Maxime Beaudoin-pouliot
Papers
1
Total Citations
12
H-Index
1
About
Dr. Maxime Beaudoin-Pouliot is a leading researcher at the intersection of robotics, computer vision, and non-destructive testing (NDT), with a particular focus on automating critical quality assurance processes in aerospace manufacturing. His most cited work, "Multi-Robot System for Automated Fluorescent Penetrant Indication Inspection with Deep Neural Nets" (2021, 12 citations), introduces a pioneering framework that replaces the traditional, labor-intensive manual visual inspection of fluorescent penetrant indications (FPI) with a coordinated multi-robot system powered by deep neural networks. This contribution directly addresses a longstanding bottleneck in aerospace NDT, where distinguishing relevant defect indications from non-relevant ones is both subjective and error-prone. By integrating robotic manipulation with advanced deep learning classification, Beaudoin-Pouliot’s research demonstrates a scalable path toward fully automated, reliable defect detection—significantly improving inspection throughput and consistency. His work stands out for its practical deployment of AI in industrial settings, bridging the gap between theoretical computer vision and real-world manufacturing constraints. For students and researchers, Beaudoin-Pouliot exemplifies how robotics and deep learning can transform traditional inspection paradigms, offering a compelling model for future work in automated quality control and intelligent manufacturing systems.
Research Focus
Key Achievements
Top Papers
- 1