Professor Georg Nemetschek, whose Nemetschek Group is composed of 13 brands that produce all types of construction technology, including Bluebeam, established the Georg Nemetschek Institute of Artificial Intelligence for the Built World (GNI) in 2020.
A partnership between the Nemetschek Innovation Foundation and the Technical University of Munich (TUM), GNI’s goal is to fund primary research in artificial intelligence (AI) related to the architecture, engineering, construction and owners/operators (AECO) industry. It announced its first call for proposals in November 2020.
Headquartered at the TUM Garching campus in Munich, the GNI has thus far provided funding for two main areas of research: research projects and support for individual researchers through post-doctoral programmes.
As the construction industry continues to embrace technology, initiatives like GNI are critical to the exploration and adoption of tools that have the potential to reshape how our world is built. While AI is already seeing some nascent uses in the industry, efforts like the GNI aim to bolster potential use cases through research that helps solidify the next generation of construction innovation.
Since GNI’s establishment, six innovative research projects were granted funding approval.
All six projects have formed and begun their first stages of work. The projects are truly exciting, as they have the potential to make field-advancing breakthroughs in the construction industry.
A summary of each project follows:
Project No. 1: Artificial Intelligence for the Automated Creation of Multi-Scale Digital Twins of the Built World (AI4TWINNING)
Digital twins are among the most anticipated technologies for the AECO industry due to their valuable cost saving and productivity enhancements. A digital twin isn’t simply a static copy of a building, but rather produces a real-time connection from the digital twin to the physical twin. The goal of the project isn’t to create a single monolithic digital twin, but instead a system of interlinked twins across different scales, providing the opportunity to seamlessly integrate city, district and building models as well as keep these up to date and consistent.
Learn more here.
Project No. 2: Artificial Intelligence for Smart Design and Testing of Cement and Concrete (AICC)
Cement and concrete are among the most commonly used materials in construction. Their usage has a tremendous impact on CO2 emissions, not only due to the large amount of yearly processed materials but also in terms of their high energy consumption during production. This project proposes machine learning-based methods to characterise the air pore system in concrete, which affects degradation and deterioration processes, mainly due to gas and moisture transport mechanisms within the solid phase. The objective of the project is to investigate different input/output variables from currently standardised methods to increase their accuracy and reliability.
Go inside the project here.
Project No. 3: Intelligent Infrastructure Maintenance with Deep Reinforcement Learning (INFRA.RELEARN)
Maintenance of civil infrastructure systems, including transportation, energy and water networks, comes at a major cost to society. Currently, planning of maintenance actions (which includes inspections) is based mainly on a combination of fixed rules and ad-hoc optimisation. This project aims to make a significant step towards AI-supported maintenance planning by setting up formal descriptions of infrastructure maintenance planning as a sequential decision problem and developing tailored DRL algorithms for identifying optimal maintenance strategies.
Discover more here.
Project No. 4: Deep Physics-Based Structural Health Monitoring (DeepMonitor)
Finding hidden structural defects is a crucial task in civil engineering. To date, however, the detection of such flaws from sensor signals is everything between time-consuming and impossible since the associated inverse problems are difficult to solve and often too ill-posed for practical applications in civil engineering.
To address this problem, a team of researchers will investigate the full range of available options in data science, ranging from data-driven supervised learning to physics-informed unsupervised learning. We will develop data-driven surrogate models to aid or fully replace the conventional full order approaches. The problem will also be addressed by learning the regularisation from data using neural networks. All methods will be evaluated first on benchmark examples and, in the final phase of the project, tested on structures of practical interest in civil engineering.
Here’s more of the project’s details.
Project No. 5: Bicycle Infrastructure & Network Design – a Human-Centric, Data-Driven Approach Using Spatio-Temporal Machine Learning (RADELN)
This project aims to develop a human-centric, data-driven approach for finding optimal bicycle infrastructure and network designs for metropolitan regions that help to shift trips from cars to bicycles.
The framework exploits all modal shift potentials by incorporating trips of longer distances and by differentiating the heterogeneous preferences of previously identified bicyclist types. To predict the impact of trip-specific bicycle infrastructure features on bicycle mode share as realistically as possible, the project’s researchers first reverse-engineer the actual realised route and mode choice based on real data. They also develop a data-driven model for bottleneck identification in existing bicycle networks.
See more here.
Project No. 6: Spatial AI for Cooperative Construction Robotics (SPAICR)
The introduction of cooperative mobile robots into construction processes holds enormous potential for architecture, engineering and construction. Their use promises an increase in efficiency and safety, a reduction in costs and errors and an increase in the accuracy that can be achieved, both for new buildings and for buildings in the existing context for renovation, repair and maintenance.
Construction sites, however, pose substantial challenges to robot deployment. They are inherently subject to change due to the construction process itself. Their environment is characterised as poorly structured and dynamic, as different actors, both humans and robots, are required to carry out various heterogeneous tasks.
Therefore, the use of mobile robots for cooperative building construction with an acceptable degree of accuracy, robustness and coordination hasn’t yet been demonstrated at scale. With this project, researchers aim to make progress towards real-world deployment of cooperative mobile construction robots by leveraging advanced spatial artificial intelligence (spatial AI) and spatial computing techniques from computer vision and robotics to create and maintain a digital twin for cooperative robotic processes.
Understand the project’s scope here.
To stay informed, visit the GNI Website to read more about the GNI, track the progress of the projects and to keep updated on the institute’s latest news.