Sagar Gubbi

Papers

Total Citations

H-Index

About

Sagar Gubbi is a researcher advancing the frontier of robotic manipulation, with a primary focus on imitation learning for contact-rich industrial tasks. His most cited work, "Imitation Learning for High Precision Peg-in-Hole Tasks" (2020, 16 citations), addresses a persistent challenge in robotics: enabling industrial manipulators to match human-level precision and speed in assembly operations. Gubbi’s key contribution lies in demonstrating generative imitation learning methods that allow a 6-DOF robot to replicate complex peg-in-hole insertions—a fundamental yet notoriously difficult task requiring fine force control and adaptability. By bridging the gap between human dexterity and robotic automation, his research has direct implications for manufacturing, where high-precision assembly remains a bottleneck. Beyond this flagship paper, Gubbi’s work explores how robots can learn from demonstration to handle variable conditions, reducing the need for manual programming. His findings are particularly valuable for students and engineers seeking to understand how machine learning can enhance robotic performance in real-world, contact-rich environments. With growing interest in autonomous manufacturing, Gubbi’s contributions are poised to shape the next generation of adaptive industrial robots.