作者: J.F. Seara , K.H. Strobl , G. Schmidt
DOI: 10.1109/IRDS.2002.1041357
关键词:
摘要: This article deals with the information management for active gaze control in context of vision-guided humanoid walking. The proposed biologically inspired predictive strategy is based on maximization visual information. quantification requires a stochastic model both, robot and perception system. information/uncertainty management, i.e. relationships between system, state estimation measurements, employs coupled (considering cross-covariances) hybrid (reflecting discontinuous character biped walking) extended (copes nonlinear systems) Kalman filter approach.