Virtual Reality, Artificial Intelligence and 3D Printing Team Up for the Production of the World’s First AI-Engineered Car

IMTS

Share this Article

logo (18)By this point, almost everyone knows that self-driving cars aren’t far from being commonplace, as multiple auto manufacturers have designed and even begun testing vehicles equipped with intelligent driving technology. The advent of smart cars will be one of the biggest upheavals in transportation since the invention of the original car itself, but it’s not the only technology creeping up to redefine the automotive industry. A Los Angeles startup is working to change not the way we drive cars, but the way we manufacture them – and their work could have just as much of an impact as self-driving cars.

autocarHack Rod was formed by a couple of stunt drivers/racers along with the former Vice President of Creative at Mattel‘s Wheels Division. Their goal? To produce the world’s first car designed in a virtual environment and engineered with artificial intelligence – essentially, a self-designing car. The implications for the automotive manufacturing industry are thrilling or terrifying, depending on how you look at it (or who you work for). Hack Rod’s theory is that with completely virtual and AI-based manufacturing, automotive design and and production could be placed into the hands of individuals (even those without many design skills) and small businesses.

To bring their idea to reality, Hack Rod partnered with several leading companies in software, manufacturing and distribution, including Autodesk, which has played a major role in the design and development of the car. In particular, their Dreamcatcher generative design system, an experimental platform that allows the software itself to have a “hand” in designing, has formed the basis of the car’s design.

Hack Rod started by scanning a prefabricated chassis and uploading it to the cloud. They then took the existing car – a very basic sportscar design – for several test drives, pushing it to the limits of its capabilities while sensors attached to the car and driver measured force and stress. The data gathered by the sensors was then fed into Dreamcatcher, which used incorporated NVIDIA graphics processing units (GPUs) to quickly analyze the data and generate several new design suggestions that would improve upon or resolve any weak points it detected in the original car, as you can see in the video below:

Hack Rod is revealing and discussing the virtual prototypes they created with Autodesk VRED, based on Dreamcatcher’s design recommendations, at SIGGRAPH 2016, which is running July 24-28. The discussion will be part of a collaborative design review powered by Silverdraft Demon VR.

“The way your world opens up from a design perspective in photoreal VR is just magic,” said Mouse McCoy, founder and creative director of Hack Rod. “The speed at which you can make decisions about your final product is unrivaled and when you start to add in AI/machine learning, it’s like you have 1,000 engineers working for you solving problems in a fraction of the time that it used to take. It’s the democratization of manufacturing.”

hackrodOnce a design is chosen from Dreamcatcher’s recommendations, it goes to the next step in the Autodesk-powered process: Design Graph, which offers part suggestions to match the design criteria. The design itself is fine-tuned in Fusion 360, then imported into Flow Analysis for virtual aerodynamic testing.

Generative design, which programs like Dreamcatcher make possible, produces some complex results which would have, not long ago, been impossible to actually manufacture. Nothing is impossible (well, almost nothing) with 3D printing, however, and during November’s Autodesk University conference, Hack Rod, Autodesk and NVIDIA will be showing off some of the complicated metal 3D printed parts that Dreamcatcher designed. In March, they plan to have a full car ready to exhibit at SXSW.

“The future of making things looks really cool,” said McCoy. “When you combine collaborative photo-real 3D VR design with AI-based generative design, machine learning and advanced manufacturing, it creates a supply chain of the future that puts the power of large organizations in the hands of the Everyman.”

When you first arrive at Hack Rod’s website, you’re presented with the question “Could 3 kids in a dorm room start a car company?” Hack Rod’s answer is an emphatic yes – thanks to the availability of makerspaces, 3D printing, and generative software. Learn more about Dreamcatcher below, and discuss this project further in the Self-Designing Car forum over at 3DPB.com.

[Source: NVIDIA]

 

Share this Article


Recent News

Liquid Metal 3D Printing Sector Emerges with Fluent Metal’s $5.5M Investment

3DPOD Episode 191: Amy Alexander, 3D Printing at the Mayo Clinic



Categories

3D Design

3D Printed Art

3D Printed Food

3D Printed Guns


You May Also Like

3DPOD Episode 190: Generative Design for 3D Printing with Novineer CEO Ali Tamijani

Ali Tamijani, a professor in the Department of Aerospace Engineering at Embry-Riddle Aeronautical University, has an extensive background in composites, tool pathing, and the development of functional 3D printed parts,...

Featured

3DPOD Episode 189: AMUG President Shannon VanDeren

Shannon VanDeren is a consultant in the 3D printing industry, focusing on implementation and integration for her company, Layered Manufacturing and Consulting. For nearly ten years, she has been involved...

3DPOD Episode 188: Clare Difazio of E3D – Growing the Industry, and Growing With the Industry

Clare DiFazio’s journey into the 3D printing industry was serendipitous, yet her involvement at critical moments has significantly influenced the sector. Her position as Head of Marketing & Product Strategy...

Featured

Printing Money Episode 15: 3D Printing Markets & Deals, with AM Research and AMPOWER

Printing Money returns with Episode 15! This month, NewCap Partners‘ Danny Piper is joined by Scott Dunham, Executive Vice President of Research at Additive Manufacturing (AM) Research, and Matthias Schmidt-Lehr,...