English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Zendy Plus

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Zendy Tools

Zendy Open

In this paper we introduce a general estimation methodology for learning amodel of human perception and control in a sensorimotor control task based upona finite set of demonstrations. The model's structure consists of i the agent'sinternal representation of how the environment and associated observationsevolve as a result of control actions and ii the agent's preferences overobservable outcomes. We consider a model's structure specification consistentwith active inference, a theory of human perception and behavior from cognitivescience. According to active inference, the agent acts upon the world so as tominimize surprise defined as a measure of the extent to which an agent'scurrent sensory observations differ from its preferred sensory observations. Wepropose a bi-level optimization approach to estimation which relies on astructural assumption on prior distributions that parameterize the statisticalaccuracy of the human agent's model of the environment. To illustrate theproposed methodology, we present the estimation of a model for car-followingbehavior based upon a naturalistic dataset. Overall, the results indicate thatlearning active inference models of human perception and control from data is apromising alternative to black-box models of driving.

Learning An Active Inference Model of Driver Perception and Control: Application to Vehicle Car-Following