Fast Company reporter Mark Wilson writes that CSAIL researchers have developed a new soft robotic gripper that is modeled after a Venus flytrap. “Dubbed the Magic Ball, it’s a rubber and plastic structure that can contract around an object like an origami flower,” Wilson explains.
CSAIL researchers have developed a new robotic gripper that contains an origami skeleton, enabling the device to open and close like a flower and grasp a variety of delicate and heavy objects, reports James Vincent for The Verge “By combining this foldable skeleton with the soft exterior, we get the best of both worlds,” explains Prof. Daniela Rus, director of CSAIL.
TechCrunch reporter Brian Heater writes that researchers at CSAIL and Harvard have developed a soft robotic gripper that can both handle delicate objects and lift items up to 100 times its own weight. “The gripper itself is made of an origami-inspired skeletal structure, covered in either fabric or a deflated balloon,” explains Heater.
In this video, HuffPost highlights a robotic cheetah created by MIT researchers that can perform a backflip from a standing position. HuffPost notes that the robot has a “range of motions, making it agile enough to pick itself up if knocked to the ground.”
Forbes reporter Eric Mack writes about the latest iteration of MIT’s robotic cheetah: A new miniature version that weighs 20 pounds. “The cheetah has heavyweight skills like walking over uneven terrain, picking itself up after a fall or a swift kick and of course, its ability to pull off a 360-degree reverse flip from a standing position,” Mack explains.
Washington Post reporter Peter Holley writes that MIT researchers have created a mini robotic cheetah that can perform a backflip and walk right-side up or upside down. “Legged robots will have a variety of uses where human or animal-like mobility is necessary, but it may be unsafe to send a person,” explains technical associate Benjamin Katz.
Fortune reporter Alyssa Newcomb writes that MIT researchers have developed a 20-pound robotic cheetah that can successfully execute a backflip and nail the landing. “The robotic mini cheetah can also gallop over uneven terrain twice as fast as the average human,” writes Newcomb.
A miniature version of the robotic cheetah developed by MIT researchers provides a testbed for researchers to experiment with new maneuvers like backflips, reports David Freeman for NBC Mach. “Having a platform that's relatively small and safe and cheap makes running experiments very easy,” says technical associate Benjamin Katz, “you don't have to worry about breaking the robot or getting hurt.”
MIT researchers have developed a miniature robotic cheetah that can perform a wide range of maneuvers, reports Brian Heater for TechCrunch. “The robot is capable of running up to five miles per hour, can perform a 360-degree backflip from a standing position and will right itself quickly after being kicked to the ground,” Heater explains.
Verge reporter Chaim Gartenberg writes that MIT researchers have developed a new mini cheetah robot that can perform backflips. Gartenberg notes that the robot is the first four-legged robot that can do a backflip, adding that it weighs “around 20 pounds, and can trot along at up to 2.45 meters per second (around 5.5 miles per hour).”
CBS This Morning correspondent Nikki Battiste visits MIT to learn more about a device developed by MIT researchers that uses wireless signals to detect food contamination. “We hope to be able to build a portable device that a person can take with them when they're trying to buy something from a supermarket or from a farmer's market,” explains Prof. Fadel Adib.
Graduate student Joy Buolamwini writes for TIME about the need to tackle gender and racial bias in AI systems. “By working to reduce the exclusion overhead and enabling marginalized communities to engage in the development and governance of AI, we can work toward creating systems that embrace full spectrum inclusion,” writes Buolamwini.
Prof. Joi Ito, director of the Media Lab, writes for Wired about how AI systems can help perpetuate longstanding discriminatory practices. “By merely relying on historical data and current definitions of fairness, we will lock in the accumulated unfairnesses of the past,” argues Ito, “and our algorithms and the products they support will always trail the norms.”
In this video, graduate student Nima Fazeli speaks with the BBC News about his work developing a robot that uses sensors and cameras to learn how to play Jenga. “It’s using these techniques from AI and machine learning to be able to predict the future of its actions and decide what is the next best move,” explains Fazeli.
CBS This Morning spotlights how MIT researchers have developed a new robot that can successfully play Jenga. “It is an automated system that has had a learning period first,” explains Prof. Alberto Rodriguez. “It uses the information from the camera and the force sensor to interpret its interactions with the Jenga tower.”