The 2020 AI-HRI symposium will take place virtually on the AAAI official Zoom. Information will be sent to all registered participants.
The Artificial Intelligence (AI) for Human-Robot Interaction (HRI) Symposium has been a successful venue of discussion and collaboration since 2014. During that time, the sub-topics of trust and explainability in robotics have been rapidly growing, with major research efforts at universities and laboratories across the world.
Trust is generally believed that trust is crucial for adoption of both AI and robotics, particularly when transitioning technologies from the lab to industrial, social, and consumer applications. Enabling a robot to provide explanations is one approach to fostering this trust.
Over the course of the two-day meeting, we will host a collaborative forum for discussion of current efforts in trust for AI-HRI, with a sub-session focused on the related topic of explainable AI (XAI) for HRI. Additionally, the symposium will include other topics related to AI for HRI.
- Trust and Explainability in HRI
- Architectures and systems supporting autonomous HRI
- Interactive task learning
- Interactive dialog systems and natural language
- Field studies, experimental, and empirical HRI
- Tools for autonomous HRI
- Robot planning and decision-making
- Ethics in HRI
- AI for social robots
- Fielding and deployment, and experimentation for autonomous robots
- Knowledge representation and reasoning to support HRI and robot tasking
Presentation and publication
All accepted full and short papers will be presented orally and published in the proceedings through arXiv. Authors will be notified as to whether they have been assigned a “full-length” or “lightning” presentation slot. Authors will be notified as to whether they have been assigned a “full-length” or “lightning” presentation slot. Authors assigned to lightning talks will be invited to participate in a poster session.
July 30, 2020 August 6, 2020
Notification of acceptance: September 10, 2020
The symposium will be held on November 13-14, 2020.
Please contact us if you require additional time to submit your contribution or have any questions.
- Julie Shah
Julie Shah is an Associate Professor in the Department of Aeronautics and Astronautics at MIT and leads the Interactive Robotics Group of the Computer Science and Artificial Intelligence Laboratory. Shah received her SB (2004) and SM (2006) from the Department of Aeronautics and Astronautics at MIT, and her PhD (2010) in Autonomous Systems from MIT. Before joining the faculty, she worked at Boeing Research and Technology on robotics applications for aerospace manufacturing. She has developed innovative methods for enabling fluid human-robot teamwork in time-critical, safety-critical domains, ranging from manufacturing to surgery to space exploration. Her group draws on expertise in artificial intelligence, human factors, and systems engineering to develop interactive robots that emulate the qualities of effective human team members to improve the efficiency of human-robot teamwork. In 2014, Shah was recognized with an NSF CAREER award for her work on “Human-aware Autonomy for Team-oriented Environments," and by the MIT Technology Review TR35 list as one of the world’s top innovators under the age of 35. Her work on industrial human-robot collaboration was also recognized by the Technology Review as one of the 10 Breakthrough Technologies of 2013, and she has received international recognition in the form of best paper awards and nominations from the International Conference on Automated Planning and Scheduling, the American Institute of Aeronautics and Astronautics, the IEEE/ACM International Conference on Human-Robot Interaction, the International Symposium on Robotics, and the Human Factors and Ergonomics Society.
- Maartje de Graaf
Talk Title: Moral Psychology in HRI
Abstract: Human society comprises a complex social system encompassing various types of relationships across nested social hierarchies, all structured by rights, rules, and obligations. Robots performing social roles meet the challenge to successfully function in these social systems. In my talk, I will present results of two studies focusing on social norm violation, blame assignment, trust assessment, and social response. These results reveal our expectations of robots regarding human social norms and offer some suggestions for how robots could deal with these expectations.
Maartje de Graaf is a communication scientist in the multidisciplinary field of human-robot interaction. Her research is driven by her intrinsic motivation to understand human behavior and its underlying psychological and cognitive processes. Since technologies are increasingly endowed with complex and humanlike interfaces and are becoming technically feasible for real-world applications, everyday living is transformed in unprecedented ways. To deal with this potentially radical transformation, De Graaf’s research gains detailed insights into the scope and limits of people’s humanlike treatment of robots on a social, emotional and cognitive level. This knowledge reveals to what extent we regard robots as social beings, which has profound ethical and societal implications for our interactions with these systems. De Graaf aims to document the social context of robot use, contribute to design considerations and policy recommendations about the future standing of robots in society, and inform developers how to design and practitioners how to integrate socially acceptable robot applications that benefit society.
Maartje de Graaf is an Assistant Professor of Information and Computing Science at the University of Utrecht. In the past, she has worked as a Postdoctoral Research Associate at Brown University’s Humanity Centered Robotics Initiative with a 2-year Rubicon grant from the Netherlands Organization for Scientific Research (NWO). She has a Bachelor of Business Administration in Communication Management (2005), a Master of Science in Media Communication (2011), and a PhD in Communication Science and Human-Robot Interaction (2015). Her website is here.
- Bertram F. Malle
Talk Title: How Trust and Explainability are Related: A Multi-Dimensional Framework
Bertram F. Malle is Professor of Cognitive, Linguistic, and Psychological Sciences at Brown University, where he is also Co-Director of the Humanity-Centered Robotics Initiative. He was trained in psychology, philosophy, and linguistics at the University of Graz, Austria, and received his Ph.D. in psychology from Stanford University in 1995. He received the Society of Experimental Social Psychology Outstanding Dissertation award, a National Science Foundation CAREER award, and is co-recipient of the 2019 Scientific Impact Award of the Society of Experimental Social Psychology. He is past president of the Society of Philosophy and Psychology and a Fellow of the Society for Experimental Social Psychology, the Association of Psychological Science, and the Society for Personality and Social Psychology. Malle’s research, which has been funded by the NSF, Army, Templeton Foundation, Office of Naval Research, and DARPA, focuses on social cognition (e.g., mental state inferences, behavior explanations), moral psychology (e.g., blame, guilt, norms, trust), and human-robot interaction (e.g., morally competent robots, socially assistive robots). He has distributed his work in over 150 scientific publications and several books. His lab page is here.
ProgramPlease find the schedule below. All times listed are in Eastern Time (GMT-5). Full-length talks are 15 minutes and short "poster" talks are 5 minutes (not including questions).
Full Papers can be found in the arXiv proceedings or in the local proceedings.Please reach out to the authors with any questions or if their paper is not available.
Friday, November 13
|10:00 ET|| Welcome & Logistics
|10:15|| Invited Talk: Maartje de Graaf
Helpfulness as a Key Metric of Human-Robot Collaboration [pdf]
Richard Freedman, Steven Levine, Brian Williams, and Shlomo Zilberstein
Supporting User Autonomy with Multimodal Fusion to Detect when a User Needs Assistance from a Social Robot [pdf]
Alex Reneau and Jason Wilson
Human-Supervised Semi-Autonomous Mobile Manipulators for Safely and Efficiently Executing Machine Tending Tasks [pdf]
Sarah Al-Hussaini, Shantanu Thakar, Hyojeong Kim, Pradeep Rajendran, Brual Shah, Alec Kanyuck, Jeremy Marvel, and Satyandra K. Gupta
|11:45|| Author discussions (Session 1)
|12:30|| Invited Talk: Bertram Malle
|13:15|| Breakout Session
Towards Using Social HRI for Improving Children's Healthcare Experiences [pdf]
Mary Ellen Foster and Ron Petrick
Face-work for Human-Agent Joint Decision Making [pdf]
JiHyun Jeong and Guy Hoffman
Stroke Modeling and Synthesis for Robotic and Virtual Patient Simulators [pdf]
Maryam Pourebadi and Laurel D. Riek
|14:00|| Author discussions (Session 2)
Impact of Explanation on Trust of an Novel Mobile Robot [pdf]
Stephanie Rosenthal and Elizabeth Carter
Towards a Policy-as-a-Service Framework to Enable Compliant, Trustworthy AI and HRI Systems in the Wild [pdf]
Alexis Morris, Hallie Siegel, and Jonathan Kelly
Towards a Conversational Measure of Trust [pdf]
Mengyao Li, Areen Alsaid, Sofia Noejovich, Ernest Cross, and John Lee
Explainable Representations of the Social State: A Model for Social Human-Robot Interactions [pdf]
Daniel Hernandez Garcia, Yanchao Yu, Weronika Sieinska, Jose Part, Nancie Gunson, Oliver Lemon, and Christian Dondrup
|15:15|| Breakout Session
|15:45|| Author Discussion (Session 3)
Saturday, November 14
|10:00 ET|| Invited Talk: Julie Shah
Axiom Learning and Belief Tracing for Transparent Decision Making in Robotics [pdf]
Tiago Mota and Mohan Sridharan
Integrating Intrinsic and Extrinsic Explainability: The Relevance of Understanding Neural Networks for Human-Robot Interaction [pdf]
Tom Weber and Stefan Wermter
A Knowledge Driven Approach to Adaptive Assistance Using Preference Reasoning and Explanation [pdf]
Jason Wilson, Leilani Gilpin, and Irina Rabkina
|11:30|| Author discussions (Session 4)
|12:30|| Invited Speaker Panel: Explainable AI for HRI
13:15 (3 short)
Projection Mapping Implementation: Enabling Direct Externalization of Perception Results and Action Intent to Improve Robot Explainability [pdf]
Zhao Han, Alexander Wilkinson, Jenna Parrillo, Jordan Allspaw, and Holly Yanco
Modeling Human Temporal Uncertainty in Human-Agent Teams [pdf]
Maya Abo Dominguez, William La, and Jim Boerkoel
Towards Preference Learning For Autonomous Ground Robot Navigation Tasks [pdf]
Cory Hayes and Matthew Marge
Self-supervised reinforcement learning for speaker localisation with the iCubhumanoid robot [pdf]
Jonas Gonzalez Billandon, Lukas Grasse, Matthew Tata, Alessandra Sciutti, and Francesco Rea
|13:30|| Author discussions (Session 5)
14:45 (2 short)
Finley Lau, Deepak Gopinath, and Brenna Argall
Accelerating the Development of Multimodal, Integrative-AI Systems with Platform for Situated Intelligence [pdf]
Sean Andrist and Dan Bohus
HAVEN: A Unity-based Virtual Robot Environment to Showcase HRI-based Augmented Reality [pdf]
Andre Cleaver, Darren Tang, Victoria Chen, and Jivko Sinapov
SENSAR: A Shared Reality with Intelligent Robots for Collaborative Human-Robot Interaction [pdf]
Andre Cleaver, Faizan Muhammad, Amel Hassan, Elaine Short, and Jivko Sinapov
|15:00|| Group discussion - next steps
|15:15|| Author discussions (Session 6)
Authors may submit under one of the following paper categories:
(The listed page limits are excluding references.)
- Full papers (6-8 pages) highlighting state-of-the-art HRI-oriented research on trust
& explainability and other related topics.
- Short papers (2-4 pages) outlining new or controversial views on AI-HRI research or describing ongoing AI-oriented HRI research.
- Tool papers (2-4 pages) describing novel software, hardware, or datasets of interest to the AI-HRI community.
Papers are to be submitted through the AAAI EasyChair site. Proceedings will be published through arXiv by each individual author.
Authors will be notified as to whether they have been assigned a full-length or 'lightning' presentation slot. Authors assigned to lightning talks will be invited to participate in a poster session. Additionally, all submitting authors will be added to the reviewer pool and may be asked to contribute to the peer-review process.
Please see the AAAI Author Kit for paper templates to ensure that your submission has proper formatting.
Contributions may be submitted here:
For any extenuating circumstances that may result in a delayed submission, please contact us.
Diversity & Inclusion at AI-HRI
AI-HRI is committed to growing the diversity of our community and is actively pursuing ways to make our community more inclusive. Our efforts include diversifying the participation among our program committee, invited speakers, paper authors, and symposium attendees.
To support attendees from under-represented groups (URGs), AI-HRI will be providing at least two complimentary registrations. This includes but is not limited to those who identify as Women, African American/Black, Hispanic/LatinX, Indigenous, persons with a disability, and/or LGBTQI+. To express your interest in receiving a complimentary registration, please fill out this form.
We are also looking to expand our ability to award complimentary registrations and are looking for sponsors to help. If you or your company is interesting in supporting our D&I initiative, please contact us.
If you have any other suggestions on how we can further promote diversity and inclusion at AI-HRI, please contact us at firstname.lastname@example.org.
Shelly Bagchi (National Institute of Standards and Technology),
Jason R. Wilson (Franklin & Marshall College),
Muneeb I. Ahmad (Heriot-Watt University),
Christian Dondrup (Heriot-Watt University),
Zhao Han (UMass Lowell),
Justin W. Hart (University of Texas Austin),
Matteo Leonetti (University of Leeds),
Katrin Solveig Lohan (University of Applied Sciences Ostschweiz OST),
Ross Mead (Semio),
Emmanuel Senft (University of Wisconsin, Madison),
Jivko Sinapov, Communications Co-Chair (Tufts University),
Megan L. Zimmerman (National Institute of Standards and Technology)
Contact us at email@example.com.