http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
유전 알고리듬을 이용한 이족 보행 로봇의 계단 오르기 최적 보행 궤적 생성
金銀宿(Eunsu Kim),金萬錫(Manseak Kim),金鍾旭(Jong-Wook Kim) 대한전기학회 2009 전기학회논문지 Vol.58 No.2
In this paper, a humanoid robot is simulated and implemented to walk up a staircase using the blending polynomial and genetic algorithm. Using recently developed kinematics for a biped robot, four schemes for walking up a staircase are newly proposed and simulated separately. For the two schemes of landing a swaying leg on the upper stair, the joint trajectories of seven motors are particularly optimized to generate an energy-minimal motion with the guarantee of walking stability. The proposed scheme of walking upstair is validated by an experiment with a small humanoid robot.
최적화 기법인 mDEAS의 개발 및 휴머노이드 이족보행 시 최적 관절궤적 생성에의 적용
金銀宿(Eunsu Kim),金祚煥(Johwan Kim),金鍾旭(Jong-Wook Kim) 대한전기학회 2009 전기학회논문지 Vol.58 No.2
This paper newly proposes a modular type dynamic encoding algorithm for searches (DEAS) which partitions the whole parameters into several modules and carries out exhaustive DEAS for each module. uDEAS is used to measure parameter sensitivities to the cost function, and the variables whose sensitivities are similar are grouped to make a module. The proposed optimization method is applied to optimal trajectory generation for biped walking of a humanoid, and the optimization result is compared with those of the former versions of DEAS.
유도된 이진난수 생성법을 이용한 uDEAS의 Multi-start 성능 개선
김은숙(Eunsu Kim),김만석(Manseak Kim),김종욱(Jong-Wook Kim) 대한전기학회 2009 전기학회논문지 Vol.58 No.4
This paper proposes a new multi-start scheme that generates guided random bits in selecting initial search points for global optimization with univariate dynamic encoding algorithm for searches (uDEAS). The proposed method counts the number of 1 in each bit position from all the previously generated initial search matrices and, based on this information, generates 0 in proportion with the probability of selecting 1. This rule is simple and effective for improving diversity of initial search points. The performance improvement of the proposed multi-start is validated through implementation in uDEAS and function optimization experiments.