Mobileye and Nissan goes to car-generated maps

25 April, 2017

Nissan Motor joins BMW and Vollkswagen to Mobileye's initiative aimed to the automatic creation of precision maps, specially designed for autonomous driving

Share via Whatsapp

The car generated mapping is entering a new phase with the cooperation between Jerusalem-based Mobileye and the Korean car manufacturer Nissan Motor. Mobileye announced today an agreement with Nissan to generate anonymized, crowd-sourced data to create next-generation precision maps. The maps will be used as a source of localization, foresight, and redundancy in order to enable safe, robust autonomous vehicles in the future.

The agreement is the next step after successful proof-of-concept work in 2016 that culminated in Mobileye’s REM (Road Experience Management) mapping technology, being utilized in Nissan’s autonomous vehicle demonstration in London (photo above). It also follows another cooperation between the two companies:  The ProPILOT, Nissan’s system that utilizes significant Mobileye technology to enable single-lane highway driving with autonomous control of steering, acceleration, and braking.

Mobileye’s Road Experience Management technology

The agreement furthers an inclusive approach, as data from multiple automakers can be merged to create a robust and rapidly-updated maps. Professor Amnon Shashua, Chairman and CEO of Mobileye said: “We now have significant commitments from multiple global automakers to generate and share data from camera-equipped ADAS vehicles, and then utilize the resulting Global RoadBook as a critical input within autonomous vehicle systems.”

The two partners will utilize Mobileye’s Road Experience Management (REM) data generation technology. REM is a mapping engine comprised of three layers: harvesting agents (any camera-equipped vehicle), map cloud server and map-consuming agents (autonomous vehicle). The harvester collect and transmit data about the driving path’s geometry and stationary landmarks around it. Mobileye’s real-time geometrical and semantic analysis, implemented in the harvesting agent compress the information to less than 10KB/km on average to be sent to the cloud.

The cloud server aggregates and reconciles the continuous stream of data into a highly accurate map, called Roadbook. The last link in the mapping chain is localization: in order for any map to be used by an autonomous vehicle, the vehicle must be able to localize itself within it. Mobileye software running within the map-consuming agent (the autonomous vehicle) automatically localizes the vehicle within the Roadbook by real-time detection of all landmarks stored in it. REM is designed to allow different OEMs to take part in the construction of the Roadbook.

Intel, BMW and Vollkswagen

Earlier this year BMW Group announced it will embed Mobileye’s REM data generation technology in newly developed BMW Group models, entering the market in 2018. It joined Vollkswagen following its decision to turn its fleet into map data gathering machines base on Mobileye’s REM technology.

Mobileye is a global leader in the development of computer vision and machine learning, data analysis, localization and mapping for Advanced Driver Assistance Systems (ADAS) and autonomous driving. Today, 27 Global automakers rely on Mobileye technology to make their vehicles safer over 15 million Vehicles worldwide, while 13 automakers are working with Mobileye to enable autonomous driving. In mid March 2017, Intel announced an agreement to buy Mobileye for $15.3 billion.

Posted in: Automotive , Autonomous Car , News