Professor: Andrea Bajcsy (abajcsy [at] cmu [dot] edu)
Office Hours: Tues, 12:20 - 1:20 pm (after class)
Office Hours Location: NSH 4629

Teaching Assistant: Pranay Gupta (pranaygu [at] andrew [dot] cmu [dot] edu)
Office Hours: 4:00 - 5:00pm
Office Hours Location: NSH 4504

Lecture Time: Tues & Thurs, 11:00 - 12:20 pm
Lecture Location: Wean 4623
Syllabus: PDF
Canvas: https://canvas.cmu.edu/courses/41578

Overview

Human-robot interaction (HRI) is a multidisciplinary field that aims to create successful interactions between people and robots. In this class, we will study algorithmic HRI topics such as mathematical human models, trajectory forecasting, shared autonomy, robot learning from human feedback, active learning, communication, and safety.

This course aims to provide an overview of the state of the art in algorithmic HRI. As such, it will cover a large number of topics, with examples drawn from foundational work and research published in the last five years. The course combines lecture, readings, in-class presentations, written reports, and a final project to engage students with the current challenges and approaches in the field. The course also emphasizes the practice of reading and discussing scientific literature to learn and communicate about the most recent progress in HRI.

News

[09/05/24]
Lecture notes 4 uploaded
[09/03/24]
Lecture notes 3 uploaded
[09/02/24]
Small updates to the first two week schedule and papers
[08/29/24]
Lecture notes 1 and 2 uploaded
[08/19/24]
New room location: Wean 4623

Schedule (tentative)

Date	Topic	Info
Week 1 Tue, Aug 27	Lecture Introduction	Please check the course syllabus Materials: *Slides*
Week 1 Thurs, Aug 29	Lecture Fundamentals	Single-Agent Decision Making Materials: *Notes*
Week 2 Tue, Sept 3	Lecture Fundamentals	Single-Agent Decision Making (cont'd) Materials: *Notes*
Week 2 Thurs, Sept 5	Lecture Fundamentals	Probability, Bayesian inference Materials: *Notes*
Week 3 Tue, Sept 10	Paper discussion Fundamentals	Required reading: [P1] Goal Inference as Inverse Planning. Baker, et al. (2007) [P2] Planning-based Prediction for Pedestrians. Zeibart, et al. (2009)
Week 3 Thurs, Sept 12	Paper discussion Mathematical Human Models	Required Reading: [P1] Where Do You Think You’re Going?: Inferring Beliefs about Dynamics from Behavior. Reddy, et al. (2018) [P2] LESS is More: Rethinking Probabilistic Models of Human Behavior. Bobu, et al. (2020)
Week 4 Tue, Sept 17	Lecture Trajectory Forecasting	Planning-based & learning-based; applications in manipulation, navigation
Week 4 Thurs, Sept 19	Paper discussion Trajectory Forecasting	Required reading: [P1] Probabilistically Safe Robot Planning with Confidence-Based Human Predictions. Bajcsy, et al. (2018) [P2] ManiCast: Collaborative Manipulation with Cost-Aware Human Forecasting. Kedia, et al. (2023)
Week 5 Tues, Sept 24	Guest Lecture Shared Autonomy	Dylan Losey (Prof @ Virginia Tech)
Week 5 Thurs, Sept 26	Paper discussion Shared Autonomy	Required reading: [P1] Shared Autonomy via Hindsight Optimization. Javdani, et al. (2015) [P2] LILA: Language-Informed Latent Actions. Karamcheti, et al. (2021)
Week 6 Tue, Oct 8	Lecture Experimental Design	Due Homework Designing and conducting user studies
Week 6 Thurs, Oct 10	Paper discussion Experimental Design	Required Reading: [P1] Review of Human Studies Methods in HRI and Recommendations. Bethel & Murphy (2010) [P2] Feel the Bite: Robot-Assisted Inside-Mouth Bite Transfer using Robust Mouth Perception and Physical Interaction-Aware Control. Jenamani, et al. (2024) [P3] Independence in the Home: A Wearable Interface for a Person with Qadriplegia to Teleoperate a Mobile Manipulator. Padmanabha, et al. (2024)
Week 7 Tue, Oct 14	No Class (Fall Break)
Week 7 Thurs, Oct 17	No Class (Fall Break)
Week 8 Tue, Oct 22	Guest Lecture Robot Learning from Human Feedback	Tesca Fitzgerald (Prof @ Yale)
Week 8 Thurs, Oct 24	Paper discussion Robot Learning from Human Feedback	Required Reading: [P1] Learning Robot Objectives from Physical Human Interaction. Bajcsy et al. (2018) [P2] Correcting Robot Plans with Natural Language Feedback. Sharma et al. (2022) [P3] Gesture-Informed Robot Assistance via Foundation Models. Lin, et al. (2023)
Week 9 Tue, Oct 29	Lecture Active Learning	Due Mid-term Report Information gain, Asking questions
Week 9 Thurs, Oct 31	Paper discussion Active Learning	Required Reading: [P1] Asking Easy Questions: A User-Friendly Approach to Active Reward Learning. Biyik, et al. (2019) [P2] INQUIRE: INteractive Querying for User-aware Informative REasoning. Fitzgerald et al. (2023)
Week 10 Tue, Nov 5	No Class (Democracy Day)
Week 10 Thur, Nov 7	Lecture Communication	Theory of mind, legibility, communicating objectives and policies
Week 11 Tue, Nov 12	Paper discussion Communication	Required Reading: [P1] Designing robot learners that ask good questions. Cakmak & Thomaz (2012) [P2] Expressing Robot Incapability. Huang, et al. (2018) [P3] Planning with Verbal Communication for Human-Robot Collaboration. Nikolaidis, et al. (2018)
Week 11 Thur, Nov 14	Lecture HRI as a Game	Influence-aware planning
Week 12 Tue, Nov 19	Paper discussion HRI as a Game	Required Reading: [P1] Towards Robots that Influence Humans over Long-Term Interaction. Sagheb, et al. (2023) [P2] Planning for Autonomous Cars that Leverage Effects on Human Actions. Sadigh, et al. (2018)
Week 12 Thurs, Nov 21	Lecture Safety & Uncertainty Quantification	Decision-theoretic & statistical safety for HRI
Week 13 Tue, Nov 26	Paper discussion Safety & Uncertainty Quantification	Required Reading: [P1] Quantifying Hypothesis Space Misspecification in Learning from Human-Robot Demonstrations and Physical Corrections. Bobu, et al. (2020) [P2] Robots That Ask For Help: Uncertainty Alignment for Large Language Model Planners. Ren, et al. (2023)
Week 13 Thurs, Nov 28	No Class (Thanksgiving)
Week 14 Tue, Dec 3	Final presentations	Due Slides uploaded to Canvas Dec. 2, 11:59pm ET
Week 14 Thurs, Dec 5	Final presentations
Week 15 Tue, Dec 10	No Class (Final Exams)	Due Final report uploaded to Canvas by Dec 10, 11:59pm ET
Week 15 Thurs, Dec 12	No Class (Final Exams)