Autonomous robotic stone stacking with online next best object target pose planning

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 that detects randomly placed objects in a scene that are used by our next best stacking pose searching method employing gradient descent with a random initial orientation, 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.

[1]  R. Livesley.  Limit analysis of structures formed from rigid blocks , 1978 .

[2]  R. Livesley.  A computational model for the limit analysis of three-dimensional masonry structures , 1992 .

[3]  Yoshiaki Ohkami,et al.  Design and implementation of a robot assisted crucible charging system , 2000, Proceedings 2000 ICRA. Millennium Conference. IEEE International Conference on Robotics and Automation. Symposia Proceedings (Cat. No.00CH37065).

[4]  Hui Chen,et al.  3D free-form object recognition in range images using local surface patches , 2004, Proceedings of the 17th International Conference on Pattern Recognition, 2004. ICPR 2004..

[5]  Philippe Block,et al.  Real-time limit analysis of vaulted masonry buildings , 2006 .

[6]  Frédo Durand,et al.  Procedural modeling of structurally-sound masonry buildings , 2009, ACM Trans. Graph..

[7]  Nico Blodow,et al.  Fast Point Feature Histograms (FPFH) for 3D registration , 2009, 2009 IEEE International Conference on Robotics and Automation.

[8]  Morgan Quigley,et al.  ROS: an open-source Robot Operating System , 2009, ICRA 2009.

[9]  Yu Zhong,et al.  Intrinsic shape signatures: A shape descriptor for 3D object recognition , 2009, 2009 IEEE 12th International Conference on Computer Vision Workshops, ICCV Workshops.

[10]  Ming-Cheng Ko.  Algorithms and Automated Material Handling Systems Design for Stacking 3D Irregular Stone Pieces , 2011 .

[11]  Ulrich Knaack,et al.  Prefabricated systems : principles of construction , 2011 .

[12]  Radhika Nagpal,et al.  Distributed amorphous ramp construction in unstructured environments , 2014, Robotica.

[13]  Paul J. Kennedy,et al.  Using Artificial Intelligence to Build with Unprocessed Rock , 2012 .

[14]  Jessica B. Hamrick,et al.  Simulation as an engine of physical scene understanding , 2013, Proceedings of the National Academy of Sciences.

[15]  Mohammed Bennamoun,et al.  Rotational Projection Statistics for 3D Local Surface Description and Object Recognition , 2013, International Journal of Computer Vision.

[16]  Yong Xiao,et al.  Towards Autonomous Robotic In-Situ Assembly on Unstructured Construction Sites Using Monocular Vision , 2014 .

[17]  Fabio Gramazio,et al.  The robotic touch : how robots change architecture : Gramazio & Kohler, research ETH Zurich 2005-2013 , 2014 .

[18]  Manish Singh,et al.  Perception of physical stability and center of mass of 3-D objects. , 2015, Journal of vision.

[19]  Stig Anton Nielsen,et al.  Fusing design and construction as speculative articulations for the built environment , 2015 .

[20]  Fabio Gramazio,et al.  Mobile Robotic Brickwork , 2016 .

[21]  Jonas Buchli,et al.  Autonomous repositioning and localization of an in situ fabricator , 2016, 2016 IEEE International Conference on Robotics and Automation (ICRA).