Ludovic Denoyer

Laboratoire de Recherche en Informatique de Paris 6, Centre National de la Recherche Scientifique

Papers

Total Citations

H-Index

About

Ludovic Denoyer is a leading researcher at the intersection of machine learning and robotics, with a core focus on developing intelligent systems capable of efficient decision-making under real-world constraints. His major contributions center on the challenge of budgeted localization—enabling robots to navigate and determine their position with minimal sensing and computational cost. In his seminal works, "Sequential Action Selection for Budgeted Localization in Robots" and "Sequential Action Selection and Active Sensing for Budgeted Localization in Robot Navigation," Denoyer pioneered algorithms that allow robots to actively choose which actions to take and which sensors to use, optimizing for both accuracy and resource efficiency. While these foundational papers have garnered modest citation counts, their conceptual impact is significant, addressing a critical gap in robotics: the need for systems that explicitly consider operational budgets during learning and execution. Denoyer’s work stands out for its principled approach to marrying active sensing with sequential decision-making, offering a framework that has influenced subsequent research in autonomous navigation, reinforcement learning, and resource-aware AI. His contributions are particularly valuable for students and researchers interested in building practical, cost-sensitive robotic systems.