Steven Holtzen

Papers

Total Citations

H-Index

About

Steven Holtzen is a researcher whose work lies at the intersection of artificial intelligence, robotics, and human-robot interaction, with a particular focus on enabling machines to understand and anticipate human behavior. His key contributions center on developing computational models for inferring human intent and theory of mind—the ability to attribute mental states to others—from sensory data. In his most-cited work, "Inferring human intent from video by sampling hierarchical plans" (2016, 28 citations), Holtzen introduced a method that allows robots to deduce a person's hierarchical goals from partially observed RGBD videos by simulating future actions. This capability is foundational for creating socially aware robots that can collaborate naturally with humans. His earlier paper, "Represent and Infer Human Theory of Mind for Human-Robot Interaction" (2015, 7 citations), further explores how robots can model human beliefs and intentions to improve interaction quality. Though his citation counts reflect a growing field, Holtzen’s work is notable for its practical approach to a core challenge in robotics: bridging the gap between raw sensory input and high-level social reasoning. His research is particularly valuable for students and researchers interested in cognitive robotics, planning under uncertainty, and human-aware AI systems.