caa a22 4500 530098245 20190202042446.0 cr unu---uuuuu 181026s2018 xx s 100 0 eng 10.3929/ethz-b-000298048 doi 10.24963/ijcai.2018/760 doi (ETHRESEARCH)oai:www.research-collection.ethz.ch:20.500.11850/298048 Greedy Stone Tower Creations with a Robotic Arm [Elektronische Daten] [Martin Wermelinger, Fadri Furrer, Hironori Yoshida, Fabio Gramazio, Matthias Kohler, Roland Siegwart, Marco; id_orcid 0000-0002-4285-4990 Hutter] s.l. Lawrence Erlbaum Associates 2018 Open access ethresearch 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. 27th International Joint Conference on Artificial Intelligence (IJCAI 2018) in Stockholm, Sweden (July 13-19, 2018) In Copyright - Non-Commercial Use Permitted http://rightsstatements.org/page/InC-NC/1.0 ethresearch Wermelinger Martin joint author Furrer Fadri joint author Yoshida Hironori joint author Gramazio Fabio joint author Kohler Matthias joint author Siegwart Roland joint author Hutter Marco; id_orcid 0000-0002-4285-4990 joint author Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence (IJCAI-18) s.l. : Lawrence Erlbaum Associates pp. 5394-5398 978-0-9992411-2-7 http://hdl.handle.net/20.500.11850/298048 text/html WWW-Backlink auf das Repository (Open access) 1 Conference Paper ethresearch ETHRESEARCH 856 40 http://hdl.handle.net/20.500.11850/298048 text/html WWW-Backlink auf das Repository (Open access) ETHRESEARCH 700 1- Wermelinger Martin joint author ETHRESEARCH 700 1- Furrer Fadri joint author ETHRESEARCH 700 1- Yoshida Hironori joint author ETHRESEARCH 700 1- Gramazio Fabio joint author ETHRESEARCH 700 1- Kohler Matthias joint author ETHRESEARCH 700 1- Siegwart Roland joint author ETHRESEARCH 700 1- Hutter Marco; id_orcid 0000-0002-4285-4990 joint author ETHRESEARCH 773 0- Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence (IJCAI-18) s.l. : Lawrence Erlbaum Associates pp. 5394-5398 978-0-9992411-2-7 BK010053 XK010053 XK010000 ETHRESEARCH ETHRESEARCH ETHRESEARCH Conference Paper Open access