Gramazio Kohler Research
Open Positions
Compas FAB
Compas Timber
AIXD: AI-eXtended Design
AI-Augmented Architectural Design
Impact Printing
AR Timber Assemblies
Architectural Design with Conditional Autoencoders
Integrated 3D Printed Facade
Think Earth SP7
Robotic Plaster Spraying
Additive Manufactured Facade
Human-Machine Collaboration
Timber Assembly with Distributed Architectural Robotics
Eggshell Benches
Autonomous Dry Stone
Data Driven Acoustic Design
Mesh Mould Prefabrication
Data Science Enabled Acoustic Design
Thin Folded Concrete Structures
Adaptive Detailing
Deep Timber
Robotic Fabrication Simulation for Spatial Structures
Jammed Architectural Structures
Digital Ceramics
On-site Robotic Construction
Mesh Mould Metal
Smart Dynamic Casting and Prefabrication
Spatial Timber Assemblies
Robotic Lightweight Structures
Mesh Mould and In situ Fabricator
Complex Timber Structures
Spatial Wire Cutting
Robotic Integral Attachment
Mobile Robotic Tiling
YOUR Software Environment
Aerial Construction
Smart Dynamic Casting
Topology Optimization
Mesh Mould
Acoustic Bricks
Additive processes
Room acoustics

Autonomous Dry Stone, 2019-2022
PhD research project
This research is focused on the autonomous, on-site planning and construction of large-scale dry stack structures (walls constructed with irregular stones, without mortar). The project develops an adaptive planning and fabrication pipeline that steers construction towards digitally defined global geometries, while allowing for the use of abundantly available—and highly varied—locally-sourced rock and recycled demolition materials that are extremely low in embodied energy. The process provides a fully reversible alternative to concrete that can be applied, for example, to the construction of retaining walls, load-bearing structures, and revetments for civil infrastructure and landscaping.

The core component of the research is a parallelized planning algorithm and custom software interface that combines feature-based candidate seeding with heuristics adapted from traditional masonry methods, constrained registration, rigid body simulation, and learned classifiers in order to select and position stones from a limited inventory of scanned objects such that they align with a designer-specified target surface.

The construction process has been tailored to the use of HEAP (Hydraulic Excavator for an Autonomous Purpose), a modified 12-ton Menzi Muck M545 walking excavator developed by the Robotic Systems Lab (RSL). The mobile machine uses GNSS and cabin- and arm-mounted LiDAR sensors to provide models of the environment, the available stones, and the in-progress wall — enabling the planner to adapt to the local terrain and account for any settling and unexpected deviations throughout construction. The high payload capacity, reach, and maneuverability of the excavator have facilitated the production of several massive demonstration structures, consisting of tens or hundreds of elements (boulders and concrete debris, approximately 1000 kg each) and reaching heights up to 6 meters.

This research project is pursued in the framework of the National Competence Centre of Research (NCCR) Digital Fabrication.

Johns, Ryan Luke, Martin Wermelinger, Ruben Mascaro, Dominic Jud, Fabio Gramazio, Matthias Kohler, Margarita Chli, and Marco Hutter. “Autonomous Dry Stone.” Construction Robotics 4, no. 3 (2020): 127–40.

Wermelinger, Martin, Ryan Luke Johns, Fabio Gramazio, Matthias Kohler, and Marco Hutter. “Grasping and Object Reorientation for Autonomous Construction of Stone Structures.” IEEE Robotics and Automation Letters 6, no. 3 (2021): 5105–12.

Gramazio Kohler Research, ETH Zurich

Collaborators: Ryan Luke Johns (project lead), Martin Wermelinger, Dominic Jud, Ruben Mascaro, Varin Buff, Vuk Pajovic, Mads Albers, Jomana Baddad, Indra Santosa Dr. Kathrin Dörfler, Dr. Aleksandra Anna Apolinarska, Dr. Lauren Vasey, Prof. Dr. Margarita Chli, Prof. Dr. Marco Hutter

Co-Supervisors: Prof. Dr. Olga Sorkine-Hornung, Prof. Dr. Marco Hutter

Research Programme: NCCR Digital Fabrication 1C2: Mobile Robotic Aggregation of Found Objects

In cooperation with: Robotic Systems Lab (RSL), Vision for Robotics Lab (V4RL)

Sponsors: Eberhard Unternehmungen AG
Copyright 2024, Gramazio Kohler Research, ETH Zurich, Switzerland
Gramazio Kohler Research
Chair of Architecture and Digital Fabrication
ETH Zürich HIB E 43
Stefano-Franscini Platz 1 / CH-8093 Zurich

+41 44 633 49 06
Follow us on:
Vimeo | Instagram