Abstract
For any mobile device, the ability to navigate smoothly in its environment is of paramount importance, which justifies researchers’ continuous work on designing new techniques to reach this goal. In this work, we briefly present a description of a hard work on designing a Same Fuzzy Logic Controller (S.F.L.C.) of the two reactive behaviors of the mobile robot, namely, “go to goal obstacle avoidance” and “wall following,” in order to solve its navigation problems. This new technique allows an optimal motion planning in terms of path length and travelling time; it is meant to avoid collisions with convex and concave obstacles and to achieve the shortest path followed by the mobile robot. The efficiency of employing the proposed navigational controller is validated when compared to the results from other intelligent approaches; its qualities make of it an efficient alternative method for solving the path planning problem of the mobile robot.
Highlights
A mobile robot is able to navigate intelligently in an uncontrolled environment without the need for physical or electromechanical guidance devices using different control techniques based on sensors
Different approaches have been applied looking for a solution to global navigation problems, notably Artificial Potential Field [1], Grids [2], Visibility Graph [3], Cell Decomposition [4], and Voronoi Graph [5]
Various researches have been conducted so far to tackle the problem of local navigation like Vector Field Histogram [6] which employs a two-dimensional Cartesian histogram grid as a world model
Summary
A mobile robot is able to navigate intelligently in an uncontrolled environment without the need for physical or electromechanical guidance devices using different control techniques based on sensors. Various researches have been conducted so far to tackle the problem of local navigation like Vector Field Histogram [6] which employs a two-dimensional Cartesian histogram grid as a world model. This model is updated continuously using onboard range sensors, Dynamic Window Approach [7]. This strategy is a local planner which calculates the optimal collision-free velocity for a mobile robot, Neural Network [8], Neurofuzzy [9], Particle Swarm Optimization [10], Genetic Algorithm [11], Ant Colony Optimization Algorithm [12], Cuckoo Algorithm [13], Simulated Annealing Algorithm [14], and Fuzzy Logic
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
