Motion planning for climbing robot based on hybrid navigation

In this paper, a motion planning method for autonomous control of a bipedal climbing robot based on hybrid navigation is presented. The algorithm of hybrid navigation blends the optimality of the trajectory planning with the capabilities in expressing knowledge and learning of the fuzzy neural network. The real task environment of the climbing robot is both known and dynamic. Therefore the trajectory planning is used to search roughly for the optimal trajectories which will lead towards the goal according to prior data. Meanwhile, by the process of the multi-sensor data fusion, the fuzzy neural network is employed in dealing efficiently with the uncertain and dynamic situations. The properties of motion planning based on the hybrid navigation are verified by the computer simulations and experiments