Practical adaptive navigation and control of a mobile robot using neuro-fuzzy systems

An Adaptive Navigation System is considered for navigation of an autonomous guided vehicles (such as non-holonomic mobile robot) with kinematics constrains in an unknown environment. The on-line navigation system, based on integrated reactive-cognitive parts, adaptively determines the required actions and/or controllers for the mobile robot. Each controller is adaptive itself, it use an Adaptive Neuro-Fuzzy Inference System (ANFIS). The ANFIS learns and generates the required knowledge for achieving desired goals from the mobile robot behaviour and its environment. Two different phases i.e. the configuration phase and the real time implementation phase are used to train the controllers. Finally, the experimental results confirm that employed methodology works well for mobile robot navigation in an unknown environment. Copyright (C) 1998 IFAC.