Symposium on Natural Communication for Human-Robot Collaboration
November 9–11, 2017
Westin Arlington Gateway
Arlington, VA USA
Overview
As robots become more and more integrated into various work and living environments, there is a growing need to develop intuitive, natural ways for humans and robots to communicate for effective collaboration. The topic of natural human-robot communication has been studied by researchers from diverse communities including Natural Language Processing, Computer Vision, Robotics, and Human-Computer Interaction. However, these communities tend to focus on specific challenges that are unique in their own disciplines, and there is relatively little collaboration across fields. This symposium aims to bring together researchers from different disciplines to brainstorm and discuss experimental ideas toward the common goal of natural human-robot interaction.
If you have any questions, please contact the organizers.
Call for Papers
We welcome exploratory ideas and cross-disciplinary work. We target a broad set of topics related to natural communication between humans and robots including, but not limited to, the following:
- Natural language grounding for robotics
- Direction following for robots
- Human-robot dialogue
- Natural language generation
- Vision-language fusion
- Visual question answering and grounding
- Physical human robot interaction (pHRI)
- Nonverbal communication, e.g., gestures, eye gaze and facial effects
We invite participants to submit extended abstracts (max two pages, exclusive of one page for references) or full-length technical papers (max six pages, exclusive of one page for references) that describe recent or ongoing research. Papers should be in PDF format and adhere to the AAAI format. The AAAI Author Kit provides templates for LaTeX and Word. Note that papers will be reviewed in a single-blind manner.
Papers, abstracts, and supplementary materials can be submitted by logging into the conference management website located at:
https://cmt3.research.microsoft.com/NCHRC2017/
Invited Speakers
We have an excellent lineup of people who will be giving invited talks at the symposium:
- Dan Bohus, Microsoft Research
- Joyce Chai, Michigan State University
- Yejin Choi, University of Washington
- Alborz Geramifard, Amazon
- Ralph Hollis, Carnegie Mellon University
- Ben Kuipers, University of Michigan
- Raymond Mooney, University of Texas, Austin
- Rohan Paul, Massachusetts Institute of Technology
- Alex Rudnicky, Carnegie Mellon University
- David Traum, University of Southern California
Important Dates
July 21, 2017 July 28, 2017 |
Abstract/paper submission deadline |
September 1, 2017 |
Notification of acceptance |
October 13, 2017 |
Registration deadline |
November 9–11, 2017 |
Fall Symposium Series |
Program
The symposium spans two-and-a-half days and will include invited and contributed talks, interactive sessions, and open discussions.
Fifteen minutes are allocated for each contributed talk, followed by an additional five minutes for questions. Five minutes are allocated for each lightning talk, with each session followed by a joint, five minute question and answer session. Authors of lightning talk papers will then present their work during the subsequent poster session. We invite authors of contributed talk papers to participate in the poster session as well.
If you would like to propose questions for the panel, please add them here: http://nchrc.ttic.edu/panel.
Thursday, November 9
09:00am–09:10am |
Welcoming Remarks |
09:10am–10:30am |
Invited Talk |
|
Ralph Hollis (Carnegie Mellon University), Physical Human-Robot Interaction with Dynamically Stable Mobile Robots |
|
Contributed Talks |
|
Junjie Hu, Desai Fan, Shuxin Yao, and Jean Oh, Natural Communication for Human-Robot Collaboration |
|
Adrian Boteanu, Jacob Arkin, Siddharth Patki, Thomas Howard, and Hadas Kress-Gazit, Robot-Initiated Specification Repair through Grounded Language Interaction |
10:30am–11:00am |
Coffee Break |
11:00am–12:30pm |
Invited Talk |
|
Alborz Geramifard (Amazon), TBD |
|
Contributed Talks |
|
Divesh Lala, Koji Inoue, Pierrick Milhorat and Tatsuya Kawahara, Detection of Social Signals for Recognizing Engagement in Human-Robot Interaction |
|
Dan Bohus, Sean Andrist, and Eric Horvitz, A Study in Scene Shaping: Adjusting F-formations in the Wild |
12:30pm–02:00pm |
Lunch |
02:00pm–03:30pm |
Lightning Talks and Poster Session |
|
Casey R. Kennington and Sarah Plane, Symbol, Conversational, and Societal Grounding with a Toy Robot |
|
Peggy Wu, Human Physical Movements for Kinematic Learning for Robots |
|
Douglas Summers-Stay and Dandan Li, Analogical Reasoning with Knowledge-based Embeddings |
|
Mara Brandt, Britta Wrede, Franz Kummert, and Lars Schillingmann, Confirmation Detection in Human-Agent Interaction Using Non-Lexical Speech Cues |
|
Raj M Korpan, Susan Epstein, Anoop Aroor, and Gil Dekel, WHY: Natural Explanations from a Robot Navigator |
03:30pm–04:00pm |
Coffee Break |
04:00pm–04:45pm |
Invited Talk |
|
Rohan Paul (Massachusett Institute of Technology), Leveraging Visual-Linguistic Context for Grounding Natural Language Instructions |
04:45pm–05:30pm |
Panel Discussion (Suggest questions here) |
Friday, November 10
09:00am–09:45am |
Invited Talk |
|
Ben Kuipers (University of Michigan), TBD |
09:45am–10:30am |
Invited Talk |
|
Joyce Chai (Michigan State University), TBD |
10:30am–11:00am |
Coffee Break |
11:00am–11:45am |
Invited Talk |
|
Yejin Choi (University of Washington), TBD |
11:45am–12:30pm |
Invited Talk |
|
Dan Bohus (Microsoft Research), Engagement and Turn-Taking in Physically Situated Language Interaction |
12:30pm–02:00pm |
Lunch |
02:00pm–03:30pm |
Lightning Talks and Poster Session |
|
Michael Wollowski, Carlotta Berry, Ryder Winck, Alan Jern, David Voltmer, Alan Chiu, and Yosi Shibberu, A Data-driven Approach Towards Human-robot Collaborative Problem Solving in a Shared Space |
|
Qiaozi Gao, Lanbo She, and Joyce Chai, Interactive Learning of State Representations through Natural Language Instruction and Explanation |
|
Stephanie Zhou, Alane Suhr, and Yoav Artzi, Visual Reasoning with Natural Language |
|
Dipendra Misra and Yoav Artzi, Reinforcement Learning for Mapping Instructions to Actions with Reward Learning |
|
Szrung Shiang, Jean Oh, and Anatole Gershman, A Generalized Model for Multimodal Perception |
|
Dianna Radpour and Vinay Ashokkumar, Non-Contextual Sarcasm Modeling with Neural Network Benchmarking |
|
Nicole K Glabinski, Rohan Paul, and Nicholas Roy, Grounding Natural Language Instructions with Unknown Object References using Learned Visual Attributes |
03:30pm–04:00pm |
Coffee Break |
04:00pm–05:00pm |
Invited Talk |
|
David Traum (University of Southern California), TBD |
|
Contributed Talk |
|
Megan Zimmerman and Jeremy Marvel, Smart Manufacturing and The Promotion of Artificially-Intelligent Human-Robot Collaborations in Small- and Medium-sized Enterprises |
05:00pm–05:30pm |
Panel Discussion (Suggest questions here)
|
Saturday, November 11
09:00am–10:30am |
Invited Talk |
|
Ray Mooney (University of Texas, Austin), Robots that Learn Grounded Language Through Interactive Dialog |
|
Contributed Talks |
|
Sergei Nirenburg and Peter Wood, Toward Human-Style Learning in Robots |
|
Andrea F. Daniele, Thomas Howard, and Matthew R. Walter, Learning Articulated Object Models from Language and Vision |
10:30am–11:00am |
Coffee Break |
11:00am–12:30pm |
Invited Talk |
|
Alex Rudnicky (Carnegie Mellon University), Blended Conversations |
|
Contributed Talks |
|
Claire N Bonial, Matthew Marge, Ron Artstein, Felix Gervits, Cory Hayes, Cassidy Henry, Susan Hill, Anton Leuski, Pooja Moolchandani, Kimberly Pollard, David Traum, Clare Voss, Ashley Foots, and Stephanie M Lukin, Laying Down the Yellow Brick Road: Development of a Wizard-of-Oz Interface for Collecting Human-Robot Dialogue |
|
Nakul Gopalan, Edward Williams, Stefanie Tellex, and Mina Rhee, Learning to Parse Natural Language to Grounded Reward Functions with Weak Supervision |
12:30pm–12:45pm |
Closing Remarks |
Registration
Please register for the symposium through the AAAI 2017 Fall Symposium site. Note that the deadline for registration is October 13, 2017.
Organizers
Jean Oh,
Carnegie Mellon University
Matthew Walter,
Toyota Technological Institute at Chicago
Zhou Yu,
University of California, Davis
Program Committee
Jacob Arkin, University of Rochester
Yoav Artzi, Cornell University
Mohit Bansal, University of North Carolina
Yonatan Bisk, University of Southern California
Joyce Chai, Michigan State University
Anthony Cohn, University of Leeds
Sanja Fidler, University of Toronto
Alborz Geramifard, Amazon
Raia Hadsell, Google DeepMind
Thomas Howard, University of Rochester
Thomas Kollar, Amazon
Hadas Kress-Gazit, Cornell University
Matthew Marge, Army Research Laboratory
Cynthia Matuszek, University of Maryland, Baltimore County
Hongyuan Mei, Johns Hopkins University
Wolfgang Minker, University of Ulm
Dipendra Misra, Cornell University
Raymond Mooney, University of Texas, Austin
Rohan Paul, Massachusetts Institute of Technology
Peter Stone, University of Texas, Austin