Download RSS feed: News Articles / In the Media / Audio
A team led by Prof. Russ Tedrake has been awarded a humanoid robot from NASA to develop software for future space missions, reports Hiawatha Bray for BetaBoston. NASA is “interested in modifications that would let the machines assist human astronauts during long-duration space missions,” writes Bray.
In this video, Jim Drury of Reuters examines the new system developed by MIT researchers that enables drones to map and successfully navigate a new landscape.
In this video, BBC News reporter Stephen Beckett speaks with Prof. Dina Katabi about a new system her group developed that can track people through walls using wireless signals. “It’s using these very low-power signals, sending them, and observing the reflection of the body through the wall,” explains Prof. Dina Katabi.
Washington Post reporter Matt McFarland writes about graduate student Andrew Barry’s work developing a system that allows drones to successfully navigate obstacles. McFarland writes, “the work is significant because it shows a drone avoiding obstacles in an area that hasn’t been previously mapped.”
MIT researchers have developed a detection system that allows a drone to navigate obstacles while flying at speeds of 30 mph, writes Barb Darrow for Fortune. Darrow explains that the research is aimed at mitigating “the risk of using potentially very useful technology not just for package delivery but for building or land inspections, journalism, even fire fighting.”
Graduate student Andrew Barry has created software that allows a self-piloting drone to dodge obstacles at 30 miles per hour, reports Robert Ferris for CNBC. “The software, which is open source and available for free online, runs 20 times faster than existing navigational software,” reports Ferris.
Alyssa Newcomb reports for ABC News on a system developed by graduate student Andrew Barry that allows drones to avoid obstacles. Newcomb explains that the system, "operates at 120 frames per second and is able to extract depth information at a speed of 8.3 milliseconds per frame."
MIT researchers “demonstrated that a drone can zip through a maze of trees at 30 miles per hour swerving past obstacles in its way. The craft was able to do this using a stereo-vision algorithm that rapidly detects and avoids objects immediately in front of the craft,” reports Nidhi Subbaraman for BetaBoston.
MIT researchers have developed a drone that can recognize obstacles while flying at speeds of 30 miles per hour, writes Mary Beth Griggs for Popular Science. The drone creates a map of the world, “identifying obstacles, and mapping a path around them.”
Huffington Post reporter Nitya Rajan writes that MIT researchers have developed a device that can see through walls. Rajan explains that the device works by “sending wireless signals through a wall and capturing whatever bounces back off to put together an image of the person on the other side of the wall.”
Washington Post reporter Matt McFarland writes that MIT researchers have developed a device that tracks human movement through walls and could be used to monitor children or the elderly. “We want to provide peace of mind without intruding too much on lives or taking independence away,” explains Prof. Dina Katabi.
MIT researchers have developed a device that can trace the movement of a person’s silhouette through a wall using wireless signals, reports Robert Ferris for CNBC. The device can "distinguish up to 15 different individuals with 90 percent accuracy,” Ferris explains.
Hiawatha Bray writes for BetaBoston about Emerald, a new device created by MIT researchers that can track a person’s movements using wireless signals. “Our main interest is really elderly care,” explains Prof. Dina Katabi.
MIT researchers have created an algorithm that outperforms humans when searching for patterns in data sets, reports Rachel Feltman for The Washington Post. The algorithm uses “raw datasets to make models predicting things such as when a student would be most at risk of dropping an online course.”
Seung Lee writes for Newsweek that MIT researchers have developed an algorithm that can outperform humans in finding patterns in data sets. The system takes “two to 12 hours for what a human could only do over the course of several months.”