A5072565326- Robotics and Sensor-Based Localization
- 3D Surveying and Cultural Heritage
- Indoor and Outdoor Localization Technologies
- Advanced Image and Video Retrieval Techniques
- Advanced Vision and Imaging
- Photonic and Optical Devices
- Robotic Locomotion and Control
- Modular Robots and Swarm Intelligence
- Plasmonic and Surface Plasmon Research
- Robotic Path Planning Algorithms
- Superconducting and THz Device Technology
- Photonic Crystals and Applications
- Terahertz technology and applications
- Artificial Intelligence in Games
- Optical measurement and interference techniques
- Reinforcement Learning in Robotics
- Robotics and Automated Systems
- Gastrointestinal Bleeding Diagnosis and Treatment
- Winter Sports Injuries and Performance
- Sleep and Work-Related Fatigue
- Telecommunications and Broadcasting Technologies
- Image Processing Techniques and Applications
- Radio Frequency Integrated Circuit Design
- Diabetic Foot Ulcer Assessment and Management
- Human-Automation Interaction and Safety
Korea Advanced Institute of Science and Technology
2019-2023
Ulsan National Institute of Science and Technology
2014
Korea Communications Commission
2011
Dongguk University
2010
National University of Singapore
2007
In feature-based simultaneous localization and mapping (SLAM), line features complement the sparsity of point features, making it possible to map surrounding environment structure. Existing approaches utilizing have primarily employed a measurement model that uses re-projection. However, direction vectors used in 3D process cannot be corrected because employs only lines' normal Plücker coordinate. As result, problems like degeneracy occur during solved. To tackle problem, this letter...
In this paper, a degeneracy avoidance method for point and line based visual SLAM algorithm is proposed. Visual predominantly uses features. However, features lack robustness in low texture illuminance variant environments. Therefore, are used to compensate the weaknesses of addition, poor representing discernable naked eye, meaning mapped cannot be recognized. To overcome limitations above, were actively employed previous studies. since arises process using features, paper attempts solve...
Feature-based visual simultaneous localization and mapping (SLAM) methods only estimate the depth of extracted features, generating a sparse map. To solve this sparsity problem, completion tasks that dense from have gained significant importance in robotic applications like exploration. Existing methodologies use SLAM mainly employ point features. However, features limitations preserving structural regularities owing to texture-less environments problems. deal with these issues, we perform...
We theoretically investigate how to efficiently couple a photonic waveguide dielectric-loaded surface plasmon polariton (DLSPP) when they are based on common core material. The DLSPP is tapered and butt coupled the waveguide. First, we propose use of dielectric with higher refractive index than dielectrics previous waveguides. waveguides designed reduce loss tapering region length coupling, optimized. achieve coupling between 1.57 2.3 dB through 3- <formula formulatype="inline"...
Numerous numbers of research have been conducted in order to improve the excavation performance for deep and strong ground. However, as a result, equipment became bulky colossal size. In addition, excavated soil removal has become an issue existing drilling tools try compensate this by utilizing fluids. overcome these limitations, digging manner burrowing animals is investigated implemented. The key components are their teeth limbs, which also take huge role removing waste. proposed design,...
In commercial autonomous service robots with several form factors, simultaneous localization and mapping (SLAM) is an essential technology for providing proper services such as cleaning guidance. Such require SLAM algorithms suitable specific applications environments. Hence, frameworks have been proposed to address various requirements in the past decade. However, we encountered challenges implementing recent innovative when handling low-end processors insufficient sensor data,...
AI technologies have been a revolution for computer vision. With AlphaGo winning the Go game against human champion in 2016, people expected technology to be applied various games. In response these expectations, first world cup competition was held at KAIST last year. Like real soccer game, five robots each team play scoring higher goals winning. However, it is not human-to-computer like AlphaGo, but some intelligent algorithms plays according learned strategy. soccer, there are factors...
In this paper, WALK-VIO, a novel visual-inertial odometry (VIO) with walking-motion-adaptive leg kinematic constraints that change body motion for localization of quadruped robots, is proposed. Quadruped robots primarily use VIO because they require fast control and path planning. However, since are mainly used outdoors, extraneous features extracted from the sky or ground cause tracking failures. addition, robots' walking wobbling, which lowers accuracy due to camera inertial measurement...
정부조직에서는 성과관리제도의 법제화 이후 중앙부처에서부터 지방자치단체에 이르기까지 광범위하게 확산되어 가고 있다. 성과관리제도가 지방자치단체에서 성공적으로 정착하기위해서는 구성원들의 수용성을 제고하는 것이 선행되어야 한다. 따라서 본 연구에서는 지방자치단체의 수용성에 영향을 미치는 요인을 확인하고 정책대안을 모색하고자 하였다. 연구결과 수용성제고를 위해서는 공정한 제도의 마련과 충분한 제도에 대한 공감대 형성이 하며, 인식개선을 위해 체계적인 교육프로그램의 시행과 의견수렴장치의 마련이 요구된다. 또한 조직에 적합한 평가체계를 수립하고 객관적인 지표도출을 위한 매뉴얼 개발 등의 적극적인 노력이 필요하다. 마지막으로 연속성을 보장하고 비전중심의 성과관리제도로 변화하는 것 중요한 요인이다. Since legalization of performance management system in Korea Government, it has been very diffused...
Line information from urban structures can be exploited as an additional geometrical feature to achieve robust vision-based simultaneous localization and mapping (SLAM) systems in textureless scenes. Sometimes, however, conventional line tracking methods fail track caused by image blur or occlusion. Even though these lost features are just a subset of plenty features, the failure potentially lead performance degradation SLAM system, particularly environments. To tackle this problem, we...
The amount of texture can be rich or deficient depending on the objects and structures building. conventional mono visual-initial navigation system (VINS)-based localization techniques perform well in environments where stable features are guaranteed. However, their performance is not assured a changing indoor environment. As solution to this, we propose Adaptive Line point feature-based Visual Inertial Odometry (ALVIO) this paper. ALVIO actively exploits geometrical information lines that...