Neuro-Fuzzy System Technique for Obstructed Avoidance of Several Mobile Robot

摘要

In this paper, navigation techniques for several mobile robot in presence of static and moving obstacles using fuzzy logic controller are investigated in a totally unknown environment Fuzzy logic controller (FLC) based on Neuro-fuzzy system using difference membership functions are developed and used to navigate mobile robots. First a Neuro-Fuzzy controller (NFC) has been used with three types of membership function of five input members and three output members. Each robot has an array of infrared sensors for measuring the distances of obstacles around it. This task could be carried out specifying a set of fuzzy rules taking into account the different situations found by the mobile robots.. The approach is to extract a set of fuzzy rule set from a set of trajectories provided by human. For this purposes the input to all the NFC are left obstacle distance, right obstacle distance, front obstacle distance and target angle considered. The output from NFC is left wheel velocity and right wheel velocity of mobile robots is in use. The fuzzy rules help the robots to avoid obstacles and find targets. The robot considered for analysis is a three types of robot such as four-wheeled robot, six leg robot and boat robot. Three robots are same control method. The position and velocities of the robots dependent on two separate motors. For example, two motors are connected to two rear wheels separately in four wheeled robot. The direction and speeds of the wheels are being controlled by the motor controller interface. To verify the validity of the proposed scheme, some typical cases are simulated in which a robot is to move from a given current position to a desired goal position in various unknown environments. In all cases the robot is able to navigate its way towards the goal while avoiding obstacles successfully. These techniques have been demonstrated in various exercises, which depicts that the robots are able to avoid obstacles as well. Amongst the techniques developed, Neuro-Fuzzy Controller (NFLC) with having Gaussian membership function was found to be most efficient foe mobile robots navigation.