http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
- 中文 을 입력하시려면 zhongwen을 입력하시고 space를누르시면됩니다.
- 北京 을 입력하시려면 beijing을 입력하시고 space를 누르시면 됩니다.
RISS 인기검색어
- 검색키워드
- 저자 : 임경일(kyungil Lim) (검색결과 6 건)
- 무료
- 기관 내 무료
- 유료
-
-
일반 대학생의 이미지 상상훈련이 정적 및 동적 균형에 미치는 영향
남형천 ( Hyoungchun Nam ),임경일 ( Kyungil Lim ),김수현 ( Suhyeon Kim ),김설지 ( Seoji Kim ),김지선 ( Jiseon Kim ),류영우 ( Youngwoo Ryu ),박인애 ( Inae Park ),이수빈 ( Subin Lee ),진한빈 ( Hanbin Jin ),문준석 ( Junseok Moon ),장세훈 대한통합의학회 2014 대한통합의학회지 Vol.2 No.2
Purpose : This study was to investigate the influence of imagery balance for healthy normal people in their twenties.Method : The study has taken a place in Kyung-buk college in Yung-jusi in Kyungbuk with a group of 21 healthy peoples. The study used measurement of good balance. we measured balance for data of each static and dynamic. Training period, a total of 2 weeks. Except Saturday and Sunday, the study did weekdays. Fist, 2-minute relaxation. Second, 6-minute imagine training. Third, 2-minute relaxation. Total 10-minute training was conducted per training. Result : In study, the subjects were compared date for before the study to date for after the study. The subjects showed a little change in each Balance. But, the improvement of balance was not a big change. Conclusion : Image training kinesthetic image using hearing improved incompletely inspite of being no gap, numerically balance
-
윤승제,정지원,홍준,임경일,김재환,김형주,Yoon, Seungje,Jung, Jiwon,Hong, June,Lim, Kyungil,Kim, Jaehwan,Kim, Hyungjoo 한국ITS학회 2020 한국ITS학회논문지 Vol.19 No.5
자율주행시스템에서 다양한 센서를 기반으로 한 외부환경 인지는 주행안전성과 직접적인 관계가 있다. 최근 머신러닝/심층 신경망 기술의 발전으로 심층 신경망 기반의 인지 모델이 사용됨에 따라, 인지 알고리즘의 올바른 학습과 이를 위한 양질의 학습데이터가 필수적으로 요구된다. 그러나 자율주행에 발생할 수 있는 모든 상황을 데이터를 수집하는 것은 현실적인 어려움이 많다. 해외와 국내의 교통 환경의 차이로 인지 모델의 성능이 저하되기도 하며, 센서가 정상동작을 못하는 악천우에 대한 데이터는 수집이 어려우며 질적인 부분을 보장하지 못한다. 때문에, 실제 도로가 아닌 시뮬레이터 내 가상 도로 환경을 구축하여 합성 데이터를 수집하는 접근법이 필요하다. 본 논문에서는 국내 실정에 맞게 국내 도로 상황을 모사한 시뮬레이터 환경 안에 날씨와 조도, 차량의 종류와 대수, 센서의 위치를 다양화하여 학습데이터를 수집하였고, 보다 더 좋은 성능을 위해 적대적 생성 모델을 활용하여 이미지의 도메인을 보다 실사에 가깝게 바꾸고 다양화 하였다. 그리고 위 데이터로 학습한 인지 모델을 실제 도로 환경에서 수집한 시험 데이터에 성능 평가를 진행하여, 실제 환경 데이터만으로 학습한 모델과 비슷한 성능을 내는 것을 보였다. The perception of traffic environment based on various sensors in autonomous driving system has a direct relationship with driving safety. Recently, as the perception model based on deep neural network is used due to the development of machine learning/in-depth neural network technology, a the perception model training and high quality of a training dataset are required. However, there are several realistic difficulties to collect data on all situations that may occur in self-driving. The performance of the perception model may be deteriorated due to the difference between the overseas and domestic traffic environments, and data on bad weather where the sensors can not operate normally can not guarantee the qualitative part. Therefore, it is necessary to build a virtual road environment in the simulator rather than the actual road to collect the traning data. In this paper, a training dataset collection process is suggested by diversifying the weather, illumination, sensor position, type and counts of vehicles in the simulator environment that simulates the domestic road situation according to the domestic situation. In order to achieve better performance, the authors changed the domain of image to be closer to due diligence and diversified. And the performance evaluation was conducted on the test data collected in the actual road environment, and the performance was similar to that of the model learned only by the actual environmental data.
-
김종민(Jongmin Kim),임경일(Kyungil Lim),김정하(Jungha Kim) 한국자동차공학회 2015 한국자동차공학회 학술대회 및 전시회 Vol.2015 No.11
In this paper, static obstacles avoidance path planning and auto-parking path planning algorithm of autonomous vehicle in parking area are proposed. The path planning technologies for auto-parking in limited parking space have been achieved but these don’t be considered about the driving environment of parking area. As a mission in parking area, the situation that obstacles appeared can be caused and then the vehicle will have to avoid the obstacles for continuously detecting a empty parking lot. In this research, for obstacles avoidance using point data from laser scanner voronoi field is used . As a map, generated voronoi field is used to search the path via the A* algorithm and finally the autonomous vehicle will do collision free driving along the generated path. The driving goal point is a parking lot. Reeds-Shepp curve consist of arcs that have minimum turning radius. this curve algorithm is used to generate auto-parking path from vehicle’s pose to a parking lot.
-
조성욱(Sungwook Jo),임경일(kyungil Lim),김윤섭(Yoonsub Kim),김정하(Jungha Kim) 한국자동차공학회 2015 한국자동차공학회 부문종합 학술대회 Vol.2015 No.5
There are many problems that generating path to traking UGV(Unmanned Ground Vehicle) in the real time in addition, most of path generation algorithm dose not take into account the kinematic characteristics of the vehicle. It is essential that path generation based to Scenario according to tracking situation. in this paper, we proposed that recognition of preceding vehicle and available overtaking path generation and path planning in restricted environment(ex. Highway). we used to LiDAR sensors, creates a path to overtake the preceding vehicle by update of obstacle in the global map based on grid. In consideration of the minimum distance(d1) can overtaking the preceding vehicle according to the entrance speed of the vehicle. minimum distance(d1) was used determined to start node. path planning is determined to judgment of overtaking about avoidance path generation, traking of front vehicle. we applied to TLPA<SUP>*</SUP> algorithm, generates overtaking path. TLPA<SUP>*</SUP> algorithm was defined by Suboptimality bound throught restrict to(∈) re-search area. using a TLPA<SUP>*</SUP> algorithm was more faster existing path generation algorithm therefore, using to LiDAR sensors, traking a front vehicle and updates position of current vehicle and obstacle and overtaking path in global map. finally, we proposed that fast and safety generating path of overtaking and path planning.
-
김윤섭(Yunsub Kim),이태영(Taeyoung Lee),임경일(Kyungil Lim),김재환(Jaehwan Kim) 한국자동차공학회 2018 한국자동차공학회 학술대회 및 전시회 Vol.2018 No.11
Technology development related to autonomous driving is rapidly progressing. Among them, the development of algorithms related to is very important because it is directly related to safety. At present, the various environment-perception sensors installed in the autonomous driving platform are at an expensive price, it is not easy to have autonomous driving platform to utilize it. KODAS recognizes this reality, it started from the point of view of securing autonomous driving technology competition from a wide viewpoint. The purpose of this research is to provide a variety of experiences to Korean researchers by providing database and research on dataset. In this paper, we present an example of utilizing the KODAS DB based on Zero City which is an actual operating environment and Zero Shuttle which is an autonomous driving platform. It is expected that more research results will be generated in relation to autonomous driving perception and the competitiveness of autonomous driving technology development will be improved.
ScienceON연관 검색어 추천
이 검색어로 많이 본 자료
활용도 높은 자료
