# Active Inference and Functional Parametrisation: Differential Flatness and Smooth Random Realisation

## TL;DR

This paper explores how nonlinear control theory can be combined with active inference, focusing on differential flatness and generative models for control.

## Contribution

The paper introduces a novel connection between differential flatness and generative model design in active inference.

## Key findings

- Differential flatness provides a framework for defining pathwise properties in control systems.
- Generalised coordinates of motion are useful for formulating continuous-time generative models in active inference.
- The oculomotor control example demonstrates the practical application of these concepts.

## Abstract

This paper is a first attempt to marry constructive nonlinear control theory techniques with active inference. Specifically, we are interested in the relationship between differential flatness and the design of generative models for use in control settings. We place specific emphasis on the pathwise properties of differentially flat systems that inherit from their definition in terms of successive temporal derivatives and relate this to the use of generalised coordinates of motion in formulating continuous-time generative models in active inference. To illustrate the basic concepts, we appeal to the example of oculomotor control.