Human-Machine Collaboration-Guided Space Design: Combination of Machine Learning Models and Humanistic Design Concepts

Abstract

The integration of machine learning (ML) into spatial design holds immense potential for optimizing space utilization, enhancing functionality, and streamlining design processes. ML can automate tasks, predict performance outcomes, and tailor spaces to user preferences. However, the emotional, cultural, and aesthetic dimensions of design remain crucial for creating spaces that truly resonate with users-elements that ML alone cannot address. The key challenge lies in harmonizing data-driven efficiency with the nuanced, subjective aspects of design. This paper proposes a human-machine collaboration framework to bridge this gap. An effective framework should recognize that while ML enhances design efficiency through automation and prediction, it must be paired with human creativity to ensure spaces are emotionally engaging and culturally relevant. Human designers contribute intuition, empathy, and cultural insight, guiding ML-generated solutions to align with users' emotional and cultural needs. Additionally, we explore how various ML models can be integrated with human-centered design principles. These models can automate design generation and optimization, while human designers refine the outputs to ensure emotional resonance and aesthetic appeal. Through case studies in office and residential design, we illustrate how this framework fosters both creativity and cultural relevance. By merging ML with human creativity, spatial design can achieve a balance of efficiency and emotional impact, resulting in environments that are both functional and deeply human.