CSCI 5402: Research Methods in HRI

Ìý

Instructor: Daniel Szafir

Daniel.Szafir@Colorado.EDU

Course Description

Introduces students to the field of human-robot interaction (HRI). Covers HRI theory, principles, methodologies, and applications with links to robotics, artificial intelligence, human factors, human-computer interaction, design, cognitive psychology, education and other domains. Coursework includes readings from state-of-the-art in HRI research, team exercises and problem-solving sessions, and implementation and evaluation of a human-robot interaction systems for specific applications.

List the Principal Topics Covered in This Course

  • History and Overview of HRI (1 week)
    • Brief history of robotics
    • Development of HRI as its own research field
    • Open problem areas within HRI
  • Overview of Research Methodology (3 weeks)
    • What is research
    • Different types of methodologies (empirical, positivist vs interpretivist, summative vs formative)
    • Methodological fit
    • Methodological considerations (sampling, control, analysis)
    • Techniques, manipulations, and trade-offs
    • Validity
  • Experimental Design (3 weeks)
    • Forming a research question
    • Developing hypotheses
    • Independent and dependent variables, understanding factors and levels
    • Understanding the trade-offs of different types of designs (laboratory, field, respondent, and theoretical)
    • Design considerations (between vs within, counterbalancing, randomization, control, etc.)
  • Bayesian Inference (2 weeks)
    • Conditional probability
    • Example: going from probability to inference and decision-making for robot perception
    • Markov networks
    • Hidden Markov Models
  • Measures (2 weeks)
    • Objective measures
    • Composite measures
    • Subjective measures
    • Scale construction and factor analysis
    • Validity
    • Reliability
  • Inferential Statistical Analysis (2 week)
    • Using R and JMP
    • When to use what test
    • Type I and II errors
    • T-test
    • ANOVA
    • Chi-square
    • Linear regression
    • Post hoc analysis
  • Qualitative Methods (1 week)
    • Ethnography
    • Grounded theory
  • Each of these methods in contextualized in an HRI topic that aligns with the course readings that week. Topics include:
    • Robot form and morphology
    • Teleoperation and control
    • Social robotics
    • Natural language for robotics
    • Robot motion and communicating robot intentions
    • Field robotics

Required Readings

Journals:Ìý

  • Goodrich & Schultz: Human-Robot Interaction: A Survey (2007)
  • Cassell, Justine. Embodied Conversational Agents: Representation and Intelligence in User Interfaces. AI magazine 22.4 (2001): 67.
  • Simmons, Reid, et al. Believable Robot Characters AI Magazine 32.4 (2011): 39-52.
  • Mcgrath, E. Methodology Matters: Doing Research in the Behavioral and Social Sciences. Readings in Human-Computer Interaction: Toward the Year 2000 (2nd ed. 1995).
  • Duffy, Brian R. "Anthropomorphism and the social robot." Robotics and autonomous systems 42.3 (2003): 177-190.
  • Strait, Megan, et al. "Let Me Tell You! Investigating the Effects of Robot Communication Strategies in Advice-giving Situations based on Robot Appearance, Interaction Modality and Distance." Proceedings of the 2014 ACM/IEEE International Conference on Human-Robot Interaction.
  • Klemmer, Scott R., Björn Hartmann, and Leila Takayama. "How bodies matter: five themes for interaction design." Proceedings of the 6th conference on Designing Interactive systems. ACM, 2006.
  • Nass, Clifford, and Youngme Moon. "Machines and Mindlessness: Social Responses to Computers." Journal of social issues 56.1 (2000): 81-103.
  • Bilge Mutlu, Toshiyuki Shiwa, Takayuki Kanda, Hiroshi Ishiguro, and Norihiro Hagita. 2009. Footing in human-robot conversations: how robots might shape participant roles using gaze cues. In Proceedings of the 2009 ACM/IEEE international conference on Human robot interaction (HRI '09). ACM, 2009.
  • Vázquez, Marynel, et al. "Spatial and other social engagement cues in a child-robot interaction: Effects of a sidekick." Proceedings of the 2014 ACM/IEEE international conference on Human-robot interaction. ACM, 2014.
  • Vázquez, Marynel, Aaron Steinfeld, and Scott E. Hudson. "Maintaining awareness of the focus of attention of a conversation: A robot-centric reinforcement learning approach." Robot and Human Interactive Communication (RO-MAN), 2016 25th IEEE International Symposium on. IEEE, 2016. Kaupp, Tobias, Alexei Makarenko, and Hugh Durrant-Whyte. "Human–robot communication for collaborative decision making—A probabilistic approach." Robotics and Autonomous Systems 58.5 (2010): 444-456.
  • Tellex, Stefanie, et al. "Approaching the symbol grounding problem with probabilistic graphical models." AI magazine 32.4 (2011): 64-76.
  • Yang, Hee-Deok, A-Yeon Park, and Seong-Whan Lee. "Gesture spotting and recognition for human–robot interaction." IEEE Transactions on Robotics 23.2 (2007): 256-270.
  • Baldwin, Dare A., and Jodie A. Baird. "Discerning intentions in dynamic human action."
  • Trends in cognitive sciences 5.4 (2001): 171-178.
  • Csibra, Gergely, and György Gergely. "‘Obsessed with goals’: Functions and mechanisms of teleological interpretation of actions in humans." Acta psychologica 124.1 (2007): 60-78.
  • Dragan, Anca D., Kenton CT Lee, and Siddhartha S. Srinivasa. "Legibility and predictability of robot motion." Human-Robot Interaction (HRI), 2013 8th ACM/IEEE International Conference on. IEEE, 2013.
  • Sheridan, T. B. (1995). Teleoperation, telerobotics and telepresence: A progress report. Control Engineering Practice, 3(2), 205-214.
  • Fong, T., Thorpe, C., & Baur, C. (2003). Multi-robot remote driving with collaborative control. IEEE Transactions on Industrial Electronics, 50(4), 699-704.
  • Nielsen, Curtis W., Michael A. Goodrich, and Robert W. Ricks. "Ecological interfaces for improving mobile robot teleoperation." IEEE Transactions on Robotics 23.5 (2007): 927-941.
  • Mutlu, Bilge, and Jodi Forlizzi. "Robots in organizations: the role of workflow, social, and environmental factors in human-robot interaction." Proceedings of the 3rd ACM/IEEE international conference on Human robot interaction. ACM, 2008.
  • Salem, Maha, et al. "Would you trust a (faulty) robot?: Effects of error, task type and personality on human-robot cooperation and trust." Proceedings of the Tenth Annual ACM/IEEE International Conference on Human-Robot Interaction. ACM, 2015.
  • Robinette, Paul, et al. "Overtrust of robots in emergency evacuation scenarios." Human-Robot Interaction (HRI), 2016 11th ACM/IEEE International Conference on. IEEE, 2016.

Student Learning Outcomes

By the end of the course, students will have gained knowledge and skills to:

  • Understand the fundamental concepts relating to HRI such as design, implementation, and evaluation
  • Read deeply, understand, and critique academic research papers relating to HRI
  • Create algorithms guiding robot behaviors and design robot interfaces with the context of HRI
  • Apply findings from relevant psychology and social sciences to the design of interactive robots
  • Work successfully with a group of peers from a variety of disciplines on a research project
  • Conduct human-subjects research within the scope of HRI
  • Communicate and present individual and group project work

Grading

  • 10% - Consistent attendance and active participation
  • 25% - Quizzes, reading responses, programming exercises, and problem sets
  • 30% - Student presentations and methods assignments
  • 35% - Final project