Social Intelligence in Humans and Robots

Workshop ICRA 2021 - June 4th


About
Social intelligence is at the core of both human and artificial intelligence. From a young age, humans can understand, interact, collaborate, and communicate with each other. Most of what we learn is taught by others, or learned in a social context. Thus, a truly intelligent AI agent should be able to understand and work with humans as well as other AI agents.

This workshop focuses on the challenges and developments in building AI systems equipped with social intelligence, and leverages theories and insights from studies of human social intelligence for achieving such goals. In particular, the workshop will explore what it would take for machines to:

  1. Understand the behaviors and mental states of humans
  2. Engage in rich and complex interactions with humans
The workshop will bring together experts from cognitive science and developmental psychology to better understand the principles and origins of human social intelligence, and experts from AI and Robotics, to discuss how to engineer socially intelligent artificial agents, and how these paradigms can be deployed in both virtual and real scenarios.


Speakers and Panelists

Anca Dragan

UC Berkeley

J. Kiley Hamlin

University of British Columbia

Dorsa Sadigh

Stanford University

Rebecca Saxe

Massachusetts Institute of Technology

Brian Scasselati

Yale University


Schedule

Time (ET)
09:30 am - 09:45 am Organizers
Introductory Remarks Video
09:45 am - 10:25 am Rebecca Saxe
Lessons for machine social intelligence from human infants Video
10:25 am - 11:05 am Brian Scasselati
Challenges of Teaching and Evaluating Social Skills Video
11:05 am - 11:15 am Coffee Break
11:15 am - 11:55 am Anca Dragan
Towards Assistance that Empowers Video
11:55 am - 12:15 am Spotlight talks (5 min + 5 min general Q&A)
  • Modeling Communication to Coordinate Perspectives in Cooperation
  • Two-Stage Clustering of Human Preferences for Action Prediction in Assembly Tasks
  • Show Me What You Can Do: Capability Calibration on Reachable Workspace for Human-Robot Collaboration
12:15 am - 01:00 pm Lunch Break
01:00 pm - 01:40 pm Dorsa Sadigh
Learning and Influencing Intelligent Interactions
Video
01:40 pm - 02:20 pm J Kiley Hamlin
On the origins of Social Intelligence Video
02:20 pm - 03:00 pm Hyowon Gweon
Title TBA Video
03:00 pm - 03:20 pm Spotlight talks (5 min + 5 min general Q&A) Video
  • Joint Attention for Multi-Agent Coordination and Social Learning
  • Sharing is Not Needed: Modeling Animal Coordinated Hunting with Reinforcement Learning
  • Modeling the Mistakes of Boundedly Rational Agents within a Bayesian Theory of Mind
03:20 pm - 04:15 pm Anca Dragan, Tao Gao, Hyowon Gweon, J Kiley Hamlin, Dorsa Sadigh, Brian Scasselati
Panel Session Video
04:15 pm - 04:55 pm On Gather.Town
Poster Session
04:55 pm - 05:00 pm Organizers
Concluding Remarks


Papers
Thank you everyone for submitting your papers to this workshop! All the papers below will be presented in the Poster Session (link TBA). Spotlight papers will additionally be presented as short talks during the Spotlight sessions.

Spotlights
Congratulations to the Spotlight Papers!
  • Poster #1 - Modeling Communication to Coordinate Perspectives in Cooperation [link]
    Stephanie Stacy; Chenfei Li; Minglu Zhao; Max Kleiman-Weiner; Tao Gao
  • Poster #2 - Two-Stage Clustering of Human Preferences for Action Prediction in Assembly Tasks [link]
    Heramb Nemlekar; Jignesh Modi; Satyandra Gupta; Stefanos Nikolaidi
  • Poster #3 - Show Me What You Can Do: Capability Calibration on Reachable Workspace for Human-Robot Collaboration [link]
    Xiaofeng Gao; Luyao Yuan; Tianmin Shu; Hongjing Lu; Song-Chun Zhu
  • Poster #4 - Joint Attention for Multi-Agent Coordination and Social Learning [link]
    Dennis Lee; Natasha Jaques; J. Chase Kew; Jiaxing Wu; Douglas Eck; Dale Schuurmans; Aleksandra Faust
  • Poster #5 - Sharing is Not Needed: Modeling Animal Coordinated Hunting with Reinforcement Learning [link]
    Minglu Zhao; Ning Tang; Annya Dahmani; Yixin Zhu; Federico Rossano; Tao Gao
  • Poster #6 - Modeling the Mistakes of Boundedly Rational Agents within a Bayesian Theory of Mind [link]
    Arwa Alanqary; Gloria Lin; Joie Le; Tan Zhi-Xuan; Vikash Mansinghka; Joshua Tenenbaum


Posters
Below is a list of the accepted papers
  • Poster #7 - Task and Motion Planning for Human-Robot Collaboration using Non-Linear Programming and Hierarchical Motion Prediction [link]
    An Thai Le; Philipp Kratzer; Simon Hagenmayer; Marc Toussaint; Jim Mainprice
  • Poster #8 - How to Understand Your Robot: A Design Space Informed by Human Concept Learning [link]
    Serena L Booth; Sanjana Sharma; Sarah Chung; Julie A. Shah; Ellena Glassmann
  • Poster #9 - Cogment: Open Source Framework For Distributed Multi-actor Human-AI Collaborative Environment [link]
    Sai Krishna Gottipati; Cloderic Mars; Gregory Szriftgiser; Sagar Kurandwad; Vincent Robert
  • Poster #10 - Adventures of human planners in Maze Search Task [link]
    Marta Kryven; SuhYoun Yu; Max Kleiman-Weiner; Joshua Tenenbaum
  • Poster #11 - Metacognitive Bandits: When Do Humans Seek AI Assistance? [link]
    Aakriti Kumar; Trisha Patel; Aaron Benjamin; Mark Steyvers
  • Poster #12 - Modeling human intention inference in continuous 3D domains by inverse planning and body kinematics [link]
    Yingdong Qian; Marta Kryven
  • Poster #13 - Communicating Natural Programs to Humans and Machines [link]
    Sam Acquaviva; Yewen Pu; Marta Kryven; Theo Sechopoulos; Michael Henry Tessler; Joshua Tenenbaum
  • Poster #14 - Individual vs. Joint Perception: a Pragmatic Model of Pointing as Communicative Smithian Helping [link]
    Kaiwen Jiang; Stephanie Stacy; Adelpha Chan; Chuyu Wei; Federico Rossano; Yixin Zhu; Tao Gao
  • Poster #15 - FACT: A Full-body Ad-hoc Collaboration Testbed for Modeling Complex Teamwork [link]
    Gopika Ajaykumar; Annie Mao; Jeremy Brown; Chien-Ming Huang
  • Poster #16 - Baby Intuitions Benchmark (BIB): Discerning the goals, preferences, and actions of others [link]
    Kanishk V Gandhi; Gala Stojnic; Brenden M Lake; Moira Dillon
  • Poster #17 - Toward Modeling the Emergence of Symbolic Communication [link]
    Emily Cheng; Yen-Ling Kuo; Ignacio Cases; Boris Katz; Andrei Barbu
  • Poster #18 - Social Interactions as Recursive MDPs [link]
    Ravi Tejwani; Yen-Ling Kuo; Tianmin Shu; Boris Katz; Andrei Barbu
  • Poster #19 - Curiosity-based Robot Navigation under Uncertainty in Crowded Environments [link]
    Kuanqi Cai; Weinan Chen; Chaoqun Wang; Shuang Song; Qinghu Max Meng


Reviewers
We wish to thank the following people for their assistance in reviewing submitted papers.

  • Aidan Curtis
  • Andrea Bajcsy
  • Aviv Netanyahu
  • Daniel Brown
  • Desmond Ong
  • Erdem Biyik
  • Heramb Nemlekar
  • Jerry Zhi-Yang He
  • Jiankun Wang
  • Joseph Suarez
  • Kanishk Gandhi
  • Lifeng Fan
  • Livia Tomova
  • Marta Kryven
  • Paul Pu Liang
  • Qianli Feng
  • Robert Hawkins
  • Serena Booth
  • Siddharth Karamcheti
  • Tan Zhi-Xuan
  • Xiaofeng Gao
  • Xu Xie
  • Michael Lopez-Brau

Frequently Asked Questions
For more questions about the workshop, contact us at socialintelligenceworkshop@gmail.com.

Will the workshop be online?
All the workshop be online. Invited talks and spotlights will be recorded, with live Q&A sessions and discussions.

How can I attend this workshop?
We will be publishing here the Zoom and Gather.Town links to attend the workshop. Stay tuned!

Can I submit previously published work?
We welcome new unpublished work into the workshop. You can however submit work that is concurrently under review in a conference or joural.

What happens if my paper is accepted at the workshop?
We will post your paper in the workshop website, and you will be abe to present a poster through Gather.town. Some selected papers will also have a spotlight presentation, which will be recorded and played during the workshop. Note that accepted papers will be non-archival and they can still be submitted in other journals and conferences.

Organizers

Xavier Puig

Massachusetts Institute of Technology

Tianmin Shu

Massachusetts Institute of Technology

Shuang Li

Massachusetts Institute of Technology

Andreea Bobu

UC Berkeley

Shari Liu

Massachusetts Institute of Technology

Mengxi Li

Stanford University

Sanja Fidler

University of Toronto, NVIDIA

Antonio Torralba

Massachusetts Institute of Technology



Contact
Reach out to socialintelligenceworkshop@gmail.com for any questions.
-->