Goal-directed, collision-free mobile robot navigation and control

Navigation and collision avoidance are major areas of research in mobile robotics. In this paper, a new approach is proposed for navigation and control of a wheeled mobile robot. A collision-free trajectory is calculated using an efficient fuzzy-neural trajectory planner-generator that is trained using genetic algorithms. The output of the navigation level is fed into a trajectory tracking level. It takes into account the complete dynamics of the mobile base. The locomotion control structure is based on the integration of a kinematic trajectory tracking controller and an adaptive fuzzy-net torque controller. Copyright (C) 1999 IFAC.