Exploring architectural identity of the city with 3D GAN and Stable Diffusion with case study of Kazan This research proposes to explore the ability and accuracy in styding and representing architectural identity of the city through the set of artistic experiments with all generated 3d geometry and 2d images in order to meet expectations of … Read more
Beginnings Our project’s concept is to develop a classification model that identifies street intersections (graph nodes) in Stockholm, Sweden, susceptible to flooding during a 100-year flood event. Based on our initial research, we found that graph machine learning operates at three levels: the graph, its edges, and its nodes. With access to a 100-year flood … Read more
TIMBER SENSING TECHNOLOGY A material system combining timber and graphene, replacing traditional sensors through graphene’s sensing capabilities. This innovative approach allows first, real-time tracking of deformations inside the wood. Second, creating a digital twin that improves maintenance efficiency in the operational phase. Third, providing a detailed service life passport, this system supports reuse and reduces … Read more
नमस्ते – مرحبًا – OLÁ – HOLÁ AIM Our aim is to make Human Robot Collaboration accessible to a variety of users via different languages by developing a speech to toolpath interface. RELEVANCE METHOD Workflow As the participant enters the room, they are greeted by a robot with a friendly waving motion. The participant can … Read more
Skyscrapers are human achievements that require innovation in the extraction of land to tower over its neighbors. The third skyscraper future reflects the past imaginary of Fritz Lang’s, Metropolis. This visualization aims to highlight the economic disparities and labor oppression depicted in the film, contrasting them with the modern logics of rentism as embodied by … Read more
What if you can control your Cobot with only hand gestures and you can work effortlessly? That’s what we came up with this experiment of using Multi agent systems to control the engagement of a collaborative robot (ur10e).Our workshop highlights an innovative approach to controlling cobots using hand gestures. This method aims to facilitate effortless … Read more
Building Together, One Word at a Time AIM The aim of this project is to enhance human-robot collaboration through the development of a user-friendly system that creates an inclusive environment. Text-to-speech (TTS) and speech-to-text (STT) systems enable humans and robots to communicate in anintuitive and engaging way. Relevance One major issue was that the human … Read more
This project explores a framework for Human-Robot Collaboration (HRC) and behavioural fabrication, focusing on constructing a Jenga-like tower using small timber blocks. Using the Agent-Based Modeling system (ABxM) from the Institute for Computational Design and Construction (ICD), a communication network was established integrating a human participant, a computer vision system, and an interactive audio interface. … Read more
“Can we understand urban environments and street characteristics from Google Street View panorama images using Machine Learning and Stable Diffusion techniques?” Project OverviewThis computational design project aims to develop a pipeline utilizing Grasshopper and Python to visualize clusters of panoramic streetscape images. The project leverages t-Distributed Stochastic Neighbor Embedding (t-SNE) for dimensionality reduction, facilitating the … Read more
Grasshopper is an incredibly versatile tool that in recent years has expanded into fields far beyond the origins in three-dimensional parametric design. One of these fields is that of GIS analysis, which has traditionally been approached through software such as QGIS. The advantages of Grasshopper and Rhinoceros3D over QGIS include the versatility and customisability of … Read more
Introduction This presentation outlines the development and evaluation of machine learning models aimed at predicting the availability of bikes at various bicing stations in Barcelona. We’ll discuss the variables involved, the modeling techniques used, and compare the performance of different models. Python is a friendly environment for preparing, training and forecasting machine learning algorithms within … Read more
Introduction Urban transportation planning relies on data science to explain the conditions driving mobility patterns. This exploration of bicing, Barcelona’s resident bike rental program, analyzes the actors impacting discrepancies in bicing data to select machine-learning strategies able to predict biking station vacancies across Barcelona for the year 2024 with an accuracy of 0.02387. With this … Read more
Bicing was launched in 2007 as a viable eco-friendly alternative or complement to traditional private and public transportation. The mobility network has also allowed for increased physical activity and better connectivity between neighbourhoods of Barcelona. It is aimed at anyone with a NIE, over the age of 16. The Bicing 2.0 models were released in 2019 to … Read more
Working in 3D CAD environments can be restrictive. While most CAD software provides tools for creating shapes and generating ideas, they often rely on a mouse and keyboard, or are very expensive. “Shape it, Feel it” investigates opportunities to generate shapes using a computer’s webcam and hand gestures. We utilize cheap and readily available hardware … Read more
Concept Most of Virtual Experiences are designed and model for humans and by humans. In this scenario believe the overall concept is that the game platform is seen from the perspective of an animal. References Aim “Our goal is to offer humans a unique experience through the eyes of a peacock. This game platform immerses … Read more
Aim “Create a range of robotic mini-games showcasing dexterity and quick reflexes, ideal for casual enjoyment.“ For this one week workshop, we drew inspiration from various games such as infinite passes, penalty shootouts, and boxing, aiming to adapt them for robotic play. Initially leaning towards infinite passes (football), we ultimately found boxing more compatible with … Read more
Due to limitation regarding the file size and quality, these performances are muted, lower quality and sped up to be under the limited file capacity. Dancing Queen(s) is an endeavor featuring a pair of robots performing synchronized dance moves. These choreographed movements mirror those of a trainer, who leads, and a follower, who emulates the … Read more
The workshop challenged us to engage with the topic of planetary urbanization through the United Nations Sustainable Development Goals 2030 agenda. We chose to work on the city of Neuquen as it represents an example of a city that is undergoing a fast transition in the context of climate change. Neuquen province has a rich … Read more
This project was part of a 1 week workshop at IAAC, utilizing the institute’s two ABB IRB6700 industrial robots. The workshop incorporated Dr. Gannon’s sophisticated simulation tools, which provide safe, real-time control of industrial robots. Under the guidance of Madeline showing us how to sketch with robots we were able to work within a flexible … Read more
The world is in constant flux, domestic and international flights play a role in the fast paced travel that has become a normality. This project was conducted with python script in Jupyter notebook, to map out the airports and routes on our planet. PYTHON SCRIPT: import pandas as pd ports = pd.read_csv(“pathtoports.csv”)print(ports)from shapely.geometryimport Pointimport geopandas … Read more
Aim: To predict the number of seating spaces based on various types of seating layout, number of corridors and dimensions of generative enclosed rectangular spaces such as an auditorium. Objectives: Dataset Design: To create Dataset for the required problem, a synthetic dataset is designed with the help of various bylaws supporting the problem. Data Analysis: … Read more
The project’s objective was to create a machine-learning model capable of classifying repurposed timber components within an assembly process as either structural or non-structural, using factors such as defect quantity, age, and exposure to weather conditions as input. Dataset Generation and Analysis The dataset was produced using Roboflow by utilizing scans of the timber elements … Read more
