Swarm intelligence based robotic search in unknown maze-like environments

This paper proposes a novel decentralize and asynchronous robotic search algorithm based on particle swarm optimization (PSO), which has focused on solving mazes and finding targets in unknown environments with minimal inter-swarm communication and without any synchronization or communication center. In the proposed method, robots are advanced particles of the PSO algorithm, enriched with a toolkit, including an angle of rotation to change the course when confronted with obstacles to avoid them (AoR tool), and a memory to remember and reuse their best personal experiences to turn back from dead-ends (Mem tool). This toolkit enables the swarm to avoid obstacles and solve mazes while moving toward the target. The performance of the proposed algorithm is tested in a specially designed framework. As a validation, the proposed algorithm is compared with some recently published methods, including Adaptive Robotic PSO (A-RPSO), Robotic Bat Algorithm (RBA), and Adaptive Robotic Bat Algorithm (ARBA), in simple search environments that they can solve. The results of this comparison show that the introduced search method has the highest success rate (100%) in environments of different sizes and reflects the nature of swarm intelligence better. The proposed method is also tested in various maze-like search environments. The results depict the algorithm's high efficiency to solve mazes in varying complexity levels and locate the target in a reliable time. It is also shown that the performance of the proposed algorithm does not decrease and remains constant as the complexity of search environments increases.

Automated summary

This paper proposes a novel decentralized and asynchronous robotic search algorithm based on particle swarm optimization (PSO), which aims to solve mazes and find targets in unknown environments with minimal inter-swarm communication. The algorithm equips robots with tools such as angle of rotation and memory, enabling them to avoid obstacles and solve mazes efficiently, achieving the highest success rate in various environments. The proposed method demonstrates high efficiency in solving maze-like search environments of varying complexity levels, with performance remaining constant even as complexity increases.