Defense Advanced Research Projects Agency (DARPA)

Victor Luckerson writes for TIME about the robotic cheetah created by a team of MIT researchers that can “autonomously leap tall obstacles in a single bound.” Luckerson explains that, “the cheetah can clear hurdles as high as 18 in. (46 cm) at an average running speed of 5 m.p.h. (8 km/h).”

Newsweek reporter Felicity Capon writes about the robotic cheetah developed by MIT researchers that can jump over hurdles autonomously. The cheetah uses an onboard mapping system to detect obstacles and estimate their height and distance. 

MIT researchers have developed a robotic cheetah that can jump over obstacles while running, reports Sandrine Ceurstemont for New Scientist. “The robot spots obstacles in its path with its built-in lidar system, which can build up a picture of the object in its way from reflected laser light,” explains Ceurstemont. 

MIT researchers have trained a cheetah robot they developed to make “flying leaps” over obstacles, reports Devin Coldewey for NBC News. The researchers behind the robotic cheetah aim to “build a ‘high-speed locomotion platform’ with the fastest land animal as its inspiration.”

The robotic cheetah developed by MIT researchers can now autonomously jump over obstacles, reports Nitya Rajan for The Huffington Post. “This is the first time a four-legged robot has used laser sensors to gauges the distance and height of obstacles in its way to plan its jump,” writes Rajan.

According to Fox News, MIT’s cheetah robot can now jump over obstacles up to 18 inches tall, which is more than half the robot’s height. “Our goal is to use this kind of robot to save lives in a disaster situation,” explains Professor Sangbae Kim. 

Allison Pohle reports for Boston.com on new algorithms that allow MIT’s robotic cheetah to jump over obstacles autonomously. “The cheetah first practiced its skills on a treadmill in a lab,” writes Pohle. “It then moved on to an indoor track, and is now being trained to jump while running on the grass.”

James Temperton writes for Wired about new developments in robotics, highlighting the MIT cheetah robot that can now autonomously jump over hurdles and the miniature origami robots developed by MIT researchers that can fold self-assemble, walk, swim and dissolve. 

Carl Franzen reports for Popular Science that the researchers behind MIT’s robotic cheetah have developed new algorithms that allow the robot to detect and jump over obstacles. “Now that the Cheetah 2 is capable of trotting, galloping, and jumping, it might be time to crown a new king of the concrete jungle,” writes Franzen.

The robotic cheetah developed by MIT researchers is now capable of jumping over obstacles without human assistance, reports Nidhi Subbaraman for BetaBoston. “As the robot approaches and detects a hurdle, algorithms plan its jumping trajectory unaided by its minders, each adjusting for the speed and position of the robot and the height of the hurdle,” Subbaraman explains. 

Wired reporter Emily Dreyfuss writes about the MIT team competing in the DARPA Robotics Challenge and their approach to the competition. The team, which is competing using the Atlas robot designed by Boston Dynamics, has built their software so that Atlas can operate autonomously, Dreyfuss explains.  

Scott Kuindersma, a post-doctoral associate and Planning and Control Lead for the MIT DARPA Robotics Challenge team, spoke with Boston.com about the Atlas robot. “Walking robots are interesting for a lot of reasons,” says Kuindersma. “They have the promise of getting over challenging terrain that would stymie many track systems.”

Nidhi Subbaraman writes for BetaBoston about MIT’s Atlas robot ahead of its participation in an international competition hosted by the Defense Advanced Research Projects Agency (DARPA). “This is the most advanced, sophisticated machine I’ve ever worked on,” said team lead Professor Russ Tedrake.

Mo Costandi reports for The Guardian on how Prof. Polina Anikeeva has developed a new technique to activate brain cells using nanoparticles. Costandi explains that, “research like this may eventually allow for wireless and minimally invasive deep brain stimulation of the human brain.”

“A team of MIT researchers found that an existing computer vision system can achieve object recognition as well as humans and other primates,” writes Jamie Ducharme for Boston Magazine. Professor James DiCarlo’s team compared the visual recognition abilities of primates to those of the advanced computer system Super Vision.