DEEP SPATIAL MEMORY: Quantifying Architectural Spatial Experiences through Agent-driven Simulations and Deep Learning

Abstract

In architectural theory, the spatial experience is dynamic, evolving from sequences of interconnected views shaped by past encounters and future expectations. Traditional computational methods such as Isovists provide geometric insights but fall short in representing their sequential nature. To address this gap, the paper introduces a novel methodology that combines agent-driven simulation, 3D Isovist sampling, and deep learning for quantitative analysis and comparison of spatial experiences in architecture. This approach leverages the Grasshopper plugin Pedsim for simulating pedestrian paths and a self-supervised video representation learning model MemDPC for processing depth panorama sequences and extracting numerical features for each sequence. The methodology is first validated through a controlled experiment with various sequence typologies, affirming its efficacy in recognizing typological similarities. A case study is conducted comparing Louis Kahn's designs with Roman architecture, quantitatively analysing their intertwined spatial experiences. This research offers a framework for quantitatively comparing spatial experiences across buildings and interpreting the nuanced impact of historical references on modern spaces.