FLC tuned with Gravitational Search Algorithm for Nonlinear Pose Filter
원문 초록
Nonlinear pose (\textit{i.e,} attitude and position) filters are characterized with simpler structure and better tracking performance in comparison with other methods of pose estimation. A critical factor when designing a nonlinear pose filter is the selection of the error function. Conventional design of nonlinear pose filter design trade-off between fast adaptation and robustness. This paper introduces a new practical approach based on fuzzy rules for on-line continuous tuning of the nonlinear pose filter. Each of input and output membership functions are optimally tuned using graphical search algorithm optimization considering both pose error and its rate of change. The proposed approach is characterized with high adaptation features and strong level of robustness. Therefore, the proposed approach results of robust and fast convergence properties. The simulation results show the effectiveness of the proposed approach considering uncertain measurements and large error in initialization.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
PoseBench3D: A Cross-Dataset Analysis Framework for 3D Human Pose Estimation
Sleep Position Classification using Transfer Learning for Bed-based Pressure Sensors
Pose Estimation for Intra-cardiac Echocardiography Catheter via AI-Based Anatomical Understanding
6D Pose Estimation on Spoons and Hands
SenseShift6D: Multimodal RGB-D Benchmarking for Robust 6D Pose Estimation across Environment and Sensor Variations
Efficient Calisthenics Skills Classification through Foreground Instance Selection and Depth Estimation
토론
이 논문과 연결된 포럼 글이 아직 없습니다.