Modeling Adaptation on Automated Vehicle Operation

This paper presents a cognitive model that simulates how the reliance on automation in a simple tracking task, which represents vehicle operation, changes as the success probabilities of automatic and manual mode vary. The model was developed by using ACT-R, and we also introduce three methods of reinforcement learning: the synchronization of utilities in the same mode, the summation of rewards over time, and the prediction from the past. The model performs this task through productions that manage perception and motor control. The utility values of these productions are updated based on rewards in every perception-action cycle. A run of this model simulated the overall trends of the behavioral data, suggesting some validity of the assumptions made in our model.