Andromeda is a Rhino-native copilot that turns briefs, context, and massing into a single, interpretable graph so designers can enrich masterplans, evaluate KPIs, and bake results back to Rhino, without leaving their workflow. Built for early-stage masterplanning, it aims to raise social value, connectivity, accessibility, and overall urban quality by unifying data, guiding program allocation, … Read more
ABSTRACT This thesis investigates the relationship between urban development patterns and outdoor thermal comfort, with a focus on Mean Radiant Temperature (MRT), a key factor in calculating the Universal Thermal Climate Index (UTCI). While graph-based approaches have long been used in spatial analysis (e.g., space syntax, circulation networks), this research extends the application of graph … Read more
ABSTRACT Recent developments in generative artificial intelligence, particularly diffusion models such as Stable Diffusion and DALL·E, have enabled the creation of visually compelling architectural façades from text-based prompts. While these outputs are expressive and stylistically diverse, they remain fundamentally unstructured, lacking spatial intelligence, semantic clarity, and geometric editability. This limits their integration into architectural design … Read more
Manual floorplan generation for high-rise residential buildings is labor-intensive and often overlooks key environmental parameters, limiting the ability to quickly assess performance-based design alternatives. Demo :
Automating Architectural Visualization: A Journey Through Technical Pivots and AI Evolution Introduction In the rapidly evolving landscape of architectural visualization, the gap between conceptual design and compelling visual presentation remains a significant challenge. While architects and designers excel at creating innovative spaces, transforming these 3D models into cinematic walkthroughs typically requires specialized skills, expensive software, … Read more
In contemporary architectural practice, the gap between conceptual design and structural analysis often leads to delays, miscommunication, and inefficient iteration cycles. This project proposes an integrated workflow that bridges this divide by creating an interactive interface where architects can receive real-time structural feedback while scanning their preliminary physical model. By combining Unity-based visualization, QR code-enabled … Read more
EcoNodes is an AI-driven urban planning platform designed to identify and prioritize the city’s most heat-stressed and impervious junctions for strategic green interventions. By combining satellite imagery, street view segmentation, and environmental datasets, EcoNodes highlights the urban nodes that lack vegetation, suffer from poor air flow, or trap excessive heat. The tool empowers planners to … Read more
Using Street View and Remote Sensing methods to infer ground level socio-economic realities The Challenge: The Urban Data Blind Spot Urban economies are dynamic, fast-evolving systems—but the data used to understand them is often static, delayed, or incomplete. In many cities, a significant share of economic activity unfolds beyond the reach of traditional measurement frameworks, … Read more
In the pursuit of a sustainable built environment, Timber Syntax demonstrates how reclaimed, non-homogeneous timber can be transformed into high-quality facade systems through a computational and robotic pipeline. Developed at the Institute for Advanced Architecture of Catalonia (IAAC), this project bridges waste reuse, advanced fabrication, and circular design to propose a new paradigm for timber … Read more
“What if you could speak your design ideas and watch them transform into complete parametric scripts in real-time?”
HaBiCoM is an AI-powered copilot designed to assist architects, designers, and users in shaping smarter, more responsive interior spaces. At its core, HaBiCoM redefines the way we approach furniture placement within residential environments by aligning each design decision with the user’s unique daily habits, lifestyle rhythms, and thermal comfort needs. Unlike traditional layout tools, HaBiCoM … Read more
Computing Risk & Planning Resilience from Afar is a remote-sensing–driven investigative study to read, identify and address underlying vulnerabilities associated with landslide risk in urban India. The project aims to develop replicable analysis workflows for compounded risk calculation—making visible what often remains hidden enabling actionable insights in places where institutional data is frequently outdated or … Read more
Introduction Urban traffic congestion is more than just an inconvenience—it’s a global challenge tied to pollution, stress, and wasted time. While cities are turning to AI-driven systems to ease the gridlock, the question remains: Do these technologies actually perform better than traditional methods?Flow – SIGHT is a comparative research project that investigates traffic systems across … Read more
