DeepAI AI Chat
Log In Sign Up

Functional Generative Design of Mechanisms with Recurrent Neural Networks and Novelty Search

by   Cameron R. Wolfe, et al.
The University of Texas at Austin

Consumer-grade 3D printers have made it easier to fabricate aesthetic objects and static assemblies, opening the door to automated design of such objects. However, while static designs are easily produced with 3D printing, functional designs with moving parts are more difficult to generate: The search space is too high-dimensional, the resolution of the 3D-printed parts is not adequate, and it is difficult to predict the physical behavior of imperfect 3D-printed mechanisms. An example challenge is to produce a diverse set of reliable and effective gear mechanisms that could be used after production without extensive post-processing. To meet this challenge, an indirect encoding based on a Recurrent Neural Network (RNN) is created and evolved using novelty search. The elite solutions of each generation are 3D printed to evaluate their functional performance on a physical test platform. The system is able to discover sequential design rules that are difficult to discover with other methods. Compared to direct encoding evolved with Genetic Algorithms (GAs), its designs are geometrically more diverse and functionally more effective. It therefore forms a promising foundation for the generative design of 3D-printed, functional mechanisms.


page 1

page 3

page 5


Functional Generative Design: An Evolutionary Approach to 3D-Printing

Consumer-grade printers are widely available, but their ability to print...

Say "Sul Sul!" to SimSim, A Sims-Inspired Platform for Sandbox Game AI

This paper proposes environment design in the life simulation game The S...

Production System Rules as Protein Complexes from Genetic Regulatory Networks

This short paper introduces a new way by which to design production syst...

Ultra-low latency recurrent neural network inference on FPGAs for physics applications with hls4ml

Recurrent neural networks have been shown to be effective architectures ...

Strongly-Typed Recurrent Neural Networks

Recurrent neural networks are increasing popular models for sequential l...