본 연구에서는 단안 카메라를 통한 실시간 차선 검출과 딥 러닝 네트워크를 기반으로 하는 객체 검출 및 거리 추정 시스템을 제안한다. 단안 카메라를 통해 취득한 이미지의 원근감을 제거한 뒤 Sliding Windows 기법을 이용해 차선에 해당하는 후보군을 선정하고, RANSAC 기법을 통해 차선을 검출한다. 객체 검출의 경우 기존의 Computer Vision 알고리즘보다 검출률이 높고 주변 환경 변화에 강인한 딥 러닝을 이용한다. 또한, 타 센서로부터 취득한 거리 데이터를 기반으로 단안 카메라에서 검출된 객체의 Bounding Box Pixel 값과 실제 거리 정보의 관계를 이용하여 수식을 세우고, 이를 통해 객체와 차량의 거리를 추정한다. 그리고 자율주행 차량의 안정적인 주행을 위해 종·횡 방향 제어를 한다. 그리고 차선유지 및 전방 객체와의 거리에 따른 위험도 판별을 긴급제동(Auto Emergency Braking) 실험을 통해 제안한 시스템의 성능을 검증한다.
Transparency in electronics can provide extra functionality and esthetic impression. Transparency plays an important role in accurate soft robot control because one can directly observe target surface condition that is usually blocked by a robot's body. Nowadays, demand for soft actuators has been rapidly increasing because soft robots have attracted much attention recently. However, conventional soft actuators are usually nontransparent with simple isotropic bending, limited performance, and limited functionality. To overcome such limitations of current soft robots, we developed a novel soft shape morphing thin film actuator with new functionalities such as high transparency and unique directional responses to allow complex behavior by integrating a transparent metal nanowire heater. A figure of merit was developed to evaluate the performance and derive an optimum design configuration for the transparent actuator with enhanced performance. As a proof of concept, various transparent soft robots such as transparent gripper, Venus flytrap, and transparent walking robot were demonstrated. Such transparent directional shape morphing actuator is expected to open new application fields and functionalities overcoming limitations of current soft robots.
본 연구에서는 차량에 부착된 모노 카메라와 딥 러닝을 이용하여 객체 검출 및 검출된 객체에 대한 거리정보를 바탕으로 하는 위험도 분류 시스템을 제안한다. 다양한 상황에서 기존 컴퓨터 비전 기법들보다 변화에 강인하며 검출 능력이 뛰어난 딥 러닝을 이용하여 주행 영상을 통해 주행환경 상에 있는 객체들을 검출한다. 이때 객체 검출기로는 합성 곱 신경망 네트워크를 기반으로 만들어진 YOLO v2(You Only Look Once v2)알고리즘을 이용하며, 해당 알고리즘은 사전에 ImageNet 1000 Class 데이터로 학습 된 Pre-trained model에 KITTI 데이터 셋 및 웹 포털 사이트에서 크롤링을 통해 획득한 12K개의 이미지를 이용하여 전이학습 하였다. 그리고 DB 구축 Tool을 이용하여 KITTI 데이터 셋에서 취득한 이미지와 캘리브레이션된 LiDAR 센서 데이터를 통해 검출된 객체와의 거리 정보를 취득하였다. 객체 검출기의 결과로는 Bounding Box의 이미지 내 좌표인 x,y와 Bounding Box의 이미지 내 크기인 width, height 정보가 나온다. 객체와의 거리정보를 특정 구간 단위로 분류하여 Class화 하였고, 해당 Class(거리 등급)와 객체 검출 정보인 Bounding box 정보들을 Multi-layer Perceptron을 이용하여 분류한다.
This review summarizes recent progress in developing wireless, batteryless, fully implantable biomedical devices for real-time continuous physiological signal monitoring, focusing on advancing human health care. Design considerations, such as biological constraints, energy sourcing, and wireless communication, are discussed in achieving the desired performance of the devices and enhanced interface with human tissues. In addition, we review the recent achievements in materials used for developing implantable systems, emphasizing their importance in achieving multi-functionalities, biocompatibility, and hemocompatibility. The wireless, batteryless devices offer minimally invasive device insertion to the body, enabling portable health monitoring and advanced disease diagnosis. Lastly, we summarize the most recent practical applications of advanced implantable devices for human health care, highlighting their potential for immediate commercialization and clinical uses.
Abstract The sense of touch and perception of hand motion form an essential part of the somatic sensory system. Although piezoelectric sensors demonstrate high sensitivity and linearity, they are traditionally not employed for electronic skins because of their limited stretchability. Here, a printed, skin‐conformal, electronic system consisting of stretchable piezoelectric pressure sensors and carbon nanotube strain gauges capable of identifying tactile sensations and joint movements on the hand is introduced. The pressure sensor demonstrates both high sensitivity (19.9 mV kPa −1 ) and linearity (0.1–1000 kPa) while being reliably stretchable to above 15%. To complement the pressure sensing functionality, a strain gauge is fabricated in a rapid stamp printing process and designed to demonstrate excellent mechanical reliability with up to 70% strain and high sensitivity (36.5‐gauge factor). These sensors can seamlessly conform to numerous anatomical regions and cover wide areas of the skin, making them ideal for deployment in an electronic skin. Finally, the sensors are integrated with a flexible microelectronic device to demonstrate their functionality in human touch and prosthetic hand applications.
Electrophysiology signals are crucial health status indicators as they are related to all human activities. Current demands for mobile healthcare have driven considerable interest in developing skin-mounted electrodes for health monitoring. Silver-Silver chloride-based (Ag-/AgCl) wet electrodes, commonly used in conventional clinical practice, provide excellent signal quality, but cannot monitor long-term signals due to gel evaporation and skin irritation. Therefore, the focus has shifted to developing dry electrodes that can operate without gels and extra adhesives. Compared to conventional wet electrodes, dry ones offer various advantages in terms of ease of use, long-term stability, and biocompatibility. This review outlines a systematic summary of the latest research on high-performance soft and dry electrodes. In addition, we summarize recent developments in soft materials, biocompatible materials, manufacturing methods, strategies to promote physical adhesion, methods for higher breathability, and their applications in wearable biomedical devices. Finally, we discuss the developmental challenges and advantages of various dry electrodes, while suggesting research directions for future studies.
'%3e%3cg id='b'%3e%3cpath id='a' stroke='%23000' stroke-width='2' d='M-6-25H6m-12 3H6m-12 3H6'/%3e%3cuse xlink:href='%23a' y='44'/%3e%3c/g%3e%3cpath stroke='%23fff' d='M0 17v10'/%3e%3ccircle r='12' fill='%23cd2e3a'/%3e%3cpath fill='%230047a0' d='M0-12A6 6 0 0 0 0 0a6 6 0 0 1 0 12 12 12 0 0 1 0-24z'/%3e%3c/g%3e%3cg transform='rotate(-123.69)'%3e%3cuse xlink:href='%23b'/%3e%3cpath stroke='%23fff' d='M0-23.5v3M0 17v3.5m0 3v3'/%3e%3c/g%3e%3c/svg%3e)
