Neuro-Fuzzy Controllers and Application to Autonomous Robots

In order to achieve correct behavior the control system of an autonomous robot must perform many complex information processing tasks in real time. The robots operate in environment where the boundary conditions vary rapidly [1]. Fuzzy logic controller is well suited for controlling a robot because it is capable of making inferences even under uncertainty [2]. Ever since the fuzzy systems were applied in industrial applications, developers know that the construction of a well performing fuzzy system is not always easy. The problem of finding appropriate membership functions and fuzzy rules is often a tiring process of trial and error. The learning parameters of neural networks made them a prime target for a combination with fuzzy systems in order to automate or support the process of developing a fuzzy system for a given task [3]. Learning allows autonomous robots to acquire knowledge by interacting with the environment. This kind of behavior learning methods can be used to solve control problems that robots encounter in unfamiliar real-world environment [4]. This paper discusses an experimental neuro-fuzzy controller for sensor based mobile robot navigation in indoor environments. Our work is a succession of previous work done on the Institute for Automation and System Engineering at the Faculty of electrical engineering and Information technologies [5].