Fatemeh Zargarbashi

ETH Zurich, Sharif University of Technology

Papers

Total Citations

H-Index

About

Fatemeh Zargarbashi is a rising force in robotics, specializing in the intersection of reinforcement learning, model-based control, and soft-rigid hybrid systems. Her work is defined by a drive to make robots both more capable and more natural—bridging the gap between computational control and physical compliance. Her most cited paper (35 citations), "RL + Model-Based Control," introduces a framework that fuses on-demand optimal control with RL to achieve versatile, robust legged locomotion, a significant step toward adaptable robots. She further explores compliance in "Deep Compliant Control for Legged Robots" (8 citations), proposing a simple yet effective modification to RL training that encourages natural, low-frequency balance recovery. Zargarbashi also contributes to the emerging field of hybrid robotics, co-authoring "Simulation and Fabrication of Soft Robots with Embedded Skeletons" (14 citations), which draws inspiration from nature to combine the strength of rigid structures with the safety of soft materials. Her work on quadcopter stability rounds out a portfolio that spans both aerial and legged platforms, demonstrating a broad, systems-level approach to robot control. With a growing citation record and a focus on practical, nature-inspired solutions, Zargarbashi is shaping the next generation of intelligent, compliant machines.