<div align="justify">Scientists have developed a new technology that enables machines to make sense of 3D objects in a richer and more human-like way, an advance that will make robots more suitable for daily chores.<br /><br />The new technology has the ability to both recognise something and fill in the blind spots in its field of vision, to reconstruct the parts it cannot see.<br /><br />"That has the potential to be invaluable in a lot of robotic applications," said Ben Burchfiel from Duke University in the US.<br /><br />A robot that clears dishes off a table, for example, must be able to adapt to an enormous variety of bowls, platters and plates in different sizes and shapes, left in disarray on a cluttered surface.<br /><br />Humans can glance at a new object and intuitively know what it is, whether it is right side up, upside down or sideways, in full view or partially obscured by other objects.<br /><br />Even when an object is partially hidden, we mentally fill in the parts we cannot see.<br /><br />The robot perception algorithm can simultaneously guess what a new object is, and how it is oriented, without examining it from multiple angles first. It can also "imagine" any parts that are out of view, researchers said.<br /><br />A robot with this technology would not need to see every side of a teapot, for example, to know that it probably has a handle, a lid and a spout, and whether it is sitting upright or off-kilter on the stove, they said.<br /><br />This is an important step towards robots that function alongside humans in homes and other real-world settings, which are less orderly and predictable than the highly controlled environment of the lab or the factory floor, Burchfiel said.<br /><br />Researchers trained their algorithm on a dataset of roughly 4,000 complete 3D scans of common household objects: an assortment of bathtubs, beds, chairs, desks, dressers, monitors, nightstands, sofas, tables and toilets.<br /><br />Each 3D scan was converted into tens of thousands of little cubes, or voxels, stacked on top of each other like LEGO blocks to make them easier to process.<br /><br />The algorithm learned categories of objects by combing through examples of each one and figuring out how they vary and how they stay the same, using a version of a technique called probabilistic principal component analysis, researchers said.<br /><br />When a robot spots something new - say, a bunk bed - it does not have to sift through its entire mental catalogue for a match. It learns, from prior examples, what characteristics beds tend to have, they said.<br /><br />Based on that prior knowledge, it has the power to generalise like a person would - to understand that two objects may be different, yet share properties that make them both a particular type of furniture. </div>
<div align="justify">Scientists have developed a new technology that enables machines to make sense of 3D objects in a richer and more human-like way, an advance that will make robots more suitable for daily chores.<br /><br />The new technology has the ability to both recognise something and fill in the blind spots in its field of vision, to reconstruct the parts it cannot see.<br /><br />"That has the potential to be invaluable in a lot of robotic applications," said Ben Burchfiel from Duke University in the US.<br /><br />A robot that clears dishes off a table, for example, must be able to adapt to an enormous variety of bowls, platters and plates in different sizes and shapes, left in disarray on a cluttered surface.<br /><br />Humans can glance at a new object and intuitively know what it is, whether it is right side up, upside down or sideways, in full view or partially obscured by other objects.<br /><br />Even when an object is partially hidden, we mentally fill in the parts we cannot see.<br /><br />The robot perception algorithm can simultaneously guess what a new object is, and how it is oriented, without examining it from multiple angles first. It can also "imagine" any parts that are out of view, researchers said.<br /><br />A robot with this technology would not need to see every side of a teapot, for example, to know that it probably has a handle, a lid and a spout, and whether it is sitting upright or off-kilter on the stove, they said.<br /><br />This is an important step towards robots that function alongside humans in homes and other real-world settings, which are less orderly and predictable than the highly controlled environment of the lab or the factory floor, Burchfiel said.<br /><br />Researchers trained their algorithm on a dataset of roughly 4,000 complete 3D scans of common household objects: an assortment of bathtubs, beds, chairs, desks, dressers, monitors, nightstands, sofas, tables and toilets.<br /><br />Each 3D scan was converted into tens of thousands of little cubes, or voxels, stacked on top of each other like LEGO blocks to make them easier to process.<br /><br />The algorithm learned categories of objects by combing through examples of each one and figuring out how they vary and how they stay the same, using a version of a technique called probabilistic principal component analysis, researchers said.<br /><br />When a robot spots something new - say, a bunk bed - it does not have to sift through its entire mental catalogue for a match. It learns, from prior examples, what characteristics beds tend to have, they said.<br /><br />Based on that prior knowledge, it has the power to generalise like a person would - to understand that two objects may be different, yet share properties that make them both a particular type of furniture. </div>