CHAOPT: A Testbed for Evaluating Human-Autonomy Team Collaboration Using the Video Game Overcooked!2

This paper introduces a new testbed called Cooking with Humans and Autonomy in Overcooked!2 for studying Performance and Teaming (CHAOPT). A validation study was conducted to examine the viability of Overcooked!2 as a research platform to explore teamwork and communication in humanautonomy teams. Unique measures derived from this platform such as productive chef actions (PCA), team expertise score and chef role contribution (CRC) distinguished performance between levels and players. Our findings demonstrate that we can derive meaningful team process, performance and communication measures and that the interactions within Overcooked!2 meet the requirements of psychological fidelity of teaming research.