Workshop on World Models and Predictive Coding in Cognitive Robotics

The workshop has been accepted to IROS 2023.

 Format

Full day.

Organizers

Website

https://world-model.emergent-symbol.systems/home

 Draft Abstract

This workshop will explore the new frontiers in robotics, emphasizing world models, predictive coding, probabilistic generative models, and the free-energy principle. Creating autonomous robots that can actively explore the environment, acquire knowledge and learn skills continuously is the ultimate achievement envisioned in cognitive and developmental robotics. Importantly, if the aim is to create robots that can continuously develop through interactions with their environment, their learning processes should be based on interactions with their physical and social world in the manner of human learning and cognitive development. Based on this context, this workshop focuses on the two concepts of world models and predictive coding in the context of cognitive robotics. Recently, world models have attracted renewed attention as a topic of considerable interest in artificial intelligence. Cognitive systems learn world models to better predict future sensory observations and optimize their policies, i.e., controllers. Alternatively, in neuroscience, predictive coding proposes that the brain continuously predicts its inputs and adapts to model its own dynamics and control behavior in its environment. Both ideas may be considered as underpinning the cognitive development of robots and humans capable of continual or lifelong learning. The workshop aims to provide a platform for researchers and practitioners in cognitive robotics to exchange ideas and explore new directions for developing autonomous cognitive and developmental robots.This workshop will be an enriching experience for all the participants and will contribute to the growth and development of the field of cognitive robotics.

 

Content of the workshop

 

Creating autonomous robots that can actively explore the environment, acquire knowledge and learn skills continuously is the ultimate achievement envisioned in cognitive and developmental robotics. Importantly, if the aim is to create robots that can continuously develop through interactions with their environment, their learning processes should be based on interactions with their physical and social world in the manner of human learning and cognitive development. Based on this context, this workshop focuses on the two concepts of world models and predictive coding in the context of cognitive robotics. Recently, world models have attracted renewed attention as a topic of considerable interest in artificial intelligence. Cognitive systems learn world models to better predict future sensory observations and optimize their policies, i.e., controllers. Alternatively, in neuroscience, predictive coding proposes that the brain continuously predicts its inputs and adapts to model its own dynamics and control behavior in its environment. Both ideas may be considered as underpinning the cognitive development of robots and humans capable of continual or lifelong learning.

 

This workshop will explore the new frontiers in robotics, emphasizing world models, predictive coding, probabilistic generative models, and the free-energy principle. The workshop aims to provide a platform for researchers and practitioners in cognitive robotics to exchange ideas and explore new directions for developing autonomous cognitive and developmental robots.

The workshop will reflect the state of the art on the topic by focusing on the latest research trends and advancements in world models and predictive coding in cognitive robotics. The keynote speakers will provide insights into the most recent findings in these areas. Importantly, many of the organizers have conducted a survey and written a review paper called “World Models and Predictive Coding for Cognitive and Developmental Robotics: Frontiers and Challenges” recently [1]. The keynote speakers will be invited based on the survey. This will ensure that the workshop will become a cutting-edge event. We will also encourage participants to submit their research papers, which will go through a rigorous review process to ensure that they reflect the current state of the art.

 

We will engage participants and exchange ideas through various activities such as interactive sessions, group discussions, and poster presentations. The workshop will provide an opportunity for participants to network, collaborate, and learn from each other. We will also organize a panel discussion to encourage an open and honest discussion about the challenges and opportunities of world models and predictive coding in cognitive robotics.

 

The proposed event will expand the content diversity of IROS 2023 by providing a platform for researchers and practitioners in cognitive robotics to present and discuss their research in world models, predictive coding, probabilistic generative models, and the free energy principle. The workshop also provides a unique opportunity for interaction between developmental robotics, supported by the IEEE CIS TC Cognitive Developmental Systems, and cognitive robotics, supported by the IEEE RAS TC Cognitive Robotics. The collaboration of two very related TCs is expected.

 

In summary, this workshop will provide a unique opportunity for researchers and practitioners in cognitive robotics to explore the latest advances in world models and predictive coding. Through this workshop, we aim to promote the development of autonomous cognitive and developmental robots and encourage the use of world models and predictive coding in cognitive robotics. We believe that this workshop will be an enriching experience for all participants and will contribute to the growth and development of the field of cognitive robotics.

 

[1] Taniguchi, T., Murata, S., Suzuki, M., Ognibene, D., Lanillos, P., Uğur, E., Jamone, L., Nakamura, T., Ciria, A., Lara, B., & Pezzulo, G. (2023). World Models and Predictive Coding for Cognitive and Developmental Robotics: Frontiers and Challenges. ArXiv, abs/2301.05832.

 

Invited Speakers

 

 

Structure of the event

This workshop will consist of invited talks, a poster session, a panel discussion, and an open discussion session.

  Poster session: We will call for a poster abstract for the poster session with a review process. If the quality of the short paper is excellent, the paper would be presented as a spotlight talk in addition to a poster presentation. The opportunity of flash talk is given for every poster paper. The flash poster session will be held before lunch to work as an icebreaker activity.

  Panel discussion:  In addition to the invited talks and poster session, we would organize a panel discussion where established experts and early-career researchers can share their perspectives on the workshop topic. This would provide an opportunity for attendees to interact with experts and learn from their experiences.

  Open discussion session: We would dedicate a session to an open discussion where attendees can share their thoughts and ideas on the workshop topic.

Additionally, we will prepare an online discussion platform, e.g, Slack.

Tentative Program

 

8:30 - 8:40

Welcome and introduction

 

8:40 - 9:25

Invited Talk 1

 

9:25 - 10:10

Invited Talk 2

 

11:00 – 11:00

Coffee break

 

11:00 - 11:45

Invited Talk 3

 

11:45 - 12:30

Flash poster and spotlight session

 

12:30 – 13:30

Lunch

 

13:30 - 14:00

Invited Talk 4

 

14:00 - 14:30

Invited Talk 5

 

14:30 - 15:00

Invited Talk 6

 

15:00 – 15:50

Coffee break

 

15:50 -16:10

Invited Talk 7

 

16:10- 16:50

Panel discussion

 

16:50 - 17:20

Open discussion

 

17:20 - 17:30

Closing remarks

 

17:30

End

 

Dissemination

Poster papers will be published on the website

We plan to organize a special issue of Advanced Robotics, RSJ.