Leila Amanzadeh
Papers
3
Total Citations
31
H-Index
3
About
Leila Amanzadeh is a rising leader in the field of robotic locomotion and multi-agent systems, with a focus on enabling robust, collaborative behaviors in legged robots. Her research centers on the intersection of model predictive control (MPC), adaptive control, and data-driven methods to solve complex coordination and manipulation challenges. Amanzadeh’s most impactful work, “Distributed Data-Driven Predictive Control for Multi-Agent Collaborative Legged Locomotion” (2023, 20 citations), introduces a novel planner based on behavioral systems theory that allows multiple holonomically constrained quadrupeds to move together reliably—a critical step toward real-world multi-robot teams. In her more recent work (2024, 8 citations), she extends this framework to payload transportation, integrating MPC with a gradient-descent-based indirect adaptive law to handle unknown dynamics and varying loads. By combining theoretical rigor with practical algorithms, Amanzadeh is advancing the frontier of cooperative legged robotics, demonstrating how data-driven predictive control can overcome the high-dimensional complexity of multi-agent systems. Her contributions are paving the way for applications in search-and-rescue, logistics, and collaborative manufacturing.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3