Cited on HN 3 times, 2011–2018, never outright recommendedscore 0
Years with an HN recommendation, 2007–2026
HN uses it as a go-to example of drones and robotics doing construction work.
A short GRASP Lab (University of Pennsylvania) demo in which teams of quadrotors autonomously assemble tower-like cubic structures from modular parts. The drones are given the target structure and work out the assembly plan themselves.
“We tell the quadrotors what structure to build and they figure out the assembly plan and then build it.” (HN, 2011)
Actually, you may be more right than you know (sorry). I've found this quote: "We tell the quadrotors what structure to build and they figure out the assembly plan and then build it." [this video] It still doesn't look very swarm-like to me (more like some kind of planner algorithm; I know the quote implies a distributed intelligence, but look at the way they queue always in exactly the same place, do laps, etc etc), but that certainly sounds more promising.
Quadrotors plan and build a structure from a specified design.
This format is painful to read, so I'm copying the content here. This is a series of tweets by [link] -- If you are using software to go after a legacy physical vertical, we are most excited if you do it "full stack" [0]. With @counsyl, we found that one cannot live by bioinformatics alone. So built a full clinical lab + software + national salesforce. Here is a video of our robotic genome factory: Also: insurance coverage, clearances, clinical integration... [1] The reason to do full stack is that it's hard to replace just one layer of an outdated legacy stack. CAC & integration costs can kill. For example, consider "restaurant powered by technology" vs "tech for restaurants". With code, reinvent industry and make better margins. You cannot automate something till you've done it manually many times. You cannot abstract an API till you've seen many specific examples. Need to build a site of the scale of [link] - and encounter all the problems - before you could do [link] . Reinventing agriculture? Build new kind of farm, w/ solar panels & self-driving tractors. Control all factors, show that code cuts costs. More examples of full stack startups.. Education: [2], Autos: [3], Hospitality: [4] By doing it end-to-end, you see things. First, sometimes a good reason beyond tradition (eg regulatory, logistical) for legacy practices. Second, your control of adjacent layers may eliminate the initial problem you were trying to solve. Analogous to: [5] Third, solving whole problem build
Some construction jobs are better than others. In SF, for example, there are many undersea construction jobs that pay very well. The CTO of Coinbase envisions that construction[0] as an industry is ripe for disruption, reaping the fruits of technology like VR controllable drones[1]. If you make construction like a video game, “young people” will flock to it. [0] [link] [1] [this video]
Example of VR-controllable drones disrupting construction.
Video list and Hacker News comment labels from HackerTube (prompted by @karpathy), released under ODC-By 1.0, built on the open-index/hacker-news archive. Hacker News data is provided by Y Combinator; comments remain the work of their authors. Video titles, channel names and thumbnails belong to their creators and are shown via YouTube. HackerTube Watch is an unofficial edition. Data export of 2026-10-31.
Plays via YouTube's privacy-enhanced embed
3 Hacker News comments
From the HN archive; up to 20 kept per video, favoring different commenters. Recommendations first.
Read more