Grasshopper – Generative Design for Architecture
Release date:2019, March 22
Duration:03 h 15 m
Author:Walter Zesk
Skill level:Beginner
Language:English
Exercise files:Yes
Generative design is a set of technologies that give you a computerized copilot for your design process, helping you engage the power of computation and algorithms to create designs. In this course, learn how to use the Grasshopper visual programming plugin with Rhino to create designs that would have been impossible in the past. Instructor Walter Zesk explains how to use physics solvers and evolutionary solvers to set goals and constraints for your designs, as well as how to use computation to meet those goals and work within your constraints. Plus, he covers how to use LunchBoxML to apply machine learning to your projects and unleash the full power of artificial intelligence to create designs.
Topics include:
What is generative design?
Limitations of generative design
Strengths and limitations of genetic/evolutional solvers
How physics solvers work
Testing and adjusting goals
Working with machine learning tools
Design requirements and diagramming
Optimizing with Galapagos
01 Introduction
001 Cyborg designers
002 What you should know
003 Versions and credits
02 What Is Generative Design?
001 Defining generative design
002 Measurable design goals
003 Design parameters
004 Solution space
005 Limitations of generative design
03 Genetic/Evolutional Solver Example
001 Brute force_ How evolution works
002 Common evolutionary solvers
003 Setting up Galapagos
004 Running Galapagos
005 Strengths and limitations of genetic_evolutional solvers
04 Physics Solver Example
001 Springs_ How physics solvers work
002 Installing Kangaroo Weaverbird and Meshedit
003 Kangaroo goals
004 Testing and adjusting goals
005 Strengths and limitations of physics solvers
05 Machine Learning Solver Example
001 Introduction to machine learning
002 Machine learning tools
003 Regression and predictive statistics
004 Clustering
005 Classification
006 Strengths and limitations of machine learning solvers
06 Applying Generative Design
001 Design requirements and diagramming
002 Sine surface points
003 Roof surface
004 Sides views and fitness value
005 Optimizing with Galapagos
006 ML structural regions
007 Roof panel clusters
008 Roof panel physics and classification
009 Structure for optimization
010 Goals and Kangaroo solver
011 Visualization
012 Adjustment and refinement
07 Conclusion
001 Next steps
Channel
