Stanford University researchers have developed a new AI system called Mobile ALOHA that can train mobile robots to perform complex tasks across different environments. The system addresses the high costs and technical challenges associated with training these robots, and it can learn from as few as 50 human demonstrations. The system is designed to be cost-effective, with a setup cost of around $32,000 compared to the up to $200,000 cost of off-the-shelf bimanual robots. While Mobile ALOHA has impressive results, it is not yet a fully autonomous system, and improvements are needed to make it more suitable for tight environments.
https://venturebeat.com/automation/stanfords-mobile-aloha-robot-learns-from-humans-to-cook-clean-do-laundry/