Liesl Wigand

Papers

Total Citations

H-Index

About

Liesl Wigand is a researcher whose work lies at the intersection of artificial intelligence and human-robot interaction, with a primary focus on intent recognition. Her foundational research addresses a critical challenge in robotics: enabling machines to accurately infer and predict human intentions during collaborative tasks. In her most-cited work, "Deep networks for predicting human intent with respect to objects" (2012, 19 citations), Wigand pioneered the use of stacked denoising autoencoders for intent recognition—an early application of deep learning to this domain. This paper not only framed the intent recognition problem for the robotics community but also demonstrated how deep architectures could improve the reliability of human-robot communication. Her subsequent work, "Intent Recognition for Human–Robot Interaction" (2014, 4 citations), further refined these concepts, exploring how robots can anticipate human actions in real-time. While her citation counts reflect a specialized niche, Wigand’s contributions are significant for advancing more intuitive and responsive robotic systems. Her research has implications for assistive robotics, manufacturing, and any domain where seamless human-robot collaboration is essential, marking her as a thoughtful contributor to the field of socially aware AI.