Papers
3
Total Citations
22
H-Index
3
About
Johann Laurent is a researcher advancing the frontier of autonomous multi-robot systems, with a primary focus on intelligent task allocation and distributed computational management. His work centers on solving the critical challenge of how robotic clusters can locally distribute processing loads without relying on cloud infrastructure, enabling missions that demand high autonomy and precision. Laurent’s major contribution lies in pioneering the application of Deep Q-Learning (DQN) as a dynamic, learning-based alternative to traditional market-based methods for Multi-Robot processing Task Allocation (MRpTA). His most cited paper, "Deep Q-Learning-Based Dynamic Management of a Robotic Cluster" (2022, 10 citations), demonstrates how reinforcement learning can optimize real-time decision-making in complex, uncertain environments. Complementing this, his comparative studies (2020, 7 citations; 2021, 5 citations) systematically validate DQN’s effectiveness over conventional approaches, providing a foundational framework for distributed intelligence in robotics. Laurent’s work is notable for bridging reinforcement learning and multi-robot coordination, offering scalable solutions that empower each robot to contribute meaningfully to collective computational tasks. His research is essential reading for students and engineers exploring autonomous systems, edge computing, and the future of decentralized robotic intelligence.
Research Focus
Key Achievements
Top Papers
- 1Deep Q-Learning-Based Dynamic Management of a Robotic Cluster10 citations · 2022
- 2
- 3