Facebook is trying to develop artificial intelligence models that will allow robots–including walking hexapods, articulated arms, and robotic hands fitted with tactile sensors–to learn by themselves, and to keep getting smarter as they encounter more and more tasks and situations. In the case of the spider-like hexapod ("Daisy") I saw walking around a patio at Facebook last week, the researchers give a goal to the robot and task the model with figuring out by trial and error how to get there. The goal can be as simple as just moving forward. In order to walk, the spider has to know a lot about its balance, location, and orientation in space. It gathers this information through the sensors on its legs.
Facebook's hexapod, Daisy, learning to walk On the rooftop of the building that houses the Facebook AI Research (FAIR) lab in Mountain View, California, there is a bootcamp for robots where the sun beams down on Daisy, a hexapod who is learning how to walk on a dirt jogging path. Her foot has become stuck in mulch as she struggles to wrestle free. A team of Facebook AI researchers eagerly look on, watching to see what she will do next as she moves forward with the curiosity and experimentation of a toddler. One flight down, Daisy's counterpart Pluto, a red arm robot, is learning how to reach for an object in its playpen. Facebook is leading an effort to teach robots how to think for themselves and develop human-like intuition that will enable them to navigate unknown circumstances.
"Much of our work in robotics is focused on self-supervised learning, in which systems learn directly from raw data so they can adapt to new tasks and new circumstances," a team of researchers from FAIR (Facebook AI Research) wrote in a blog post. "In robotics, we're advancing techniques such as model-based reinforcement learning (RL) to enable robots to teach themselves through trial and error using direct input from sensors." Specifically, the team has been trying to get a six-legged robot to teach itself to walk without any outside assistance. "Generally speaking, locomotion is a very difficult task in robotics and this is what it makes it very exciting from our perspective," Roberto Calandra, a FAIR researcher, told Engadget. "We have been able to design algorithms for AI and actually test them on a really challenging problem that we otherwise don't know how to solve."
As the term "machine learning" has heated up, interest in "robotics" (as expressed in Google Trends) has not altered much over the last three years. So how much of a place is there for machine learning in robotics? While only a portion of recent developments in robotics can be credited to developments and uses of machine learning, I've aimed to collect some of the more prominent applications together in this article, along with links and references. Before I delve into machine learning in robotics, go ahead and define "robot". Though at first this might seem simple, it's no easy task to come to an agreement on just what a robot is and what it is not, even amongst roboticists.