Daniel Giger

Papers

Total Citations

H-Index

About

Daniel Giger is a leading researcher at the intersection of human-robot interaction and autonomous manipulation, with a focus on making robots both more capable and more transparent. His work is distinguished by two major contributions: pioneering the use of Behavior Trees as a foundation for robot explanation generation, and advancing mobile manipulation in highly constrained, real-world environments. In his most-cited work (34 citations), Giger addresses the critical challenge of robot transparency by developing a structured framework that organizes complex, hierarchical tasks into readily explainable sequences. This approach allows autonomous systems to articulate not just *what* they are doing, but *why*—a crucial step for trust and safety in human-adjacent deployments. Complementing this, his research on the FetchIt! Mobile Manipulation Challenge (18 citations) tackles the physical side of autonomy, demonstrating robust multi-task manipulation with irregular objects in confined, integrated spaces. By bridging the gap between explainable AI and practical, dexterous robotics, Giger’s work is shaping a future where robots can both perform complex tasks and clearly communicate their reasoning to the people they work alongside.