MIT researchers have developed a new “socially aware” robot that can follow the rules of pedestrian conduct, reports Ben Thompson for The Boston Globe. Thompson explains that the robot, “can seamlessly move with people in public spaces. The technology could eventually lead to robots that perform a variety of delivery and transportation tasks.”
During this episode of Globo’s “Caldeirão do Huck”, host Luciano Huck speaks with several MIT affiliates, including graduate student João Ramos to learn more about his research at MIT. The episode features a visit to Prof. Sangbae Kim’s lab, where Ramos demonstrates a robot the group developed that could be used to aid with disaster response.
A team of researchers from MIT and Princeton participating in the Amazon Robotics Challenge are using GelSight technology to give robots a sense of touch, reports Tom Simonite for Wired. Simonite explains that the, “rubbery membranes on the robot’s fingers are tracked from the inside by tiny cameras as they are deformed by objects it touches.”
CBS This Morning’s Dana Jacobson explores how MIT researchers are developing technology to enable robots to assist with disaster response, including a robotic cheetah and a system that 3-D prints robots. Prof. Russ Tedrake says that, “there's a natural transition from the robots in the labs now into the robots doing meaningful work.”
MIT researchers have designed a drone that can stay aloft for several days and could serve as an airborne telecommunications hub for disaster zones, reports Katherine Lin for NBC News. Prof. Warren Hoburg explains that the aircraft has a, “five-day endurance that is sized to carry a 10-pound payload at 15,000 feet.”
TechCrunch reporter Brian Heater writes that MIT researchers have developed a drone that can stay aloft for five days on a single tank of gas. “In addition to supporting areas in the wake of a disaster, the team believes the drone could go a ways toward helping tech companies…achieve their longstanding…dream of delivering internet access to rural areas.”
In an article for The New York Times about the growing number of autonomous public transportation programs in Europe, Mark Scott highlights Prof. Carlo Ratti’s work testing driverless boats in Amsterdam. In addition to ferrying people and goods, the driverless boats will also be able to “automatically dock with each other, creating on-demand bridges and walkways whenever necessary."
CSAIL researchers have developed a new system that allows camera-equipped drones to maintain certain framing parameters of an aerial shot, Sean O’Kane for The Verge. O’Kane explains that the system allows directors to define basic parameters of a shot and to alter the “settings on the fly and the drone will adjust how it’s filming accordingly.”
CSAIL researchers have developed a system that allows robots to teach one another learned skills, reports Grace Williams for FOX News. Williams explains that the system, “gives non-coders the ability to teach robots various tasks using information about manipulating objects in a single demonstration. These skills can then be passed along to other robots that move in different ways.”
Boston Globe reporter Steve Annear writes that a replica “Star Wars” X-wing Starfighter made an appearance in Lobby 7 on Monday. The replica was originally created for the annual 2.007 robot competition, during which students navigate robots that they designed and built themselves through a “Star Wars”-themed course.
Ben Guarino of The Washington Post revisits research by Profs. Annette Hosoi and Amos Winter examining how razor claims burrow through sand. Hosoi and Winter developed a device that “mimics the razor clam's digging ability, allowing an object to secure itself to the sea floor,” and could be used to anchor underwater autonomous vehicles or deposit undersea cables.
Researchers at CSAIL have developed a new system to train robots called C-LEARN, which imbues “a robot with a knowledge base of simple steps that it can intelligently apply when learning a new task,” writes Matthew Hutson for Science.
Anthony Cuthbertson of Newsweek reports that PhD student Claudia Pérez D’Arpino has developed a system that allows robots to learn a skill and teach it to another robot. Armed with knowledge of how to perform a task, a 3-D interface demonstrates the tasks “allowing [the robot] to understand the motions it is being taught in the real world,” explains Cuthbertson.
This CNN video highlights a new system developed by CSAIL researchers that allows noncoders to teach robots to perform a task after a single demonstration. The new programming method also enables robots to learn from other robots, which could enable “a variety of robots to perform similar tasks.”
Wired reporter Matt Simon writes that CSAIL researchers have developed a new system that allows noncoders to be able to teach robots a wide range of tasks, and enables robots to transfer new skills to other robots. Simon notes that the development is a “glimpse into a future where, more and more, robots communicate without humans at all.”