Navid Aghasadeghi

University of Illinois Urbana-Champaign, University of Illinois System, Max Planck Institute for Biological Cybernetics

Papers

Total Citations

H-Index

About

Navid Aghasadeghi is a researcher whose work bridges robotics, control theory, and human-robot interaction. His key research areas include inverse optimal control, hybrid dynamical systems, and aerial robotics manipulation. Aghasadeghi made significant contributions to understanding how robots can learn from human demonstrations, particularly through his work on inverse optimal control for hybrid systems with impacts (23 citations), which provides a framework for inferring cost functions from observed behaviors in systems that undergo discrete changes like collisions. His innovative approach to quadrotor payload manipulation, detailed in his paper on a passive cam-follower mechanism (8 citations), demonstrates practical engineering solutions for aerial robotics, enabling efficient payload pickup and release without active control. Additionally, his work on maximum entropy inverse reinforcement learning in continuous state spaces (4 citations) extends learning from demonstration techniques to more complex, real-world scenarios. Aghasadeghi’s research has been recognized for its novel integration of theoretical control methods with practical robotic applications, making his work valuable for students and researchers interested in robot learning, optimal control, and autonomous aerial systems.