What AIs are not Learning (and Why)

What applications is AI ready for? Advances in deep learning and generative approaches have produced AI that learn from massive online data and outperform manually built AIs. Some AIs outperform people. It is easy (but misleading) to conclude that today's AI technologies can learn to do everything. Conversely, it is striking that big data, deep learning, and generative AI have had so little impact on robotics. For example, today's autonomous robots do not learn to provide home care or to be nursing assistants. Instead, current projects rely on mathematical models, planning frameworks, and reinforcement learning. These methods have not lead to the leaps in performance and generality seen with deep learning. Today's AIs do not learn to do such applications because they do not collect, use, and effectively generalize the necessary experiential data by interacting with the world including people. Aspirationally, robotic AIs would learn experientially, learn from people, serve people broadly, and collaborate with them. Getting to such a future requires understanding the opportunity and creating a path to get there. A path forward would combine multimodal sensing and motor control technology from robotics with deep learning technology adapted for embodied systems. Analogous to foundation classes in deep learning, it would create experiential foundation classes. Success would greatly increase the broad utility of AI robots and grow the market for them. This would lead to lower costs and democratize AI.