Google Integrates Artificial Intelligence into Robots to Train them in Garbage Disposal

Google








recently unveiled its latest artificial intelligence model, Robotics Transformer 2 (RT-2), which aims to enhance robot understanding and performance in tasks such as trash disposal.

RT-2 is a vision-language-action model that uses information and images from the internet to train robots. This model enables the translation of visual and linguistic inputs into actionable responses for the robot.

While humans perceive tasks like trash disposal as straightforward, robots require a series of instructions to learn and perform them effectively. RT-2 allows robots to leverage web-based knowledge to understand and carry out such tasks, even without explicit training on the specific steps.

Google stated that the new model has significantly improved the robots’ performance in previously unseen scenarios compared to the earlier version. The updated model also incorporates rudimentary reasoning capabilities to respond to user commands.

According to The New York Times, Google currently has no immediate plans to release or sell robots equipped with this technology, but there is potential for future applications in areas such as warehouses or home assistance.

Subscribe to CNBC on YouTube.

WATCH: How autonomous inventory robots could save retailers billions