1 / 13

AGENCY GP: Agent-Based Genetic Programming for Spatial Exploration

AGENCY GP: Agent-Based Genetic Programming for Spatial Exploration. Peter Testa, Una-May O’Reilly Simon Greenwold Emergent Design Group, MIT mit.edu/arch/edg. Outline. Background and Motivation Genetic Programming Platform Innovations 3D Modeler Integration User Control

thi
Download Presentation

AGENCY GP: Agent-Based Genetic Programming for Spatial Exploration

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript


  1. AGENCY GP: Agent-Based Genetic Programming for Spatial Exploration Peter Testa, Una-May O’Reilly Simon Greenwold Emergent Design Group, MIT mit.edu/arch/edg

  2. Outline • Background and Motivation • Genetic Programming • Platform Innovations • 3D Modeler Integration • User Control • Agent-based fitness • Representation and Interface • Conclusion

  3. Background and Motivation • Non-hierarchical organizations • Information technology • Increasing speed of production • New materials and techniques of manufacture

  4. Genetic Programming

  5. Platform Innovations: 3D Modeler Integration Spatial Model Agency Plug-in Alias|Wavefront Maya Extruded Maya Curves

  6. Population Individual 1 Curve 1 Parameters {Fixed} Operations {Variable} Maya Shape Curve 2 Parameters {Fixed} Operations {Variable} Maya Shape Curve 3 Parameters {Fixed} Operations {Variable} Maya Shape …

  7. Language: Operations Rotate Translate Scale Cut Boolean: Intersect Boolean: Union

  8. Platform Innovations: User Control • Starting Curves • Agents (modification of fitness function) • Interruption, Intervention, Resumption (modification of population)

  9. Interruption, Intervention, Resumption (IIR) ZWidening = 1.114 ZWidening = .8

  10. Platform Innovations: Agents • Agent-based Evaluation

  11. Representation and Interface • Data Cloud

  12. Representation and Interface • Reactive Interface Reactive Interface by Axel Kilian (MIT Thesis 2000)

  13. Conclusion • What we have • GP engine • Interpreter • IIR • Basic Agent • What we’ve shown • Where we’re going

More Related