Automated Workflow for KPI Extraction from Versioned Models in Speckle Why KPI Tracking Breaks Down During Iterative Design In the current studio workflow, KPI extraction and performance evaluation depend on repeated manual operations across design iterations. This slows down feedback, introduces version mismatch risks, and disconnects analytical outputs from the model itself. This tool was … Read more
Our project is Flux Façade, a collaborative workflow for data-driven parametric façade design.The project was developed by Team 3.2 as part of the Collaborative Workflow Seminar in the Master in Advanced Computation for Architecture. Flux Façade focuses on improving how environmental analysis and façade geometry interact within the design workflow. Problem Statement In large architectural … Read more
Problem Statement & Context Target User Proposed Solution How it works User Workflow Speckle Automation Demo Success criteria Limitations and future scope
The Problem No single source of truth for KPIs In our studio workflow, KPIs are everywhere and nowhere at the same time. Each team tracks performance in its own way—some in Grasshopper scripts, some in spreadsheets, some buried inside models—and none of these sources fully agree with each other. Because updates are slow and fragile, … Read more
Solutions for Rapid Data Acquisition in Disaster Scenarios This project explores a robotic perception pipeline designed to support post-disaster assessment and early response scenarios. The core objective is to detect and map cracks in damaged buildings using vision-based data, assisting rescue teams by providing spatial information about potentially unsafe areas. Rather than aiming for full … Read more
This project explores a robotic system that translates digital vision into physical matter through the constraint of continuity. Rather than behaving like a conventional plotter that freely lifts and re-positions its pen, the system confronts a more complex challenge: it must interpret image topology and compute a path that allows the entire drawing to be … Read more
Robotic Disassembly & Reassembly with Spatial AI Abstract The project explores a circular construction workflow that integrates robotic systems with Spatial AI to automate the disassembly and reassembly of brick structures. Utilizing a Gemini Vision-Language Model (VLM) pipeline, the system performs autonomous material evaluation, identifying surface damages such as chipping, spalling, and staining, as well … Read more
Agricultural landscapes often disappear from visual and political attention during conflict, overshadowed by images of urban destruction. This project uses satellite imagery to examine agricultural land in Gaza, focusing on the Beit Hanoun belt as an intersection between destruction and food systems. Through vegetation indices and bombing crater detection, the study distinguishes seasonal agricultural cycles … Read more
India’s solar ambition is written into its landscape. Since the launch of the Jawaharlal Nehru National Solar Mission in 2010, the country has pursued one of the most aggressive renewable energy expansions in history —targeting 500GW of solar capacity by 2030. But the geography of that expansion follows a troubling logic. The regions chosen for … Read more
During the AI in Architecture and Urbanism Seminar, our team built an automated compliance checking system that validates architectural projects directly from IFC models. Building regulation checks are traditionally manual, slow, and error-prone. Architects review 2D drawings, interpret regulations individually, and often wait weeks for compliance feedback. We asked a simple question: what if compliance … Read more
How can robots reach trash and recycle it? What components are we using? What is the system process? Main system
Deforestation Raster Map – 2024 The visualization depicts accumulated and annual deforestation patterns in Brazil from 1985 to 2024. The accumulated dataset shows a continuous rise in total deforested areas, reaching over 140 milllion hectares. Annual trends reveal strong fluctuations, with peaks in the late 1980’s and mid-2000’s, followed by decreases and renewed variability in … Read more
In the following blog post, we will analyse the development of the concept of our project carried out in Workshop 2.1. Team Collaborative Workflow and Modular System Development Guide, in which a Rotatory Gantry structure is proposed for the flip-type movement of a robotic arm. AIRFLIP – Rotary Gantry System for Small-Scale Cobots Overview The … Read more
This project was developed within the framework of MRAC Workshop 2.1: Team Collaborative Workflow and Modular System Development. The workshop focuses on learning, internalizing, and applying collaborative software development practices using Git and GitHub through the development of a modular robotic system. In this context, the group was tasked with designing and implementing a robotic … Read more
In our final exercise of our Urban Data seminar, we were asked to create an interactive web platform, using the python library Dash. Dash allows users to upload and format datasets to be interactive, easily toggling between different data visuals rather than showing static imagery. In personal experience, our group has noted how applicable this … Read more
