One Paper Conditionally Accepted for CHI '24!

We propose a novel computationally rational model that features modeling users’ attention switch when multitasking, especially in the context of reading on OHMDs while walking. We develop a hierarchical reinforcement learning architecture to capture users’ key cognitive processes and realize them in a physics engine called MuJoCo. The model successfully replicates user behaviors, including attention switch, walking speed control, and reading. Please see our paper for more details!

Codes will also be available here: https://github.com/Synteraction-Lab/heads-up-multitasker