Robots One Step Closer to Learning Like Humans
Watch how University of Michigan researchers use a new data augmentation-based method to train robots how to learn faster like humans.
“If you maximize the diversity of the data, it won’t be relevant enough. But if you maximize relevance, it won’t have enough diversity,” said doctoral student in robotics, Peter Mitrano . “Both are important.”
More From SAE Media Group
Tech Briefs
A Picking Robot for a Greenhouse More