UAS see-and-avoid strategy using a fuzzy logic controller optimized by Cross-Entropy in Scaling Factors and Membership Functions

Abstract

Abstract-This work aims to develop a novel Cross-Entropy (CE) optimization-based fuzzy controller for Unmanned Aerial Monocular Vision-IMU System (UAMVIS) to solve the seeand-avoid problem using its accurate autonomous localization information. The function of this fuzzy controller is regulating the heading of this system to avoid the obstacle, e.g. wall.In the Matlab Simulink-based training stages, the Scaling Factor (SF) is adjusted according to the specified task firstly, and then the Membership Function (MF) is tuned based on the optimized Scaling Factor to further improve the collison avoidance performance. After obtained the optimal SF and MF, 64% of rules has been reduced (from 125 rules to 45 rules), and a large number of real flight tests with a quadcopter have been done. The experimental results show that this approach precisely navigates the system to avoid the obstacle. To our best knowledge, this is the first work to present the optimized fuzzy controller for UAMVIS using Cross-Entropy method in Scaling Factors and Membership Functions optimization.

Design, Simulation, Analysis and Optimization of PID and Fuzzy Based Control Systems for a Quadcopter

“…Fu et al [30] introduced a fuzzy logic controller based on a novel cross-entropy optimization for a quadcopter, which enables the vehicle to avoid obstacles. An algorithm that could detect objects that arise in the scene was also designed (i.e., a system based on artificial vision).…”

Post‐disaster assessment with unmanned aerial vehicles: A survey on practical implementations and research approaches

“…In relation to obstacle avoidance, fuzzy logic has been applied to a ground robot using a behavior decomposition approach; however, the approach was subject to classical problems such as oscillations and local minima . When applied to obstacle avoidance of UAV, fuzzy logic has been integrated with the cross‐entropy method …”

Design Genetic Algorithm Optimization Education Software based Fuzzy Controller for a Tricopter Fly Path Planning

“…The FLC dynamic behavior, which is based on expert knowledge, is characterized by a set of linguistic rules (Fu, 2013, Chiou, 2013, Passino, 1998, Suzuki, 1992, Mandani, 1977, Felicia, 2015. The input variables are error e(t) and error rate de(t)/dt and the output is ci.…”

“…Fuzzy logic controllers (FLC), which is based on expert knowledge, have the advantage solution to the topics that human operators can realize. It have been applied successfully in many control system issues and even given better results than others (Fu, 2013, Chiou, 2013, Mandani, 1977. Fuzzy rule-based model is suitable when information about the physical process is vague and data availability is scarce.…”