Hybrid navigation for a climbing robot by fuzzy neural network and trajectory planning
Yong Dong Jiang, Mingyang Zhao, Hong-Guang Wang, Lijin Fang · 2005
In this paper, a hybrid navigation method for the autonomous control of a miniature climbing robot is presented. The method of navigation blends the optimality of the trajectory planning algorithm with the capabilities in expressing knowledge and learning of the fuzzy neural network. The actual task environment of the climbing robot is both known and dynamic. Therefore the trajectory planning is used to search roughly the optimal trajectories towards the goal based the priori data. Meanwhile, by the multi-sensor data fusion process, the fuzzy neural network is employed in dealing properly with the uncertain and dynamic situations. The experiment platform of the miniature climbing robot is also described in the paper. The properties of the hybrid navigation method are verified by the computer simulation.