Treffer: Autonomous Obstacle Avoidance for Skid Steering Mobile Robot Based on Fuzzy Logic.

The robot's obstacle avoidance system requires sensors to recognize its environment. The desired behavior is taken in the environment based on the robot's state and sensor perception. Then a specific system processes the information obtained to take appropriate action. In this research, fuzzy logic techniques have been presented. This control system has been implemented on a mobile robot with a LIDAR sensor. Python and the fuzzy library are used to create the fuzzy controller. This project is implemented in a real environment. RPLIDAR measures distances from any obstacle around the robot. Only the front half, divided into three equal parts at 45 degrees, has been selected. Twenty-seven cognitive states have been used so that the robot could perform with three sets of inputs, three linguistic values for each set, and two sets of outputs with four linguistic values for each set. Each situation is associated with a reaction determined by 27 basic rules. The inputs to the controller are Head Distance (DH), Left Distance (DL), and Right Distance (DR). The result is the angular velocity of the wheels on the left side (L) and the right side (R). A map of 1.8 m x 2 m has been developed as a working area for the robot, with no obstacles at first to test the designed control unit. The robot has avoided the walls without colliding with them, and the control unit was operated admirably in the actual world and simulation. Furthermore, the control unit has been tested with three obstacles present. This control unit has achieved good results in avoiding obstacles. [ABSTRACT FROM AUTHOR]

Copyright of International Review of Automatic Control is the property of Praise Worthy Prize S.r.L. and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)