Google DeepMind researchers Keerthana Gopalakrishnan and Ted Xiao discuss breakthroughs in AI robotics, including models for robots to understand new objects, learn from human demos, and operate ethically. They cover six papers showing progress in general-purpose robotics, touching on topics like object manipulation, human-like features in robots, and visual object models for directing motion in tasks.

In this podcast, they discuss breakthroughs in robotics research such as internet-scale vision-language for robots, training robots with a single human demonstration, and using language models for ethical oversight. They also cover challenges in robotics models, safety concerns, and advancements in vision-language generalization for robots.