최근 지속적으로 발생하고 있는 메르스와 같은 신종 감염병은 초기발견, 격리, 위기대응 등 많은 대응책을 필요로하고 있으며 아울러 일반인의 문병과 간호 간병 통합서비스 시행 등 병원의 문화가 바뀌는 추세이다. 그러나 병원에서 근무하는 의료인의 자격조건, 규정 등이 까다로와지면서 해외에서는 린넨, 폐기물, 수액 이동 등 로봇으로 가능한 부분은 대체하는 추세이다. 본 연구에서는 병원 내에서 발생하는 각종 물품의 배송 업무를 수행할 수 있는 IoT 기반의 병원 물류 로봇으로 다양한 종류의 물건을 원하는 위치까지 안전하게 이동 할 수 있는 기술에 대하여 연구하였다. 병원 내 로봇의 이동은 사람 또는 사물간 충돌을 발생 시킬 수 있기 때문에 충돌을 최소화 해야 한다. 충돌을 최소화하기 위해서는 로봇의 이동 경로에 사물의 유무를 판단하고 사물이 있다면 이동하는 것인지 아닌지를 인지해야 한다. 그래서 얼굴/전신정보 검출과 3D Vision영상분할 기술을 이용하여 장애물의 상황 정보를 생성하였다. 생성 된 정보를 활용하여 로봇 이동 범위 내 사물과 사람을 고려한 맵을 생성하여 로봇이 안전하고 효율적으로 운행 될 수 있도록 하였다.
최근 지속적으로 발생하고 있는 메르스와 같은 신종 감염병은 초기발견, 격리, 위기대응 등 많은 대응책을 필요로하고 있으며 아울러 일반인의 문병과 간호 간병 통합서비스 시행 등 병원의 문화가 바뀌는 추세이다. 그러나 병원에서 근무하는 의료인의 자격조건, 규정 등이 까다로와지면서 해외에서는 린넨, 폐기물, 수액 이동 등 로봇으로 가능한 부분은 대체하는 추세이다. 본 연구에서는 병원 내에서 발생하는 각종 물품의 배송 업무를 수행할 수 있는 IoT 기반의 병원 물류 로봇으로 다양한 종류의 물건을 원하는 위치까지 안전하게 이동 할 수 있는 기술에 대하여 연구하였다. 병원 내 로봇의 이동은 사람 또는 사물간 충돌을 발생 시킬 수 있기 때문에 충돌을 최소화 해야 한다. 충돌을 최소화하기 위해서는 로봇의 이동 경로에 사물의 유무를 판단하고 사물이 있다면 이동하는 것인지 아닌지를 인지해야 한다. 그래서 얼굴/전신정보 검출과 3D Vision 영상분할 기술을 이용하여 장애물의 상황 정보를 생성하였다. 생성 된 정보를 활용하여 로봇 이동 범위 내 사물과 사람을 고려한 맵을 생성하여 로봇이 안전하고 효율적으로 운행 될 수 있도록 하였다.
New infectious diseases such as MERS have been in need of many measures such as initial discovery, isolation, and crisis response. In addition, the culture of hospitals is changing, such as the general public 's visiting and Nursing Care Integration Services. However, as the qualifications and regul...
New infectious diseases such as MERS have been in need of many measures such as initial discovery, isolation, and crisis response. In addition, the culture of hospitals is changing, such as the general public 's visiting and Nursing Care Integration Services. However, as the qualifications and regulations of medical personnel in hospitals become rigid, overseas such as linens, wastes movements are replacing possible works with robots. we have developed a hospital logistics robot that can carry out various goods delivery within a hospital, and can move various kinds of objects safely to a desired location. In this thesis, we have studied a hospital logistics robot that can carry out various kinds of goods delivery within the hospital, and can move various kinds of objects such as waste, and linen safely to a desired location. The movement of a robot in a hospital may cause a collision between a person and an object, so that the collision must be prevented. In order to prevent collision, it is necessary to recognize whether or not an object exists in the movement path of the robot. And if there is an object, it should recognize whether it moves or not. In order to recognize human beings and objects, we recognize the person with face/body recognition technology and generate the context awareness of the object using 3D Vision image segmentation technology. We use the generated information to create a map that considers objects and person in the robot moving range. Thus, the robot can be operated safely and efficiently.
New infectious diseases such as MERS have been in need of many measures such as initial discovery, isolation, and crisis response. In addition, the culture of hospitals is changing, such as the general public 's visiting and Nursing Care Integration Services. However, as the qualifications and regulations of medical personnel in hospitals become rigid, overseas such as linens, wastes movements are replacing possible works with robots. we have developed a hospital logistics robot that can carry out various goods delivery within a hospital, and can move various kinds of objects safely to a desired location. In this thesis, we have studied a hospital logistics robot that can carry out various kinds of goods delivery within the hospital, and can move various kinds of objects such as waste, and linen safely to a desired location. The movement of a robot in a hospital may cause a collision between a person and an object, so that the collision must be prevented. In order to prevent collision, it is necessary to recognize whether or not an object exists in the movement path of the robot. And if there is an object, it should recognize whether it moves or not. In order to recognize human beings and objects, we recognize the person with face/body recognition technology and generate the context awareness of the object using 3D Vision image segmentation technology. We use the generated information to create a map that considers objects and person in the robot moving range. Thus, the robot can be operated safely and efficiently.
* AI 자동 식별 결과로 적합하지 않은 문장이 있을 수 있으니, 이용에 유의하시기 바랍니다.
문제 정의
Particular attention should be paid to the fact that a number of physically fragile patients will be included because of the specialty of hospitals[3]. In this study, we have conducted research for obstacle attribute recognition using user detection and object movement information to generate obstacle context awareness map combining obstacle attribute information.[4][5]
제안 방법
In order to generate the map that informed the obstacle situation by using 3D Vision information and image segmentation, the depth information of the Kinect sensor was integrated and the pseudo-LRF function was implemented and the user was detected and tracked using face / omega detection. Also, to measure the congestion level and to upgrade the map based on the cumulative driving information, we measured the congestion information of the route using the frequency of obstacles and user appearance. Also, to measure the congestion level and update the map attribute by region based on cumulative running information, we measured the congestion of path using obstacle and user appearance frequency.
Also, to measure the congestion level and to upgrade the map based on the cumulative driving information, we measured the congestion information of the route using the frequency of obstacles and user appearance. Also, to measure the congestion level and update the map attribute by region based on cumulative running information, we measured the congestion of path using obstacle and user appearance frequency.
53% was obtained. Based on the results obtained, we have field tested that the logistics robot operates smoothly in the hospital and that it operates safely and efficiently by passing the automatic door installed in the Laboratory Medicine field tests. Therefore, the technological spin-off effect is very effective by successfully applying the logistic robot system to the complex environment like the hospital, and naturally securing the essential technology that can be easily extended to similar environments and uses such as nursing homes, warehouses, and large libraries.
In order to generate the map that informed the obstacle situation by using 3D Vision information and image segmentation, the depth information of the Kinect sensor was integrated and the pseudo-LRF function was implemented and the user was detected and tracked using face / omega detection.
However, since people move, they must recognize the direction and speed of movement. Therefore, in this study, the recognition of obstacles is performed using geometric information and omnidirectional detection technology. The figure shows people and objects recognized.
이론/모형
) into consideration first in the hospital environment. The driving model was designed to design the protocol and sensitivity zone related to Safety and Smoothness and to design the Human-Centered Navigation (HCN) model. Also, the field of view (FOV) should be widened for user detection and tracking using face / omega /body detection.
성능/효과
Therefore, in this study, the performance of the algorithm is verified by using 13 sensor data sets captured by using the robot sensor while directly moving the robot. As a result of the performance verification, it is expressed as Confusion Matrix, and the final recognition performance is evaluated as 91.53%.
참고문헌 (10)
S.H.Lee, et al., "Top 10 Science & Technology Issues in 2015", Featured Policy, Science & Technology Policy, pp14-15, 2015
https://www.amazonrobotics.com.
Nessi, F., Beretta, E., Gatti, C., Ferrigno, G., De Momi, E., "Gesteme-free context-aware adaptation of robot behavior in human-robot cooperation:, ARTIFICIAL INTELLIGENCE IN MEDICINE, Vol.74, pp32-43, 2016.
Hong, C..S., Cho, J. , Lee, K. W. , Suh, Y.-H., Kim, H., Lee, H.-C., "Developing a Context-Aware System for Providing Intelligent Robot Services", Lecture Notes in Computer Science, No.4727, pp.174-189, 2006.
Bae, N.; Kwak, K.; Saraswathi, S.; Park, J.; Shin, "A Study of Robot-Based Context-Aware Fire Escape Service Model:, "Lecture Notes in Computer Science, No.7973, pp.287-293, 2013.
Shimamura, J.; Arakawa, K., "Location-Aware Projection with Robust 3-D Viewing Point Detection and Fast Image Deformation", ACM Press, Vol.12, pp296-299, 2004.
Nessi, F.; Beretta, E.; Gatti, C.; Ferrigno, G.; D "Gesteme-free context-aware adaptation of robot behavior in human-robot cooperation", Elsevier Science B.V., Amsterdam, Vol.74, 2016.
Chan-Woo Moon, Young-Dae Lee, "Implementation of an Indoor Mobile Robot and Environment Recognition using Line Histogram Method", The Journal of The Institute of Internet, Broadcasting and Communication (JIIBC), Vol. 9 No. 2, pp.45-50, 2009.
Tae-Woo Han, Yong-Ho Seo, "Emergency Situation Detection using Images from Surveillance Camera and Mobile Robot Tracking, System", The Journal of The Institute of Internet, Broadcasting and Communication (JIIBC), Vol. 9 No. 5, pp.101-107, 2009.
Jeon, Young-Pil; Park, Jong-Ho; Lim, Shin-Teak; Chong, Kil-To,"Research for robot kidnap problem in the indoor of utilizing external image information and the absolute spatial coordinates", Journal of the Korea Academia-Industrial cooperation Society, Vol. 16, No. 3, pp.2123-2130, 2015. DOI : http://dx.doi.org/10.5762/KAIS.2015.16.3.2123
※ AI-Helper는 부적절한 답변을 할 수 있습니다.