Autonomy enables adaptive built environment

Autonomous operation, though posing certain challenges, seems to be heading in the direction of creating an environment that can adapt to environmental change over time and make decisions.


Designers' novel thinking about data, tools and methods is advancing to a point where it's possible to foresee an autonomously crafted built environment, one that mimics nature's ability to adapt to environmental change over time. This technology will be a vital way of dealing with the effects of an increasingly volatile climate.

When built environments' systems possess artificial intelligence (AI) fed by sensors a degree of autonomous decision making becomes possible. Autonomy is achieved by combining local learning from cameras and sensors, correlated to data and intelligence drawn from other AI-enabled assets.

Built environments that respond to a changing climate

This combination of advances means our built assets will be able to respond to their environment, autonomously reacting to changes in temperature, weather, human usage patterns, and other factors. In this convergence, designers and data scientists contribute their insights into the model, to ensure the variety of aspects taken into consideration and sheer volume of data is provided to shape the kinds of adapting preferred scenarios the artificial intelligence understands. These scenarios in turn train machines to rapidly produce the most sensitive and customized design solutions. A continuous feedback loop of data from the asset's environment and its users ensures success.

The comfort and energy performance benefits of this new approach are clear. A feedback loop is used by the Hong Kong-based start-up Ambi Climate, an Internet of Things (IoT) app that controls individual air conditioning units located in different rooms from a smart phone. Ambi Climate learns the inhabitant's preferences (times at work, temperatures enjoyed), applies this knowledge, and autonomously creates a tailored profile.

In the future, because homes, buildings and urban infrastructure will be connected and self-aware through smart components, design updates will occur autonomously. Inefficient, over-scheduled maintenance schemes will be replaced by machine-learning algorithms that are far more capable of knowing when preventative maintenance is needed, based on a growing bank of performance data from sensors. Resources and energy will all be saved.

Challenges of autonomy

Autonomy also represents a challenge to traditional human roles in the design of the built environment, because it can match and surpass human solutions at scale. This approach will be an improvement on today's often outdated, inappropriate designs, ones that often focus only on the requirements of society's top one per cent. The challenge for human designers will be how to embrace this new data paradigm of timely, appropriate and scalable design solutions.

This amount of autonomy also presents a challenge to the operators and regulators of the built environment. Current data privacy and confidentiality barriers will need to be overcome and new local connectivity systems for instant and robust connectivity (hubs) will need to be developed to provide instant yet democratic harmonization of the built environment.

Adoption a question of time?

The future points to an autonomously crafted built environment where assets can adapt intelligently to both users’ changing needs and the threats of a changing climate. Courtesy: AI Build.Fully autonomous operation might still be in the future, but a measure of it has already been achieved on projects like the 3D printed Daedalus Pavilion. On this project an algorithm autonomously adapted the material density required for the building. At the same time, a robot fabricator with cameras connected to AI capabilities was able to judge how far its landing position to deposit material was from the design position, and thus able to correct itself. An AI feedback loop allowed it to be quicker by being more daring - it learnt from its mistakes.

With the amount of investment currently being directed at machine learning and artificial intelligence I think it is more a question of when, not if, autonomous decision making like this will become possible.

Alvise Simondetti is member of the foresight, research and innovation team at Arup. This article originally appeared on Arup Thoughts. Arup is a CFE Media content partner.  

Product of the Year
Consulting-Specifying Engineer's Product of the Year (POY) contest is the premier award for new products in the HVAC, fire, electrical, and...
40 Under Forty: Get Recognized
Consulting-Specifying Engineer magazine is dedicated to encouraging and recognizing the most talented young individuals...
MEP Giants Program
The MEP Giants program lists the top mechanical, electrical, plumbing, and fire protection engineering firms in the United States.
November 2018
Emergency power requirements, salary survey results, lighting controls, fire pumps, healthcare facilities, and more
October 2018
Approaches to building engineering, 2018 Commissioning Giants, integrated project delivery, improving construction efficiency, an IPD primer, collaborative projects, NFPA 13 sprinkler systems.
September 2018
Power boiler control, Product of the Year, power generation,and integration and interoperability
Data Centers: Impacts of Climate and Cooling Technology
This course focuses on climate analysis, appropriateness of cooling system selection, and combining cooling systems.
Safety First: Arc Flash 101
This course will help identify and reveal electrical hazards and identify the solutions to implementing and maintaining a safe work environment.
Critical Power: Hospital Electrical Systems
This course explains how maintaining power and communication systems through emergency power-generation systems is critical.
Data Center Design
Data centers, data closets, edge and cloud computing, co-location facilities, and similar topics are among the fastest-changing in the industry.
click me