Research Highlights: Interactive continual learning for robots: a neuromorphicapproach

Print Friendly, PDF & Email

Title: Interactive continual learning for robots: a neuromorphic approach

Overview: Researchers at Intel Labs, in collaboration with the Italian Institute of Technology and the Technical University of Munich, have introduced a new approach to neural network-based object learning, specifically targeting future robotics applications such as robotic assistants that interact with unconstrained environments – in situations like logistics, health- or elderly care.  

The researchers developed new models that successfully demonstrated continual interactive learning on Intel’s neuromorphic research chip measuring up to 175x lower energy to learn a new object instance with similar or better speed and accuracy compared to conventional methods running on a central processing unit (CPU). This research is a crucial step in improving the capabilities of future assistive or manufacturing robots using neuromorphic computing to enable them to adapt to the unforeseen and work more naturally alongside humans.  

Read the full paper HERE, which was named “Best Paper” at this year’s International Conference on Neuromorphic Systems (ICONS) hosted by Oak Ridge National Laboratory.    

Sign up for the free insideBIGDATA newsletter.

Join us on Twitter: @InsideBigData1 –

Speak Your Mind