Getting Data for Robot AI — Hard, but Possible
Embodied AI agents need data of interactions with the real world, which is far more difficult to get than data of other AI domains like vision and language.
This is the third of a series on the challenges and opportunities of applying AI to robotics, specifically in the setting of autonomous service robots that can assist humans in everyday tasks. See the overview here.
TL;DR Deep-learning-driven AI needs a lot of data. Robot AIs need data of robots interacting with the world, which is a lot harder to get th…
Keep reading with a 7-day free trial
Subscribe to Last Week in AI to keep reading this post and get 7 days of free access to the full post archives.