Google's DeepMind robotics team has unveiled three new advancements designed to help robots make faster, better, and safer decisions in real life.
One of these includes a training data collection system with a “robot constitution” to ensure your robot office assistant can bring you printer paper but without bumping into a human on their desk.
The robot's condition
Google's data collection system, AutoRT, uses language models that work together to understand known or unknown environments and decide on appropriate tasks.
The Robot Constitution, inspired by Isaac Asimov's “Three Laws of Robotics,” is described as a set of safety-focused rules that tell the model to avoid tasks involving humans, animals, sharp objects and even electrical devices.
Robot with on/off button
For added safety, DeepMind programmed the robots to automatically stop when the force on their joints exceeds a certain threshold and gave them a physical switch that human operators can use to deactivate them.
Within seven months, Google deployed a fleet of 53 AutoRT robots in four different office buildings and conducted more than 77,000 tests. For testing purposes, these rudimentary robots were controlled remotely by human operators, while others operated either script-based or fully autonomous using Google's Robotic Transformer (RT-2) artificial intelligence learning model.
According to Google's blog, the robot needed to understand the environment to perform tasks like placing a snack on the counter.
Google mentions other DeepMind technologies like SARA-RT and RT-Trajectory to help robots better perform certain physical tasks like wiping a table.
We're still a long way from autonomous robots that can serve drinks or iron clothes, but when they become available they may have learned from a system like AutoRT.