BEIJING – Analog Devices, Inc. (ADI) and Momenta, an autonomous driving technology company based in Beijing and Suzhou, announced on January 3 a strategic collaboration to advance the development of high-definition (HD) maps in autonomous vehicles. HD maps are a critical element of autonomous driving and must deliver accurate, real-time information to help safely guide the vehicle to its destination. As part of the collaboration, ADI’s inertial measurement units (IMUs) will be used to improve the mapping system setup and technology upgrades in Momenta’s L3 freeway ramp-to-ramp solution and L4 full autonomy driving solutions.
Under poor weather conditions, or when a GPS signal is lost, an IMU becomes essential in delivering high-precision mapping output. ADI’s IMUs will be used to enhance Momenta’s mapping solutions to more effectively meet the demanding accuracy requirements of HD maps. ADI’s IMUs exceed the value/performance ratio of higher cost alternative sensors based on fiber optic gyro or laser gyro technologies.
“Analog Devices is committed to the development of differentiated technologies to address high performance, high reliability and safety needs that are critical for autonomous driving,” said Chris Jacobs, vice president, Autonomous Transportation and Safety at Analog Devices. “ADI’s sensor solutions provide autonomous driving systems with reliable, high-fidelity navigational and perception information. By combining ADI’s leading IMU performance with Momenta’s extensive experience in deep learning algorithms, the collaboration between both companies is expected to deliver safe, reliable and implementable solutions for autonomous driving.”
In creating HD maps, crowdsourcing has become a mainstream development tool due to its low cost and timely updating features. This is particularly important, for example, in Asia where infrastructure updates are frequent. Momenta’s vision-based semantic HD maps are crowdsourced, highly accurate and frequently updated. They have the capability to provide map update and localization services. Momenta is also able to leverage modules mounted on taxis, trucks and buses at a large scale to create a crowdsourcing map for building the “brains” of autonomous vehicles.
“HD maps are crucially important to launching safe and reliable autonomous driving solutions,” said Momenta CEO Cao Xudong. “ADI has extensive experience in developing IMUs, and the company’s high-performance, high-precision sensor technologies can help Momenta build accurate, reliable and easy-to-update HD Maps. Momenta is excited to work together with Analog Devices to advance HD maps for autonomous vehicles.”
Momenta’s team is comprised of some of the world’s foremost experts on computer vision and deep learning, including one of the authors of Faster R-CNN and ResNet, the most influential deep learning network, and winners of various top Computer Vision Competitions (ImageNet 2015, MS COCO Challenge 2015, ImageNet 2017, etc.). Group members mainly come from top universities and well-known technology companies. Momenta is a leader in the autonomous driving software space with advanced technical competence and a strong commitment to innovation.
Analog Devices has more than 30 years of experience in MEMS inertial sensor design. ADI’s MEMS IMUs have been successfully applied in the avionics and smart agriculture sectors in which requirements are like those for autonomous driving. Analog Devices’ MEMS IMUs are comprehensively verified by market and capable of maintaining critical specifications such as bias, sensitivity, and cross-axis sensitivity under all conditions, including time variation, shock, vibration, and temperature conditions.
Momenta, established in 2016, recently secured over $200 million in total funding, at a valuation north of $1 billion. It is building the “brains” for autonomous vehicles. Its deep-learning based software in perception, HD semantic mapping, and data-driven path planning enables the realization of full autonomy.