A Hybrid Metaheuristic Navigation Algorithm for Robot Path Rolling Planning in an Unknown Environment

Abstract

In this paper, a new method for robot path rolling planning in a static and unknown environment based on grid modelling is proposed. In an unknown scene, a local navigation optimization path for the robot is generated intelligently by ant colony optimization (ACO) combined with the environment information of robot's local view and target information. The robot plans a new navigation path dynamically after certain steps along the previous local navigation path, and always moves along the optimized navigation path which is dynamically modified. The robot will move forward to the target point directly along the local optimization path when the target is within the current view of the robot. This method presents a more intelligent sub-goal mapping method comparing to the traditional rolling window approach. Besides, the path that is part of the generated local path based on the ACO between the current position and the next position of the robot is further optimized using particle swarm optimization (PSO), which resulted in a hybrid metaheuristic algorithm that incorporates ACO and PSO. Simulation results show that the robot can reach the target grid along a global optimization path without collision.

Optimizing Path Planning for Smart Vehicles: A Comprehensive Review of Metaheuristic Algorithms

“…When it comes to covering the search space effectively, a multi-objective GWO demonstrates superior performance over multi-objective PSO and GA [190]. ACO outshines GA in obtaining optimal paths [191], and a hybrid ACO-PSO algorithm yields more optimal robot paths than ACO alone [192]. Moreover, ABC is noted for achieving shorter paths than PSO, as evidenced by simulation results [88].…”