Hanover, Germany – Continental has acquired a minority stake in Recogni, a German-US start-up working on a new chip architecture for AI-based object-recognition in real time.
The San Jose, California-based tech firm’s chips are intended for use in Continental’s vehicle computers, for example to perform rapid processing of sensor data for automated and autonomous driving.
As an investor – percentage stake not disclosed – the Hanover-based group is contributing financial support and expertise in the field of AI, vehicle sensors and advanced driver assistance systems to Recogn’s chip design work.
Continental said volume production featuring the new chip application could begin as early as 2026: the new processors serving as “ultra-economical data boosters: with minimal energy consumption.”
The development, it added, will enable vehicle computers to gain a rapid sense of the vehicle’s immediate surroundings, thus creating the basis for automated and autonomous driving.
“Without faster chips, there will be no networking, no automation and no autonomous driving,” said Frank Petznick, head of Continental’s ‘advanced driver assistance systems’ unit.
Strategic partnerships with large chip makers such as NVIDIA and the investment in Recogni, are a step toward meeting the future requirements of powerful, high-performance vehicle computers, added Petznick.
“Continental’s support is a strong endorsement of Recogni’s approach to solving the most difficult challenges in autonomous driving,” said Recogni CEO R K Anand.
The goal, he said, is to build “the world’s highest performing AI inference system at the lowest energy consumption, by developing cutting-edge ASICs for state-of-the-art inference algorithms.”
Whereas just a few megabytes of sensor data per second had to be analysed a couple of years ago, that figure is set to increase to several gigabytes per second in the coming years, noted Continental.
Such capabilities, it added, will be needed in autonomous vehicles, which are forecast to use more than 20 high-resolution vehicle-surroundings sensorsm such as radar, camera and lidar simultaneously.