Introduction
The goal of the Artificial Intelligence for Human-Robot Interaction (AI-for-HRI) symposium is to bring together the large community of researchers working on artificial intelligence (AI) challenges inherent to human-robot interaction (HRI). While most current, traditional HRI research involves investigating ways for robots to effectively interact with people, HRI’s overarching goal is to develop robots that are intelligent, autonomous, and capable of interacting with, modeling, and learning from humans. These goals greatly overlap with some central goals of AI; however, much AI research takes place without consideration of humans, and thus does not consider the inherent uncertainty in dynamics, structure and interaction that humans and human-populated environments bring with them. We thus believe that HRI is an extremely interesting problem domain for AI and Robotics research, as humans and human-populated environments bring with them inherent uncertainty in dynamics, structure, and interaction.
Our symposium will focus on the larger intellectual picture to address the statements “HRI is an AI problem” and “AI is an HRI problem”. The symposium will include current research talks and discussions both to share work in this intersectional area, guidance for how to best frame AI-centric HRI work within AI venues, and invited speaker panels to give different perspectives on AI-for-HRI.
In addition to oral and poster presentations of accepted papers, this year's symposium will include panel discussions, position talks, keynote presentations, and a hack session with ample time for networking.
Planned activities
SPEAKERS: Keynote talks will give different perspectives on AI-HRI and showcase recent advances towards humans interacting with robots on everyday tasks. Moderated discussions and debates will allow participants to engage in collaborative public discussion on controversial topics and issues of interest to the AI-HRI community.
NETWORKING: A large part of this effort is to bring together a community of researchers, strengthen old connections, and build new ones. Ample time will be provided for networking and informal discussions.
Presentation and publication
All accepted full and short papers will be presented orally and published in the proceedings. Authors will be notified as to whether they have been assigned a “full-length” or “lightning” presentation slot. Authors assigned to full-length talks will be invited to participate in a panel discussion. Authors assigned to lightning talks will be invited to participate in a poster session.
Important dates
Submission: July 27, 2017.
Notifications: August 11, 2017.
Camera-ready version of Accepted Submissions: August 29, 2017.
(To be collected into a technical report for the symposium attendees.)
Registration deadline: September 15, 2017 (invited participants), October 13, 2017 (everyone).
The symposium will be held November 9-11, 2017 at the Westin Arlington Gateway in Arlington, Virginia, USA.
Invited Keynote Speakers
- Tony Belpaeme. Carefully nudging towards autonomous social HRI.
- Michael A. Goodrich. Toward Human Interaction with Bio-Inspired Robot Swarms.
- Séverin Lemaignan. From children's freeplay to robots AI.
- Matthias Scheutz. One-Shot Robot Learning through Natural Language Interactions with Humans.
- Brian Scassellati. Robots for Autism.
Schedule
November 9, 2017
| 09:00 – 09:10 | Introduction |
| 09:10 – 09:30 | Announcements |
| 09:30 – 10:30 | Invited Talk Mike Goodrich -- Toward Human Interaction with Bio-Inspired Robot Swarms | 10:30 – 11:00 | Coffee Break |
| 11:00 – 12:00 | Invited Talk Tony Belpaeme -- Carefully nudging towards autonomous social HRI |
| 12:00 – 13:30 | Lunch |
| 13:30 – 14:30 | Paper Presentations Mohan Sridharan -- Integrating knowledge representation, reasoning and learning for human-robot interaction Sarath Sreedharan, Tathagata Charkaborti and Subbarao Kambhampati -- Balancing explicability and explanation in human-aware planning Aomar Osmani, Mannisissa Hamidi and Abdelghani Chibani -- Platform for assessment and monitoring of infant comfort |
| 14:30 – 15:30 | Invited Talk Séverin Lemaignan -- From children's freeplay to robots AI |
| 15:30 – 16:00 | Coffee Break |
| 16:00 – 16:30 | Author Panel/Moderated Discussion |
| 16:30 – 17:30 | Lightning Talks and Poster Session Chris Crawford, Marvin Andujar and Juan E. Gilbert -- Neurophysiological Heat Maps for Human-Robot Interaction Evaluation Emmanuel Senft, Séverin Lemaignan, Paul Baxter and Tony Belpaeme -- Toward Supervised Reinforcement Learning with Partial States for Social HRI Jesse Parent and Yelin Kim -- Towards Socially Intelligent HRI Systems: Quantifying Emotional, Social, and Relational Context in Real-World Human Interactions Richard Freedman and Shlomo Zilberstein -- Does the Human's Representation Matter for Unsupervised Activity Recognition? |
| 18:00 – 19:00 | Reception |
November 10, 2017
| 09:30 – 10:30 | Invited Talk Matthias Scheutz -- One-Shot Robot Learning through Natural Language Interactions with Humans |
| 10:30 – 11:00 | Coffee Break |
| 11:00 – 12:30 | Paper Presentations Maartje De Graaf and Bertram Malle -- How people explain action (and autonomous intelligent systems should too) Maj Stenmark, Elin Anna Topp, Mathias Haage and Jacek Malec -- Knowledge for synchronized dual-arm robot programming Naouel Ayari, Hazem Abdelkawy, Abdelghani Chibani and Yacine Amirat -- Towards semantic multimodal emotion recognition for enhancing assistive services in ubiquitous robotics Daniel Brown and Scott Niekum -- Toward probabilistic safety bounds for learning from demonstration |
| 12:30 – 14:00 | Lunch |
| 14:00 – 15:00 | Invited Talk Brian Scassellati -- Robots for Autism |
| 15:00 – 15:30 | Author Panel/Moderated Discussion |
| 15:30 – 16:00 | Coffee Break |
| 16:00 – 17:30 | Lightning Talks and Poster Session Montana Roberts, Brenda Castro, Karla Mena and Jim Boerkoel -- Who Takes the Lead? Automated Scheduling for Human-Robot Teams Teun F. Krikke, Frank Broz and David Lane -- Who said that? A comparative study of non-negative matrix factorisation and deep learning techniques Sean Trott and Federico Rossano -- Theoretical Concerns for the Integration of Repair Raymond Sheh -- Different XAI For Different HRI |
| 18:00 – 19:00 | Plenary Session |
November 11, 2017
| 09:00–10:00 | Paper Presentations Larz Kunze, Tom Williams, Nick Hawes and Matthias Scheutz -- Spatial referring expression generation for HRI: Algorithms and evaluation framework Edilson Rodrigues and Brandon Bennett -- Formalism for treatment of the ambiguity in front/back axis expressions Nia Peters, Bhiksha Raj and Griffin Romigh -- Topic and prosodic modeling for interruption management in multi-use multitasking communication interactions |
| 10:00–10:30 | Author Panel/Moderated Discussion |
| 10:30–11:00 | Coffee Break |
| 11:00–12:00 | Tool Talks Sean Trott and Benjamin Bergen -- A theoretical model of indirect request comprehension Anoop Aroor, Susan Epstein and Raj Korpan -- MengeROS: A crowd simulation tool for autonomous robot navigation Utkarsh Patel, Emre Hatay, Michael D’Arcy, Ghazal Zand and Pooyan Fazli -- Beam: A collaborative autonomous service robot Andrew Specian -- Quori |
| 12:00–12:30 | Wrap-Up/General Discussion |
Organizing Committee
Elin A. Topp (Lund University)
Laura M. Hiatt (Naval Research Laboratory)
Luca Iocchi (Sapienza University of Rome)
Kalesha Bullard (George Institute of Technology)
Emmanuel Senft (Plymouth University)
Tian Zhou (Purdue University)
Marc Hanheide (University of Lincoln)
Frank Broz (Heriott-Watt University)
Dan Grollman (Sphero, Inc)
Katrin Lohan (Heriot-Watt University)
Ross Mead (Semio)
Tom Williams (Tufts University/Colorado School of Mines)