Dr. Rob's new AI mannequin guarantees to scale back plane improvement time from months to days

The British startup PhysicsX, founded by former Formula 1 engineering expert Robin “Dr. Rob” Tuluie, has revealed an AI tool that could cut the time it takes to develop a new aircraft from months to just a few days.

Synchronized LGM Aero, that software creates new designs for aircraft. Using advanced, trained algorithms The model includes more than 25 million geometries predicts lift, drag, stability, structural stress and other attributes for each shape. The design is then adapted to the desired functions of your aircraft.

PhysicsX said the AI ​​is that first Large Geometry Model (LGM) for aerospace engineering. A barebones version of the model, Ai.rplane, is also available for free.

“This is a first step in transforming the way engineering is practiced in advanced industries [like automotive, aerospace, and manufacturing]said Tuluie, founder and chairwoman of PhysicsX.

“Over time, we will add new features to LGM-Aero and Ai.rplane that allow users to select powertrains, add controls and other content to achieve mature designs in days rather than months or years,” he said.

What day is today? It's CYBER MONDAY!

TNW Conference is offering an exclusive 30% discount on their startup and scaleup programs this week only. This is the best deal you'll get before prices change in January.

Tuluie wasn't always an entrepreneur. In the first half of his life he worked as an astrophysicist alongside Nobel Prize winners. Then, at 41, he entered the F1 scene where He created designs that helped Renault and later Mercedes win four Formula 1 world championships together.

In 2019, Tuluie co-founded PhysicsX with her Jacomo Corbo, a Harvard-educated engineer who led McKinsey's AI lab. Together, the duo has assembled a 50-person team of some of the world's best minds in data science, AI and machine learning.

PhysicsX based in London, emerged from stealth in November 2023 with financing of 30 million euros. The company is on a mission to reimagine simulation for science and engineering using AI in industries such as automotive, aerospace and manufacturing.

PhysicsX says it wants to help engineers better anticipate design bottlenecks, such as the resistance of a new airplane or car design, before they start building a physical prototype – saving time and money. Its software acts like a supercharged wind tunnel for ideas.

“Just as large language models understand text, Ai.rplane has extensive knowledge of the shapes and structures important to aerospace engineering,” Corbo explained.

“The technology can optimize multiple types of physics in seconds, many orders of magnitude faster than numerical simulations and with the same accuracy.”

Corbo described LGM-Aero as “an important step towards the development of fundamental physical models”. These are AI systems designed to simulate and solve complex physics problems by learning patterns from data and physical laws.

The application of AI to complex scientific problems is becoming increasingly important. In 2020, Google Deepmind's Alphafold model became known a mystery solved in protein biology that had puzzled scientists for centuries. The discovery has advanced research in drug development, molecular biology and bioengineering.

Other companies, like Dutch scaleup VSParticle, use algorithms to speed up the discovery and synthesis of potential data groundbreaking materials.

While the applications of AI in science may vary from discipline to discipline, the benefits are all the same: Artificial intelligence can advance scientific discoveries by analyzing data, simulating complex systems, and uncovering insights faster than humans ever could.

So AI isn't just about asking ChatGPT what to have for dinner? No, dear reader, it's actually a pretty big deal.