Robotic Construction Gets Fancy at ETH Zurich's Digital Fabrication Lab

Bricklaying robots, building structures out of rubble, and creative concrete are all works in progress at ETH Zurich

2 min read
Robotic Construction Gets Fancy at ETH Zurich's Digital Fabrication Lab
Photo: NCCR Digital Fabrication/ETH Zurich

Last week, we wrote about some robots that are making construction more efficient by automating work with bricks and concrete. At ETH Zurich, the Swiss National Science Foundation (through the National Centres of Competence in Research) has just opened a Digital Fabrication lab that’s exploring what else is possible with construction autonomy, and they’ve come up with some very cool ideas.

The flagship project (for the moment, in that it looks to be the most complete) is the In-situ Fabricator, an autonomous construction robot. It’s an industrial arm on a mobile base that can lay bricks, but the difference between this system and the one from last week is that the In-situ Fabricator is designed to be completely self-contained, without requiring any external localization systems. The robot has a 2D laser rangefinder on it, and once it gets to the construction site, it can build up a 3D map that gets registered to existing localized structural plans. That way, the robot always knows where it is, and can move around a construction site without any additional infrastructure, even autonomously adapting to minor design variations when necessary.

Even though the In-situ Fabricator is, arguably, much more intelligent than last week’s bricklaying robot, it’s also much farther from commercialization, requiring humans to feed it bricks. It also places bricks without mortar, which is something to keep in mind if you were expecting the walls that it puts up to stay up for any appreciable length of time. It’s not necessarily the focus of this project to make a completely commercially viable robot, and these issues are solvable, but we’re certainly looking at a construction robot here that’s most comfortable in a lab environment, for the moment.

img

Photo: Digital Fabrication/ETH Zurich

Another project from the NCCR Digital Fabrication program is “robotic aggregations of materials with unpredictable geometry,” which is developing a system that can build things out of rubble, basically:

The use of building materials with unpredictable geometries, such as raw quarry stones or recycled concrete rubble, is a challenge for the traditions of digital fabrication. This research work focuses on developing advanced three-dimensional scanning of materials, real-time analysis, and digital robotic fabrication that is able to respond to such irregular materials. The goal for this research is therefore to define an innovative and environmentally sound building system that foregoes traditional binding materials, reinforcement systems and formwork.

img

Photo: Digital Fabrication/ETH Zurich

This last one is called Mesh Mould:

This project explores the folding of two separate yet essential concrete construction components – reinforcement and formwork – into a unified robotic fabrication process. The idea is a digitally-controlled extrusion process of bespoke “leaking formwork” elements for non-standard concrete structures that are environmentally sound and structurally lean, and that can be efficiently fabricated directly on the construction site.

If buildings could take advantage of these customized concrete forms (which are tedious for humans to construct), it would make interesting architecture much more affordable, and by optimizing form for function, you could potentially save a lot of time, money, and material by not having to over-engineer structures.

There are a huge number of other projects on the NCCR Digital Fabrication initiative that are worth checking out; we’ve only featured a couple of them here, so click the link below to see everything that they’re working on.

[ dfab ]

Thanks Jonas!

The Conversation (0)

How the U.S. Army Is Turning Robots Into Team Players

Engineers battle the limits of deep learning for battlefield bots

11 min read
Robot with threads near a fallen branch

RoMan, the Army Research Laboratory's robotic manipulator, considers the best way to grasp and move a tree branch at the Adelphi Laboratory Center, in Maryland.

Evan Ackerman
LightGreen

“I should probably not be standing this close," I think to myself, as the robot slowly approaches a large tree branch on the floor in front of me. It's not the size of the branch that makes me nervous—it's that the robot is operating autonomously, and that while I know what it's supposed to do, I'm not entirely sure what it will do. If everything works the way the roboticists at the U.S. Army Research Laboratory (ARL) in Adelphi, Md., expect, the robot will identify the branch, grasp it, and drag it out of the way. These folks know what they're doing, but I've spent enough time around robots that I take a small step backwards anyway.

This article is part of our special report on AI, “The Great AI Reckoning.”

The robot, named RoMan, for Robotic Manipulator, is about the size of a large lawn mower, with a tracked base that helps it handle most kinds of terrain. At the front, it has a squat torso equipped with cameras and depth sensors, as well as a pair of arms that were harvested from a prototype disaster-response robot originally developed at NASA's Jet Propulsion Laboratory for a DARPA robotics competition. RoMan's job today is roadway clearing, a multistep task that ARL wants the robot to complete as autonomously as possible. Instead of instructing the robot to grasp specific objects in specific ways and move them to specific places, the operators tell RoMan to "go clear a path." It's then up to the robot to make all the decisions necessary to achieve that objective.

Keep Reading ↓ Show less