© 2023 All rights reserved
Human-AI Interaction is a rapidly growing research area. As Artificial intelligence (AI) and machine learning (ML) increasingly take over tasks previously performed only by humans, it leads to more situations where humans and machines need to cooperate. Compared to their traditional supportive role, current AI products increasingly make autonomous decisions and share responsibility with humans in a wide range of domains such as self-driving cars, robotic surgical systems, and human-AI decision-making teams. In many cases, social interaction convention developed between humans, such as collaboration and competition, is becoming a starting point for understanding and designing human-machine cooperation (HMC) on topics such as ability, authority, and control.
Computer games and playful media provide a unique platform to study human-AI interaction. Many games are social by nature as they embed mechanisms for collaborative and competitive play between players and AIs. When a user co-creates new game levels with an AI, they collaborate through play.
In this workshop, we explore the questions around human-AI cooperation through play. How to design playful interactions that facilitate human-AI teams? Can affects associated with gameplay be used to guide human-AI collaboration? How do we design gameplay where multiple AIs and multiple players interact with one another? How do we conceptualize adversarial AI and human-AI competition as a productive alternative? What evaluation methods are needed that fully account for the autonomy of AI? Which factors of human-AI collaborations lead to productive and fun interactions ?
Jichen Zhu, IT University of Copenhagen
Mike Preuss, Universiteit Leiden
Antonios Liapis, University of Malta
Casper Harteveld, Northeastern University
Alena Denisova, University of York
Seth Cooper, Northeastern University
Guillaume Chanel, University of Geneva
Video Games and Computer Vision research have long held a symbiotic relationship. On the one hand, virtual worlds in games are often used for collecting training data or as testbeds for computer vision models since they provide a greater deal of flexibility, control and scalability in the data collection process compared to the real world. On the other hand, computer vision advancements have enabled us to push the frontiers of what is possible within these artificial game worlds and have transformed the processes with which these worlds are created. However, significant research questions still remain unaddressed both in the field (Computer Vision) and the domain (Games), which include technical and engineering challenges. This workshop invites research papers aiming to bridge the existing gaps between computer vision research and games engineering, with the motive of bringing together the games research community and the computer vision community that have largely operated independently until now. In this workshop Computer Vision and Technical Games Researchers will discuss methods that can be beneficial for both the Computer Vision field and the Games domain.
Chintan Trivedi, University of MaltaKonstantinos Makantasis, University of MaltaNicu Sebe, University of TrentoJulian Togelius, New York University / modl.aiGeorgios N. Yannakakis, University of Malta / modl.aiMatthew Guzdial, University of Alberta
© 2023 All rights reserved