Ivan Gavran

Max Planck Institute for Software Systems

Papers

Total Citations

H-Index

About

Ivan Gavran is a researcher at the intersection of formal methods, robotics, and human-robot interaction, with a focus on making complex task specification accessible to non-experts. His most cited work, "Antlab" (2017, 26 citations), introduced an end-to-end system that allows users to specify robotic tasks declaratively using linear temporal logic (LTL) with quantifiers, enabling intuitive control over robot collectives without requiring programming expertise. Building on this, Gavran developed "Interactive synthesis of temporal specifications from examples and natural language" (2020, 19 citations), which bridges the gap between formal logic and natural human communication by synthesizing LTL specifications from examples and natural language descriptions—a critical contribution for robotics applications where domain experts may lack formal training. His work "Flipper" (2018) further advanced this vision by providing a natural language interface that compiles high-level task descriptions into robot actions, while his "Tᴏᴏʟ" system (2018) extended these ideas to industrial human-robot collaboration, offering an expressive domain-specific language for manufacturing planning. Gavran’s research has been recognized for its practical impact, with his systems enabling more intuitive and accessible robot programming, and his work continues to influence the development of human-centered automation.