Google Tasks Robots with Learning Skills from One Another via Cloud Robotics
Steve Arar for All About Circuits: Humans use language to tap into the knowledge of others and learn skills faster. This helps us hone our intuition and go through our daily activities more efficiently. Inspired by this, Google Research, DeepMind (its UK artificial intelligence lab), and Google X have decided to allow their robots share their experiences. Sharing the learning process among multiple robots, the research team has considerably expedited general-purpose skill acquisition of robots.
Using an artificial neural network, we can teach a robot to achieve a goal by analyzing the result of its previous experiences. At first, the robot may seem to act randomly simply working based on trial and error. However, it examines the result of each trial and, if satisfactory, focuses on similar experiments during the next trials. Making a connection between each experience and the obtained result, the robot would be able to gradually make better choices. Cont'd...
Mining 24 Hours a Day with Robots
Tom Simonite for MIT Technology Review: Each of these trucks is the size of a small two-story house. None has a driver or anyone else on board.
Mining company Rio Tinto has 73 of these titans hauling iron ore 24 hours a day at four mines in Australia’s Mars-red northwest corner. At this one, known as West Angelas, the vehicles work alongside robotic rock drilling rigs. The company is also upgrading the locomotives that haul ore hundreds of miles to port—the upgrades will allow the trains to drive themselves, and be loaded and unloaded automatically.
Rio Tinto intends its automated operations in Australia to preview a more efficient future for all of its mines—one that will also reduce the need for human miners. The rising capabilities and falling costs of robotics technology are allowing mining and oil companies to reimagine the dirty, dangerous business of getting resources out of the ground. Cont'd...
Amazon patents system to defend drones against hackers, jammers … and arrows
Alan Boyle for GeekWire: If there are any Robin Hoods out there who are thinking about shooting down drones while they’re making deliveries, Amazon has a patented plan to stop you.
The patent, filed in 2014 but published just last week, lays out countermeasures for potential threats ranging from computer hacking to lightning flashes to bows and arrows.
If nothing else, the 33-page application illustrates how many things could possibly go wrong with an autonomous navigation system for unmanned aerial vehicles, or UAVs.
The “compromise system” that Amazon’s engineers propose relies on an array of sensors to orient the drone based on the sun’s position in the sky, if need be. That’s in case the drone gets confused by, say, lightning or a muzzle flash. Cont'd.. .
The Aggressively Flying Quadrotor
Steve Arar for All About Circuits: Recently, Vijay Kumar’s lab at the University of Pennsylvania in cooperation with researchers from Qualcomm has unveiled a quadrotor which can fly aggressively through a window. You may think that you have seen similar robots before; however, there is a big difference between previously designed robots and this new technology.
Generally, to exhibit challenging maneuvers, a quadrotor depends on an array of cameras mounted on the walls and some external processors. The image captured by the cameras is processed and the outcome is delivered to the robot. The computer can issue precise commands and the only thing that the robot needs to do is to follow the orders. However, the new robot performs both the image capturing and processing onboard.
The quadrotor carries an IMU, a Qualcomm Snapdragon, and Hexagon DSP. With the onboard sensors and processors, the robot is able to perform localization, state estimation, and path planning autonomously. Cont'd...
Robotics Veteran Raises Venture Capital to Build Exoskeleton
Alistair Blair for Bloomberg Technology: The word "robot" conjures images of bulky, metal humanoid objects moving awkwardly. Robotics veteran Rich Mahoney is trying to change that perception by creating a robotic exoskeleton people can wear.
After more than seven years running a robotics group at Silicon Valley research institution SRI International, Mahoney left about a year ago to form a startup called Superflex. On Tuesday, the company said it raised $9.6 million from investors including Japanese venture capital group Global Brain and Horizons Ventures, the VC fund of Asian billionaire Li Ka-shing.
Superflex is developing a lightweight suit with electric "muscles" that help the elderly and other less-mobile people move around. The system, which will look a bit like a unitard, is designed to provide the wearer with extra strength to get up from a chair or stand for longer. The device has thin actuators built in that use battery power to contract at the same time as people's real muscles. Cont'd...
A Robotics ETF Tries to Find its Way
Brenton Garen for ETF Trends: This year has seen another crowded field of new exchange traded funds come to market and within that group are plenty of niche funds, indicating that ETF issuers continue to slice and dice investment ideas into increasingly fine fund packages.
The Global X Robotics & Artificial Intelligence Thematic ETF (NasdaqGM: BOTZ) is one of those niche funds. BOTZ provides exposure to companies involved in the adoption and utilization of robotics and artificial intelligence (AI), including those involved with industrial manufacturing, medicine, autonomous vehicles, and other applications.
BOTZ follows the Indxx Global Robotics & Artificial Intelligence Thematic Index. The ETF, which debuted in September with the Global X FinTech Thematic ETF (NasdaqGM: FINX) and the Global X Internet of Things Thematic ETF (NasdaqGM: SNSR), holds 28 stocks with an average market cap of $8.8 billion, putting the ETF in mid-cap territory. Cont'd...
Engineers Devise New Method to Heighten Senses of Soft Robot
Written by AZoRobotics: Most robots achieve grasping and tactile sensing through motorized means, which can be excessively bulky and rigid. A Cornell group has devised a way for a soft robot to feel its surroundings internally, in much the same way humans do.
A group led by Robert Shepherd, assistant professor of mechanical and aerospace engineering and principal investigator of Organic Robotics Lab, has published a paper describing how stretchable optical waveguides act as curvature, elongation and force sensors in a soft robotic hand.
Doctoral student Huichan Zhao is lead author of “Optoelectronically Innervated Soft Prosthetic Hand via Stretchable Optical Waveguides,” which is featured in the debut edition of Science Robotics. The paper published Dec. 6; also contributing were doctoral students Kevin O’Brien and Shuo Li, both of Shepherd’s lab. Cont'd.. .
MIT's Modular Robotic Chain Is Whatever You Want It to Be
Evan Ackerman for IEEE Spectrum: As sensors, computers, actuators, and batteries decrease in size and increase in efficiency, it becomes possible to make robots much smaller without sacrificing a whole lot of capability. There’s a lower limit on usefulness, however, if you’re making a robot that needs to interact with humans or human-scale objects. You can continue to leverage shrinking components if you make robots that are modular: in other words, big robots that are made up of lots of little robots.
In some ways, it’s more complicated to do this, because if one robot is complicated, robots tend to be complicated. If you can get all of the communication and coordination figured out, though, a modular system offers tons of advantages: robots that come in any size you want, any configuration you want, and that are exceptionally easy to repair and reconfigure on the fly.
MIT’s ChainFORM is an interesting take on this idea: it’s an evolution of last year’s LineFORM multifunctional snake robot that introduces modularity to the system, letting you tear of a strip of exactly how much robot you need, and then reconfigure it to do all kinds of things. Cont'd...
Boeing buys Liquid Robotics to boost autonomous surveillance at sea
Alan Boyle for Geekwire: The Boeing Co. says it has agreed to acquire Liquid Robotics, its teammate in a years-long effort to create surfboard-sized robots that can use wave power to roam the seas.
The acquisition is expected to help Boeing create military communication networks that can transmit information autonomously from the sea to satellites via Sensor Hosting Autonomous Remote Craft, or SHARCs.
Liquid Robotics was founded in 2007 and currently has about 100 employees in California and Hawaii. Once the deal is completed, the company will become a subsidiary of Boeing. The arrangement is similar to the one that applies to Insitu, a Boeing subsidiary that is headquartered in Bingen, Wash., and manufactures ScanEagle military-grade drones. Cont'd...
Robots won't kill the workforce. They'll save the global economy.
Ruchir Sharma for The Washington Post: The United Nations forecasts that the global population will rise from 7.3 billion to nearly 10 billion by 2050, a big number that often prompts warnings about overpopulation. Some have come from neo-Malthusians, who fear that population growth will outstrip the food supply, leaving a hungry planet. Others appear in the tirades of anti-immigrant populists, invoking the specter of a rising tide of humanity as cause to slam borders shut. Still others inspire a chorus of neo-Luddites, who fear that the “rise of the robots” is rapidly making human workers obsolete, a threat all the more alarming if the human population is exploding.
Before long, though, we’re more likely to treasure robots than to revile them. They may be the one thing that can protect the global economy from the dangers that lie ahead. Cont'd...
Metallic glass gears make for graceful robots
Science Daily: Throw a baseball, and you might say it's all in the wrist. For robots, it's all in the gears.
Gears are essential for precision robotics. They allow limbs to turn smoothly and stop on command; low-quality gears cause limbs to jerk or shake. If you're designing a robot to scoop samples or grip a ledge, the kind of gears you'll need won't come from a hardware store.
At NASA's Jet Propulsion Laboratory in Pasadena, California, technologist Douglas Hofmann and his collaborators are building a better gear. Hofmann is the lead author of two recent papers on gears made from bulk metallic glass (BMG), a specially crafted alloy with properties that make it ideal for robotics. Cont'd...
Stanford study concludes next generation of robots won't try to kill us
Bruce Brown for DigitalTrends: It sounds like we can all take a breath and forget about robot attacks occurring — at least anytime soon. Robots turning against their makers is a common theme in science fiction. However, there’s “no cause for concern that AI poses an imminent threat to humanity,” according to Fast Company, citing the first report from the One Hundred Year Study on Artificial Intelligence (AI100).
The Stanford University-hosted project represents a standing committee of AI scientists. The AI100 project is ongoing but will not issue reports annually — the next one will be published “in a few years.” The first report, Artificial Intelligence and Life in 2030, downloadable at this link, looks at how advances in AI will make a difference in the U.S. between now and 2030. Areas of change explored by the report include transportation, healthcare, education, the workplace, and policing and public safety. Cont'd...
Robotics entrepreneur unveils spider creation set to take gaming world by storm
David Clensy for Bristol Post: For Silas Adekunle, the fascination has always been about how the very best robotics learns from biology.
There is a twinkle in the eye of the 25-year-old Reach Robotics founder, as he introduces me to Mekamon – the spider-like robot with which he plans to transform the future of augmented reality gaming among techies around the world.
Silas only graduated from the University of the West of England in 2014, but is already employing 10 people in his rapidly growing tech company. Cont'd...
A new standard in robotics
Phys.org: On the wall of Aaron Dollar's office is a poster for R.U.R. (Rossum's Universal Robots), the 1920 Czech play that gave us the word "robot." The story ends with the nominal robots seizing control of the factory of their origin and then wiping out nearly all of humanity. Dollar, fortunately, has something more cheerful in mind for the future of human-robot relations.
He sees them as helpers in our daily lives—performing tasks like setting the table or assisting with the assembly of your new bookcase. But getting to the point where robots can work in the unstructured environment of our homes (as opposed to industrial settings) would take a major technological leap and a massive coordination of efforts from roboticists around the globe. The living room has been called the last frontier for robots—but first, the robotics community needs some standards that everyone can agree on.
Enter a suitcase-sized box containing 77 objects. It contains things like hammers, a cordless drill, a can of Spam and a nine-hole peg test. As ordinary as they may seem, these carefully curated household items could be the future of a new kind of standardization for robotics. Known as the Yale-CMU-Berkeley (YCB) Object and Model Set, the intent is to provide universal benchmarks for labs specializing in robotic manipulation and prosthetics around the world. Cont'd...
Innovative Machine Learning Training Method Opens New Possibilities for Artificial Intelligence
From AZoRobotics: As a result of a new machine learning algorithm formulated by engineering researchers Parham Aarabi (ECE) and Wenzhi Guo (ECE MASc 1T5) at University of Toronto, smartphones may soon be able to provide users with honest answers.
The researchers prepared an algorithm that was capable of learning directly from human instructions, instead of an existing set of examples, and surpassed conventional techniques of training neural networks by 160%.
But more astonishingly, their algorithm also surpassed its own training by 9% - it learned to identify hair in pictures with better reliability than that enabled by the training, signifying a major leap forward for artificial intelligence. Cont'd...
Records 76 to 90 of 243
First | Previous | Next | Last
Personal & Service Robots - Featured Product
Maplesoft - Free Whitepaper: Developing a Robot Model using System-Level Design
This paper uses NAO, the humanoid robot from Aldebaran Systems, to demonstrate how MapleSim can be used to develop a robot model, and how the model can be further analyzed using the symbolic computation engine within Maple.
