ZF propel vehicle intelligence with new AI supercomputer
German car part maker Zahnradfabrik Friedrichshafen (ZF) has unveiled the next generation of its ZF ProAI at Auto Shanghai 2021.
It is designed for the requirements of software-defined vehicles and their new electric/electronic architectures, this artificial intelligence (AI) capable high-performance computer can serve as domain, zone or central controller.
“Several significant orders for our high-performance computing platform confirm our vanguard position to drive vehicle intelligence,” said Dr. Holger Klein, ZF Board Member for the Asia-Pacific region.
“Offering high computing power, cutting-edge software solutions, intelligent sensors, and smart actuators from a single source, ZF creates new possibilities for data-based business models for next generation mobility.”
The supercomputers AI capabilities are optimized for deep learning processes. It has up to 66 per cent more computing power than its predecessor and also consumes up to 70 per cent less power (3 teraOPS per Watt, on average). Its high-performance board features a 360° GPU for storing sensor data, light detection and ranging (LiDAR) system, cameras, and audio units.
Its modular set-up means it can be fitted with System-on-Chip (SoC) variants from different manufacturers to achieve the preferred customer solution. It can operate ZF’s own software or that of third-party suppliers. Standardized connectors and the option to link more ZF ProAI units together make it flexible for use and installation in any type of vehicle.
ZF ProAI will go into serial production latest in 2024.
Automated Valet Parking
ZF is also currently developing a driverless automated parking system which is based solely on vehicles’ sensor sets.
At Auto Shanghai 2021, ZF demonstrated Visual Simultaneous Localization and Mapping (vSLAM) technology to the public that enables centimeter-accurate localisation and real-time map generation. The sensor set is mainly based on one front camera, one front radar, four surrounding cameras and twelve ultrasonics but scalable with more advanced sensors as well as connectivity.
“The entire system is developed in China and will have its debut at a Chinese car manufacturer at the end of 2022,” said Ms. Renee Wang, President of ZF China and Senior Vice President Operations for the Asia-Pacific region.
“We believe that this infrastructure-independent automated valet parking system from ZF will be a cost-effective solution for many global OEMs.”
What is neuromorphic AI?
AI is dead. Long live AI?
AI is evolving. The first generation of machine learning used ordinary logic and rules to draw conclusions in a very specific manner. A good example would be IBM’s Deep Blue computer, which was trained to play chess to championship standard. That hasn’t disappeared, but it has been augmented by more perceptive deep learning networks that can analyze a broader set of parameters and provide intelligent insights.
And neuromorphic AI is next?
Correct. Neuromorphic computing is a way of designing hardware – microprocessors, really – to work more like human brains. The idea is that this new iteration of AI hardware will allow machine learning of the future to deal better with ambiguity and contradiction, things that are currently difficult to process for computers.
How does neuromorphic AI work?
The problem with current chip architecture is that it is not very efficient. Because of the linearity of the process, the chips have to built with a massive amount of horsepower just in case it’s needed. Building a human brain that way would be unfeasible, so engineers have had to rethink the nature of chip design in their quest to get computers to perform more of the tasks human brains are good at. Enter SNNs.
What’s an SNN?
A spiking neural network (SNN) is, in the words of chipmaker Intel, “a novel model for arranging those elements to emulate natural neural networks that exist in biological brains.” Each ‘neuron’ fires independently, triggering other neurons only when they are required. Intel again: “By encoding information within the signals themselves and their timing, SNNs simulate natural learning processes by dynamically remapping the synapses between artificial neurons in response to stimuli.”