In a blog post on Friday, the company announced that its Everyday Robots Project — an unit under Google’s experimental X laboratories dedicated to creating “a general-purpose learning robot” — has moved out several of its robot prototypes from the lab to some of Google’s Bay Area campuses to do useful cleaning duties. These robots are autonomously performing a range of useful tasks around Google facilities in the U.S., including as wiping tables, sorting trash, gripping cups, and even opening meeting room doors to check if the room needs to be tidied or if it’s missing chairs. “We now manage a fleet of over 100 robot prototypes that autonomously perform a variety of useful tasks in our offices. The same robot that sorts the garbage can now be equipped with a squeegee to clean the tables and use the same gripper that grabs the cups can learn to open doors,” Hans Peter Brondmo, Chief Robotic Officer of Everyday Robot wrote in a blog post. Over the last few years, Alphabet has been building an integrated hardware and software system that is designed for learning — including transferring learning from the virtual world to the real world. The robots are equipped with a mix of different cameras and sensors to take in the world around them. Using a combination of machine learning techniques like reinforcement learning, collaborative learning, and learning from demonstration, the robots have steadily gained a better understanding of the world around them and become more skilled at doing everyday tasks. It initially took approximately four months for one robot to learn how to perform a simple grasp with a 75% success rate in an office environment. With less than a day of real-world learning, a single robot can now learn how how to perform a complex task such as opening doors with a 90% success rate. “Even more excitingly, we’ve shown that we can build on the algorithms and learnings from door opening and apply them to a new task: straightening up chairs in our cafes. This progress gives us hope that our moonshot for building general purpose learning robots might just be possible,” Brondmo added. The robot prototypes will initially come to Alphabet’s Mountain View offices in the coming months. “Over time, we will be expanding the types of tasks they are doing and the buildings where we operate and look forward to sharing updates from our journey over the coming months and years,” Brondmo concluded.
