Robotics & AI

The Berkeley-based startup is developing exciting new technology that is truly the stuff of comic books and, formerly, of science fiction. Specifically, the company is making wearable, artifi­cially intelligent bionic devices that it calls “exoskeletons”. This has taken shape in two significant forms: eLEGS and HULC. Both of which you can see (as well as an interview with Berkeley Bionics CEO Eythor Bender) in the accompanying video.

Researchers at the University of Pennsylvania are developing algorithms to enable robots to learn to read like a human toddler. Using a Willow Garage PR2 robot (nicknamed Graspy), the researchers demonstrate the ability for a robot to learn to read anything from simple signs to full-length warnings. Graspy recognizes the shapes of letters and associates them with sounds. Part of the computer vision challenge is reading hundreds of different fonts. More information is available in a Psyorg article and from the ROS website.

During the Google IO event, two new great features of the popular Android OS were announced. The most important from a robotics point of view is the Android Open Accessory standard that is Arduino based and enables Android devices to integrate with hardware via usb (or bluetooth in the near future). You can read more in the posts on engadget.com and robots-dreams.com (where the video is from). Also engadget reports on the Android @ Home framework that aspires to interconnect every home appliance, device or gadget to an integrated network. More information and details will be announced soon from Google but already the potential for various robotic applications that could take advantage of these projects looks promising.

Google announced at Google IO conference 2011 that they will supply Android@Home framework for home automation to developers, giving them the ability to think of "every appliance in your home" as a potential accessory for your phone. The Google team teased ideas like lights turning on and off based on calendar events, applications talking to washing machines, games automatically adjusting for mood lighting, and basically little green dudes taking care of all the menial duties in your house. One amazing demo was a concept, Android-powered device hub called Tungsten. Using RFID embedded into CD cases the device was able to detect the CD and add it to your library. Another touch and it started automatically.

This is Treebot. As you might expect, Treebot was designed to do one thing: climb trees. It is by no means the first robot able to do this, but its arboreal predecessors (RiSE and Modsnake and accidentally PackBot are just a few) weren't autonomous and didn't have the skills necessary to negotiate the complex network of branches that you tend to find on trees worth climbing.

This video from PAL Robotics shows the teleoperation system of its REEM robot. Equipped with a Kinect sensor as a motion capture device, a laptop captures the gestures and movements of a person and feeds the result to the robot as commands. This process is called motion retargeting and the teleoperation system was developed by Marcus Liebhardt as part of his master thesis project. PAL Robotics is a small Spanish company based in Barcelona, part of the PAL Group from Abu Dhabi. It develops humanoid robots since 2004 and its latest version of the REEM line of robots focuses towards commercial applications.

Back in 2008, IBM announced their plan to try and create a computer that more accurately imitated the computing process of the human brain. Now, with a little help from 4 research Universities and DARPA, they’ve produced prototypes of the first few chips and are on the way to building their first, full-fledged robo-brain. If you’re going to run for the hills, now would be a good time to start. The project’s goal is to drastically alter the way in which computers compute by changing their structure to mimic the human brain instead of functioning as calculators. You see, most computers are von Neumann machines, meaning that the memory and processor are separated. The practical result of this is that as you reach the limit of how fast information can be passed from the memory to the processor via the bus, you reach the limit of computing power. In the human brain, the memory and the processors are in thousands of nodes that communicate slower, but simultaneously and radially. IBM’s prototypes are chips that, in quantity, can emulate those nodes.

Back in 2008, IBM announced their plan to try and create a computer that more accurately imitated the computing process of the human brain. Now, with a little help from 4 research Universities and DARPA, they’ve produced prototypes of the first few chips and are on the way to building their first, full-fledged robo-brain. If you’re going to run for the hills, now would be a good time to start. The project’s goal is to drastically alter the way in which computers compute by changing their structure to mimic the human brain instead of functioning as calculators. You see, most computers are von Neumann machines, meaning that the memory and processor are separated. The practical result of this is that as you reach the limit of how fast information can be passed from the memory to the processor via the bus, you reach the limit of computing power. In the human brain, the memory and the processors are in thousands of nodes that communicate slower, but simultaneously and radially. IBM’s prototypes are chips that, in quantity, can emulate those nodes.

So after all that you are probably asking, “What is SimpleCV?” It is an open source computer vision framework that lowers the barriers to entry for people to learn, develop, and use it across the globe. Currently there are a few open source vision system libraries in existence, but the downside to these is you have to be quite the domain expert and knowledgeable with vision systems as well as know cryptic programming languages like C. Where SimpleCV is different, is it is “simple”. It has been designed with a web browser interface, which is familiar to Internet users everywhere. It will talk to your webcam (which most computers and smart phones have built in) automatically. It works cross platform (Windows, Mac, Linux, etc). It uses the programming language Python rather than C to greatly lower the learning curve of the software. It sacrifices some complexity for simplicity, which is needed for mass adoption of any type of new technology.

IROS 2011 takes place later this month in San Francisco (25th ~ 30th), and as usual there’s so many interesting projects being presented that attendees won’t be able to see them all. We’ve looked at the schedule and will highlight some of them, beginning with this robot developed at the Graduate School of Information Science & Technology, The University of Tokyo, Japan.

Using robots, the two ETH architects, who run the Gramazio & Kohler design studio, have fabricated intricate building parts out of wood, concrete, bricks, and foam, and have used these parts to build complex, beautiful installations in Zurich, London, Barcelona, New York, and other locations.

Android Robotics Projects

Setting up a development environment ready for Android robotics code Learning how to program for the AVR microcontroller Connecting servos and sensors Home-brewing your own PCB design, and choosing PCB suppliers Mounting the phone as a robot brain and teaching the robot to obey touch commands Approaching and designing different robot architectures