You’ve seen MIT’s robotic gripper, now here’s a first look at Carnegie Mellon University’s robotic arm that can be trained using AI-generated human movements. Put simply, augmented reality examples helped to decrease the robot’s learning time for the block pick-and-place task compared to a machine learning architecture alone.
When AR was paired with collection of human data through a VR headset simulation, they discovered that the research method has the potential to produce promising results with “under a minute of human input.” The researchers hope to use similar methods to teach the robot how to interact with more malleable materials such as clay, and predict how it will shape them.
- BUILD WORKING ROBOTS: Teach your kids mechanical engineering in a way they can't resist! Designed for kids 12+, this kit will guide your learner...
- POWERED BY WATER: Use the power of hydraulics to harness and control the Hydrobot! The arm includes 6 different axes and can rotate up to 270 degrees...
- MOVES, ROTATES & GRABS: Use the levers to control the gripper which can open and close or be replaced with suction components to pick up objects
If I want to show you how to do a task, I just have to do it once or twice before you pick up on it. So it’s very promising that now we can get a robot to replicate our actions after just one or two demos. We have created a control structure where it can watch us, extract what it needs to know, and then perform that action,” said Abraham George, CMU Ph.D. candidate.
