Using interactive evolution to design behaviors for non-deterministic self-organized construction

Heinrich, Mary Katherine; Zahadat, Payam; Harding, John; Brandt, Mads Nikolaj

Abstract

Self-organizing construction is an emerging subdomain for on-site construction robots. This not only presents new challenges for robotics, but due to the stochasticity involved in such systems, impacts the modeling and prediction of resulting built structures. Self-organizing models have been explored by architects for generative design and for optimization, but so far have infrequently been studied in the context of construction. Here we present a strategy for architects to design with non-deterministic self-organizing behaviors, using interactive evolution to incorporate user judgment. We introduce our "Integrated Growth Projection'' method, having implemented it into a software pipeline for early phase design. We test the software with an initial user group of architects, to see whether the method and pipeline helps them design a non-deterministic self-organizing behavior. The user group creates several hybrid controllers that reliably solve their chosen design tasks.

• Presentation Conference Type: Conference Paper (unpublished)
• Conference Name: Symposium on Simulation for Architecture and Urban Design (SimAUD) 2018
• Start Date: Jun 4, 2018
• End Date: Jun 6, 2018
• Acceptance Date: Feb 23, 2018
• Publication Date: Jun 4, 2018
• Peer Reviewed: Peer Reviewed
• Pages: 213-220
• Keywords: swarm construction, self-organization, artificial growth, artificial selection, interactive evolution
• Public URL: https://uwe-repository.worktribe.com/output/867069
• Publisher URL: http://simaud.com/proceedings/
• Additional Information: Title of Conference or Conference Proceedings : Symposium on Simulation for Architecture and Urban Design (SimAUD) 2018, TU Delft, Delft, The Netherlands