Luca Zanatta

Papers

Total Citations

H-Index

About

Luca Zanatta is a researcher at the forefront of neuromorphic computing and autonomous robotics, specializing in the intersection of Spiking Neural Networks (SNNs) and Deep Reinforcement Learning (DRL). His primary research focuses on developing bio-inspired computational models—specifically SNNs, the third generation of artificial neural networks—to enable agile, robust flight policies for nano-drones and other robotic platforms. Zanatta’s major contribution lies in demonstrating how SNNs, which mimic the mammalian brain’s spiking dynamics through ordinary differential equations, can be effectively integrated with DRL to produce intelligent, real-time control policies for complex robotic tasks. His most-cited work, “Exploring spiking neural networks for deep reinforcement learning in robotic tasks” (2024, 24 citations), provides a foundational comparative study that bridges theoretical neuromorphic computing with practical deployment challenges. Additionally, his research on “Towards Nano-Drones Agile Flight Using Deep Reinforcement Learning” (2024) addresses the critical gap between simulation and real-world hardware, pushing the boundaries of autonomous micro-aerial vehicles. With a growing citation impact, Zanatta’s work is shaping the future of energy-efficient, brain-inspired AI for robotics.