MIT researchers have created a system that aims to teach robots how to perform household chores by breaking down activities into simple steps, reports Sean Captain for Fast Company. Captain explains that in order to simplify each chore, the researchers, “identified sub-tasks to describe thousands of duties in settings such as kitchens, dining rooms, and home offices.”
Wired reporter Matt Simon writes that CSAIL researchers have developed a new virtual system that could eventually be used to teach robots how to perform household chores. Researchers hope the system could one day help robots, “learn to anticipate future actions and be able to change the environment for the human,” explains PhD student Xavier Puig.
MIT researchers have developed a virtual reality system that can train drones to fly faster while also avoiding obstacles, reports Lauren Barack for Salon. Barack explains that the “researchers are programming the drones so they think they're in a living room or bedroom while they fly. They virtually see obstacles around them, but those impediments aren't really there.”
MIT researchers have developed an algorithm that can accurately determine how many taxis a city needs, providing a way to reduce the number of cars on the road, according to Xinhua. “Using the new algorithm, they found the fleet size of cab-hailing service in New York could be cut down by about 30 percent in an optimal scenario.”
MIT researchers are using virtual reality to train autonomous drones to fly in a variety of environments, writes Steven Melendez for Fast Company. Future tests may train the drone to fly safely around humans “as if they were in the same area, enabling it to practice sharing a space without actually endangering any human lives,” Melendez notes.
Research scientist Bryan Reimer speaks to WBUR about the ramifications for the autonomous vehicle industry in response to the recent fatality caused by a self-driving Uber. “As we look forward…we need to work together in ways through policy, technology development, advocacy, to set a pathway to safety,” Reimer says.
Mashable highlights the robotic system, developed by researchers at MIT and Princeton, that can pick up, recognize, and place assorted objects. The researchers created an algorithm that allows the crane to “grab and sort objects (such as medicine bottles) into bins making it a potential timesaver for medical experts.”
A robotic carpenter developed by CSAIL is pre-cutting wood for flat-pack furniture, making assembly safer and more efficient. Called AutoSaw, the idea “was not to replace human carpenters but to allow them to focus on more important tasks such as design,” writes Dave Lee for the BBC.
David Grossman of Popular Mechanics writes about AutoSaw, a system developed by CSAIL researchers that assists in custom build carpentry projects. The system is designed “to split the difference between machine-built quality and unique customization” and requires human assembly after the pieces are cut, explains Grossman.
AutoSaw, developed in CSAIL, is “a new system of robot-assisted carpentry that could make the creation of custom furniture and fittings safer, easier, and cheaper,” writes James Vincent of The Verge. As postdoc Jeffrey Lipton explains, AutoSaw “shows how advanced robotics could fit into the workflow of a carpenter or joiner.”
Using a modified Roomba vacuum, CSAIL researchers are able to autonomously cut pieces of wood for assembling furniture, writes Leah Crane for New Scientist. “Two lifting robots pick up a piece of wood, bring it over to a chop saw, and hold it in place while the saw cuts it to size,” Crane explains.
Spencer Buell of Boston Magazine speaks with graduate student Joy Buolamwini, whose research shows that many AI programs are unable to recognize non-white faces. “‘We have blind faith in these systems,’ she says. ‘We risk perpetuating inequality in the guise of machine neutrality if we’re not paying attention.’”
Danny Crichton of TechCrunch highlights Media Lab researchers Kent Larson and John Clippinger, who are sorting socio-economic factors into datasets in order to create a model that can guide a community towards success. “Wouldn’t it be great to create an alternative where instead of optimizing for financial benefits, we could optimize for social benefits, and cultural benefits, and environmental benefits,” said Larson.
Researchers in CSAIL are developing a steering program for drones that allows them to process uncertainty and avoid hitting objects while flying autonomously. Called Nanomap, the drone uses depth measurements to determine the safest path. “This technique creates an on the fly map that lets the drone handle uncertainty as opposed to being ready in every situation,” writes John Biggs for TechCrunch.
CSAIL researchers have developed a new navigation method that allows drones to process less data, have faster reaction times, and dodge obstacles without creating a map of the environment they’re in, writes James Vincent of The Verge. “Because we’re not taking hundreds of measurements and fusing them together, it’s really fast,” said graduate student Peter Florence.