You can find below our recently accepted work at IEEE Access regarding “Distributed Maze Exploration Using Multiple Agents and Optimal Goal Assignment”, authored by M. Linardakis, I. Varlamis and G. Th. Papadopoulos.
Many existing approaches to robotic exploration adopt optimization techniques through the development of multi-agent systems; however, such methods often overlook critical real-world factors, such as broadcast range limitations, communication costs and coverage overlap.
The current study addresses these gaps by proposing a distributed maze exploration strategy (CU-LVP) that assumes constrained broadcast ranges and utilizes Voronoi diagrams for better area partitioning. By adapting traditional multi-agent methods to distributed environments with limited broadcast ranges, this work evaluates their performance across diverse maze topologies.
- Code available at this link: https://github.com/manouslinard/multiagent-exploration/
- Paper link: https://ieeexplore.ieee.org/document/10605811?source=authoralert