If, while playing Jenga, you’ve ever wished you had the focus, predictive capabilities, and nerves of steel that would rival a robot, watch this video from the Department of Mechanical Engineering at MIT. The robot and its algorithms were developed by MIT MCube Lab researchers using artificial intelligence and sensory hardware. From MIT News:
As the robot carefully pushes against a block, a computer takes in visual and tactile feedback from its camera and cuff, and compares these measurements to moves that the robot previously made. It also considers the outcomes of those moves — specifically, whether a block, in a certain configuration and pushed with a certain amount of force, was successfully extracted or not. In real-time, the robot then “learns” whether to keep pushing or move to a new block, in order to keep the tower from falling…
“Unlike in more purely cognitive tasks or games such as chess or Go, playing the game of Jenga also requires mastery of physical skills such as probing, pushing, pulling, placing, and aligning pieces. It requires interactive perception and manipulation, where you have to go and touch the tower to learn how and when to move blocks,” [assistant professor Alberto] Rodriguez says. “This is very difficult to simulate, so the robot has to learn in the real world, by interacting with the real Jenga tower. The key challenge is to learn from a relatively small number of experiments by exploiting common sense about objects and physics.”
Watch these impressive robot videos next: Solving a Rubik’s Cube in 0.38 seconds, Ultra Fast Robots Pick & Place Batteries to Form Group Patterns, Madeline the Robot Tamer, and Robotic Loop: Train vs. Robot.
via Laughing Squid.