CumInCAD is a Cumulative Index about publications in Computer Aided Architectural Design
supported by the sibling associations ACADIA, CAADRIA, eCAADe, SIGraDi, ASCAAD and CAAD futures

PDF papers
id acadia19_16
authors Hosmer, Tyson; Tigas, Panagiotis
year 2019
title Deep Reinforcement Learning for Autonomous Robotic Tensegrity (ART)
source ACADIA 19:UBIQUITY AND AUTONOMY [Proceedings of the 39th Annual Conference of the Association for Computer Aided Design in Architecture (ACADIA) ISBN 978-0-578-59179-7] (The University of Texas at Austin School of Architecture, Austin, Texas 21-26 October, 2019) pp. 16-29
summary The research presented in this paper is part of a larger body of emerging research into embedding autonomy in the built environment. We develop a framework for designing and implementing effective autonomous architecture defined by three key properties: situated and embodied agency, facilitated variation, and intelligence.We present a novel application of Deep Reinforcement Learning to learn adaptable behaviours related to autonomous mobility, self-structuring, self-balancing, and spatial reconfiguration. Architectural robotic prototypes are physically developed with principles of embodied agency and facilitated variation. Physical properties and degrees of freedom are applied as constraints in a simulated physics-based environment where our simulation models are trained to achieve multiple objectives in changing environments. This holistic and generalizable approach to aligning deep reinforcement learning with physically reconfigurable robotic assembly systems takes into account both computational design and physical fabrication. Autonomous Robotic Tensegrity (ART) is presented as an extended case study project for developing our methodology. Our computational design system is developed in Unity3D with simulated multi-physics and deep reinforcement learning using Unity’s ML-agents framework. Topological rules of tensegrity are applied to develop assemblies with actuated tensile members. Single units and assemblies are trained for a series of policies using reinforcement learning in single-agent and multi-agent setups. Physical robotic prototypes are built and actuated to test simulated results.
series ACADIA
type normal paper
full text file.pdf (6,844,481 bytes)
references Content-type: text/plain
Details Citation Select
100%; open Brand, Stewart. (1995) Find in CUMINCAD How Buildings Learn: What Happens after They’re Built , Penguin

100%; open Brooks, Rodney A. (1991) Find in CUMINCAD New Approaches to Robotics , Science 253 (5025): 1227–32

100%; open Foerster, Jakob, Richard Y Chen, Maruan Al-Shedivat, Shimon Whiteson, Pieter Abbeel, and Igor Mordatch (2018) Find in CUMINCAD Learning with Opponent-Learning Awareness , Proceedings of the 17th International Conference on Autonomous Agents and MultiAgent Systems, 122–30

100%; open Gerhart, John, and Marc Kirschner. (2007) Find in CUMINCAD The Theory of Facilitated Variation , Proceedings of the National Academy of Sciences 104 (suppl 1): 8582–89

100%; open Graham, Jason M, Albert B Kao, Dylana A Wilhelm, and Simon Garnier. (2017) Find in CUMINCAD Optimal Construction of Army Ant Living Bridges , Journal of Theoretical Biology 435: 184–98

100%; open Ingber, Donald E. (1998) Find in CUMINCAD The Architecture of Life , Scientific American 278 (1): 48–57

100%; open Jenett, Ben, and Kenneth Cheung. (2017) Find in CUMINCAD Bill-e: Robotic Platform for Locomotion and Manipulation of Lightweight Space Structures , 25th AIAA/AHS Adaptive Structures Conference, 1876

100%; open Kober, Jens, J Andrew Bagnell, and Jan Peters. (2013) Find in CUMINCAD Reinforcement Learning in Robotics: A Survey , The International Journal of Robotics Research 32 (11): 1238–74

100%; open Kulkarni, Tejas D, Karthik Narasimhan, Ardavan Saeedi, and Josh Tenenbaum. (2016) Find in CUMINCAD Hierarchical Deep Reinforcement Learning: Integrating Temporal Abstraction and Intrinsic Motivation , Advances Neural Information Processing Systems, 3675–83

100%; open Lee, Seunghye, and Jaehong Lee. (2016) Find in CUMINCAD A Novel Method for Topology Design of Tensegrity Structures , Composite Structures 152: 11–19

100%; open Levin, Stephen M. (2006) Find in CUMINCAD Tensegrity: The New Biomechanics , Textbook of Musculoskeletal Medicine 9

100%; open Levine, Sergey, Chelsea Finn, Trevor Darrell, and Pieter Abbeel. (2016) Find in CUMINCAD End-to-End Training of Deep Visuomotor Policies , The Journal of Machine Learning Research 17 (1): 1334–73

100%; open Li, Yuxi. (2017) Find in CUMINCAD Deep Reinforcement Learning: An Overview , ArXiv Preprint ArXiv:1701.07274

100%; open Lu, Andong. (2017) Find in CUMINCAD Autonomous Assembly as the Fourth Approach to Generic Construction , Architectural Design 87 (4): 128–33

100%; open Mao, Hongzi, Mohammad Alizadeh, Ishai Menache, and Srikanth Kandula. (2016) Find in CUMINCAD Resource Management with Deep Reinforcement Learning , Proceedings of the 15th ACM Workshop on Hot Topics Networks, 50–56

100%; open Mnih, Volodymyr, Koray Kavukcuoglu, David Silver, Alex Graves, Ioannis Antonoglou, Daan Wierstra, and Martin Riedmiller. (2013) Find in CUMINCAD Playing Atari with Deep Reinforcement Learning , ArXiv Preprint ArXiv:1312.5602

100%; open Nagase, K, T Yamashita, and N Kawabata (2016) Find in CUMINCAD On a Connectivity Matrix Formula for Tensegrity Prism Plates , Mechanics Research Communications 77: 29–43

100%; open Parter, Merav, Nadav Kashtan, and Uri Alon. (2008) Find in CUMINCAD Facilitated Variation: How Evolution Learns from Past Environments to Generalize to New Environments , PLoS Computational Biology 4 (11): e1000206

100%; open Pathak, Deepak, Chris Lu, Trevor Darrell, Phillip Isola, and Alexei A Efros. (2019) Find in CUMINCAD Learning to Control Self-Assembling Morphologies: A Study of Generalization via Modularity , ArXiv Preprint ArXiv:1902.05546

100%; open Petersen, Kirstin, and Radhika Nagpal. (2017) Find in CUMINCAD Complex Design by Simple Robots: A Collective Embodied Intelligence Approach to Construction , Architectural Design 87 (4): 44–49

last changed 2019/12/18 08:01
pick and add to favorite papersHOMELOGIN (you are user _anon_955065 from group guest) CUMINCAD Papers Powered by SciX Open Publishing Services 1.002