Kevin French

Papers

Total Citations

H-Index

About

Kevin French is a leading researcher in robot learning from demonstration (LfD) and semantic programming for taskable robots. His work focuses on making robotic programming accessible to non-experts by enabling robots to learn complex, multi-step tasks from human demonstrations. French’s most influential paper, "Learning Behavior Trees From Demonstration" (2019, 78 citations), introduced a novel method for translating human demonstrations into structured behavior trees, allowing robots to execute intricate sequences of actions without requiring low-level programming expertise. This work has been widely cited for its practical impact on simplifying robot task learning. More recently, French developed "Super Intendo: Semantic Robot Programming from Multiple Demonstrations" (2023), which advances LfD by integrating semantic reasoning to handle variability across demonstrations, improving robot adaptability in real-world settings. His contributions bridge the gap between human intuition and robotic execution, with potential applications in manufacturing, healthcare, and domestic assistance. French’s research is particularly notable for its emphasis on democratizing robotics—empowering users with no technical background to program robots for arbitrary tasks. His ongoing work continues to push the boundaries of intuitive human-robot interaction.