Last year, we reported that British researchers are using a Charles Babbage robot head to develop emotional machines. We wondered whether the Charles head was a Hanson Robotics creation. We now have the answer.
"Yes, Charles is a Hanson Robotics creation," David Hanson, founder and CTO of the company, tells us.
Hanson says they built the robot more than a year ago and he was pleased to see that the Cambridge researchers have put it to work. "I think they’re up to some good stuff," he says.
Above is an image of Charles at the Hanson robot factory.
Hanson also updated us on his company's latest developments -- they've been busy working on some new robots and updating old ones. These creations are incredible, and I can't decide where I'd put them in the uncanny valley chart.
First, there's Zeno. No, not the little Zeno. This is a big Zeno, modeled after Zeno of Elea, the mathematical philosopher who, as Hanson puts it, "introduced riddles of recursion that vexed the Greeks so terribly, and inspired [Douglas] Hofstadter so much that he included Zeno as a character in 'Gödel, Escher, Bach.' "
Here's a video, and there's a photo of it below as well:
Hanson has been putting a lot of effort on software, and the latest version has "features enabling common sense reasoning and learning," he says. "This is a collaboration of numerous groups through the Apollo Mind Initiative"—a nonprofit he helped found—"dedicated to helping institutions collaborate on realizing greater-than-human genius in machine intelligence."
The company has also just rebuilt their famed Philip K. Dick robot. The upgrade, commissioned by a Dutch public TV station working on a documentary about the author, is "more expressive and intelligent," Hanson says:
And I know you're wondering: What about the little Zeno? Hanson pointed us to this video from last year, and shared this bit of news: He expects the robot to be ready for a release to researchers in 2011, and consumers in 2012.
The pi4 Workerbot is a new industrial robot capable of using its two arms to perform a variety of handling, assembly, and inspection tasks. It's designed to work alongside human workers -- and the robot's LCD face even displays a broad smile when things are running smoothly.
One of the innovative things about the robot is its control system. The Workerbot, which made its debut at the Automatica show last June, relies on a method known as impedance control, which allows the robot's arms to cooperate as they handle objects, keeping forces at desired levels and adjusting to disturbances -- a crucial capability when it comes to bimanual manipulations.
With its human-inspired size and looks [see images above], the Workerbot is a far cry from traditional factory bots, especially those used by the auto industry.
That's not to say that the automotive industry hasn't been good to robotics. Quite the opposite. Thanks to car manufacturers, industrial robots evolved into fast, reliable, powerful, and precise machines. But there's a flip side to the story.
Traditional industrial robots are rather complex to integrate into existing manufacturing processes; deploying them at a factory is an arduous, costly, and time-consuming task. The robots are also difficult to reprogram when changes become necessary, and they can't safely share spaces with human workers.
This barrier to entry has kept small and medium companies in industrialized countries "robot-less" -- at a time when robots, more than ever, could boost productivity and ameliorate labor shortages. To automate their production lines, which often include many different items manufactured in low volumes, these companies need robots that are inexpensive and intuitive, but still reliable and precise.
This is a promising, and potentially hugely lucrative, market that pi4_robotics and other companies -- including, it appears, Rodney Brooks' secretive start-up, Heartland Robotics -- want to explore.
The Workerbot's arms have seven degrees of freedom each (like humans arms), with grippers equipped with force sensors that can adjust the pressure that they apply. The head has two inspection cameras on the sides, a 3-D camera on the forehead, and a display screen that provides feedback to operators (a smile means all is okay; a frown indicates that something is wrong, or that the robot could work faster). The Workerbot is not a mobile robot, though human workers can use its wheeled base to move it manually.
Watch the robot in action:
According to Fraunhofer engineer Dragoljub Surdilovic, their approach to compliant control is what makes the Workerbot different from similar two-armed bots, like the Motoman SDA10D and the DLR/KUKA Justin humanoid.
"We created a new dual-arm programming language and environment that incorporate impedance control and make it easier to plan, program, and realize bimanual contact tasks," Surdilovic says.
Most industrial robots don't use impedance control, but rather they implement position control. In this approach, the robot tries to make its arms follow as closely as possible a series of positions in space. If the arms go off their trajectory, the motors try to bring them back on track.
The problem is, if you have two robots, or one robot with two arms, that need to collaborate and they are position controlled, coordinating their movements can be difficult. Imagine that the two arms are manipulating the same object. If at any point one of the arms becomes off-trajectory and starts pushing to get back on track, the other arm might go off-trajectory and start exerting forces as well.
Using impedance control, bimanual manipulation becomes much easier. The way this scheme works is the robot simulates a dynamic behavior for its arms that is different from the arms' intrinsic mechanical dynamics (which depends on its linkages, motors, and joints). The idea is to actuate the motors by simulating a mass-damper system. Imagine moving an object through a viscous liquid. The control system can adjust its parameters so you feel that you are moving a greater mass, for example, or add more damping so you don't overshoot when trying to bring the arm to a given position.
The upshot is that impedance control makes the arms capable of adjusting to errors and disturbances while at the same time keeping applied forces within desired limits.
This approach is also key to improve safety, because the robot won't push back if a person accidentally comes into contact with it. Indeed, the Workerbot meets the ISO 10218 norm for "inherent safe design of industrial robot." Another important benefit is that human operators can manually guide the robot arms to teach it an assortment of tasks, simplifying the programming process.
It will be interesting to compare the Workerbot to the Heartland Robotics system. Both companies seem to target assembly, handling, and inspection tasks. Whereas pi4_robotics claims that its bot will "help keep European production competitive," Heartland wants to "reinvigorate American manufacturing." The German firm plans to lease their robot for about 4,800 euros per month, and recentreports indicate that Heartland might sell its robot for US $5,000, although details are still murky.
One thing is certain: This is going to be an exciting chapter in robotics, and I'm looking forward to seeing how things will unfold -- and most important, whether these robots will help the many manufacturers that have long awaited for them.
We’ve been waiting for this moment for literally three years now. Keepon, everyone’s favorite yellow squishbot and arguably the world’s best robot dancer, is going to be available.
BeatBots, maker of the Keepon Pro (the $30,000 research Keepon) has partnered with the UK’s Wow! Stuff (who also made this) to create ‘My Keepon,’ a toy version of the Keepon that we know and love. From the press release:
Wow!’s design experts and robotics engineers, based in their recently-opened Los Angeles office, worked closely with BeatBots to design a toy that captured the essence of the Keepon character while replicating the robot’s most engaging interactive traits. These features include reactivity to touch and an amazing ability to listen to music, detect the beat, and dance in perfect rhythm!
But most importantly, Wow! Stuff and BeatBots are working to ensure that the success of My Keepon will directly support the social welfare goals at the heart of the Keepon story. “A percentage of the pro¿t from each My Keepon will go towards subsidizing and donating BeatBots’ research-grade robots to therapists and researchers,” said Taylor. “We are so proud to make Keepon available to a broader audience, and we will choose retail partners who also feel proud to sell him.”
Michalowski commented, “Our dream is to make Keepon Pro units widely available to researchers and practitioners. Our work with Keepon suggests that the character’s simplicity, combined with a caregiver’s ability to conduct mediated interactions through the robot, can facilitate social engagement in a novel and exciting way. We hope that the toy version of our robot can channel public excitement towards general autism awareness while supporting our distribution of tools and resources to people and organizations around the world working to understand and treat it.”
Sadly, these are all the details that I’ve got for you at the moment. I did talk with Dr. Michalowski a little bit about the toy, and I can say that they’re trying very hard to make sure that the core functionality (and look) that makes Keepon Pro so endearing will be there in the toy version. It’s easy to look at that $40 price point with concern, but I’m optimistic, and it’s also important to remember that commercializing My Keepon is going to help make Keepon Pro cheaper and more available to people who need it, so it’s good news for everyone.
My Keepon is still in the prototype stage, but we’ve been promised one of the first review units when they’re available, which means you’ll get the first look at them too. SWEET!
Silicon Valley start-up Anybots is announcing today that it has begun shipping its QB telepresence robot.
Customers who pre-ordered the US $15,000 QB robot will begin receiving it this week. Those who order today will receive their units in March, the company said.
Over the past year, several people and organizations have been beta testing the robot, providing feedback to the company. The beta testers include Carnegie Mellon University faculty and NASA executives.
Even I got to be a QB for a week last year -- and I have to say, showing up to work in a robot body is a pretty cool experience:
Now the initial beta-testing phase has ended, and after improving the QB design, Anybots is ready to ship the robot. And who's buying it? Alas, the company declined to name any customers who ordered this first batch of bots.
The QB model shipping now includes several new features. Now users controlling the robot can use high-definition zoom to get a closer look of people and objects. The robot is also capable of seamlessly switching from one Wi-Fi access point to another.
But the most important feature: Finally, QB is capable of two-way video streaming, with the face of the operator appearing on a small LCD display on the robot's head. This was a major limitation with the pre-production prototype I tested.
Needless to say, Anybots is pretty excited about the possibilities of robotic telepresence. Indeed, it's been a long journey for them, and I applaud their persistence in putting a sophisticated robot in the market.
"Everyone from a cookie manufacturer looking to manage remote factories to a CEO who simply can’t make it to every meeting in person--teleporting via an Anybot has already given these people a new perspective on work," Anybots founder and CEO Trevor Blackwell said in a statement.
"At first I thought the bot would pay for itself if it could just replace one international trip," said Phil Libin, founder and CEO of Evernote and one of the beta testers, "but now I realize that the real value is letting me preserve spontaneous interactions at the office even when I'm thousands of miles away."
The European project SARTRE focuses on an alternative to single, completely autonomous vehicles such as those developed at Google by Sebastian Thrun or those of the autonomous taxi developed by the AutoNOMOS Project or by the MadeInGermany project, both by Raúl Rojas. Instead, SARTRE develops road trains - convoys of vehicles that autonomously follow a lead vehicle driven by a professional driver.
Such vehicle platoons function much like an improved version of adaptive cruise control, matching a car's movements to the distance, speed, and the direction of the car in front. Once in a platoon, this allows drivers to relax and do other things like reading or even taking a nap while the platoon drives toward its long distance destination.
SARTRE has now shown what this could look like in a real-world demonstration of a single autonomous car following a human-driven test vehicle in highway conditions (video above).
"We are very pleased to see that the various systems work so well together already the first time,” says Erik Coelingh, engineering specialist at Volvo Cars. “After all, the systems come from seven SARTRE-member companies in four countries. The winter weather provided some extra testing of cameras and communication equipment.”
The project participants hope that platooning will not only improve road safety, but also drastically reduce fuel consumption, cutting it by up to 20%, with a similar cut in emissions. In addition, platooning is expected to reduce traffic congestion, because it will allow cars to travel at highway speeds with only a few meters between them.
The researchers and their industrial partners expect the technology to be ready for production in a few years. The biggest remaining hurdles are no longer technological, but legal and social: Not sure I'd feel safe taking my hands off the wheel and foot off the brakes when going 130km/h and driving only 5 meters behind a truck.
The insane epicness of this movie cannot possibly be overstated. And somehow, the fact that it’s overdubbed in Russian makes it just that much more awesome. It’s called "Enthiran," or "Robot," and if you get a copy, send it to me. Immediately.
Update: the full movie is here on YouTube (all 2+ hours of it), with English captions!
Remember how RoboCup keeps saying that they’ll have a team of fully autonomous humanoids ready to take on BrazilItaly Spain (or whoever) by 2050? RoMeLa’s CHARLI could be the progenitor of those eventual champions, as it’ll be competing in the humanoid adult class at RoboCup 2011. Adult class means that CHARLI is more or less the size of a person; it’s 4 foot 7 which I think is slightly taller than Diego Maradona.
Also heading to RoboCup 2011 from RoMeLa is Team DARwIn and their (slightly smaller) autonomous humanoids:
Not bad, I’d say, and I especially liked those two what I’m going to assume were deliberate fake-outs at the end there. You had me fooled, you tricky little robot you!
Harvest is not your typical robotics start up. For a start, the experience of the founding and management team is unusual for any start up, and truly exceptional in the very young industry of autonomous robotics. Joe Jones alone has more than 24 years of robotics experience. As the first employee of iRobot, he invented the Roomba vacuum cleaning robot, which to date has sold in more than 3 million units, and next to numerous research articles, Jones has also authored three books on robotics, and holds 15 patents. Also, unlike most start ups, the Harvest team had no particular product or application in mind when they first got together in 2007 under the initial name Q-Robotics. Instead, they went on an extended fact-finding mission about possible markets for a robot "one step beyond the Roomba".
What they've come up with is surprising. Agriculture may not seem like the easiest way to start: it's an outdoor application which means dealing with rain, mud, and temperature variations, environments are typically very unstructured, your typical user is unlikely to be highly skilled in software or automation, and tasks are normally accomplished using big machinery - all very different from the Roomba. However, Harvest has found a niche application which eliminates at least two of these challenges and which - they hope - can act as a stepping stone.
Harvest is targeting wholesale shrub farms as the one in the image above, which can have as many as 3 million containers of ornamental plants in 500 acres. Their robots lift and move the plants to perform tasks like spacing potted plants in grids - an operation that has to be repeated as plants grow, to efficiently use space at first, and then again to avoid that they grow into each other. The current human workers will essentially serve as supervisors to Harvest’s robots - they still give direction at a high level, but the machines are doing the heavy lifting. First trials have proven very successful, and the team is now working on a production version.
The Robots podcast interview with Joe Jones gives a deep insight into what it takes to bridge the gap between academia and industry. Jones explains more about the how's and why's of Harvest Automation, why moving potted plants is the next logical step after the Roomba and how they plan to tap into a potentially huge market for autonomous robots.
The DLR hand has the shape and size of a human hand, with five articulated fingers powered by a web of 38 tendons, each connected to an individual motor on the forearm.
The main capability that makes the DLR hand different from other robot hands is that it can control its stiffness. The motors can tension the tendons, allowing the hand to absorb violent shocks. In one test, the researchers hit the hand with a baseball bat—a 66 G impact. The hand survived.
The video below shows the fingers moving and the hand getting hit by a hammer and a metal bar:
The DLR team didn’t want to build an anatomically correct copy of a human hand, as other teams have. They wanted a hand that can perform like a human hand both in terms of dexterity and resilience.
The hand has a total of 19 degrees of freedom, or only one less than the real thing, and it can move the fingers independently to grasp varied objects. The fingers can exert a force of up to 30 newtons at the fingertips, which makes this hand also one of the strongest ever built.
Another key element in the DLR design is a spring mechanism connected to each tendon. These springs [photo left] give the tendons, which are made from a super strong synthetic fiber called Dyneema, more elasticity, allowing the fingers to absorb and release energy, like our own hands do. This capability is key for achieving robustness and for mimicking the kinematic, dynamic, and force properties of the human hand.
During normal operation, the finger joints can turn at about 500 degrees per second. By tensioning the springs, and then releasing their energy to produce extra torque, the joint speed can reach 2000 degrees per second. This means that this robot hand can do something few others, if any, can: snap its fingers.
Why build such a super strong hand?
Markus Grebenstein, the hand's lead designer, says that existing robot hands built with rigid parts, despite their Terminator-tough looks, are relatively fragile. Even small collisions, with forces of a few tens of newtons, can dislodge joints and tear fingers apart.
“If every time a robot bumps its hand, the hand gets damaged, we’ll have a big problem deploying service robots in the real world,” Grebenstein says.
To change its stiffness, the DLR hand uses an approach known as antagonistic actuation. The joints of each finger [photo below] are driven by two tendons, each attached to one motor. When the motors turn in the same direction, the joint moves; when they turn in opposite directions, the joint stiffens.
Other hands, such as the Shadow hand designed in the U.K., also use antagonistic actuation. But the Shadow uses pneumatic artificial muscles, which have limitations in how much they can vary their stiffness.
Before developing the new hand, Grebenstein designed the hand of another advanced robot, the humanoid Justin. He says that in one experiment they would throw heavy balls and have Justin try to catch them. “The impact would strain the joints beyond their limits and kill the fingers,” he says.
The new hand can catch a ball thrown from several meters away. The actuation and spring mechanisms are capable of absorbing the kinetic energy without structural damages.
But the hand can’t always be in a stiff mode. To do manipulation tasks that require accuracy, it’s better to have a hand with low stiffness. By adjusting the tendon motors, the DLR hand can do just that.
To operate the hand, the researchers use special sensor gloves or simply send grasping commands. The control system is based on monitoring the joint angles. It doesn’t need to do impedance control, Grebenstein says, because the hand has compliance within the mechanics.
To detect whether an object is soft and must be handled more gently, the hand measures force by keeping track of the elongation of the spring mechanisms.
“In terms of grasping and dexterity, we’re quite close to the human hand,” he says, adding that the new hand is “miles ahead” of Justin’s hands.
About 13 people have worked on the hand, and Grebenstein insists it’s hard to estimate the cost of the project. But he says that the hardware for one hand would cost between 70,000 and 100,000 euros.
The researchers are now building a complete two-arm torso called the DLR Hand Arm System. Their plan is to study innovative grasping and manipulation strategies, including bimanual manipulations.
Grebenstein hopes that their new approach to hand design will help advance the field of service robots. He says that current robot hardware has limited new developments, because it's costly and researchers can't afford to do experiments that might damage them.
“The problem is," he says, "you can’t learn without experimenting.”
In the first “Matrix” movie, there’s a scene where Neo points to a helicopter on a rooftop and asks Trinity, “Can you fly that thing?” Her answer: “Not yet.” Then she gets a “pilot program” uploaded to her brain and they fly away.
For us humans, with our non-upgradeable, offline meat brains, the possibility of acquiring new skills by connecting our heads to a computer network is still science fiction. Not so for robots.
Several research groups are exploring the idea of robots that rely on cloud-computing infrastructure to access vast amounts of processing power and data. This approach, which some are calling "cloud robotics," would allow robots to offload compute-intensive tasks like image processing and voice recognition and even download new skills instantly, Matrix-style.
Imagine a robot that finds an object that it's never seen or used before—say, a plastic cup. The robot could simply send an image of the cup to the cloud and receive back the object’s name, a 3-D model, and instructions on how to use it, says James Kuffner, a professor at Carnegie Mellon currently working at Google.
Kuffner described the possibilities of cloud robotics at the IEEE International Conference on Humanoid Robots, in Nashville, Tenn., this past December. Embracing the cloud could make robots “lighter, cheaper, and smarter,” he said in his talk, which created much buzz among attendees.
For conventional robots, every task—moving a foot, grasping an object, recognizing a face—requires a significant amount of processing and preprogrammed information. As a result, sophisticated systems like humanoid robots need to carry powerful computers and large batteries to power them.
According to Kuffner, cloud-enabled robots could offload CPU-heavy tasks to remote servers, relying on smaller and less power-hungry onboard computers. Even more promising, the robots could turn to cloud-based services to expand their capabilities.
As an example, he mentioned the Google service known as Google Goggles. You snap a picture of a painting at a museum or a public landmark and Google sends you information about it. Now imagine a “Robot Goggles” application, Kuffner suggested; a robot would send images of what it is seeing to the cloud, receiving in return detailed information about the environment and objects in it.
Using the cloud, a robot could improve capabilities such as speech recognition, language translation, path planning, and 3D mapping.
The idea of connecting a robot to an external computer is not new. Back in the 1990s, Masayuki Inaba at the University of Tokyo explored the concept of a “remote brain,” as he called it, physically separating sensors and motors from high-level “reasoning” software.
Now cloud robotics seeks to push that idea to the next level, exploiting the cheap computing power and ubiquitous Net connectivity available today.
As a side project, he's now exploring a variety of cloud robotics ideas at Google, including "using small mobile devices as Net-enabled brains for robots,” he told me. "There is an active group of researchers here at Google who are interested in cloud robotics," he says.
But cloud robotics is not limited to smartphone robots. It could apply to any kind of robot, large or small, humanoid or not. Eventually, some of these robots could become more standardized, or de facto standards, and sharing applications would be easier. Then, Kuffner suggested, something even more interesting could emerge: an app store for robots.
The app paradigm is one of the crucial factors behind the success of Apple’s iPhone and Google’s Android. Applications that are easy to develop, install, and use are transforming personal computing. What could they do for robotics?
It’s too early to say. But at the Nashville gathering, attendees received Kuffner’s idea with enthusiasm.
“The next generation of robots needs to understand not only the environment they are in but also what objects exist and how to operate them,” says Kazuhito Yokoi, head of the Humanoid Research Group at Japan's National Institute of Advanced Industrial Science and Technology (AIST). “Cloud robotics could make that possible by expanding a robot’s knowledge beyond its physical body.”
“Coupling robotics and distributed computing could bring about big changes in robot autonomy,” said Jean-Paul Laumond, director of research at France’s Laboratory of Analysis and Architecture of Systems, in Toulouse. He says that it’s not surprising that a company like Google, which develops core cloud technologies and services, is pushing the idea of cloud robotics.
But Laumond and others note that cloud robotics is no panacea. In particular, controlling a robot’s motion—which relies heavily on sensors and feedback—won’t benefit much from the cloud. “Tasks that involve real time execution require onboard processing,” he says.
Stefan Schaal, a robotics professor at the University of Southern California, says that a robot may solve a complex path planning problem in the cloud, or possibly other optimization problems that do not require strict real-time performance, "but it will have to react to the world, balance on its feet, perceive, and control mostly out of local computation."
And there are other challenges. As any Net user knows, cloud-based applications can get slow, or simply become unavailable. If a robot relies too much on the cloud, a problem could make it "brainless."
Kuffner is optimistic that new advances will make cloud robotics a reality for many robots. He envisions a future when robots will feed data into a "knowledge database," where they'll share their interactions with the world and learn about new objects, places, and behaviors.
Maybe they'll even be able to download a helicopter pilot program?
Below are some other examples of cloud robotics projects:
• Researchers at Singapore's ASORO laboratory have built a cloud computing infrastructure to generate 3-D models of environments, allowing robots to perform simultaneous localization and mapping, or SLAM, much faster than by relying on their onboard computers. The backend system consists of a Hadoop distributed ¿le system that can store data from laser scanners, odometer data, or images/video streams from cameras. The researchers hope that, in addition to SLAM, the cluster could also perform sensor fusion and other computationally intensive algorithms.
• At LAAS, Florent Lamiraux , Jean-Paul Laumond, and colleagues are creating object databases for robots to simplify the planning of manipulation tasks like opening a door. The idea is to develop a software framework where objects come with a "user manual" for the robot to manipulate them. This manual would specify, for example, the position from which the robot should manipulate the object. The approach tries to break down the computational complexity of manipulation tasks into simpler, decoupled parts: a simpli¿ed manipulation problem based on the object's "user manual," and a whole-body motion generation by an inverse kinematics solver, which the robot's computer can solve in real time.
• Gostai, a French robotics firm, has built a cloud robotics infrastructure callled GostaiNet, which allows a robot to perform speech recognition, face detection, and other tasks remotely. The small humanoid Nao by Aldebaran Robotics will use GostaiNet to improve its interactions with children as part of research project at a hospital in Italy. And Gostai's Jazz telepresence robot uses the cloud for video recording and voice synthesis.
• At present the iCub humanoid project doesn't rely on "cloud robotics," but Giulio Sandini, a robotics professor at the Italian Institute of Technology and one of the project's leaders, says it's "a precursor of the idea." The iCub, an open child-sized humanoid platform, works as a "container of behaviors," Sandini says. "Today we share simple behaviors, but in the same way we could develop more complex ones like a pizza making behavior, and our French collaborators could develop a crepes making behavior." In principle, you'd just upload a "behavior app" to the robot and it would cook you pizzas or crepes.
[If you know of other cloud robotics projects, let me know.]