Development of an Optimal Path Planning Using Elite Opposition Based Bat Algorithm for a Mobile Robot

Abstract

This research work presents the development of an optimal path planning using elite opposition based bat algorithm (EOBA) for mobile robot, such that the robot avoids obstacle(s) without making contact with them. The bat algorithm (BA) is a nature inspired meta-heuristic algorithm that works on the basis of the echolocation behavior of bat. It, however, has a poor exploration capability leading to it easily getting stuck in local optima. The EOBA is developed by modifying the BA with the elite opposition-based learning (EOBL) so as to diversify the solution search space and the inertial weight in order to balance its exploration and exploitation. The performance of the proposed path planning technique was compared with that of the standard BA based on the ability to generate an optimal path for a mobile robot in a developed simulation environment. The simulation results showed that EOBA provide an optimal path with minimum elapsed time as compared to that of the standard BA. All simulations were carried out using MATLAB R2013b.

Path Planning Algorithms for Mobile Robots: A Survey

“…During the search process of the algorithm, the swarm of particles achieves the objective of obtaining the optimal solution by sharing common information across each member in the swarm. This enables them to globally move together, knowing the position of each at every step of the particles [1,30,41].…”

“…Mobile robots play a crucial role in diverse applications, including search and rescue, cargo and packet delivery, environmental monitoring, and remote sensing, among others [1][2][3]. These robots operate in various environments and are classified according to their deployment technology into ground mobile robots, aerial mobile robots, water surface mobile robots, and underwater mobile robots.…”

“…During global path planning, the robot calculates the optimal path just once at the beginning and then follows this path until it reaches the target destination. This approach assumes that the environment remains static and does not change during the robot's movement [8,11].…”

“…It uses the sensor data to build a map that accurately represents the structure of the environment. Based on this dynamic map, the robot then plans its path on-the-fly, continuously adapting to changing conditions and obstacles as it navigates toward its goal [8,10,12].…”

“…In the domain of mobile robot path planning, researchers have explored a variety of approaches in the literature to address this challenging problem. These approaches can be broadly classified into three categories: classical (conventional), heuristics, and metaheuristics [12][13][14].…”