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).”
WBUR’s Deborah Becker speaks with Prof. Regina Barzilay about her work applying AI to health care and Prof. Sangbae Kim about how the natural world has inspired his robotics research during a special Radio Boston segment highlighting innovation in the greater Boston area.
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.”
MIT researchers have developed a robot that can play Jenga. “It "learns" whether to remove a specific block in real time, using visual and tactile feedback, in much the same way as a human player would switch blocks if the tower started to wobble,” reports Jack Guy for CNN.
MIT researchers have developed a robot that can learn how to successfully play Jenga, reports Brian Heater for TechCrunch. “The robot has to learn in the real world, by interacting with the real Jenga tower,” explains Prof. Alberto Rodriguez. “The key challenge is to learn from a relatively small number of experiments by exploiting common sense about objects and physics.”
Gizmodo reporter Andrew Liszewski writes that MIT researchers have developed a robot that can play Jenga using visual and physical cues. The ability to feel “facilitated the robot’s ability to learn how to play all on its own, both in terms of finding a block that was loose enough to remove, and repositioning it on the top of the tower without upsetting the delicate balance.”
MIT researchers have developed a robot that can play Jenga by combining interactive perception and manipulations, reports Mattha Busby for The Guardian. “In what marks significant progress for robotic manipulation of real-world objects, a Jenga-playing machine can learn the complex physics involved in withdrawing wooden blocks from a tower through physical trial and error,” Busby explains.
Principal Research Scientist Andrew McAfee speaks with NBC's Stephanie Ruhle about the ways robots are changing work. “The hollowing out of the middle class has not yet been replaced by middle class 2.0,” says McAfee. “That should be our real homework going forward, not trying to demonize the automation or the technology.”
A new robot developed by MIT researchers uses AI and sensors to play the game of Jenga, reports Rob Verger for Popular Science. “It decides on its own which block to push, [and] which blocks to probe; it decides on its own how to extract them; and it decides on its own when it’s a good idea to keep extracting them, or to move to another one,” says Prof. Alberto Rodriguez.
Wired reporter Matt Simon writes that MIT researchers have engineered a robot that can teach itself to play the game of Jenga. As Simon explains, the development is a “big step in the daunting quest to get robots to manipulate objects in the real world.”
Prof. Daniela Rus and R. David Eldeman, director of the Project on Technology, Economy, and National Security at MIT speak with Matt Simon at Wired about working with robots. “The robots have a fixed architecture and they have a fixed vocabulary,” explains Rus. “So, people will continue to have to learn that and understand what the tool is useful for.”
Popular Mechanics reporter Jill Kiedaisch writes that MIT researchers have developed a plant cyborg, named Elowan, that can move itself towards sources of light. Kiedaisch writes that Elowan “could elevate how we interface with the world around us, leveraging the natural abilities of plants to inform how we animals express our own agency to live, and keep living, perhaps a bit more symbiotically.”
The Today Show highlights Spyce, a restaurant started by four MIT alumni where “robots prep and cook the meal and a team member completes it,” explains Sheinelle Jones. “What we are automating are the tough, repetitive monotonous jobs,” says co-founder Michael Farid, “to allow people to focus on what people are really good at - customer service, creativity, the presentation of your bowl.”
Chronicle highlights MIT startup Spyce, a restaurant with a robotic kitchen. At Spyce, the flames used to heat a wok “are replaced with induction metal,” explains Erika Tarantal. “The robot-controlled rotation ensures cooking on all sides.”