Google’s X moonshot program late last week teased at its internal robotics projects, mentioning that the combination of machine learning and robotics will be at the heart of many of its ventures.

While no distinct details were released, Google X said that its robotics arm is closely collaborating with its Google Brain deep learning artificial intelligence research arm, manager Hans Peter Brondmo wrote in a blog post.

“The combination of machine learning and robotics is one of the reasons I’m most excited to be at X today. ML will be necessary to make machines that are useful and reliable in unstructured environments. It’s at this point that robotics will really begin to open up new frontiers for attacking previously intractable problems,” Brondmo wrote in the blog post.

In the post, Brondmo mentioned that Google is currently operating a laboratory of robotic manipulation arms specifically tasked for machine learning research. Brondmo said that the company is “working with the Google Brain team to explore how to teach robots new skills by learning from their shared experience, learning from human demonstration” and “simulating robots in the cloud so they can train fast, and then we’re transferring this learning onto real robots.”

The company still has a long journey to building machines that can learn new skills quickly and operate cost effectively, Brondmo said, with final applications that “could be decades away.”

In the post, Brondmo said that the company couldn’t share details of its robotics projects yet, but teased that “there’s a lot of really exciting work going on as we build a bridge from science fiction to solving high-impact problems in the real world.”