Technology from Bedrock Robotics, in partnership with Sundt Construction, is being used to automate the massive removal of earth from excavators for site preparation of a 130-acre manufacturing facility in the southwestern United States that supports the domestic energy market.
Bedrock’s autonomous systems have moved more than 65,000 cubic meters of soil and rock by loading human-powered articulated rock trucks with the same workflow used in manual operations: trucks stopping to be loaded by an excavator scooping up scoops from a dismantled pile. The integration demonstrates the commercial viability of autonomous construction, Bedrock says. The technology is now installed in various models of excavators ranging from 20 to 80 tonne machines on the big job, adapting their systems from compact units to large-scale earthworks.
“They’re one tool in a much bigger toolbox that we have on this,” said Dan Green, Sundt’s senior project manager, noting that about 700,000 cubic yards of rock and soil are planned to be moved on the project. “That’s the scale of what we’re moving,” he said. Bedrock excavators “are about 10% of our utilization.”
Bedrock, a San Francisco-based autonomous equipment startup, has Austin Bridge & Road, Maverick Constructors and Haydon Cos. along with previous partners Champion Site Prep, Zachry Construction, Haydon Companies and Sundt as partners who are testing their additional kits for stand-alone teams.
Moving that amount of earth “is something that would have to be done by a team of people, super routine, in the sense that it’s a very similar task 12 hours a day, seven days a week,” says Eric Cylwik, Sundt’s chief innovation officer. “It’s a very intense schedule. By being able to take something that is not a desirable, repetitive activity for someone off their to-do list, it frees up our operators to do the more difficult and critical associated work.”
Large, remote jobs that require skilled operators where such workers are not readily available come at a premium and have become a fertile test bed for autonomous teams. Bechtel has used Built Robotics excavators for trenching on solar projects in Texas and has used autonomous balls on other projects. Moog’s autonomous skidsteers were used to deliver solar panels, just in time for installation at a solar project in Western New York. Green said adding artificial intelligence and machine learning to the process has helped Sundt operators bring their autonomous co-workers on board more quickly.
“We’ve taken very experienced operators and they’re teaching how a human does this task using multiple operators,” explains Green. “It’s getting to feel the difference between them, because each operator is different in how they do it [their job]Using the efficiency of AI, “you’re taking that consolidated knowledge from multiple operators and turning it into one operator, and that’s very powerful,” he adds.
Bedrock was founded by engineers and executives from commercial autonomous vehicle startup Waymo. CEO and co-founder Boris Sofman said that developing Bedrock’s technology on active job sites with real projects and contractors allows the company to scale quickly in the same way Waymo did, solving orientation, topography and other challenges that map-based navigation didn’t initially understand.
“We’ve been very pleased with the amount of a fairly significant group, a portion of the industry that is accepting the possibility of this,” Sofman said. He added that facing challenges, including labor availability, that limit project capacity for contractors, while ensuring Bedrock uses an intuitive approach that doesn’t harm partners and customers, has allowed the startup to grow quickly. He also noted the security protections offered by autonomous geofencing teams that prevent on-site interactions with humans at sites.
“Just the availability of labor is a big issue, so a lot of jobs just aren’t getting done,” Sofman said, noting “a ripple effect on a lot of construction companies.”
With more operators retiring, younger workers may lack skills, leaving “safety as one of the biggest issues and fears in the industry,” he said. “You have the ability to compress schedules and move jobs faster, which is very obviously beneficial.”
