Innovative hardware components such as circuit boards are required to overcome the limitations of today's computer hardware.

Neuromorphic computing

More energy efficiency in autonomous driving of the future.

December 06, 2024 – Future vehicles will include more and more functionalities, with those for autonomous driving being just one example. As this will lead to significantly higher energy requirements, efficiency is a crucial factor.

Mercedes Benz is a pioneer in automated driving and safety technologies. The vision for the future is autonomous driving, which will redefine the role of the automobile. Not only will it increase safety, efficiency and comfort on the road. It will also give time back to passengers by allowing them to devote their attention to things other than driving. In addition, the autonomous car will communicate with the cities of the future. To realise all this calls for innovative algorithms and hardware components that overcome the limits of today’s computer hardware.

Through research into artificial neural networks, Mercedes-Benz and its partners from research and industry are breaking new ground in the creation of computer architectures. The company recently announced a research cooperation with the Canadian University of Waterloo in the field of neuromorphic computing. By mimicking the workings of the human brain, neuromorphic computing could make AI computations significantly more energy-efficient and faster.

Neuromorphic computing (NC) mimics the way the human brain works and could therefore make AI calculations more efficient and faster.
Neuromorphic computing (NC) mimics the way the human brain works and could therefore make AI calculations more efficient and faster.
Innovative hardware components such as circuit boards are required to overcome the limitations of today's computer hardware.
Innovative hardware components such as circuit boards are required to overcome the limitations of today's computer hardware.
Safety systems could, for example, recognise traffic signs, lanes and other road users much better and react faster, even in poor visibility.
Safety systems could, for example, recognise traffic signs, lanes and other road users much better and react faster, even in poor visibility.
Instead of full images (frames), neuromorphic camera for interior monitoring delivers individual pixels (events – hence the name event-based camera), which is extremely fast with minimal delay.
Instead of full images (frames), neuromorphic camera for interior monitoring delivers individual pixels (events – hence the name event-based camera), which is extremely fast with minimal delay.
Neuromorphic computing (NC) mimics the way the human brain works and could therefore make AI calculations more efficient and faster.
Innovative hardware components such as circuit boards are required to overcome the limitations of today's computer hardware.
Safety systems could, for example, recognise traffic signs, lanes and other road users much better and react faster, even in poor visibility.
Instead of full images (frames), neuromorphic camera for interior monitoring delivers individual pixels (events – hence the name event-based camera), which is extremely fast with minimal delay.

Safety systems could, for example, recognise traffic signs, lanes and other road users much better and react faster, even in poor visibility. And they could do so ten times more efficiently than current systems. There would be benefits in using a neuromorphic camera for interior monitoring, for example. Instead of full images (frames), it delivers individual pixels (events – hence the name event-based camera). The process is extremely fast with minimal delay. This means, for instance, a rapid system reaction to the blinking of a driver’s eye caused by fatigue. Neuromorphic computing has the potential to reduce the energy required for data processing in autonomous driving by 90 per cent compared to current systems.

Autonomous Driving.

Autonomous Driving.

Autonomous driving is redefining the role of the automobile.