Spatial Assembly with Self-Play Reinforcement Learning (2020)
article⁄Spatial Assembly with Self-Play Reinforcement Learning (2020)
abstract⁄We present a framework to generate intelligent spatial assemblies from sets of digitally encoded spatial parts designed by the architect with embedded principles of prefabrication, assembly awareness, and reconfigurability. The methodology includes a bespoke constraintsolving algorithm for autonomously assembling 3D geometries into larger spatial compositions for the built environment. A series of graphbased analysis methods are applied to each assembly to extract performance metrics related to architectural spacemaking goals, including structural stability, material density, spatial segmentation, connectivity, and spatial distribution. Together with the constraintbased assembly algorithm and analysis methods, we have integrated a novel application of deep reinforcement RL learning for training the models to improve at matching the multiperformance goals established by the user through selfplay. RL is applied to improve the selection and sequencing of parts while considering local and global objectives. The user’s design intent is embedded through the design of partial units of 3D space with embedded fabrication principles and their relational constraints over how they connect to each other and the quantifiable goals to drive the distribution of effective features. The methodology has been developed over three years through three case study projects called ArchiGo 20172018, NoMAS 20182019, and IRSILA 20192020. Each demonstrates the potential for buildings with reconfigurable and adaptive life cycles.
|
|
| Year |
2020 |
| Authors |
Hosmer, Tyson; Tigas, Panagiotis; Reeves, David; He, Ziming. |
| Issue |
ACADIA 2020: Distributed Proximities / Volume I: Technical Papers |
| Pages |
382-393. |
| Library link |
N/A |
| Entry filename |
spatial-assembly-with-self-play-reinforcement |
