Learning An Active Inference Model of Driver Perception and Control: Application to Vehicle Car-Following
This work addresses the need for interpretable models of human driving behavior for applications in autonomous vehicles and human-robot interaction, representing an incremental advancement in applying cognitive science theories to robotics.
The paper tackled the problem of modeling human perception and control in sensorimotor tasks by introducing a methodology to learn active inference models from demonstrations, applied to car-following behavior with results showing it as a promising alternative to black-box driving models.
In this paper we introduce a general estimation methodology for learning a model of human perception and control in a sensorimotor control task based upon a finite set of demonstrations. The model's structure consists of i the agent's internal representation of how the environment and associated observations evolve as a result of control actions and ii the agent's preferences over observable outcomes. We consider a model's structure specification consistent with active inference, a theory of human perception and behavior from cognitive science. According to active inference, the agent acts upon the world so as to minimize surprise defined as a measure of the extent to which an agent's current sensory observations differ from its preferred sensory observations. We propose a bi-level optimization approach to estimation which relies on a structural assumption on prior distributions that parameterize the statistical accuracy of the human agent's model of the environment. To illustrate the proposed methodology, we present the estimation of a model for car-following behavior based upon a naturalistic dataset. Overall, the results indicate that learning active inference models of human perception and control from data is a promising alternative to black-box models of driving.