Deep in the basement of MIT\u2019s Building 3, a two-legged robot named HERMES is wreaking controlled havoc: punching through drywall, smashing soda cans, kicking over trash buckets, and karate-chopping boards in half. Its actions, however, are not its own.<\/p>\n
Just a few feet away, PhD student Joao Ramos stands on a platform, wearing an exoskeleton of wires and motors. Ramos\u2019 every move is translated instantly to HERMES, much like a puppeteer controlling his marionette. As Ramos mimes punching through a wall, the robot does the same. When the robot\u2019s fist hits the wall, Ramos feels a jolt at his waist. By reflex, he leans back against the jolt, causing the robot to rock back, effectively balancing the robot against the force of its punch.<\/p>\n
The exercises are meant to demonstrate the robot\u2019s unique balance-feedback interface. Without this interface, while the robot may successfully punch through a wall, it would also fall headlong into that wall. The interface allows a human to remotely feel the robot\u2019s shifting weight, and quickly adjust the robot\u2019s balance by shifting his own weight. As a result, the robot can carry out momentum-driven tasks \u2014 like punching through walls, or swinging a bat \u2014 while maintaining its balance.<\/p>\n
Ramos says the interface takes advantage of a human\u2019s split-second reflexes, which give the robot much faster reaction times than robots that adjust their balance based on visual feedback from onboard cameras.<\/p>\n
\u201cThe processing of images is typically very slow, so a robot has difficulty reacting in time,\u201d says Ramos, of MIT\u2019s Department of Mechanical Engineering. \u201cInstead, we\u2019d like to use the human\u2019s natural reflexes and coordination. An example is walking, which is just a process of falling and catching yourself. That\u2019s something that feels effortless to us, but it\u2019s challenging to program into a robot to do it both dynamically and efficiently. We want to explore how humans can take over complex actions for the robot.\u201d<\/p>\n
Ultimately, Ramos and his colleagues envision deploying HERMES to a disaster site, where the robot would explore the area, guided by a human operator from a remote location.<\/p>\n
\u201cWe\u2019d eventually have someone wearing a full-body suit and goggles, so he can feel and see everything the robot does, and vice versa,\u201d Ramos says. \u201cWe plan to have the robot walk as a quadruped, then stand up on two feet to do difficult manipulation tasks such as open a door or clear an obstacle.\u201d<\/p>\n
Ramos and his colleagues, including PhD student Albert Wang and Sangbae Kim, the Esther and Harold E. Edgerton Center Career Development Associate Professor of Mechanical Engineering, will present a paper<\/a> on the interface at the IEEE\/RSJ International Conference on Intelligent Robots and Systems in September.<\/p>\n \u201cWe don’t quite understand how humans master such gracious dynamic movements,\u201d Kim says. \u201cThis research might provide us an opportunity to learn about how we balance during such complex manipulation tasks.\u201d<\/p>\n