Get Rolling: Automotive AI and ADAS Innovations

By Ken Briodagh

Senior Technology Editor

Embedded Computing Design

January 23, 2024


Get Rolling: Automotive AI and ADAS Innovations

Embedded for Automotive is the sleeping giant industry right now. The fact that so much of CES was about automotive technology and supporting applications would be indication enough, but we’ve also seen huge partnership announcements, new investments from the biggest RISC-V players, and tech innovations from major embedded companies like STMicroelectronics and Microchip.

This article won’t begin to cover what’s coming for Embedded Automotive this year, or all the things we saw at CES, especially when paired with AI enhancements, but we wanted to give you a taste.

Infineon and Aurora Labs Rock Predictive Maintenance

Infineon Technologies and Aurora Labs unveiled a new set of AI-based solutions designed to improve long-term reliability and safety of critical automotive components, the partners said. These systems include steering, braking and airbags. They have paired Aurora Labs’ Line-of-Code Intelligence (LOCI) AI with Infineon’s 32-bit TriCore AURIX TC4x family of microcontrollers (MCUs) to improve the longevity of vehicles, according to the release.

“The solution supports real-time monitoring and response to software failures at the MCU- and ECU-level according to WP29 requirements. By protecting applications and over the air (OTA) updates, the joint solution helps prevent malicious attacks and hardware safety failure,” said Zohar Fox, CEO and Co-founder of Aurora Labs. “Our solution streamlines OEM software development at lines-of-code and hardware peripheral resolution to enable them to develop safer systems in accordance with ASIL-D.”

Thomas Schneid, Senior Director Software, Partner and Ecosystem Management of Infineon, added, “With the combination of Infineon’s proven AURIX MCUs, along with Aurora Labs’ software to prevent silent data corruption and software misbehavior in chipsets, our new solution gives car manufacturers and drivers an extended level of safety confidence for critical automotive applications such as steering, braking and airbags.”

The MCUs reportedly are designed for next-generation eMobility, advanced driver assistance (ADAS), automotive E/E architectures, and affordable artificial intelligence (AI) applications. The solution is already available here.

Luna Systems Layers AI into Electric Motorcycles

Luna Systems was showing its Advanced Rider Assistance Systems (ARAS) solutions, loaded with computer vision, set to be deployed on the Snapdragon Digital Chassis solution for 2-wheelers and other vehicles. The system offers in-ride warnings across a range of high-risk scenarios, post-ride safety analysis, and coaching technology to improve rider behavior and skill.

Reportedly, the ARAS solution is based on the QWM2290 and QWS2290 platforms from Qualcomm and will enable OEMs to offer:

  • Forward Collision Warning
  • Headway Monitoring Warning
  • Pedestrian Detection
  • Lane Type Detection (which can be used for Lane Departure Warning). 
  • Traffic Light Detection

“Safety is not just about increasing situational awareness in risk scenarios, but also giving riders the kind of education and self-awareness they need to improve their safety skills,” said Andrew Fleury, CEO and Co-Founder, Luna Systems. “Many accidents can be avoided through simple education, and it’s our goal that our technology will help with this.”

Automotive Grade Linux Sets a Standard for OS

Automotive Grade Linux (AGL) has set its sights on Android, and according to Dan Cauchy, General Manager of Automotive and Executive Director of the Automotive Grade Linux (AGL) Collaborative Project at The Linux Foundation, the AGL OS is already winning. The advantage for automotive OEMs to deploy a Linux OS rather than an Android one is the customization and platform ownership that comes with being open source. What’s more, the development process is shortened by the AGL team.

“We’ve already done 60-80 percent of the development process for them,” he said. “The biggest struggle with embedded [for automotive] is that it’s hard. So, we provide a full Yocto [Linux]-based board.”

AGL has just announced a new UI, that includes “Flutter,” an open-source UI and app framework development toolkit built by Google, and customized for automotive by Toyota, then contributed back to AGL for use by anyone.

There’s LOTS more to tell you about, and we’ll be doing so all year, so keep an eye out for all the Software Defined Vehicle (SDV) goodness coming your way.  

Ken Briodagh is a writer and editor with two decades of experience under his belt. He is in love with technology and if he had his druthers, he would beta test everything from shoe phones to flying cars. In previous lives, he’s been a short order cook, telemarketer, medical supply technician, mover of the bodies at a funeral home, pirate, poet, partial alliterist, parent, partner and pretender to various thrones. Most of his exploits are either exaggerated or blatantly false.

More from Ken