David Klotz

About

David Klotz is a researcher whose work sits at the intersection of human-robot interaction (HRI), multimodal dialogue systems, and conversational AI. His primary contributions center on enabling robots to engage naturally in multi-party, real-world conversations—a challenge far removed from simple one-on-one command interfaces. Klotz was instrumental in creating the "Vernissage Corpus," a landmark multimodal HRI dataset introduced in a series of papers (2012–2013, accumulating over 50 citations collectively). This corpus, built around a humanoid NAO robot interacting with multiple people in a social setting, provides richly annotated data for tasks like speaker localization, visual focus of attention recognition, and engagement detection. His work on "Engagement-based Multi-party Dialog with a Humanoid Robot" (2011, 28 citations) directly tackled the robot’s challenge of deciding when and how to interact with specific users in a group. By developing frameworks for acquiring whole-system interaction data and leveraging robot dialogue state for perceptual tasks, Klotz has helped lay the empirical groundwork for robots that can read social cues and participate fluidly in human conversation, moving HRI from scripted exchanges toward truly interactive, context-aware systems.

Research Focus

Key Achievements

Top Papers

1. 1
   The vernissage corpus: A conversational Human-Robot-Interaction dataset

   33 citations · 2013
2. 2
   Engagement-based Multi-party Dialog with a Humanoid Robot

   28 citations · 2011
3. 3
   THE VERNISSAGE CORPUS: A MULTIMODAL HUMAN-ROBOT-INTERACTION DATASET

   15 citations · 2012
4. 4
   A Framework for the Acquisition of Multimodal Human-Robot Interaction Data Sets with a Whole-System Perspective

   9 citations · 2012
5. 5
   Leveraging the robot dialog state for visual focus of attention recognition

   3 citations · 2013

Key Collaborators

Contact & Links