Figure 1 - available via license: Creative Commons Attribution 4.0 International
Content may be subject to copyright.
Pepper taking images of a laptop and asking a human to manipulate it for learning the property Folded.
Source publication
Autonomous agents embedded in a physical environment need the ability to recognize objects and their properties from sensory data. Such a perceptual ability is often implemented by supervised machine learning models, which are pre-trained using a set of labelled data. In real-world, open-ended deployments, however, it is unrealistic to assume to ha...