Social Intelligence in Humans and Robots

Workshop RSS 2024 - July 19 (1:45pm - 6pm in Delft, Netherlands)

In person locatoin: ME Hall D - Watt

Video recordings are available on our YouTube channel: link

in

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


Jacob Andreas

Massachusetts Institute of Technology

Confirmed (Remote)

Andreea Bobu

Boston Dynamics AI Institute / MIT

Confirmed (Remote)

Yonatan Bisk

Carnegie Mellon University

Confirmed (In-Person)

Michael Franke

University of Tübingen

Confirmed (In-Person)

Séverin Lemaignan

PAL Robotics

Confirmed (Remote)

Carolina Parada

Google Deepmind

Confirmed (In-Person)


Schedule

Time (Delft Time, Netherlands)
1:45 pm - 2:00 pm Organizers
Introductory Remarks
2:00 pm - 2:30 pm Carolina Parada
Foundation Models for Social Robots
2:30 pm - 3:00 pm Yonatan Bisk
Everything Fails, Everything is Ambiguous
3:00 pm - 3:30 pm Andreea Bobu
Aligning Robot and Human Representations
3:30 pm - 4:00 pm Break and Poster Session
4:00 pm - 4:30 pm Contributed Talks
  • A Framework for Music-Evoked Autobiographical Memories in Robot-Assisted Tasks for People with Dementia
  • AToM-Bot: Embodied Fulfillment of Unspoken Human Needs with Affective Theory of Mind
  • Enhancing Older Adults' Prospective Memory and Experience with Personalized Reminders: Design of the MemFlow Robot Framework
  • Find It Like a Dog: Using Gesture to Improve Robot Object Search
4:30 pm - 5:00 pm Michael Franke
Understanding Language Models: On Japanese Rooms & Minimal World Models
5:00 pm - 5:30 pm Séverin Lemaignan
Modelling the social sphere in the age of LLMs
5:30 pm - 6:00 pm Jacob Andreas
Good Old-fashioned LLMs (or, Autoformalizing the World)
6:00 pm - 6:02 pm Organizers
Closing Remarks


Papers
  • Paper #1 - A Framework for Music-Evoked Autobiographical Memories in Robot-Assisted Tasks for People with Dementia [link]
    Paul Raingeard de la Bletiere, Mark Neerincx, Rebecca Schaefer, Catharine Oertel
  • Paper #2 - AToM-Bot: Embodied Fulfillment of Unspoken Human Needs with Affective Theory of Mind [link]
    Fanhong Li, Wei Ding, Ziteng Ji, Zhengrong Xue, Jia Liu
  • Paper #3 - Enhancing Older Adults' Prospective Memory and Experience with Personalized Reminders: Design of the MemFlow Robot Framework [link]
    Yanzhe Li, Bernd Dudzik, Frank Broz, Mark Neerincx
  • Paper #4 - Find It Like a Dog: Using Gesture to Improve Robot Object Search [link]
    Ivy Xiao He, Madeline H. Pelgrim, Kyle Lee, Falak Pabari, Stefanie Tellex, Thao Nguyen, Daphna Buchsbaum


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

  • Abrar Anwar
  • Aidan Curtis
  • Amar Halilovic
  • Amy O'Connell
  • Leticia Leonor Pinto Alva
  • Livia Tomova
  • Maria R. Lima
  • Marlene Berke
  • Nathaniel S. Dennler

Organizers

Tianmin Shu

Johns Hopkins University

Xavier Puig

Meta AI

Shuang Li

Massachusetts Institute of Technology

Zhonghao Shi

Univeristy of Southern California

Tsung-Chi Lin

Johns Hopkins University

Andi Peng

Massachusetts Institute of Technology

Aviv Netanyahu

Massachusetts Institute of Technology

Antonio Torralba

Massachusetts Institute of Technology



Contact
Reach out to Tianmin Shu (tianmin.shu@jhu.edu) for any questions.
-->