Workshop on Grand Challenges of Next-Generation Cognitive and Developmental Robotics

General Information

This website is for the online workshop held in conjunction with ICDL-Epirob 2021.
The IEEE CIS Cognitive Developmental Systems (CDS) Technical Committee Task Force on Robotics and the IEEE RAS Cognitive Robotics (CoRo) Technical Committee have collaborated to organize this workshop. On December 21, 2020, the organizers held a collaborative online round table titled ``What is the role of next generation of cognitive robotics?'' to explore the next generation of cognitive robotics studies. The round table discussion aimed to bridge the gaps between cutting-edge researchers’ challenges in cognitive and developmental robotics. Based on the discussion, the organizers and speakers are collaboratively writing a survey paper, which will be on arXiv very soon (before the call for papers of this workshop).

Owing to the round table’s overwhelming success, we are eager to expand the activity to the CDS and CoRo communities. We will have an open discussion about the future development of studies in the CDS and CoRo communities, i.e., core participants of ICDL-Epirob.

In this workshop, we will discuss ``grand challenges'' to clarify and share current achievements and future challenges in cognitive and developmental robotics. The workshop will be held virtually because of COVID-19. However, we believe that having this virtual workshop will allow us to welcome more scholars and students from around the world, thereby expanding the community of cognitive and developmental robotics.

Speakers

Aim of this workshop

Recently, there has been a surge in social demand for robots to serve as our companions. To be our daily companion, a robot must be able to observe the environment, understand the surrounding situation, and communicate with humans and other robots [1]. Additionally, the robot must decide what actions to take in a given situation and control its body in accordance with its surroundings. There will be no objections to the abstract argument that ``a high level of cognitive function is essential for the robot to be our partner''. However, what kinds of cognitive functions are required for this purpose?

We held an online round table discussion titled ``What is the role of next generation of cognitive robotics?'' to discuss how cognitive functions manifest as robot behaviors and what kinds of functions are required for robots to move in the real world. We discussed everything from basic cognitive function skills to real world implementation during the discussion. During the round table discussion, we initially clarified what key features distinguish cognitive systems for these robots than those from other fields. In classical robot control point of view, robots have been controlled using a model-based approach, wherein important information for control, such as the robot bodies, the environment, and constraint conditions, are mathematically modeled and a suitable controller is designed.

Although the model-based approach succeeded in creating robots with abilities superior to those of humans in quick and accurate repetitive tasks in stable environments, as exemplified by industrial robots, dealing with the uncertainties in the control loop has become increasingly difficult as robot applications become more diverse. Robots must face uncertainties that are qualitatively different from those encountered in factories, such as situations wherein behavioral goals can only be set in context and communication using ambiguous expressions. These types of uncertainties cannot be handled by the controller’s conventional robustness. Cognitive and developmental approaches to robotics are becoming more important to deal with such situations.

For more than two decades, we have made significant efforts to establish the research field of cognitive and developmental robotics on the shoulders of pioneers [2,3]. Along with the enormous success of artificial intelligence, new trends in cognitive and developmental robotics have emerged recently [4,5]. To extend our community further, having a discussion on the role of the next-generation cognitive and developmental robotics is crucial.

One of the important conclusions of the round table is that we need clear grand challenges, which means a clear goal of robot actions that include all the key factors for cognitive and developmental robots to be our partners.

In this workshop, we hope to begin a discussion about establishing “Grand Challenge of Cognitive and Developmental Robotics” not only with senior cognitive robotics researchers, but also with young researchers who have incredible dreams for the advancements in robotic technology.

References

• [1] A. Lieto, M. Bhatt, and D. Vernon, “The role of cognitive architectures in general artificial intelligence,” Cognitive System Research, vol. 48, pp. 1–3, 2017.

• [2] M. Asada, K. Hosoda, Y. Kuniyoshi, H. Ishiguro, T. Inui, Y. Yoshikawa, M. Ogino, and C. Yoshida, “Cognitive developmental robotics: A survey,” IEEE transactions on autonomous mental development, vol. 1, no. 1, pp. 12–34, 2009.

• [3] A. Cangelosi and M. Schlesinger, Developmental robotics: From babies to robots. MIT press, 2015.

• [4] T. Taniguchi, T. Nagai, T. Nakamura, N. Iwahashi, T. Ogata, and H. Asoh, “Symbol emergence in robotics: a survey,” Advanced Robotics, vol. 30, no. 11-12, pp. 706–728, Apr. 2016.

• [5] T. Taniguchi, E. Ugur, M. Hoffmann, L. Jamone, T. Nagai, B. Rosman, T. Matsuka, N. Iwahashi, E. Oztop, J. Piater et al., “Symbol emergence in cognitive developmental systems: a survey,” IEEE Transactions on Cognitive and Developmental Systems, 2018.

Workshop proposal

[PDF]

Organizer

• • Tadahiro Taniguchi (Ritsumeikan University)

  • Shingo Shimoda (Riken)

  • Takayuki Nagai (Osaka University)

  • Chie Hieida (NAIST)