Manos Kirtas

About

Manos Kirtas is a researcher at the forefront of integrating deep reinforcement learning with practical robotics, with a particular emphasis on accessible, low-cost solutions. His work centers on developing intelligent navigation and control frameworks for autonomous systems, making cutting-edge AI-driven robotics more attainable. Kirtas is perhaps best known for his foundational contribution, "Deepbots: A Webots-Based Deep Reinforcement Learning Framework for Robotics" (2020), which has garnered 32 citations and established a widely-used simulation environment for training robotic agents. This work provides a crucial bridge between virtual training and real-world deployment. Building on this, his recent research tackles the challenge of affordable autonomous navigation. In his 2023 paper, he demonstrates how differential-drive robots can successfully navigate to targets while avoiding obstacles using only low-cost sensors, achieved through innovative action masking in deep reinforcement learning. This approach significantly reduces the hardware barrier to entry, moving beyond expensive LiDAR and depth cameras. Kirtas’s contributions are shaping a future where intelligent, self-navigating robots are not just for well-funded labs but are accessible for broader research and educational applications.

Research Focus

Key Achievements

Top Papers

1. 1
   Deepbots: A Webots-Based Deep Reinforcement Learning Framework for Robotics

   32 citations · 2020
2. 2
   Deep learning for robotics examples using OpenDR

   2 citations · 2022
3. 3
   Deep Reinforcement Learning With Action Masking for Differential-Drive Robot Navigation Using Low-Cost Sensors

   2 citations · 2023

Key Collaborators

Contact & Links