Jerusalem Post
Separator
Business & Innovation
 

Mobileye, Delphi partner to jump-start fully automated driving

Car-maker Tesla has said that it will have level 4 technology available by 2018.

By NIV ELIS
Mobileye Logo (photo credit: Wikimedia Commons)
Mobileye Logo
(photo credit: Wikimedia Commons)
Israel's Mobileye on Tuesday announced a collaboration with British company Delphi that they say will help them to get fully driverless car technology on the road by 2019.
“The Mobileye and Delphi relationship started in 2002 with the implementation of what was one of the most advanced active safety systems of the time. Our long history together is key to the success of this ambitious endeavor,” said Professor Amnon Shashua, Mobileye Chairman and Chief Technology Officer.
The collaboration will focus on putting fully autonomous cars on the road by 2019. On the five-point scale of autonomy used in the industry, the companies say they will have level 4 technology, which is for all intents and purposes a vehicle that can perform all safety-critical functions throughout a trip. The only higher level, level 5, actually bans options for human driving.
Car-maker Tesla has said that it will have level 4 technology available by 2018.
The MObileye Delphi collaboration will aim to produce a“Central Sensing Localization and Planning” (CSLP) platform, which automakers can integrate into their cars.
Mobilieye will contribute it sensor signal processing, fusion, world view generation and Road Experience Management (REM™) system, which will be used for real time mapping and vehicle localization. Delphi will incorporate automated driving software algorithms from its Ottomatika acquisition, which include the Path and Motion Planning features, and Delphi’s Multi Domain Controller (MDC) with the full camera, radar and LiDAR suite.
In addition, teams from both companies will develop the next generation of sensor fusion technology as well as the next generation human-like “driving policy.”  This module combines Ottomatika’s driving behavior modeling with Mobileye’s deep reinforcement learning in order to yield driving capabilities necessary for negotiating with other human drivers and pedestrians in complex urban scenes.