Thibaut Deleruyelle

Institut Supérieur de l'Électronique et du Numérique

Papers

1

Total Citations

5

H-Index

1

About

Thibaut Deleruyelle is a researcher at the forefront of embedded robotics and adaptive control systems, with a focus on integrating large language models (LLMs) with reinforcement learning for real-time autonomous navigation. His most notable contribution is the development of a hybrid LLM Q-learning/deep Q-network (DQN) framework, first introduced in his 2025 paper, which has already garnered 5 citations. This pioneering work demonstrates how a locally deployed LLM can enhance obstacle avoidance by enabling an STM32WB55RG microcontroller to make context-aware, real-time decisions using sensor data—a significant leap in bridging natural language processing with resource-constrained embedded systems. Deleruyelle’s research addresses critical challenges in adaptive robotics, offering a scalable solution for safer, more intelligent autonomous agents. His achievements highlight a unique interdisciplinary approach, combining reinforcement learning, edge computing, and AI, positioning him as an emerging leader in the field. For students and researchers, his work exemplifies how cutting-edge AI can be practically deployed in low-power environments, opening new avenues for next-generation robotic systems.

Research Focus

Key Achievements

1
H-Index
1
Papers
5
Total Citations
5
Avg Citations/Paper
🏆 Most Cited Paper
Evaluating a Hybrid LLM Q-Learning/DQN Framework for Adaptive Obstacle Avoidance in Embedded Robotics
5 citations · 2025
📈 Most Prolific Year: 2025 (1 Papers)
🤝 Key Collaborators: 2
🏛 Institutions: Institut Supérieur de l'Électronique et du Numérique

Top Papers

  1. 1

Key Collaborators

Contact & Links

Available for collaboration
Content generated · 13 days ago