Mohsen Davoudi

About

Mohsen Davoudi is a researcher whose work sits at the intersection of control theory, reinforcement learning, and autonomous navigation. His primary research areas include inverse reinforcement learning, path planning under uncertainty, and the integration of deep learning with classical control methods. Davoudi’s most significant contribution is his comprehensive historical review, "From inverse optimal control to inverse reinforcement learning: A historical review" (2020), which has garnered 114 citations—a testament to its value as a foundational resource for researchers navigating these interconnected fields. In his work "Uncertainty-aware Path Planning Using Reinforcement Learning and Deep Learning Methods" (2020), Davoudi proposed novel algorithms that enhance Reinforcement Learning and Deep Q-Network methods specifically for path planning in environments with perceptual uncertainty. This contribution directly addresses a critical challenge in robotics and autonomous systems: optimizing safe, efficient trajectories while accounting for imperfect sensor data. By formulating and solving the path planning optimization problem to avoid obstacles under uncertainty, Davoudi’s research bridges theoretical advances with practical deployment, making his work essential reading for students and engineers developing intelligent, adaptive navigation systems.

Research Focus

Key Achievements

Top Papers

1. 1
   From inverse optimal control to inverse reinforcement learning: A historical review

   114 citations · 2020
2. 2
   Uncertainty-aware Path Planning Using Reinforcement Learning and Deep Learning Methods

   3 citations · 2020

Key Collaborators

Contact & Links