Lea Heitlinger

Papers

Total Citations

H-Index

About

Lea Heitlinger is an emerging researcher working at the intersection of human-robot interaction (HRI), multimodal learning, and adaptive systems design. Her work focuses on developing intelligent frameworks that enable robots to engage more naturally and effectively with humans, drawing on insights from human-human interaction as a foundation for robotic behavior. Among her most notable contributions is a hybrid modeling approach that combines Hidden Markov Models (HMMs) with Variational Autoencoders to learn joint distributions over interacting agents, allowing robots to acquire well-coordinated interaction skills by observing how humans naturally engage with one another. This work, which has garnered citations across both its 2023 and 2025 iterations, reflects her commitment to bridging theoretical machine learning with practical robotic applications. Her research also addresses the challenge of personalization in human-robot systems, as evidenced by her work emphasizing that universal solutions are insufficient for diverse user needs — a perspective that underscores a human-centered philosophy in her approach to system design. Though early in her career, Heitlinger's contributions signal a promising trajectory in the development of socially intelligent robots, making her work increasingly relevant to researchers in robotics, cognitive science, and artificial intelligence.