Mobileye Driving Experience Platform: Architecture, Abstractions, and APIs

As a follow up to Mobileye: Now. Next. Beyond., Mobileye CTO Prof. Shai Shalev-Shwartz presents Mobileye's Driving Experience Platform: Architecture, Abstractions, and APIs at CES 2024. Prof. Shalev-Shwartz showcased how the platform's APIs provide automakers with the tools to program the AI's functionality to the unique desired driver characteristics of each car model.
About Mobileye:
Mobileye is leading the mobility revolution with its autonomous-driving and driver-assist technologies, harnessing world-renowned expertise in computer vision, machine learning, mapping, and data analysis.
Our technology enables self-driving vehicles and mobility solutions, powers industry-leading advanced driver-assistance systems, and delivers valuable intelligence to optimize mobility infrastructure. Mobileye pioneered such groundbreaking technologies as True Redundancy™ sensing, REM™ crowdsourced mapping, and Responsibility Sensitive Safety (RSS) technologies that are driving the ADAS and AV fields towards the future of mobility.
Connect with Mobileye:
WEBSITE: www.mobileye.com/
LINKEDIN: / mobileye
TWITTER: / mobileye
FACEBOOK: / mobileye
INSTAGRAM: / mobileye

[@Scott-sm9nm]

Really an excellent presentation that gave an overview of the complication and what was taken into account for a more generic implementation.

[@andrewsteinhaus8267]

Over time, all of this differentiation will converge as users will have preferences. Most cars in the future will have some setting between sport and comfort. All OEMs will be offering these for users to setup the mode. For Robot taxis, it will likely baised to comfort mode

[@heyalchang]

There's a certain amount of (understandable) cope in this presentation. Differentiation is a secondary requirement to having a working solution that's competitive in the marketplace.

[@blanamaxima]

So Shai argues for OEMs to stop doing SW and tune the Mobileye SW 😂 I am sure they love it.

[@noisypl]

This makes no sense to me, to work on making the final solution different for different OEMs, before solving autonomy first. It is like at the stage of planning, making sure that each space elevator will be different and unique. This doesn't matter. Big LOL.

[@blanamaxima]

Automated features exist today, this applies to them as well , not only for robotaxi.