition(SVD) to neatly solve the given optimization problem. We present experimental results that demonstrate the ability of the proposed method to estimate camera 6DOF with the ease of implementation.

• Journal of Positioning, Navigation, and Timing
• /
• 제4권2호
• /
• pp.57-65
• /
• 2015

Global Navigation Satellite System (GNSS) including Global Positioning System (GPS) is an important element for navigation of both the military and civil Unmanned Aerial Vehicle (UAV). Contrary to the military UAVs, the civil UAVs use the civil signals which are unencrypted, unauthenticated and predictable. Therefore if the civil signals are counterfeited, the civil UAV’s position can be manipulated and the appropriate movement of the civil UAV to the target point is not achieved. In this paper, spoofing on the autonomous navigation UAV is implemented through field experiments. Although the demanded conditions for appropriate spoofing attack exists, satisfying the conditions is restricted in real environments. So, the Way-point of the UAV is assumed to be known for experiments and assessments. Under the circumstances, GPS spoofing signal is generated based on the Software-based GNSS signal generator. The signal is emitted to the target UAV using the antenna of the spoofer and the effect of the signal is analyzed and evaluated. In conclusion, taking the UAV to the target point is hardly feasible. To implement the spoofing as expectation, the position and guidance system of the UAV has to be known. Additionally, the GPS receiver on the UAV could be checked whether it appropriately tracks the spoofing signal or not. However, the effect of the spoofing signal on the autonomous UAV has been verified and assessed through the experimental results. Spoofing signal affects the navigation system of the UAV so that the UAV goes off course or shows an abnormal operation.

• 대한조선학회논문집
• /
• 제59권4호
• /
• pp.214-224
• /
• 2022

It is necessary to estimate manoeuvring characteristics of submerged bodies at the design stage in order to ensure the safe operations. In this study, added mass coefficients in the mathematical model of submerged bodies are estimated by captive model tests and numerical calculations. Two kinds of models, MARIN 'BB2'submarine model and AUV (Autonomous unmanned vehicle) model are utilized in the forced oscillation tests. Compared to BB2 submarine, AUV with cylindrical type hull form shows relatively small added masses in roll, pitch, and yaw directions. Next, numerical calculations based on potential theory are performed under the assumption that viscous effects on inertia forces are negligible. Added masses obtained by numerical calculations are in good agreements with forced oscillation test results. And if slow manoeuvres of submerged bodies are presumed, some of velocity coupled terms can be approximated by combinations of added mass coefficients.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제12권2호
• /
• pp.829-842
• /
• 2018

Unmanned Aerial Vehicle (UAV) is diversely utilized in our lives such as daily hobbies, specialized video image taking and disaster prevention activities. New ways of UAV application have been explored recently such as UAV-based delivery. However, most UAV systems are being utilized in a passive form such as real-time video image monitoring, filmed image ground analysis and storage. For more proactive UAV utilization, there should be higher-performance UAV and large-capacity memory than those presently utilized. Against this backdrop, this study described the general matters on proactive software platform and high-performance UAV hardware for real-time target tracking; implemented research on its design and implementation, and described its implementation method. Moreover, in its established platform, this study measured and analyzed the core-specific CPU consumption.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2002년도 ICCAS
• /
• pp.109.5-109
• /
• 2002

Autonomous underwater vehicles (AUVs) are unmanned underwater vessels to investigate sea environments, oceanography and deep-sea resources autonomously. Docking systems are required to increase the capability of the AUVs to recharge the batteries and to transmit data in real time in underwater. This paper presents a visual servo control system for an AUV to dock into an underwater station with a camera. To make the visual servo control system , this paper derives an optical flow model of a camera mounted on an AUV, where a CCD camera is installed at the nose center of the AUV to monitor the docking condition. This paper combines the optical flow equation of the camera with the AUV's equation o...

• 한국마린엔지니어링학회:학술대회논문집
• /
• 한국마린엔지니어링학회 2012년도 전기공동학술대회 논문집
• /
• pp.214-214
• /
• 2012

본 논문 만타형 무인잠수정을 이용한 실해역 자율주행 성능시험에 관한 내용을 다룬다. 만타형의 개발을 위해서 6자유도 운동방정식에 대한 시뮬레이션을 실시하였으며, 시뮬레이션 결과를 바탕으로 만타형 무인잠수정을 개발하여 실해역에서 성능시험을 실시하였다. 실해역 자율주행 시험은 가시선 방법(LOS, Line of Sight)방법을 이용하였으며, 제어에는 PD 제어기를 사용하였다. 목표반경을 10m로 하였을 때, 설정된 좌표로 이동하는 것을 확인하였다.

• International Journal of Internet, Broadcasting and Communication
• /
• 제14권1호
• /
• pp.209-218
• /
• 2022

Today, with the development of the Internet and mobile technology, consumers' purchasing patterns have shifted from offline to online. In addition, due to the recent COVID-19, online purchases have significantly increased, and accordingly, the courier industry for logistics delivery has also grown significantly. Various logistics robots are being operated in many industrial and can reduce the labor intensity and physical and mental fatigue of workers. However, if the logistics robot does not properly recognize the people or environment around it, it can lead to a serious accident. We conducted that how logistics robots can perform safe work in a working environment such as a logistics warehouse through the application of ISO/DIS 21448 (SOTIF) to autonomous logistics transport robots. This result is expected to contribute to the operation of unmanned logistics warehouses using AGV.