American auto maker adopts Adasky thermal sensor

Israeli-based Adasky, developer of an advanced thermal sensor for the automotive industry and smart city applications, reported on a mass production agreement with a leading american auto maker. According to this agreement, the auto maker will incorporate Adasky’s Viper sensor in one of its future models, planned to be launched during 2023. The sensor, together with the software interpreting the signals will be incorporated in the advanced driver assistance system (ADAS) installed in the vehicle. This integration is the first milestone in a joint multi-annual development plan, which may lead for incorporating Viper into other models and additional applications in the future.  

Viper includes designated software for distance estimation, which enhances the Automatic Emergency Braking (AEB) applications and Forward Collision Warning (FCW) system. In order to promote the cooperation, Adasky will speed up the opening of a new production line near its headquarters in Yoqne’am, and also plan to launch a new branch in the U.S. 

Adasky’s Viper, is comprised of a high-performing thermal camera and state-of-the-art machine vision algorithms, together in one complete solution, that can be added to any autonomous vehicle to enable it to see better and analyze its surroundings. Viper passively collects FIR signals through detection of thermal energy radiated from objects and their body heat. AdaSky’s algorithms process the signals collected by the camera to provide accurate object detection and scene analysis, giving the vehicle the ability to precisely detect pedestrians at a few hundreds of meters, allowing more distance in which to react to driving decisions.

According to the company, Viper is the first high-resolution, thermal camera for autonomous vehicles with minimal size, weight and power consumption and no moving parts – at a price suited for mass market. Viper generates a new layer of information, originated from a different band of the electromagnetic spectrum, significantly increasing performance for classification, identification, and detection of objects and of vehicle surroundings, both near and far range.

AV, Covid-19 detection and Smart City

Based on its core technology, Adasky has released three product lines: thermal sensor for ADAS and AV systems, a customized system recently developed to monitor body temperature of passersby in crowded spaces, to detect persons potentially infected with Covid-19, and a thermal system for smart city applications.

Seoul Robotics to employ Cognata LiDAR Simulator

Above: Winter driving in difficult visibility conditions – in Cognata’s synthetic simulator

Cognata was chosen to provide a simulator of LiDAR sensors signals to Seoul Robotics, which develops software for analyzing data coming from the sensors, in order to extract information about the vehicle’s environment. The collaboration deepens Cognata’s grip on the ADAS systems market. Founded in 2016 by the CEO Danny Atsmon, the Rehovot-based (near Tel aviv) Cognata has developed a virtual platform used to train and test autonomous vehicles even before the vehicle hits the road for field tests.

The system is based on several layers: a static environment, a dynamic environment, sensors and cloud interface. The static environment is built from realistic imaging of entire cities, including streets, trees, road defects, etc. The dynamic layer mimics the behavior of other drivers on the road and the sensor layer mimics the information coming from each of the 40 different sensors found today in autonomous vehicles.

The chosen imaging software of Innoviz

Cognata is well acquainted with the field of LiDAR. In December 2019, it was selected by Innoviz to test Innoviz’s LiDAR technology. Cognata’s software can simulates how Innoviz’s LiDAR signals are reflected from different surfaces and materials, and how the sensors will function under different road conditions. A few days later it was also chosen by the Rehovot-based Foresight to test its QuadSight system, based on the use of two infrared cameras and two visible-light cameras, to produce a stereoscopic (three-dimensional) machine vision capability.

The agreement with Seoul Robotics is Cognata’s second major deal in Korea. In August 2020, it was selected by Hyundai MOBIS to supply a simulator for the development of ADAS systems and autonomous vehicles. Hyundai MOBIS is a Tier 1 supplier of the Korean automotive industry and manufactures auto parts for Hyundai, Kia and Genesis Motors.

Renesas and CEVA to Develop a SoC for ADAS

CEVA from Herzlya, Israel, announced that Renesas has licensed its DSP technology to develop an automotive System-on-Chip (SoC) for a new ADAS system of a  a very large automotive manufacturer in Japan. “This is a monumental agreement”, said Gideon Wertheizer, CEO of CEVA, during the company’s earnings call for Q3, 2020. In fact, this design win put both CEVA and Renesas in a direct competition with Intel’s Mobileye and NVIDIA Drive.

Naoki Yoshida, Vice President at Renesas noted regardin the agreement: “In active safety and self-driving applications, DSP processing is a key IP for processing and segmenting sensor data generated by sensors on vehicles.” This is exactly what CEVA is doing: It provides IPs of Digital Signal Processors, AI processors, wireless platforms and complementary software for sensor fusion, image enhancement, computer vision, voice input and artificial intelligence.

During the conference call, Gideon Wertheizer revealed more interesting details: “The agreement is based on a project. Our customer (Renesas Electronics) won with a very large automotive manufacturer in Japan, for an ADAS solution for new L2+ and L3 cars, which are projected to start production by 2025. It’s a mid-range car, that means volume versus the premium part.”

CEVA is not unfamiliar with the automotive industry: It has Automotive agreements with On Semiconductor, Yamaha, Toshiba, Rohm, AutoTalks and others to provide IP blocks for Wi-Fi, V2X, cameras and more, but becoming a main technology provider for an ADAS system is something else. This is a strategic platform – the playground of giants. And it turns out that the giants may be too big for their clients.

Wertheizer: “NVIDIA and Mobileye push their own closed and vertically integrated solutions. But automotive Tier one and OEMs are seeking an open high-performance technology where they can take advantage of their in-house excellence while not being locked into a certain vendor. Our powerful DSPs, AI technologies and our collaborate business model set a comprehensive foundation that enable OEMs to become supplier agnostic and translate their innovation into a competitive edge.”

Knorr invests additional $10 million in Rail Vision

The Israeli Rail Vision signed a $10 million funding agreement with the German company Knorr-Bremse. The investment will be made at a company value of about $50 million, post-money valuation. This is a follow-on investment, arriving after an investment of $10 million made by the German company in March 2019. After the two investments, it will hold 36.79% of Rail Vision’s shares. The holdings of Foresight, which founded Rail Vision, will amount to 19.34%.

In addition, the agreement provides Real Vision with an option to call for an additional $5 million. Trains have difficulties dealing with unexpected obstacles because the braking distance of a high-speed moving train can reach up to half a mile on average, and so there is a need for a system that detects obstacles from a very long distance. Rail Vision has developed an early warning system that warns the locomotive driver of a potential collision with obstacles in all weather and lighting conditions. This is done using dedicated cameras that detect objects from a distance of slightly more than one mile (1.2 miles).

The camera array (pictured above) includes a visible light camera and two thermal cameras with complementary wavelengths. These in turn feed the information into an image processing and machine learning algorithm, which fuses all the information into a unified image and identifies the objects located on the train track. The algorithm is designed to identify objects relevant to the train’s setting, such as humans, animals, cars, bridges, interchanges, signs, signal marks along the track intended for the locomotive driver, etc.

Knorr’s investment is a strategic investment related to one of its key areas of activity. Its systems division manufactures braking, steering and control systems for trains and commercial vehicles. For the past 100 years, the parent company has been supplying driver assistance and braking systems for vehicles and trains. In 2019, its sales totaled about 6.6 billion euros.