What is the potential for AI in construction?
A drone comes into view and hovers over your construction site. Moments later, the tablet you are holding lights up with several observations the drone has made: a labourer in section B is not wearing his helmet. Four of your diggers are underutilised. A dark patch of earth in section D suggests the area is becoming waterlogged. This kind of useful information is the promise of AI in construction.
Right now, no Artificial Intelligence (AI) technology is anywhere near offering this level of functionality. Nevertheless, there are numerous businesses currently trying to train AI systems that could make the construction industry work better.
What is the current state of AI in construction, and what is the potential of this new technology?
What is AI in construction?
Artificial Intelligence is a term used to describe how machines can be trained to imitate human cognitive functions – spotting patterns, learning from experience or understanding images. AI in construction involves using these technologies to make building sites safer, reduce waste and boost efficiency.
AI in construction is one of several major innovations in construction technology to have emerged in recent years. And while the technology is still relatively new and not yet widely used, it is expected to grow. Indeed, one forecast reckons the building AI market will reach USD $4.5 billion by 2026.
However, AI construction technologies face a handful of key obstacles to wider adoption:
- AI machines require large amounts of data to ‘train’ algorithms to spot patterns. For example, an AI system that is trained to see if labourers are wearing helmets would need to view millions of photos of people of different heights and at different distances to know when to sound the alarm. Without enough data, this kind of training isn’t possible.
- In the sectors which most successfully use AI (such as tech or financial services), the sheer scale of the companies means they have access to troves of data. However, most construction businesses are relatively small in size (at least compared to an Amazon or an HSBC) – so they do not hold anywhere near as much data to train their algorithms.
- There is a shortage of data scientists and they tend to command extremely high salaries. Only the biggest firms can attract top AI talent.
While these obstacles are important, the potential benefits of AI in construction are significant and make it an opportunity worth exploring. And, as the following examples demonstrate, there are several scenarios where construction AI is already in use – or could be in the coming years.
5 use cases for AI in construction
The following examples give some insight into the ways AI could be used in construction:
- Generative design
One of AI’s greatest strengths is its ability to explore many different variations of a model to find the best option – this is known as ‘generative design’. Generative design has already been used in manufacturing and companies like Alice Technologies are trying to bring it to the construction sector too.
Generative design could be useful for designers using BIM technology. AI would take a BIM model and explore tens of thousands of minor and major design changes to make a design safer, more stable, or simply cheaper and faster to build. For a human to explore all these possibilities would require months – an AI engineering programme could do so in hours.
- Predictive maintenance
AI is very effective at analysing historical data and using this to create likely forecasts of future events. While no technology has yet been designed to do this, the data that apps like PlanRadar collect could feasibly be used to train a machine to spot patterns in maintenance issues and locations.
Picture an AI system which assesses hundreds of thousands of damage or issue reports for different kinds of buildings over time, as well as information from IoT sensors. Eventually, it could plausibly begin to predict when certain surfaces, fittings or materials will become damaged or worn and alert maintenance teams to this.
- Project management
Construction projects frequently become delayed or experience cost overruns – even with skilled project managers overseeing them. However, academic research into AI forecasting algorithms has proven highly accurate in estimating cost overruns of projects.
Project managers could use AI-enhanced PPM software that identifies how likely their plans are to be delayed. This could help them revise projects and find ways to manage time and resources better.
AI construction robotics represent an exciting possibility for saving time and reducing risk. We’re still a long way from a world of autonomous robot bricklayers, yet firms like Built Robotics are already providing bulldozers and excavators which can be given defined tasks and work alone.
This kind of technology could save enormous sums of money and make projects progress faster. Imagine a project in a remote location that it is difficult to get workers to – remote diggers could work 24/7 clearing sites and get the work done much faster.
- AI-enhanced drones
Drones are already being used on construction sites to give builders new perspectives on projects and progress. And now, firms like Skycatch are training drones to ‘understand’ what they are seeing.
The applications here are enormous – from spotting dangerous activity to monitoring productivity levels, intelligent drones could help make sites safer, more efficient and productive.
The promise of AI in construction
How would your firm go about using Artificial Intelligence? In an article on the potential of AI in construction, analysts at McKinsey recommend builders identify high impact use cases that are relevant to their activities.
If, for instance, you hold extensive project management data, this would be the place to start. Or, if you have conducted thousands of maintenance reports, a building AI solution that crunches through that data would make sense.
At present, AI in construction remains a relatively little used technology. Nevertheless, with the correct execution, it could have a major influence on how your firm works.
PlanRadar was founded in 2013 and provides innovative mobile-first software solutions to the construction and real estate industries. Our app is available on all iOS, Android and Windows devices and has helped more than 7,000 customers in over 44 countries to digitise their workflow.