Communication-Free Shepherding Navigation with Multiple Steering Agents

TL;DR

This paper introduces a decentralized shepherding navigation method where multiple steering agents independently guide passive agents without communication, demonstrating high success rates and low costs in simulations, especially as the number of steering agents increases.

Contribution

The paper proposes a novel decentralized shepherding approach that eliminates the need for inter-agent communication, enhancing robustness and scalability.

Findings

High success rate in guiding passive agents

Low control costs achieved in simulations

Performance improves with more steering agents

Abstract

Swarm guidance addresses a challenging problem considering the navigation and control of a group of passive agents. To solve this problem, shepherding offers a bio-inspired technique of navigating such group of agents by using external steering agents with appropriately designed movement law. Although most shepherding researches are mainly based on the availability of centralized instructions, these assumptions are not realistic enough to solve some emerging application problems. Therefore, this paper presents a decentralized shepherding method where each steering agent makes movements based on its own observation without any inter-agent communication. Our numerical simulations confirm the effectiveness of the proposed method by showing its high success rate and low costs in various placement patterns. These advantages particularly improve with the increase in the number of steering agents.