Assignment: Looking Ahead - Machine Learning and Artificial Intelligence

Pick one of the three talks below. Watch the video, skim the handout/presentation if it helps. They each cover a different angle on AI and ML in the built environment, so pick the one that pulls at you.

Option A - The technical pipeline: Using Generative Design and Machine Learning for Faster Analysis Feedback (AU 2020) A workflow walkthrough: generate synthetic data with Generative Design in Revit/Dynamo, train an ML model to predict energy analysis results faster. Best if you want to see the end-to-end engineering of how ML actually gets built into an AEC tool. → Watch

Option B - The industry vision: The Future of BIM Is NOT BIM, And It's Coming Faster Than You Think - The Sequel (Bill Allen, AU 2019) The sequel to the most-watched AU talk ever. Three years after Bill's 2016 predictions about how generative design, algorithms, and robotic construction would reshape the industry, he revisits what came true, what didn't, and what's next. → Watch

Option C - A concrete case study: A Practical Use of Machine Learning in the AEC Industry (KLH Engineers, AU 2019) KLH built an ML model in Python to automate the painful AutoCAD-to-Revit layer conversion problem — translating thousands of inconsistent layer names into proper Revit elements using their own historical data. A demystifying look at solving one specific real problem with ML. → Watch

Write a short response (a few paragraphs)

Cover:

• What problem the speakers are solving/talking about, and the approach they take/propose
• One thing in the talk that genuinely surprised you, or that you'd push back on
• What you'd want to try yourself or what would have to be true for you to try it in a project

Look back at the parametric work you've done over the past 8 weeks - building forms, flexing them, evaluating metrics, plotting tradeoffs. Where did you hit friction? Where did things take much longer than you expected? Where did you find yourself doing repetitive work that felt like it should be automated?

Now imagine an AI or ML tool that could have helped you at one of those friction points.

Write a short reflection covering:

• One or two moments from the quarter where you felt the limits of the current tools
• What an AI- or ML- augmented version of that workflow might look like, even speculatively
• Whether you'd actually want that augmentation, or whether part of the friction was the point

Length: 1-2 paragraphs is enough, we value a shorter response written by you more than an AI-generated several pages

Find three tools, companies, projects, research or open-source efforts working at the intersection of AI/ML and the built environment. They don't all have to be startups, a research lab, an open-source library, a plugin, or a feature inside a bigger tool all count. The only rule is: it should be something that didn't exist (or wasn't usable) a few years ago.

For each one, write a short paragraph covering:

• What it does, in your own words
• Why it's interesting, what problem it's solving or what makes it new
• Whether it would have changed something about how you worked this quarter, and how

If you want some starting points to look for: text-to-floor-plan tools, generative design plug-ins, AI-augmented BIM, AI for energy/daylight prediction, AI-driven site analysis, 3D model generation from sketches or images, AI assistants inside Revit or Grasshopper, ML for structural sizing, etc. but don't limit yourself to these. Surprise us.