University West

Towards Situation Awareness and Attention Guidance in a Multiplayer Environment using Augmented Reality and Carcassonne

This research introduces a framework for developing a Situation Awareness and Attention Guidance (SAAG) system within a multiplayer augmented reality (AR) environment.

• Researchers have developed a Situation Awareness and Attention Guidance (SAAG) pipeline using an augmented reality version of the board game Carcassonne to study human-computer interaction and cognitive modeling.
• The system utilizes two distinct game state encodings: a bit-based 120x120 sub-tile matrix for CNN-based gameplay AI training and a graph-based representation for logical game mechanics and GNN-based situation modeling.
• A CNN-based gameplay agent trained via Unity's ML-Agents framework successfully learns complex strategies, evidenced by increased city completions, improved meeple management, and more frequent point-scoring turns.