An improved collision avoidance scheme using Artificial Potential Field with fuzzy logic

The Artificial Potential Field (APF), reputed for being one of the most prominent algorithm for traversing a path in the shortest distance possible, has a critical disability when confronted by obstacles classified by the state of being under local minima. The said state occurs when the APF algorithm yields an appreciable attractive force between the immediate position of the robot and the goal distance while, at the same time, yielding a considerable repulsive force due to the presence of obstacles that prevents it from determining its next position. The solution manifested by the researchers utilizes another reputed algorithm known as the Fuzzy Logic Inference (FLI) System by using membership functions that takes input from ultrasonic distance sensors and outputs left and right motor speed that implicitly controls the robot turn as well. Membership functions have a given pre-determined range of values that control the state of an input or an output. The fuzzy rule base, a linguistic set of IF-THEN statements, used in this FLI system follows a wall-following robot behaviour accessed if and only if the robot determines that it is under the state of local minima. Simulation and experiments of their algorithm shows good performance and ability to overcome the local minimum problem associated with potential field methods.