Papers
4
Total Citations
49
H-Index
4
About
Serge Garlatti is a leading researcher in autonomous robotics, specializing in the application of reinforcement learning (RL) to reconfigurable and assistive robots. His work focuses on solving the complex control challenges of articulated tracked robots navigating unstructured environments, particularly the high-risk task of staircase traversal. Garlatti’s major contribution is the development of scalable, AI-driven control frameworks that replace platform-specific programming with adaptive learning. He has pioneered RL-based methods for staircase negotiation, demonstrating successful simulation-to-reality transfer for robots with varying degrees of freedom. His most cited paper (20 citations) establishes a foundational approach for autonomous control of reconfigurable robots, while his open-source software framework (10 citations) provides a critical research tool built on Gazebo and ROS, enabling the broader community to develop and test RL-based control skills. By bridging the gap between simulation and physical deployment, Garlatti’s work is advancing the practicality of assistive and field robots, making them more adaptable to diverse hardware and unpredictable real-world conditions.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3
- 4