Design, Cups, and Blankets. A Free-Energy-Principle-Based Approach to Product Design

TL;DR

This paper proposes a novel inference-based approach to product design using the free-energy principle, modeling object types as inferred structures rather than predefined categories.

Contribution

It introduces requirement-steered inference for object types and extends the Dynamic Markov Blanket Detection algorithm to make this inference computationally feasible.

Findings

Models product surface as a Markov blanket to infer object types.

Reframes design as inference rather than optimization.

Provides a theoretical proof of concept for the approach.

Abstract

Classical design theory treats the type of an object as a given: the designer decides in advance that this will be a cup, then optimizes its parameters. This paper argues that object type is not a presupposition but an inference, something that can be determined from physical data and functional requirements jointly. We call this problem requirement-steered interface type inference and show that it is inexpressible within existing design frameworks. This paper makes two contributions that are jointly necessary and individually incomplete. The first is the problem itself, which classical design cannot pose because it presupposes the very thing our problem seeks to determine. The second is C-DMBD, a constrained extension of the Dynamic Markov Blanket Detection algorithm, which makes requirement-steered inference computationally tractable. Drawing on the free-energy principle and active inference, established frameworks in theoretical neuroscience and Bayesian mechanics, we model a product's surface as a Markov blanket: the minimal boundary through which all causal exchange between object and environment must pass. Different blanket structures correspond to different object types; different parameterizations of the same structure correspond to different functional modes of the same type. This paper is a proof of concept and a theoretical proposal. It reframes design as inference rather than optimization, and as a relation between generative models rather than a specification of parameters.