Improved Artificial Bee Colony Algorithm-based Path Planning of Unmanned Aerial Vehicle Using Late Acceptance Hill Climbing

Abstract

The unmanned aerial vehicle's primary goal (UAV) in route planning is to create a flight path from starting point to the ending point in space to avoid obstacles. The UAV path planning needs a real-time adaption and rapid reaction to the dynamic nature of the operational area since the path computing time, and average path length is very important factors over some cost function that reflects its effectiveness, such as power consumption or average trip time. Creating an ideal path must embrace a particular standard to reduce the distance the drone must travel. The artificial bee colony (ABC) represents one of the most important global search algorithms. The main problem with ABC is that it neglects the local search factor and uses the total search to find the optimal path to the target point since it searches the path to the target in remote areas rather than dealing with the nearby or neighboring areas, and this requires more time to find the path to reach the goal. On the other hand, late acceptance hill climbing (LAHC) algorithm uses the local search operator, which searches for the target point in the areas close to the starting point, thus providing a shorter path to reach a goal. This paper proposes and evaluates a new drone path planning algorithm, hybrid artificial bee colony (HABC). HABC algorithm design is based on modifying the ABC algorithm by cross-layer design between ABC and LAHC algorithms. The HABC is different from the original ABC algorithm in that it modifies the original one to reduce the total search by 3% and pushes ABC's search agent to use local search by 3% to start the process of rediscovering a new path to the target. The evaluation and analysis were performed for several performance metrics under different static evaluation scenarios. It has been observed from the results that the HABC outperforms the original ABC concerning average path length and standard deviation by a reduction reach to 25%, which leads to improved path planning.

PID Controller Enhanced A* Algorithm for Efficient Water Boat

“…The route planning method involves determining the best route to take from one place to another. Route planning problems are widely observed in transportation logistics, automobile navigation systems, computer communication networks, and decision-making systems for people fleeing disasters [13]. Applications of network design and graph theory depend on finding optimal or near-optimal paths [14].…”

A Constraint Optimization path planning for Dynamic Environment

“…In path planning, the robot must navigate a particular route in a given environment according to criteria such as distance, time, or energy, whether the environment is familiar to the robot. The robot must safely navigate these barriers without colliding with them to identify the best route from its starting point to its destination during navigation, for that path planning involves pre-calculating an obstacle-free route in which the controller guides the vehicle [1,2]. Path planning aims to find the optimum, collision-free route between two points in a given environment.…”