Energy-efficient AI for tomorrow’s autonomous devices
Neuromorphics Lab
With the Neuromorphics Lab, fortiss offers with a flexible experimental platform for testing AI applications with neuromorphic support. The presentation includes a unique robotic arm controlled by a neuromorphic algorithm and a state-of-the-art low-power gesture recognition sensor that relies on event-based image processing. Flexible control and autonomous movement of robots and visual sensing are challenging in AI due to their complexity and the limited battery capacity of mobile devices. Robot motion is calculated using a neuromorphic “Loihi” chip based on spiking neural networks (SNN), such as those found in the human brain. These neural networks serve as an inspiration and use event-based sensors to sense the environment like eyes.
Neuromorphic computing enables a significant reduction in the cost and weight of rechargeable batteries and extends their service life, one day allowing a wide range of robot and everyday systems to benefit and be brought to life. This development will result in a multitude of industrial applications in areas such as the Internet of Things (IoT), mobile robots, autonomous vehicles, aerospace and medical devices. Concrete examples include voice recognition in vehicles, movement detection in drones, gesture control in household appliances, augmented reality in smartphones, liquids analysis in medical instruments and debris detection in mini-satellites.
Focus
Demonstrators
As part of the Neuromorphic Lab, various demonstrators are presented to showcase the practical applications of neuromorphic systems in real-world scenarios.
The following examples highlight different fields of application in robotics, gesture recognition, and object detection:
- Cable insertion using a robotic arm
- Music gesture recognition
- Sports motion analysis (e.g., tennis)
- Object identification via drone
- Object tracking on a conveyor belt
- 3D robotic control through gestures
Services
- Information
Opportunity for informal exchange about the state of the art based on concrete application examples in the field of neuromorphic computing. - Events
Informational events provide broad expertise on AI on mobile and edge devices. - Research
- Porting of mobile AI applications to neuromorphic hardware
- Provisioning of latency- and energy-efficient systems that can be isolated from the network
- Consulting
Consulting on technical feasibility, industrial maturity (TRL) - Network
The Neuromorphic Computing (NC) field of competence is part of the Intel Neuromorphic Research Team and is thus networked with more than 90 worldwide top laboratories in the field of NC.
