메뉴 건너뛰기
소속 기관 / 학교 인증
인증하면 논문, 학술자료 등을  무료로 열람할 수 있어요.
한국대학교, 누리자동차, 시립도서관 등 나의 기관을 확인해보세요
(국내 대학 90% 이상 구독 중)
고객센터 ENG
주제분류

논문 기본 정보

저자정보
(Beihang University (BUAA)) (SMSS, Beihang University(BUAA)) (Beijing University of Posts and Telecommunications) (Beihang University (BUAA))
저널정보
제어로봇시스템학회 제어로봇시스템학회 국제학술대회 논문집 ICCAS 2012
오류 신고하기

피인용 0

검색

    초록·키워드

    A velocity control law is developed for the kinematic steering system of nonholonomic mobile robot to track a reference trajectory not only to make the posture error asymptotically stable but also considered optimality based on a pre-defined cost function. In order to make the cost function finite, we transformed the tracking problem into a regulation problem by redefining system states and inputs. The proposed online and forward-in-time policy iteration (PI) algorithm based on approximate dynamic programming (ADP) to solve the continuous-time(CT) optimal control problem with infinite horizon cost by solving of Hamilton-Jacobi-Bellman (HJB) equation. This method learns online in real-time to approximate the cost function by using a single neural networks (NNs), and then the near optimal control policy can be computed directly according to the cost function, which removes the action network appearing in the ordinary ADP methods. Simulation results are provided to demonstrate the effectiveness of the proposed approach.

    최근 본 자료 전체보기