Simon Keizer
Papers
7
Total Citations
117
H-Index
5
About
Simon Keizer is a leading researcher in social human-robot interaction (HRI), with a particular focus on developing autonomous systems capable of managing multi-party, dynamic social scenarios. His work centers on creating robots that can understand and engage with multiple humans simultaneously, moving beyond one-on-one interactions. Keizer’s major contribution is the development of a data-driven, machine-learning framework for social state recognition and action selection, demonstrated through his influential “robot bartender” platform. This system, which tracks multiple customers, takes orders, and serves drinks, serves as a testbed for modeling complex social dynamics. His key papers, including “Machine Learning for Social Multiparty Human–Robot Interaction” (38 citations) and “Training and evaluation of an MDP model for social multi-user human-robot interaction” (30 citations), showcase his pioneering use of Markov Decision Processes (MDPs) to learn optimal interaction strategies. Keizer has also advanced the field by addressing the critical challenge of handling uncertain sensory input, using belief tracking and clarification strategies to maintain robust interaction. His work, implemented on both a full-scale robot and a Nao robot, has been validated through extensive user evaluations, cementing his reputation as a key figure in creating socially aware, multi-user robotic systems.
Research Focus
Key Achievements
Top Papers
- 1Machine Learning for Social Multiparty Human--Robot Interaction38 citations · 2014
- 2
- 3Evaluating a social multi-user interaction model using a Nao robot19 citations · 2014
- 4
- 5Handling uncertain input in multi-user human-robot interaction8 citations · 2014
- 6
- 7