Tag Archives: hand
#433506 MIT’s New Robot Taught Itself to Pick ...
Back in 2016, somewhere in a Google-owned warehouse, more than a dozen robotic arms sat for hours quietly grasping objects of various shapes and sizes. For hours on end, they taught themselves how to pick up and hold the items appropriately—mimicking the way a baby gradually learns to use its hands.
Now, scientists from MIT have made a new breakthrough in machine learning: their new system can not only teach itself to see and identify objects, but also understand how best to manipulate them.
This means that, armed with the new machine learning routine referred to as “dense object nets (DON),” the robot would be capable of picking up an object that it’s never seen before, or in an unfamiliar orientation, without resorting to trial and error—exactly as a human would.
The deceptively simple ability to dexterously manipulate objects with our hands is a huge part of why humans are the dominant species on the planet. We take it for granted. Hardware innovations like the Shadow Dexterous Hand have enabled robots to softly grip and manipulate delicate objects for many years, but the software required to control these precision-engineered machines in a range of circumstances has proved harder to develop.
This was not for want of trying. The Amazon Robotics Challenge offers millions of dollars in prizes (and potentially far more in contracts, as their $775m acquisition of Kiva Systems shows) for the best dexterous robot able to pick and package items in their warehouses. The lucrative dream of a fully-automated delivery system is missing this crucial ability.
Meanwhile, the Robocup@home challenge—an offshoot of the popular Robocup tournament for soccer-playing robots—aims to make everyone’s dream of having a robot butler a reality. The competition involves teams drilling their robots through simple household tasks that require social interaction or object manipulation, like helping to carry the shopping, sorting items onto a shelf, or guiding tourists around a museum.
Yet all of these endeavors have proved difficult; the tasks often have to be simplified to enable the robot to complete them at all. New or unexpected elements, such as those encountered in real life, more often than not throw the system entirely. Programming the robot’s every move in explicit detail is not a scalable solution: this can work in the highly-controlled world of the assembly line, but not in everyday life.
Computer vision is improving all the time. Neural networks, including those you train every time you prove that you’re not a robot with CAPTCHA, are getting better at sorting objects into categories, and identifying them based on sparse or incomplete data, such as when they are occluded, or in different lighting.
But many of these systems require enormous amounts of input data, which is impractical, slow to generate, and often needs to be laboriously categorized by humans. There are entirely new jobs that require people to label, categorize, and sift large bodies of data ready for supervised machine learning. This can make machine learning undemocratic. If you’re Google, you can make thousands of unwitting volunteers label your images for you with CAPTCHA. If you’re IBM, you can hire people to manually label that data. If you’re an individual or startup trying something new, however, you will struggle to access the vast troves of labeled data available to the bigger players.
This is why new systems that can potentially train themselves over time or that allow robots to deal with situations they’ve never seen before without mountains of labelled data are a holy grail in artificial intelligence. The work done by MIT’s Computer Science and Artificial Intelligence Laboratory (CSAIL) is part of a new wave of “self-supervised” machine learning systems—little of the data used was labeled by humans.
The robot first inspects the new object from multiple angles, building up a 3D picture of the object with its own coordinate system. This then allows the robotic arm to identify a particular feature on the object—such as a handle, or the tongue of a shoe—from various different angles, based on its relative distance to other grid points.
This is the real innovation: the new means of representing objects to grasp as mapped-out 3D objects, with grid points and subsections of their own. Rather than using a computer vision algorithm to identify a door handle, and then activating a door handle grasping subroutine, the DON system treats all objects by making these spatial maps before classifying or manipulating them, enabling it to deal with a greater range of objects than in other approaches.
“Many approaches to manipulation can’t identify specific parts of an object across the many orientations that object may encounter,” said PhD student Lucas Manuelli, who wrote a new paper about the system with lead author and fellow student Pete Florence, alongside MIT professor Russ Tedrake. “For example, existing algorithms would be unable to grasp a mug by its handle, especially if the mug could be in multiple orientations, like upright, or on its side.”
Class-specific descriptors, which can be applied to the object features, can allow the robot arm to identify a mug, find the handle, and pick the mug up appropriately. Object-specific descriptors allow the robot arm to select a particular mug from a group of similar items. I’m already dreaming of a robot butler reliably picking my favourite mug when it serves me coffee in the morning.
Google’s robot arm-y was an attempt to develop a general grasping algorithm: one that could identify, categorize, and appropriately grip as many items as possible. This requires a great deal of training time and data, which is why Google parallelized their project by having 14 robot arms feed data into a single neural network brain: even then, the algorithm may fail with highly specific tasks. Specialist grasping algorithms might require less training if they’re limited to specific objects, but then your software is useless for general tasks.
As the roboticists noted, their system, with its ability to identify parts of an object rather than just a single object, is better suited to specific tasks, such as “grasp the racquet by the handle,” than Amazon Robotics Challenge robots, which identify whole objects by segmenting an image.
This work is small-scale at present. It has been tested with a few classes of objects, including shoes, hats, and mugs. Yet the use of these dense object nets as a way for robots to represent and manipulate new objects may well be another step towards the ultimate goal of generalized automation: a robot capable of performing every task a person can. If that point is reached, the question that will remain is how to cope with being obsolete.
Image Credit: Tom Buehler/CSAIL Continue reading
#432657 Video Friday: Cassie on Fire, ...
Your weekly selection of awesome robot videos Continue reading
#432572 Robots Can Swim, Fetch, Lift, and Dance. ...
Robotics has come a long way in the past few years. Robots can now fetch items from specific spots in massive warehouses, swim through the ocean to study marine life, and lift 200 times their own weight. They can even perform synchronized dance routines.
But the really big question is—can robots put together an Ikea chair?
A team of engineers from Nanyang Technological University in Singapore decided to find out, detailing their work in a paper published last week in the journal Science Robotics. The team took industrial robot arms and equipped them with parallel grippers, force-detecting sensors, and 3D cameras, and wrote software enabling the souped-up bots to tackle chair assembly. The robots’ starting point was a set of chair parts randomly scattered within reach.
As impressive as the above-mentioned robotic capabilities are, it’s worth noting that they’re mostly limited to a single skill. Putting together furniture, on the other hand, requires using and precisely coordinating multiple skills, including force control, visual localization, hand-eye coordination, and the patience to read each step of the manual without rushing through it and messing everything up.
Indeed, Ikea furniture, while meant to be simple and user-friendly, has left even the best of us scratching our heads and holding a spare oddly-shaped piece of wood as we stare at the desk or bed frame we just put together—or, for the less even-tempered among us, throwing said piece of wood across the room.
It’s a good thing robots don’t have tempers, because it took a few tries for the bots to get the chair assembly right.
Practice makes perfect, though (or in this case, rewriting code makes perfect), and these bots didn’t give up so easily. They had to hone three different skills: identifying which part was which among the scattered, differently-shaped pieces of wood, coordinating their movements to put those pieces in the right place, and knowing how much force to use in various steps of the process (i.e., more force is needed to connect two pieces than to pick up one piece).
A few tries later, the bots were able to assemble the chair from start to finish in about nine minutes.
On the whole, nicely done. But before we applaud the robots’ success too loudly, it’s important to note that they didn’t autonomously assemble the chair. Rather, each step of the process was planned and coded by engineers, down to the millimeter.
However, the team believes this closely-guided chair assembly was just a first step, and they see a not-so-distant future where combining artificial intelligence with advanced robotic capabilities could produce smart bots that would learn to assemble furniture and do other complex tasks on their own.
Future applications mentioned in the paper include electronics and aircraft manufacturing, logistics, and other high-mix, low-volume sectors.
Image Credit: Francisco Suárez-Ruiz and Quang-Cuong Pham/Nanyang Technological University Continue reading