Maryam Parsa

Papers

Total Citations

H-Index

About

Maryam Parsa is a rising leader at the intersection of neuromorphic computing, swarm robotics, and edge intelligence. Her research focuses on enabling ultra-low-power artificial intelligence for autonomous systems, particularly through the use of spiking neural networks (SNNs) and bio-inspired control strategies. In her most cited work, "Evolutionary vs Imitation Learning for Neuromorphic Control at the Edge" (2021, 21 citations), Parsa systematically compares learning paradigms for deploying SNN-based controllers on resource-constrained hardware, establishing foundational principles for energy-efficient autonomous agents. She further advances the field by pioneering methods to address the simulation-reality gap in robot swarms, as demonstrated in "Simulate Less, Expect More: Bringing Robot Swarms to Life via Low-Fidelity Simulations" (2023), where she proposes a paradigm shift: instead of endlessly refining simulations, researchers should characterize when low-fidelity models are sufficient for real-world transfer. Most recently, her work "Spiking Neural Networks as a Controller for Emergent Swarm Agents" (2024) explores how SNNs can generate organic, mosquito-like swarm behaviors in low-cost drones. Parsa’s contributions are shaping the future of edge-deployed autonomous swarms, offering practical pathways to bridge simulation and reality while dramatically reducing power consumption.