FABU Technology Develops A Full-stack Artificial Intelligence Algorithms for Autonomous Driving

Artificial Intelligence News

FABU_Technology-Develops-A-Full-stack-Artificial-Intelligence-Algorithms-for-Autonomous-Driving FABU Technology Develops A Full-stack Artificial Intelligence Algorithms for Autonomous DrivingThe leader in research and development of autonomous technology, Artificial Intelligence chips, and intelligent scheduling systems, FABU Technology Ltd. has brought a comprehensive approach to the challenge of developing Advanced Driver Assistance Systems (ADAS) and Autonomous Driving solutions. The company is committed to developing a full-stack of algorithm and software infrastructure and a new System-On-Chip (SoC) platform tailored for autonomous vehicles.

With deep expertise in Machine Learning, computer vision, robotics, automobile engineering, and large-scale integrated circuit design, FABU believes that tackling the challenges of Autonomous Driving requires not only commanding Machine Learning algorithms but also more efficient and cost-effective hardware performance. With research and development centers in both the United States and China, FABU has deployed its self-driving technologies on the road. Established in the year 2017, this automotive leading company plans to deploy their Autonomous Driving solutions in vans and heavy trucks, after the five light trucks outfitted with a FABU Level 4 autonomous driving solution. FABU’s new System-On-Chip (SoC) design customized for self-driving. Where the company’s Founder and CEO, Xiaofei He stated that generic, off-the-shelf chips may lack the essential performance, or have need of more power, or are not qualified for automotive safety standards. Hence, to best optimize for performance, power, and cost, FABU designs its own dedicated, intelligent SoCs for the ultimate integrated solution for in-vehicle intelligence. The company has built a new architecture made-to-order for deep learning and Autonomous Driving algorithms, named the Massive, Parallel and Volumetric (MPV) architecture, to meet the specialized data processing requirements.

FABU’s Phoenix series of automotive safety integrity level AI chips comprise the full algorithmic requirements of self-driving by addressing three stages of Autonomous Driving data processing- sensor input and perception, sensor data integration and fusion, and smart automated decision making. The key factor for the Phoenix-100, the Deep Learning accelerator, conducts real-time, high accuracy 3D perception of the environment and was successfully taped out with silicon functionality verified in late 2018. Moreover, FABU plans to introduce its automotive-grade sensor fusion chip Phoenix-200 this year and its Phoenix-300 automated decision-making chip later this year. By building and incorporating this series of AI chips, FABU will develop a driverless computing platform called The Phoenix that will extend self-driving driving capabilities from SAE Level 3 to Level 5.