US-China Clean Energy Research Center issues $12.5M solicitation to address the energy-water nexus; $50M effort in all
Microbial Capacitive Desalination Cell could make treatment and reuse of oil and gas wastewater simpler, cheaper

Mobileye unveils Gen4 system-on-chip EyeQ4; visual processing for ADAS and automated driving; design win for 2018

Mobileye N.V., a designer and developer of camera-based Advanced Driver Assistance Systems (ADAS) for the automotive industry, introduced its 4th-generation system-on-chip, the EyeQ4. Leveraging the company’s more than 15 years of expertise in designing computer-vision specific cores, the EyeQ4 consists of 14 computing cores out of which 10 are specialized vector accelerators with extremely high utilization for visual processing and understanding.

The first design win for EyeQ4 in series production has been secured for a global premium European car manufacturer for production to start in early 2018. The EyeQ4 would be part of a scalable camera system starting from monocular processing for collision avoidance applications, in compliance with EU NCAP, US NHSTA and other regulatory requirements, up to trifocal camera configuration supporting high-end customer functions including semi-autonomous driving. The EyeQ4 would support fusion with radars and scanning-beam lasers in the high-end customer functions.

Supporting a camera centric approach for autonomous driving is essential as the camera provides the richest source of information at the lowest cost package. To reach affordable high-end functionality for autonomous driving requires a computing infrastructure capable of processing many cameras simultaneously while extracting from each camera high-level meaning such as location of multiple types of objects, lanes and drivable path information. The EyeQ4 continues a legacy that began in 2004 with EyeQ1 where we leveraged deep understanding of computer vision processing to come up with highly optimized architectures to support extremely intensive computations at automotive compliant power consumption of 2-3 Watts.

—Prof. Amnon Shashua, co-founder, CTO and Chairman of Mobileye

The EyeQ4 will feature four CPU cores with four hardware threads each, coupled with six cores of Mobileye’s innovative and well-proven Vector Microcode Processors (VMP) that has been running in the EyeQ2 and EyeQ3 generations. The EyeQ4 will also introduce novel accelerator types: two Multithreaded Processing Cluster (MPC) cores and two Programmable Macro Array (PMA) cores.

EyeQ4-High block diagram. Click to enlarge.

MPC is more versatile than a GPU or any other OpenCL accelerator, and with higher efficiency than any CPU, according to Mobileye. PMA features compute density nearing that of fixed-function hardware accelerators, and unachievable in the classic DSP architecture, without sacrificing programmability. All cores are fully programmable and support different types of algorithms.

Using the right core for the right task saves both computational time and energy. This is critical, Mobileye says, as the EyeQ4 is required to provide “super-computer” capabilities of more than 2.5 teraflops within a low-power (approximately 3W) automotive grade system-on-chip.

The enhanced computational capabilities give EyeQ4-based ADAS the ability to use advanced computer vision algorithms like Deep Layered Networks and Graphical Models while processing information from 8 cameras simultaneously at 36 frames per second.

The design was done according to the ISO-26262 standard and will provide a safety level of ASIL-B(D). The EyeQ4 will accept multiple camera inputs from a trifocal front-sensing camera configuration, surround-view-systems of four wide field of view cameras, a long range rear-facing camera and information from multiple radars and scanning beam lasers scanners. Taken together, the EyeQ4 will be processing a safety cocoon around the vehicle—essential for autonomous driving.

In addition to the EyeQ4 high capability version, at an ASP of approximately three times that of an ADAS functionality chip, Mobileye also plans the launch of the EyeQ4 “medium” variant within the same timeframe. The EyeQ4M will include a subset of EyeQ4’s computational cores, enabling a select group of functions. In producing a family of EyeQ4 processors Mobileye will ensure that car makers can deliver a scalable hardware solution with full code and pin compatibility, thereby reducing complete validation costs and ensuring that multiple feature bundles can be offered to the end customer at the best possible price.

Engineering samples of EyeQ4 are expected to be available by the fourth quarter of 2015. First test hardware with the full suite of applications including active safety suite of customer functions, environmental modeling (for each of the 8 cameras), path planning for hands-free driving and fusion with sensors, is expected to be available in the second quarter of 2016. Series production is supported for early 2018 start of production.

Mobileye’s EyeQ chip and algorithms have been integrated into new car models since 2007. The first million-chip celebration took place in the middle of 2012. Another 1.3 million chips were added in 2013, and as of March 2014, the chip was estimated to be integrated in approximately 3.3 million vehicles. Mobileye products are or will be integrated into car models from 23 global automakers including BMW, Ford, General Motors, Nissan and Volvo. The products are also available in the aftermarket.



A very recent American study found that autonomous driving could reduce ground vehicle acccidents and fatalities by 90% and reduce damage direct costs by over $190 B/year in USA.

Indirect health care and lost of production savings would be more important, specially if electrified vehicles were used.

The total potential gains are so important that it will drive wide spread application by 2030-2035.

The comments to this entry are closed.