Paul Reisert
Papers
1
Total Citations
13
H-Index
1
About
Paul Reisert is a pioneering researcher at the intersection of human-robot interaction and natural language processing, with a primary focus on making social robots more engaging conversational partners. His most cited work, "Ain't Misbehavin' - Using LLMs to Generate Expressive Robot Behavior in Conversations with the Tabletop Robot Haru" (2024, 13 citations), represents a significant breakthrough in overcoming the limitations of scripted robot interactions. By integrating large language models into the Haru tabletop robot, Reisert has demonstrated how AI can generate more natural, expressive, and contextually appropriate behaviors during conversations—a critical step toward robots that can form genuine long-term bonds with humans. This work bridges the gap between rigid pre-programmed responses and the fluid, adaptive communication that users expect. His contributions are particularly valuable for students and researchers exploring how LLMs can enhance non-verbal expressiveness, such as gestures and vocal tones, in embodied agents. Reisert's research not only advances technical capabilities but also addresses fundamental questions about what makes human-robot interaction feel authentic and sustainable over time.
Research Focus
Key Achievements
Top Papers
- 1