Presentation
Leveraging Generative AI to Create Lightweight Simulations for Far-Future Autonomous Teammates
SessionPoster Session 1
DescriptionAs the domain of AI advances, the design and capability of human-AI teams are becoming increasingly complex. Unfortunately, this complexity has increased the pace at which research needs to be performed. On the one hand, low-fidelity survey-based experiments have provided an opportunity for rapid human-AI teaming research, but this pace often comes at the cost of depth. Alternatively, high-fidelity research studies that use full-fledged simulations remain relevant, but their development overhead and usage in human-subject experiments often slow the pace of research. This paper proposes a system design that splits the difference between these two platforms to provide the ability to explore human-AI teams at a medium fidelity that allows for rapid prototyping from researchers and interaction from participants. The proposed platform consists of a predictive simulation engine that uses generative AI to ingest, modify, and predict simulation states. Researchers can describe teammate capabilities, environments, and goals, which can be stored in a traditional JSON game state. The proposed platform can then display this state to a participant and allow said participant to interact with a real-time HAT. The proposed simulation provides an interactive opportunity to explore modern and far-future HATs, which will improve the options available to researchers.
Event Type
Poster
TimeTuesday, October 14th5:30pm - 6:30pm CDT
LocationRiverside East