Check out all the on-demand sessions from the Intelligent Security Summit here.

A startup called Doxel launched today with the promise that its robots and artificial intelligence hold the key to solving late and over-budget construction projects.

The company uses robots to autonomously capture 3D scans of construction sites and then feeds that data into a deep neural network that classifies how far along different sub-projects are. If things seem out of whack, the management team can step in to deal with small problems before they become major issues.

It’s a far cry from the current state of construction. Doxel CEO Saurabh Ladha told VentureBeat in an interview that most construction managers only hear about problems four to eight weeks after they’ve arisen, when they’ve already wreaked havoc on the timetable for a larger project.

Kaiser used Doxel on a recent construction project in San Diego and was able to bring it in 11 percent under budget because of the software’s feedback. The company and its contractors were able to increase labor productivity by 38 percent.


Intelligent Security Summit On-Demand

Learn the critical role of AI & ML in cybersecurity and industry specific case studies. Watch on-demand sessions today.

Watch Here

Since construction sites are usually poorly lit, the machine learning system at work in Doxel’s product has been trained to recognize different features of a construction project, like ductwork and wiring conduits, using 3D scan data. Ladha said the point clouds generated by the company’s sensors are accurate to around 2 millimeters, providing high-precision information about how a project is going.

Construction timetables are personal for Ladha. He grew up in India, where his father worked in manufacturing. When he was five years old, his father decided to open his own business, which first required building a factory. Ladha said that his family nearly lost their house because of construction overruns.

The story turned out well. The family was able to keep their house, and working at his father’s factory taught Ladha the importance of feedback systems for manufacturing projects, something that he drew on to create this company.

To help fuel its ambitions, Doxel raised a $4.5 million investment led by Andreessen Horowitz, with participation from Alchemist Accelerator, Pear Ventures, SV Angel, and Steelhead Ventures. Ladha said that Doxel plans to use the cash to hire more engineers, as well also building out its sales, marketing, and customer success teams.

Don’t expect Doxel to be put to use in a home renovation near you, though. The company is currently only looking for jobs with a contract value of more than $20 million.

VentureBeat's mission is to be a digital town square for technical decision-makers to gain knowledge about transformative enterprise technology and transact. Discover our Briefings.