Thomas Chaffre
Papers
1
Total Citations
4
H-Index
1
About
Thomas Chaffre is a researcher at the forefront of bridging the gap between simulation and reality in autonomous robotics, with a primary focus on reinforcement learning and robot navigation. His most cited work, "Sim-to-Real Transfer with Incremental Environment Complexity for Reinforcement Learning of Depth-based Robot Navigation" (2020), tackles one of the most persistent challenges in model-free control: transferring learning-based policies from simulated environments to physical robots without performance degradation. Chaffre’s key contribution lies in developing a curriculum learning approach that incrementally increases environmental complexity during training, enabling robust depth-based navigation policies that generalize effectively to real-world settings. This work has accumulated 4 citations, reflecting its relevance to researchers grappling with the sim-to-real gap. By addressing the high cost of real-world data collection and the sample inefficiency of deep reinforcement learning algorithms, Chaffre’s methodology offers a practical pathway for deploying autonomous systems in unstructured environments. His research continues to push the boundaries of how robots learn to navigate safely and efficiently, making him a notable voice in the growing field of transferable robotic intelligence.
Research Focus
Key Achievements
Top Papers
- 1