Andrea Acquaviva

Papers

Total Citations

H-Index

About

Andrea Acquaviva is a leading researcher at the intersection of neuromorphic computing and autonomous robotics, with a primary focus on enabling intelligent, energy-efficient flight for small-scale drones. His major contributions lie in pioneering the use of Spiking Neural Networks (SNNs)—the third generation of artificial neural networks that more closely mimic the mammalian brain—for deep reinforcement learning (DRL) in robotic tasks. Acquaviva’s work demonstrates how SNNs, governed by ordinary differential equations, can achieve robust control policies while offering significant power advantages over traditional neural networks. His most cited paper, "Exploring spiking neural networks for deep reinforcement learning in robotic tasks" (2024, 24 citations), establishes a foundational framework for this approach. He has further advanced the field by applying DRL to achieve agile flight on nano-drones, addressing the critical challenge of deploying complex policies on real, resource-constrained hardware. Through comparative studies, Acquaviva systematically evaluates the performance and efficiency of SNN-based DRL against conventional methods, positioning him as a key figure in the push toward brain-inspired, low-power autonomy for next-generation robotic systems.