Tag Archives: dexterous hand

#437859 We Can Do Better Than Human-Like Hands ...

Posted on December 2, 2020 by Android

One strategy for designing robots that are capable in anthropomorphic environments is to make the robots themselves as anthropomorphic as possible. It makes sense—for example, there are stairs all over the place because humans have legs, and legs are good at stairs, so if we give robots legs like humans, they’ll be good at stairs too, right? We also see this tendency when it comes to robotic grippers, because robots need to grip things that have been optimized for human hands.

Despite some amazing robotic hands inspired by the biology of our own human hands, there are also opportunities for creativity in gripper designs that do things human hands are not physically capable of. At ICRA 2020, researchers from Stanford University presented a paper on the design of a robotic hand that has fingers made of actuated rollers, allowing it to manipulate objects in ways that would tie your fingers into knots.

While it’s got a couple fingers, this prototype “roller grasper” hand tosses anthropomorphic design out the window in favor of unique methods of in-hand manipulation. The roller grasper does share some features with other grippers designed for in-hand manipulation using active surfaces (like conveyor belts embedded in fingers), but what’s new and exciting here is that those articulated active roller fingertips (or whatever non-anthropomorphic name you want to give them) provide active surfaces that are steerable. This means that the hand can grasp objects and rotate them without having to resort to complex sequences of finger repositioning, which is how humans do it.

Photo: Stanford University

Things like picking something flat off of a table, always tricky for robotic hands (and sometimes for human hands as well), is a breeze thanks to the fingertip rollers.

Each of the hand’s fingers has three actuated degrees of freedom, which result in several different ways in which objects can be grasped and manipulated. Things like picking something flat off of a table, always tricky for robotic hands (and sometimes for human hands as well), is a breeze thanks to the fingertip rollers. The motion of an object in this gripper isn’t quite holonomic, meaning that it can’t arbitrarily reorient things without sometimes going through other intermediate steps. And it’s also not compliant in the way that many other grippers are, limiting some types of grasps. This particular design probably won’t replace every gripper out there, but it’s particularly skilled at some specific kinds of manipulations in a way that makes it unique.

We should be clear that it’s not the intent of this paper (or of this article!) to belittle five-fingered robotic hands—the point is that there are lots of things that you can do with totally different hand designs, and just because humans use one kind of hand doesn’t mean that robots need to do the same if they want to match (or exceed) some specific human capabilities. If we could make robotic hands with five fingers that had all of the actuation and sensing and control that our own hands do, that would be amazing, but it’s probably decades away. In the meantime, there are plenty of different designs to explore.

And speaking of exploring different designs, these same folks are already at work on version two of their hand, which replaces the fingertip rollers with fingertip balls:

For more on this new version of the hand (among other things), we spoke with lead author Shenli Yuan via email. And the ICRA page is here if you have questions of your own.

IEEE Spectrum: Human hands are often seen as the standard for manipulation. When adding degrees of freedom that human hands don’t have (as in your work) can make robotic hands more capable than ours in many ways, do you think we should still think of human hands as something to try and emulate?

Shenli Yuan: Yes, definitely. Not only because human hands have great manipulation capability, but because we’re constantly surrounded by objects that were designed and built specifically to be manipulated by the human hand. Anthropomorphic robot hands are still worth investigating, and still have a long way to go before they truly match the dexterity of a human hand. The design we came up with is an exploration of what unique capabilities may be achieved if we are not bound by the constraints of anthropomorphism, and what a biologically impossible mechanism may achieve in robotic manipulation. In addition, for lots of tasks, it isn’t necessarily optimal to try and emulate the human hand. Perhaps in 20 to 50 years when robot manipulators are much better, they won’t look like the human hand that much. The design constraints for robotics and biology have points in common (like mechanical wear, finite tendons stiffness) but also major differences (like continuous rotation for robots and less heat dissipation problems for humans).

“For lots of tasks, it isn’t necessarily optimal to try and emulate the human hand. Perhaps in 20 to 50 years when robot manipulators are much better, they won’t look like the human hand that much.”
—Shenli Yuan, Stanford University

What are some manipulation capabilities of human hands that are the most difficult to replicate with your system?

There are a few things that come to mind. It cannot perform a power grasp (using the whole hand for grasping as opposed to pinch grasp that uses only fingertips), which is something that can be easily done by human hands. It cannot move or rotate objects instantaneously in arbitrary directions or about arbitrary axes, though the human hand is somewhat limited in this respect as well. It also cannot perform gaiting. That being said, these limitations exist largely because this grasper only has 9 degrees of freedom, as opposed to the human hand which has more than 20. We don’t think of this grasper as a replacement for anthropomorphic hands, but rather as a way to provide unique capabilities without all of the complexity associated with a highly actuated, humanlike hand.

What’s the most surprising or impressive thing that your hand is able to do?

The most impressive feature is that it can rotate objects continuously, which is typically difficult or inefficient for humanlike robot hands. Something really surprising was that we put most of our energy into the design and analysis of the grasper, and the control strategy we implemented for demonstrations is very simple. This simple control strategy works surprisingly well with very little tuning or trial-and-error.

With this many degrees of freedom, how complicated is it to get the hand to do what you want it to do?

The number of degrees of freedom is actually not what makes controlling it difficult. Most of the difficulties we encountered were actually due to the rolling contact between the rollers and the object during manipulation. The rolling behavior can be viewed as constantly breaking and re-establishing contacts between the rollers and objects, this very dynamic behavior introduces uncertainties in controlling our grasper. Specifically, it was difficult estimating the velocity of each contact point with the object, which changes based on object and finger position, object shape (especially curvature), and slip/no slip.

What more can you tell us about Roller Grasper V2?

Roller Grasper V2 has spherical rollers, while the V1 has cylindrical rollers. We realized that cylindrical rollers are very good at manipulating objects when the rollers and the object form line contacts, but it can be unstable when the grasp geometry doesn’t allow for a line contact between each roller and the grasped object. Spherical rollers solve that problem by allowing predictable points of contact regardless of how a surface is oriented.

The parallelogram mechanism of Roller Grasper V1 makes the pivot axis offset a bit from the center of the roller, which made our control and analysis more challenging. The kinematics of the Roller Grasper V2 is simpler. The base joint intersects with the finger, which intersects with the pivot joint, and the pivot joint intersects with the roller joint. It’s symmetrical design and simpler kinematics make our control and analysis a lot more straightforward. Roller Grasper V2 also has a larger pivot range of 180 degrees, while V1 is limited to 90 degrees.

In terms of control, we implemented more sophisticated control strategies (including a hand-crafted control strategy and an imitation learning based strategy) for the grasper to perform autonomous in-hand manipulation.

“Design of a Roller-Based Dexterous Hand for Object Grasping and Within-Hand Manipulation,” by Shenli Yuan, Austin D. Epps, Jerome B. Nowak, and J. Kenneth Salisbury from Stanford University is being presented at ICRA 2020.

< Back to IEEE Journal Watch Continue reading →

Posted in Human Robots

#433506 MIT’s New Robot Taught Itself to Pick ...

Posted on September 18, 2018 by Android

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 →

Posted in Human Robots