In an episode of BBC Click, host Spencer Kelly visits CSAIL to learn about developments in robotics and deep learning algorithms. Kelly notes that CSAIL is, “at the forefront of robotics, building machines in shapes and sizes that challenge our very idea of what a robot is.”
This CNN video profiles the new Cheetah 3 robot, which can avoid obstacles and climb stairs without using external visual sensors. CNN notes that the cheetah, “relies on ‘feel’ in place of cameras or sensors, using ‘blind locomotion.’”
ABC News reporter Bopha Phorn writes about the latest iteration of a robotic cheetah developed by MIT researchers. Phorn explains that the researchers hope the cheetah will eventually be able to, “help some work that’s impossible for humans to do,” like search and rescue operations.
In this video, Reuters reporter Roselle Chen spotlights the Cheetah 3 robot, which utilizes two algorithms to run across rough terrain and maintain its balance without using cameras or sensors. Chen explains that the robot being able to navigate without cameras or sensors is like a human being able to walk around while its pitch black out.
MIT researchers have unveiled the latest iteration of their robotic cheetah that can navigate without the use of cameras or sensors and could be used for disaster response, reports Jordan Graham for The Boston Herald. “We’re mostly thinking about sending robots instead of humans where potential hazards like toxicity or radiation or dangers can be,” explains Prof. Sangbae Kim.
Writing for Popular Mechanics, Eric Limer highlights how the updated Cheetah 3 robot can navigate by feeling its way around its environment and can leap up onto tables. Limer explains that the robotic cheetah is, “able to rear back on its hind legs, leap into the air, and make a solid landing on a platform much taller than it is.”
TechCrunch reporter Brian Heater writes that Prof. Sangbae Kim and his research group robotic cheetah can now run up the stairs and walk over debris without the use of cameras or sensors. Heater explains that the robot, “utilizes a pair of new algorithms — contact detection and model-predictive control — which help it recover its balance in the case of slippage.”
CSAIL researchers have created a deep learning system that can isolate individual musical instruments in a video by clicking on the specific instrument, writes Andrew Liszewski for Gizmodo. The researchers suggest the system, “could be a vital tool when it comes to remixing and remastering older performances where the original recordings no longer exist,” explains Liszewski.
Researchers from MIT’s Little Devices Lab have developed Lego-like devices that can perform diagnostic tests, writes UPI reporter Allen Cone. The devices could significantly reduce the cost of diagnostic tests and as they don't require refrigeration or special handling, “they could be particularly useful in the developing world.”
Verge reporter Rachel Becker writes that MIT researchers have developed a robotic cheetah that can run up the stairs and navigate without the use of cameras. Becker explains that the Cheetah 3 robot navigates its environment by touch, which could allow it to, “venture where humans can’t — like deep inside power plants for inspections.”
MIT researchers have developed a new waterproof coating method that is safer for both the environment and humans, reports Brooks Hays for UPI. Lab tests showed the coating, “works to waterproof a variety of fabrics and materials against a variety of liquids,” Hays explains.
MIT researchers have created a new fabrication technique to create intricate, 3-D printed magnetic options that react to magnetic fields hitting them at different angles, reports Mark Wilson for Co.Design. In the future the structures, “could be placed in the human body, manipulated via wireless, harmless magnetism, and carry out intricate tasks like on-site drug delivery.”
This BBC Click segment highlights the artificial intelligence system developed by CSAIL researchers that can monitor people’s movements through walls. Prof. Dina Katabi explains that the device helps preserve the privacy of those being monitored by separating and encrypting, “any identifiable information from the measurement.”
Wired reporter Aarian Marshall highlights how MIT is launching a new undergraduate major that will combine computer science and urban planning. Prof. Eran Ben-Joseph explains that the motivation for the major is studying how, “you make a better connection between the training and computation, and what the implication of the work will be, for communities, for policies.”
Fast Company reporter Steven Melendez writes that CSAIL researchers have created a new system that allows a robot to detect human brainwave patterns so it knows when it made a mistake. Melendez explains that, “Teaching robots to understand human nonverbal cues and signals could make them safer and more efficient at working with people.”