Mobileye for Autonomous Driving and ADAS

-

Automation is now in demand in every industry, especially in the car manufacturing sector. Mobileye is one of the popular suppliers of vision technology in the autonomous driving industry because of its advanced technology. Eventually acquired by Intel in 2017, it started as an expansion of Amnon Shashua‘s research on detecting vehicles through software algorithms and a camera.

Additionally, to supports Mobileye’s goal as an autonomous mobility provider, Intel also acquired Moovit in 2020. Now, its future goal is to support fully and semi-autonomous driving; its system-on-chip (SoC) currently supports Advances Driver Assistance Systems (ADAS) functions.

The Mobileye strategy

With its realistic, scalable go-to-market strategies, Mobileye has three pillars. The first is having a camera-centric configuration designed for a self-driving system. Here, the cameras allow the vehicles to drive safely while keeping them cost-effective.

Udelv-Mobilye-3
Udelv unveiled the first cab-less autonomous electric vehicle for multi-stop delivery at CES 2022. The company aims to have 50,000 units of the Transporter, driven by Mobileye, on public roads by 2028, with the first Transporters being commercially deployed in 2023. (Credit: Udelv)

The next pillar is the ADAS programs that undergo stringent safety testing. This ensures that the technological building blocks of autonomous vehicles are validated. Mobileye claims that more than 60 million vehicles on roads today consist of its ADAS programs.

Powerful computer vision tech and natural language models turn industry’s leading dataset into AV training gold mine.
Like all drivers, autonomous vehicles will face a “long tail” of problems in which a self-driving vehicle encounters something it has not seen or experienced before. An example would be a tractor covered in snow, as shown here. Mobileye’s state-of-the-art computer vision coupled with extremely capable natural language models allows for hard mining of Mobileye’s 200 petabytes of data, delivering thousands of results within seconds, even for extremely rare conditions and scenarios. (Image: Mobileye, an Intel Company)

Lastly, it has a Road Experience Management that acts as a high-definition map. Here, the HD map is updated through crowd-sourcing to ensure precise localization of the vehicles.

The goal

Mobileye utilizes crowdsourcing, deep learning, AI, and other new technology to support the pillars of its strategy. These technologies are essential to creating the software and hardware it provides to its over 25 OEM partners.

Image: Intel

One of Mobileye’s partners is the world’s third-largest public transportation operator based in Paris, the RATP Group. It works by having an autonomous robotaxis that the Galeries Lafayette Paris Haussmann employees use to have a ride. This is similar to the automated transportation called Next.

Mobileye has also collaborated with the leading international mobility services provider called Sixt SE which launched a self-driving robotaxi service in Germany. Unlike in Paris, which has a safety driver behind each robotaxi, the ones in Germany authorized self-driving taxis without safety drivers.

Udelv-Mobileye-1
Udelv unveiled the first cab-less autonomous electric vehicle for multi-stop delivery at CES 2022. The company aims to have 50,000 units of the Transporter, driven by Mobileye, on public roads by 2028, with the first Transporters being commercially deployed in 2023. (Credit: Udelv)

However, the safety of having autonomous vehicles on the road is still a threat to the full implementation of driverless cars. Mobileye has developed Responsibility-Sensitive Safety (RSS) to solve such issues, which has formal logic and rules on safety. Here, the vehicles are programmed to the following:

  • Have a safe distance between other cars
  • Avoid unsafe cut-ins
  • Adhere to the right of way rules
  • Be cautious in areas with limited visibility
  • Avoid crashes without causing another one

Mobileye aims to let everyone understand that automated vehicles can drive safely alongside people through these five safety rules.

Photo credit: The images used are owned by Intel and have been provided for press usage.
Source: Ingrid Lunden (TechCrunch)

Was this post helpful?

April Tsuan Matchok
April Tsuan Matchok
Tech Journalist at your service. Listening to the sounds of my keyboard keeps me alive. Give me any topic, and I'll make sure to write it for your audience's delight.
- Advertisment -
- Advertisment -
- Advertisment -
- Advertisment -
- Advertisment -
- Advertisment -