Ludovic Trottier

Papers

Total Citations

H-Index

About

Ludovic Trottier’s research lies at the intersection of computer vision and robotic manipulation, with a core focus on enabling autonomous systems to grasp and handle objects in dynamic, real-world environments. His work addresses a fundamental challenge in both domestic and industrial robotics: how a robot can identify stable, reliable grasp locations on objects it has never seen before. Trottier pioneered the use of sparse dictionary learning and deep learning architectures to solve this problem, developing methods that allow robots to recognize and localize grasps using 3D sensor data from devices like the Microsoft Kinect. His most cited paper, “Sparse Dictionary Learning for Identifying Grasp Locations” (2017, 10 citations), and its companion work on dictionary learning for grasp recognition (8 citations) laid the groundwork for more efficient, data-driven grasp detection. He further advanced the field by introducing convolutional residual networks for grasp localization and deep object ranking for template matching, techniques that improve both the precision and speed of pick-and-place operations. Though his citation counts are modest, Trottier’s contributions are notable for their practical impact on autonomous manipulation, offering scalable solutions that help robots transition from controlled lab settings to cluttered, unpredictable environments.