Can Aykin

Papers

Total Citations

H-Index

About

Can Aykin is a researcher at the intersection of reinforcement learning and multi-agent robotic systems, with a primary focus on formation control for autonomous agents. His most-cited work, "Formation control using GQ(λ) reinforcement learning" (2017, 20 citations), addresses a critical challenge in swarm robotics and human-robot teams: enabling groups of agents—from drones to ground robots—to autonomously coordinate their spatial configurations without explicit programming. By applying the GQ(λ) algorithm, a gradient-based temporal-difference learning method, Aykin demonstrated how agents can learn stable, adaptive formation behaviors through trial and error, even in dynamic or uncertain environments. This contribution is particularly significant for real-world applications where centralized control is impractical, such as search-and-rescue missions or collaborative manufacturing. Aykin’s work bridges theoretical reinforcement learning advances with practical robotic coordination, offering a scalable framework for decentralized decision-making. Though his citation count reflects an emerging career, his research has laid groundwork for integrating learning-based approaches into multi-agent systems, making him a notable voice in the growing field of intelligent autonomous swarms.