Michael Barlow

University of Canberra, Camden and Campbelltown Hospitals, UNSW Canberra

Papers

Total Citations

H-Index

About

Michael Barlow’s research lies at the intersection of artificial intelligence, swarm robotics, and collective emergent behavior, with a particular focus on bio-inspired control systems. His most influential work introduces a **Deep Hierarchical Reinforcement Learner for Aerial Shepherding of Ground Swarms** (2019, 25 citations), a pioneering framework that applies biomimicry of sheepdog herding to the control and guidance of multi-robot systems. This work addresses the fundamental challenge of managing coupled interactions within both cooperative and non-cooperative swarms, offering a scalable solution for applications ranging from robotics to crowd simulation. Barlow further advances the field through his contributions to **Automatic Recognition of Collective Emergent Behaviors Using Behavioral Metrics** (2023), developing computational methods to identify and classify the complex, evolutionarily-derived patterns seen in natural flocks and schools. His research on autonomous recognition of collective behavior in robot swarms (2020, 5 citations) and continuous deep hierarchical reinforcement learning for ground-air swarm shepherding (2020, 3 citations) solidifies his reputation as a key innovator in swarm intelligence. By bridging theoretical models with practical, nature-inspired algorithms, Barlow’s work provides essential tools for designing resilient, autonomous multi-agent systems.