Learning to design from humans: Imitating human designers through deep learning

TL;DR

This paper introduces a deep learning framework that enables computer agents to learn human design strategies from historical data, allowing them to generate feasible and efficient designs in a human-like manner without explicit problem-specific information.

Contribution

The paper presents a novel two-step deep learning approach for imitating human design strategies directly from observation, without requiring explicit objective or performance metrics.

Findings

Agents can generate feasible, efficient designs similar to humans

The framework successfully learns implicit design strategies from data

Designs produced by agents outperform random or non-imitative approaches

Abstract

Humans as designers have quite versatile problem-solving strategies. Computer agents on the other hand can access large scale computational resources to solve certain design problems. Hence, if agents can learn from human behavior, a synergetic human-agent problem solving team can be created. This paper presents an approach to extract human design strategies and implicit rules, purely from historical human data, and use that for design generation. A two-step framework that learns to imitate human design strategies from observation is proposed and implemented. This framework makes use of deep learning constructs to learn to generate designs without any explicit information about objective and performance metrics. The framework is designed to interact with the problem through a visual interface as humans did when solving the problem. It is trained to imitate a set of human designers by observing their design state sequences without inducing problem-specific modelling bias or extra information about the problem. Furthermore, an end-to-end agent is developed that uses this deep learning framework as its core in conjunction with image processing to map pixel-to-design moves as a mechanism to generate designs. Finally, the designs generated by a computational team of these agents are then compared to actual human data for teams solving a truss design problem. Results demonstrates that these agents are able to create feasible and efficient truss designs without guidance, showing that this methodology allows agents to learn effective design strategies.