Dry Stacking for Automated Construction with Irregular Objects

We describe a method for automatically building structures from stacked, irregularly shaped objects. This is a simplified model for the problem of building dry stacked structures (i.e. no mortar) from found stones. Although automating such construction methods would be ideally suited for disaster areas or remote environments, currently such structures need to be built by skilled masons. No practical methods for automating the assembly planning process are known. The problem is challenging since each assembly action can be drawn from a continuous space poses for an object and several local geometric and physical considerations strongly affect the overall stability. We show that structures that are built following a stacking order for perfect bricks can accommodate a limited amount of irregularity, however, their performance degrades quickly when objects deviate from their ideal shape. We present a strategy for stacking irregular shapes that first considers geometric and physical constraints to find a small set of feasible actions and then further refines this set by using heuristics gathered from instructional literature for masons. The proposed method of choosing assembly actions allows construction with objects that contain a significant amount of variation.

[2]  Tsuhan Chen,et al.  3D Reasoning from Blocks to Stability , 2015, IEEE Transactions on Pattern Analysis and Machine Intelligence.

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

[4]  M. S. Shunmugam,et al.  Evaluation of circularity and sphericity from coordinate measurement data , 2003 .

[5]  J. Andrew Bagnell,et al.  Perceiving, learning, and exploiting object affordances for autonomous pile manipulation , 2013, Auton. Robots.

[6]  Marco Dorigo,et al.  Autonomous Construction with Compliant Building Material , 2014, IAS.

[7]  Leslie Pack Kaelbling,et al.  Automated Design of Adaptive Controllers for Modular Robots using Reinforcement Learning , 2008, Int. J. Robotics Res..

[8]  Felix Schill,et al.  Fluid-Mediated Stochastic Self-Assembly at Centimetric and Sub-Millimetric Scales: Design, Modeling, and Control , 2016, Micromachines.

[9]  V. Milenkovic,et al.  Compaction and separation algorithms for non-convex polygons and their applications☆ , 1995 .

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

[11]  Justin Werfel,et al.  TERMES: An Autonomous Robotic System for Three-Dimensional Collective Construction , 2011, Robotics: Science and Systems.

[12]  Joshua B. Tenenbaum,et al.  A Compositional Object-Based Approach to Learning Physical Dynamics , 2016, ICLR.

[13]  Misha Denil,et al.  Learning to Perform Physics Experiments via Deep Reinforcement Learning , 2016, ICLR.

[14]  Thomas Bock,et al.  Construction Automation and Robotics , 2008 .

[15]  Philippe Block,et al.  Thrust Network Analysis : exploring three-dimensional equilibrium , 2009 .

[16]  Roland Siegwart,et al.  Autonomous robotic stone stacking with online next best object target pose planning , 2017, ICRA 2017.

[17]  Yoshiaki Ohkami,et al.  Robotic Manipulation of Highly Irregular Shaped Objects: Application to a Robot Crucible Packing System for Semiconductor Manufacture , 2002 .

[18]  Paulo B. Lourenço,et al.  In-Plane Experimental Behavior of Stone Masonry Walls under Cyclic Loading , 2009 .

[19]  Joseph Moses Juran,et al.  Quality-control handbook , 1951 .

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

[21]  F. Forgó,et al.  On equilibrium of systems , 1985 .

[22]  A. Barrientos,et al.  Robot assembly system for the construction process automation , 1997, Proceedings of International Conference on Robotics and Automation.

[23]  Jonas Neubert,et al.  Stochastic Modular Robotic Systems: A Study of Fluidic Assembly Strategies , 2010, IEEE Transactions on Robotics.