German manufacturer of BMW vehicles plans to start manufacturing transmissions for electric vehicles in a large factory in Regensburg, Bavaria, later in 2021. Long before the release of new production of the entire manufacturing process, the entire manufacturing process will be carried out with real details amazing within a virtual version of the factory.
The simulation allows managers to plan the production process in more detail than was previously possible, says Markus Grüeneisl, who leads BMW’s production strategy. “We now have a perfect digital twin of our real-time production,” he says.
The simulation is part of BMW’s plan to use more artificial intelligence in manufacturing. Grüeneisl states that machine learning algorithms can simulate robots performing complex maneuvers to find the most efficient process. Over time, BMW wants to use simulation so that robots learn to perform increasingly complex tasks.
BMW used a software platform called Omniverse, developed by chip maker Nvidia, to recreate the Regensburg production line. Last year, BMW said it was using an Nvidia AI platform called Isaac to train robots for certain new tasks.
“In the future, I’m pretty sure we can just put a new robot in this facility and say,‘ Okay, talk to the other robots and find the best way to produce this body, ’” Grüeneisl says.
Manufacturers have used computer simulations to perfect their assembly lines for some time. But Omniverse allows you to simulate the whole production process with photorealistic details and physical properties such as gravity and different materials. It is possible to establish the production process from start to finish and see how changes in one part can have side effects in another. It is easier to build a more complex virtual environment because different 3D models can be imported into the system. Omniverse uses an open file standard that supports numerous computer-aided design packages.
The software will also simulate avatars of human workers grabbing parts and tools and assembling components to find the best procedure and minimize ergonomic problems. Grüeneisl can also make it possible for fewer workers to complete a specific job.
“We do AI simulations of how people move around the factory,” says Richard Kerris, CEO of Omniverse at Nvidia. He calls the project “one of the most complex simulations ever made.”
There is a growing interest in using AI to control robots and other industrial machines. Encouraged by recent advances in AI, some startups focus on getting robots to learn in simulations how to perform extremely difficult tasks such as catching irregular objects, technology that could eventually help automate a lot of e-commerce and logistics work. An artificial intelligence approach called reinforcement learning is often used, which involves experimenting and learning an algorithm, based on positive feedback, how to achieve a specific goal.
“This is definitely the way to go,” says Ding Zhao, a professor at Carnegie Mellon University who focuses on digital and AI simulations. Zhao says simulations are crucial to using AI for industrial applications, in part because it is impossible to run machines for millions of cycles to collect training data. In addition, he says, it is important for machine learning models to learn by experiencing unsafe situations, such as colliding two robots, which cannot be done with real hardware. “Machine learning is hungry for data and collecting it in the real world is expensive and risky,” he says.
Willy Shih, a professor at Harvard Business School who specializes in manufacturing technology, says the sophistication of the simulation has been steadily increasing, and claims that the simulation primarily saves time and money by avoiding future manufacturing problems.
Shih says there are a lot of bubbles around AI for manufacturing, but adds, “There are a lot of applications” for the technology as well.
Nvidia CEO Jensen Huang spoke about BMW’s use of Omniverse during its keynote address at the company’s annual GTC conference, held virtually Monday. Nvidia initially manufactured graphics chips for gaming, but expanded its focus when these chips proved to be skilled at training AI programs. Since then, the company has jumped into several other industries where AI is important, including medical and automotive imaging.
Bigger cable stories
- 📩 The latest in technology, science and more: get our newsletters.
- A boy, his brain and a medical controversy of decades
- Why stay awake even when you know you shouldn’t?
- After a remote year, the shadowy workforce of technology barely stands still
- Bill Gates is optimistic about climate, capitalism and even politics
- How to stop misinformation before it is shared
- 👁️ Explore AI like never before with our new database
- 🎮 WIRED Games: Get the latest tips, reviews and more
- 💻 Update your working game with laptops, keyboards, typing alternatives, and headphones that eliminate your favorite noise from our Gear computer.