Technology Category
Humans and AI: Game Design — Procedural Content Generation & StorytellingPlanning, Routing, and Scheduling: Planning with Language ModelsSearch and Optimization: Sampling/Simulation-based Search
Illuminating Spaces: Deep Reinforcement Learning and Laser-Wall Partitioning for Architectural Layout Generation
🤖 AI Summary
This work addresses the challenge in early-stage architectural layout design where deep reinforcement learning (DRL) struggles to simultaneously satisfy geometric constraints, topological validity, and architectural intuition. We propose a Proximal Policy Optimization (PPO)-based procedural generation method. Its core innovation is the novel “laser wall” spatial partitioning mechanism: walls are modeled as entities emitting virtual light beams, enabling dynamic path planning, beam-above/beam-below transformations, and marker-aware perception—yielding intuitive, evolvable, and semantically explicit zoning. The method operates within our custom OpenAI Gym–compatible environment, SpaceLayoutGym, and employs a vector-pixel hybrid representation alongside a joint geometric-topological reward function. Experiments demonstrate significant improvements over pure pixel-based baselines in layout diversity, functional rationality, and architectural intuitiveness, with markedly higher geometric constraint satisfaction rates and enhanced topological connectivity.
Technology Category
Application Category
📝 Abstract
Space layout design (SLD), occurring in the early stages of the design process, nonetheless influences both the functionality and aesthetics of the ultimate architectural outcome. The complexity of SLD necessitates innovative approaches to efficiently explore vast solution spaces. While image-based generative AI has emerged as a potential solution, they often rely on pixel-based space composition methods that lack intuitive representation of architectural processes. This paper leverages deep Reinforcement Learning (RL), as it offers a procedural approach that intuitively mimics the process of human designers. Effectively using RL for SLD requires an explorative space composing method to generate desirable design solutions. We introduce"laser-wall", a novel space partitioning method that conceptualizes walls as emitters of imaginary light beams to partition spaces. This approach bridges vector-based and pixel-based partitioning methods, offering both flexibility and exploratory power in generating diverse layouts. We present two planning strategies: one-shot planning, which generates entire layouts in a single pass, and dynamic planning, which allows for adaptive refinement by continuously transforming laser-walls. Additionally, we introduce on-light and off-light wall transformations for smooth and fast layout refinement, as well as identity-less and identity-full walls for versatile room assignment. We developed SpaceLayoutGym, an open-source OpenAI Gym compatible simulator for generating and evaluating space layouts. The RL agent processes the input design scenarios and generates solutions following a reward function that balances geometrical and topological requirements. Our results demonstrate that the RL-based laser-wall approach can generate diverse and functional space layouts that satisfy both geometric constraints and topological requirements and is architecturally intuitive.
Problem
Research questions and friction points this paper is trying to address.
Innovative deep Reinforcement Learning for architectural layout generation.
Laser-wall method bridges vector and pixel-based space partitioning.
Generates diverse, functional layouts with geometric and topological balance.
Innovation
Methods, ideas, or system contributions that make the work stand out.
Deep Reinforcement Learning
Laser-wall partitioning
SpaceLayoutGym simulator
🔎 Similar Papers
No similar papers found.
