J. P. Mercier

Papers

Total Citations

H-Index

About

J. P. Mercier is a roboticist whose research focuses on the intersection of sensor placement, object localization, and robotic manipulation. Mercier’s work addresses fundamental challenges in enabling robots to perceive and interact with complex, unstructured environments. A key contribution is the development of a complete system for optimal multisensor placement in unknown 3D spaces, using a novel visibility estimation and derivative-free optimization approach (9 citations). This work is critical for tasks like autonomous exploration and inspection. In the domain of robotic manipulation, Mercier has advanced template-matching techniques for pick-and-place operations, proposing a deep object ranking method that improves precision when handling numerous objects (6 citations). More recently, Mercier has tackled the data-hungry nature of deep learning for pose estimation, developing a method that learns accurate 6D object localization from simulation and only weakly labeled real-world images (3 citations). This work is particularly valuable for applications in cluttered, tight environments like shelves. Mercier’s contributions are paving the way for more adaptable and data-efficient robotic systems, with direct implications for industrial automation and service robotics.