MOUNTAIN VIEW, Calif. – Los Angeles startup Machina Labs is expanding its role within the space sector by working with satellite and hypersonic vehicle manufacturers.
Since Machina Labs was founded in 2019, the corporate has worked with NASA, the U.S. Air Force Research Laboratory and SpaceX to use robotics and artificial intelligence to space-related manufacturing processes.
Work with AFRL focused on developing robotic technology for manufacturing metal tooling for composite structures. For NASA, Machina Labs developed machine learning-based software for in-space manufacturing with autonomous articulated robots.
Now, Machina Labs is working with satellite manufacturers to assist them rapidly iterate designs.
“I can check out a design of a tank after which see if it really works,” Edward Mehr, Machina Labs CEO and co-founder, told at Satellite Innovation 2023. As well as, Machina Labs helps customers manufacture “things that were traditionally impossible,” he added.
For instance, doughnut-shaped toroidal propellant tanks, popular many years ago, have rarely been produced lately because they’re difficult and time-consuming to fabricate. Machina Labs’ process, called Roboforming, reduces the price and hurries up manufacturing of toroidal tanks, said Mehr, a former Relativity program manager and SpaceX software engineer.
Hypersonic Vehicles
For hypersonic vehicles, Machina Labs works with materials tough enough to face up to the warmth of reentry.
“With our technology, we are able to process a few of those materials like titanium or Inconel,” Mehr said.
AI and ML
Machina Labs machines, which use Nvidia chips, depend on machine learning to duplicate the work of people that incrementally deform metals or composites to create shapes.
“We want to duplicate what happens within the mind of a craftsman,” Mehr said.
To do this, the corporate built empirical models of how materials deform throughout the shaping process. Then, Machina Labs engineers determine the suitable set of processes.
“For each geometry, what are the correct process parameters and where does the robot have to go to get to the correct part?” Mehr asked.