Google’s DeepMind team highlights new system for teaching robots novel tasks


Share post:

One of the first things you discover in the world of robotics is the complexity of simple tasks. Things that appear simple to humans have potentially infinite variables that we take for granted. Robots don’t have such luxuries.

That’s precisely why much of the industry is focused on repeatable tasks in structured environments. Thankfully, the world of robotic learning has seen some game-changing breakthroughs in recent years, and the industry is on track for the creation and deployment of more adaptable systems.

Last year, Google DeepMind’s robotics team showcased Robotics Transformer — RT-1 — which trained its Everyday Robot systems to perform tasks like picking and placing and opening draws. The system was based on a database of 130,000 demonstrations, which resulted in a 97% success rate for “over 700” tasks, according to the team.

Image Credits: Google DeepMind

Today it’s taking the wraps off RT-2. In a blog post, DeepMind’s Distinguished Scientist and Head of Robotics, Vincent Vanhoucke, says the system allows robots to effectively transfer concepts learned on relatively small datasets to different scenarios.

“RT-2 shows improved generalisation capabilities and semantic and visual understanding beyond the robotic data it was exposed to,” Google explains. “This includes interpreting new commands and responding to user commands by performing rudimentary reasoning, such as reasoning about object categories or high-level descriptions.” The system effectively demonstrates a capacity to determine things like the best tool for a specific novel task based on existing contextual information.

Vanhoucke cites a scenario in which a robot is asked to throw away trash. In many models, the user has to teach the robot to identify what qualifies as trash and then train it to pick the garbage up and throw it away. It’s a level of minutia that isn’t especially scalable for systems that are expected to perform an array of different tasks.

“Because RT-2 is able to transfer knowledge from a large corpus of web data, it already has an idea of what trash is and can identify it without explicit training,” Vanhoucke writes. “It even has an idea of how to throw away the trash, even though it’s never been trained to take that action. And think about the abstract nature of trash — what was a bag of chips or a banana peel becomes trash after you eat them. RT-2 is able to make sense of that from its vision-language training data and do the job.”

The team says the efficacy rate on executing new tasks has improved from 32% to 62% in the jump from RT-1 to RT-2.

Source link

Lisa Holden
Lisa Holden
Lisa Holden is a news writer for LinkDaddy News. She writes health, sport, tech, and more. Some of her favorite topics include the latest trends in fitness and wellness, the best ways to use technology to improve your life, and the latest developments in medical research.

Recent posts

Related articles

Tinder goes ultra-premium, Amazon invests in Anthropic and Apple explains its new AirPods

It’s that time of the week again, folks — time for Week in Review (WiR), TechCrunch’s newsletter...

How much can artists make from generative AI? Vendors won’t say

As tech companies begin to monetize generative AI, the creators on whose work it is trained are...

Venture capital is opening the gates for defense tech

Welcome to the TechCrunch Exchange, a weekly startups-and-markets newsletter. It’s inspired by the daily TechCrunch+ column where...

Humane’s ‘AI Pin’ debuts on the Paris runway

You’d better believe that Humane is going to milk the media hype cycle for all it’s worth....

Kick streamers consider leaving over CEO’s comments in a sex worker ‘prank’ stream

Streamers are leaving Kick en masse in protest of the platform’s lack of safety guidelines, after a...

VW bails on its plan for a $2.1B EV plant in Germany

Volkswagen’s $2.1 billion plan to launch a dedicated electric-vehicle factory in Wolfsburg, Germany is kaput.  The automaker instead...

When predatory investors damage your chances of success

Welcome to Startups Weekly. Sign up here to get it in your inbox every Friday. You know what...

Pudgy Penguins’ approach may be the answer to fixing NFTs’ revenue problems

Pudgy Penguins was once solely known for its 8,888 NFT collection. But ever since 24-year-old Luca Netz...