Abstract
Predominately, robotic construction is applied as prefabrication in structured indoor environments with standard building materials. Our work, on the other hand, focuses on utilizing irregular materials found on-site, such as rubble and rocks, for autonomous construction. We present a pipeline to detect arbitrarily placed objects in a scene and form a structure out of the detected objects. The next best stacking pose is selected using a searching method employing gradient descent with ran dom initial orientations, exploiting a physics engine. This approach is validated in an experimental setup using a robotic manipulator by constructing balancing vertical stacks without mortars and adhesives. We show the results of eleven consecutive trials to form such towers autonomously using four arbitrarily in front of the robot placed rocks. Show more
Permanent link
https://doi.org/10.3929/ethz-b-000298048Publication status
publishedExternal links
Book title
Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence (IJCAI-18)Journal / series
IJCAI International Joint Conference on Artificial IntelligencePages / Article No.
Publisher
Lawrence Erlbaum AssociatesEvent
Organisational unit
09570 - Hutter, Marco / Hutter, Marco
03737 - Siegwart, Roland Y. / Siegwart, Roland Y.
03708 - Gramazio, Fabio / Gramazio, Fabio
03709 - Kohler, Matthias / Kohler, Matthias
02284 - NFS Digitale Fabrikation / NCCR Digital Fabrication
Notes
RSL; dfab; manipulation; construction; roboticMore
Show all metadata
ETH Bibliography
yes
Altmetrics