RoboCat masters diverse robotics tasks with DeepMind's help.

DeepMind has developed an AI model called RoboCat that can perform a range of tasks across different models of robotic arms and can solve and adapt to multiple tasks using different real-world robots. The model was trained on images and actions data collected from robotics both in simulation and real life. RoboCat was able to learn new tasks with as few as 100 demonstrations and could herald a lowering of the barrier to solve new tasks in robotics. The research team aims to reduce the number of demonstrations needed to teach RoboCat to complete a new task to fewer than 10.