Graduate School of Natural and Applied Sciences
Permanent URI for this community
Browse
Browsing Graduate School of Natural and Applied Sciences by Author "Abdi, Mohammed Isam Ismael"
Now showing 1 - 1 of 1
Results Per Page
Sort Options
Item AN EFFECTIVE PATH PLANNING ALGORITHM FOR SWARM OF ROBOTS IN AN UN-KNOWN ENVIRONMENT(2022-01-25) Abdi, Mohammed Isam Ismael; Khan, UmerIn many circumstances, several mobile robots —independent agents— team up to achieve goals that are hard or impossible for an individual robot. These mobile robots cooperate to perform any particular task, complexity of this cooperation is correlated with the swarm size. Each individual robot is to interact with the local environment using sensors. The primary concern for the swarm is to define and follow a safe route from initial to target location. To achieve this task, many algorithms exist in the literature, namely, Neural Network, Genetic Algorithms, Bacterial Foraging Optimization, Ant Colony Optimization, Artificial Potential Field etc. Among these, Bacterial Foraging Optimization (BFO) algorithm has attracted the attention of many scientists due to its effectiveness of finding the destination with the consideration of all known obstacles in the work space ensuring safety. Furthermore, it discovers and always follows the determined path correctly. BFO is a straightforward but strong bioinspired method of optimization using the analogy of swarming principles and social behavior in nature. The BFO successfully searches for an optimal path from start to goal point in the presence of obstacles over a flat surface map. However, the algorithm suffers from getting stuck in local minima whenever non-convex obstacles are encountered. In case of any of these robots from the swarm getting stuck is considered as the failure of the whole task. This research proposes an improved version of BFO algorithm that can effectively avoid obstacles, both of convex and non-convex nature. The proposed algorithm helps the robot to recover from local minima by covering a certain distance in an opposite direction to the obstacle. The algorithm will start generating virtual obstacles to generate a safe path when facing acute angle. This information is then passed onto other robots, so that they can also avoid local minima. To test the effectiveness of the proposed algorithm, a comparison is made against the existing BFO algorithm. The performance of both algorithms is tested in an unknown dynamic and static environments. Through results, it is witnessed that the proposed approach successfully recovers from the local minima, whereas, BFO gets stuck.