Alexandros Anemogiannis

Papers

Total Citations

H-Index

About

Alexandros Anemogiannis is a researcher working at the intersection of robotics, machine learning, and communications systems, with a particular focus on the emerging field of cloud robotics and networked robotic perception. His work addresses a critical challenge facing modern autonomous systems: how resource-constrained robots — from low-power drones to space and subterranean rovers — can efficiently transmit high-bitrate sensory data, including video and LIDAR streams, to remote compute servers for real-time inference and decision-making. A central contribution of Anemogiannis's research is the co-design of communication and machine inference pipelines, an approach that optimizes both data transmission and AI-driven perception jointly, rather than treating them as independent problems. His 2021 paper on this topic has garnered 5 citations, while his complementary work on task-relevant representation learning (2020) demonstrates how robots can learn compact, meaningful data representations tailored specifically to downstream inference tasks, reducing unnecessary bandwidth usage. A follow-up study in 2023 further consolidated these ideas. Though still early in accumulating citations, Anemogiannis's research addresses foundational bottlenecks in deploying intelligent robotic systems in bandwidth-limited, real-world environments — making his work increasingly relevant as autonomous systems proliferate across industry and exploration.