Advanced Search   
  Look in
       Name    Email
       Former RI Members 
Illah Nourbakhsh
Professor, RI
Office: NSH 3105
Phone: (412) 268-2007
Fax: 412-268-5571
  Mailing address:
Carnegie Mellon University
Robotics Institute
5000 Forbes Avenue
Pittsburgh, PA 15213
Administrative Assistant: Karen R. Widmaier
Affiliated Center(s):
 Center for the Foundations of Robotics (CFR)
Personal Homepage
Research Interests

For more than ten years I have been exploring human-robot interaction with the aim of creating rich, effective and satisfying interactions between humans and robots. My research has focused specifically on human-robot collaboration, wherein the robotic and human agents in the system share the same unifying goal or utility function. I further sharpen my scope to human-robot collaboration for learning, in which the measurable outcomes are information gain on the part of the humans in the system. In the context of my focus on collaboration for learning, rich means a cognitively sophisticated interaction in which humans and robots communicate as peers; effective means that formal measures of human learning should yield significant outcomes; satisfying means that humans should find the interaction both useful and pleasurable.

Three key questions govern my inquiry into human-robot collaboration:

  • What enabling competencies in the areas of social perception and control are required for applicability of the resulting models?
  • What principles of robot morphology and robot behavior design have broad applicability to the design of interaction systems?
  • Can a principled interaction evaluation methodology enable us to implement complete, feedback-driven design life cycles for interaction systems?

One research focus has been to develop embedded solutions to the problem of semantic interpretation of events using visual sensing. Another focus has been robot navigation because it is an important prerequisite to many forms of social interaction when the robot shares the human physical space. For example visual-topological navigation and hybrid metric-topological models aim to provide navigation competency with a minimum of computational and memory demands. Because of the cross-disciplinary nature of the human-robot collaboration problem, integrative research must bring robotics together with other fields that model human cognition and social behavior. I have joined and extended models of interaction and evaluation methodology from Human Factors, HCI and Cognitive Psychology, outstanding complements to robotics since these fields already consider human relationships to physical embodiments and consider human behavioral change over time.

Most recently we have begun to study the role of a research lab in meaningful design, dissemination and scaling with communities of practice. Our working model is one in which participatory design, design-based thinking and robotic innovation are combined to achieve positive social impact on specific problems throughout societies. For specific information about these projects, all of which are dedicated to make real impact while also establishing models for laboratory-community interaction, see my CREATE Lab website.