Ignacio Gil

About

Ignacio Gil is a leading researcher in aerial robotics and intelligent control systems, with a focus on integrating computer vision and reinforcement learning for autonomous drone navigation. His most influential work, "Image-Based Visual Servoing Controller for Multirotor Aerial Robots Using Deep Reinforcement Learning" (2018, 66 citations), pioneered a novel approach that combines Deep Deterministic Policy Gradients (DDPG) with visual servoing to enable multirotor UAVs to perform precise, image-driven maneuvers without explicit state estimation. This contribution bridges the gap between classical control theory and modern deep learning, offering a robust framework for real-time adaptive flight in unstructured environments. Gil’s research has significant implications for search-and-rescue, inspection, and agricultural monitoring, where visual feedback is critical. By training his RL-IBVS controller entirely in Gazebo simulation, he demonstrated the viability of sim-to-real transfer for complex aerial tasks. His work is widely cited by researchers advancing vision-based autonomy and reinforcement learning for robotics, marking him as a key innovator in the field of intelligent aerial systems.

Research Focus

Key Achievements

Top Papers

1. 1
   Image-Based Visual Servoing Controller for Multirotor Aerial Robots Using Deep Reinforcement Learning

   66 citations · 2018

Key Collaborators

Contact & Links