Intelligent Trajectory Planning Algorithms for Autonomous Mobile Robots

Abstract

Given the widespread utilization of autonomous mobile robots in the past two decades, the path planning problem has received considerable attention from researchers. The goal is to find a collision-free path from a start point to a target point in an environment full of obstacles whilst satisfying some criteria, such as time, distance, and safety.

This study proposes an intelligent hybrid optimisation method for autonomous mobile robots (AMRs) to reach a target or multiple targets in environments filled with obstacles. The proposed method combines two algorithms. The first algorithm is the probabilistic roadmap algorithm, which tries to explore the search space and generate several free collision paths to be utilised as a population for the second algorithm. The second algorithm is the enhanced genetic algorithm (EGA), which is utilised to plan the shortest and smoothest path depending on the population generated by PRM. The EGA presents an effective and accurate fitness function, improves the genetic operators of a conventional genetic algorithm (GA), and proposes a new genetic modification operator.The efficiency of the proposed method is verified by several simulations in various environments and real-time experiments on a nonholonomic wheeled mobile robot. Results show that the proposed hybrid approach outperforms the conventional GA, probabilistic roadmap, ant colony optimisation, the Bezier smoothing algorithm, and other algorithms in planning a smooth, near-optimal, collision-free path in competitive time.