Wired reporter Matt Simon writes that CSAIL researchers have developed a system of drones that can successfully fly and drive through a city-like setting. Simon explains that the framework is a good step, “toward imagining a transportation infrastructure that works in three dimensions, not just two.”
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.”
Prof. Erik Brynjolfsson and Principal Research Scientist Andrew McAfee speak with Tom Ashbrook of On Point about their new book, “Machine, Platform, Crowd.” Speaking about how much decision-making machines could be handling in the future, Brynjolfsson explains that “instead of having us humans try to tell the machines exactly what needs to be done, machines are learning on their own.”
Graduate student Shriya Srinivasan speaks with Ira Flatow of PRI’s Science Friday about the surgical technique she and her colleagues developed to make prosthetic limbs feel more natural. Srinivasan explains that the technique allows patients to have, “finer prosthetic control — and be able to modulate position, velocity, and stiffness of prosthetic devices, which is a significant improvement to the clinical standard.”
MIT researchers have developed a surgical technique that could make prosthetic limbs feel more natural, writes Karen Weintraub for Scientific American. “With this approach, we’re very confident that the human will actually feel position, will actually feel speed, will actually feel force,” says Prof. Hugh Herr. “It’ll completely feel like their own limb.”
Researchers at MIT have developed a surgical technique that could lead to more lifelike prosthetic limbs, reports Matthew Hutson for Science. The new technique, coupled with a smart prosthetic, should enable users to “feel the same way that they once felt when they had a limb,” says Prof. Hugh Herr.
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.
New Scientist reporter Timothy Revell writes that a new study by Prof. Iyad Rahwan shows that automation will have a larger impact on jobs in smaller cities. Rahwan and his colleagues found that “towns and small cities have a smaller proportion of jobs that will be resilient to automation than larger urban centers.”
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.”