Gilles Louppe
Papers
2
Total Citations
4
H-Index
2
About
Gilles Louppe is a leading researcher at the intersection of machine learning, simulation-based inference, and robotics. His work focuses on developing probabilistic methods to enable robust decision-making under uncertainty, particularly for complex physical systems. Louppe’s major contributions include pioneering the use of sequential neural ratio estimation (SNRE) for robotic grasping, where he has introduced novel frameworks that combine Bayesian inference with neural implicit representations. His 2021 work on simulation-based Bayesian inference for multi-fingered robotic grasping addresses the fundamental challenge of controlling dexterous hands in the presence of nonsmooth contact dynamics and sensor noise. More recently, his 2024 paper on 6-DoF grasping under uncertainties extends this approach to cluttered environments, computing maximum a posteriori hand configurations. While these specific papers have accrued modest citation counts as emerging works, Louppe’s broader impact is evidenced by his highly cited foundational contributions to probabilistic programming and neural density estimation, including the widely-used BayesFlow library. His research is notable for bridging cutting-edge machine learning with practical robotic manipulation, offering principled solutions to real-world uncertainty.
Research Focus
Key Achievements
Top Papers
- 1
- 2Simulation-based Bayesian inference for multi-fingered robotic grasping2 citations · 2021