MIT engineers have developed a method that enables robots to make similarly intuitive, task-relevant decisions. The team’s new approach, named Clio, enables a robot to identify the parts of a scene that matter, given the tasks at hand. With Clio, a robot takes in a list of tasks described in natural language and, based on those tasks, it then determines the level of granularity required to interpret its surroundings and “remember” only the parts of a scene that are relevant.
New method enables robots to quickly map a scene
Helping robots zero in on the objects that matter
Photon momentum effectively turns indirect silicon into direct semiconductor
Optical properties of materials can be dramatically enhanced.
Antarctic Krill locks similar levels of carbon as mangroves
Unveiling the Carbon Storage Potential of Antarctic Krill
New catalyst produces methane using electricity
Methane that doesn’t contribute to global warming.
Cognitive changes linked to COVID-19 identified in study
Study highlights specific changes associated with COVID-19 in particular brain function
Researchers observed the formation of small water bubbles in real time
Scientists witnessed the merging of hydrogen and oxygen atoms.
The molecular map paves the way for improved food choices
A new map of the molecules in our food holds promise in nurturing optimal gut function and overall well-being.
Reactivating a specific memory circuit in mice
Findings could spur new ways to study and treat human memory loss.