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...

Irishman's soft robotics exosuit wins major tech award

Colm Gorey for SiliconRepublic:  Irishman Conor Walsh’s soft robotics exosuit was among the award winners at the recent Rolex Awards, due to the creator’s continuing efforts to develop tech for the benefit of humanity. Now in its 40th year, the Rolex Awards are part of an international philanthropic programme that supports new and ongoing projects by individuals taking on major challenges to benefit humankind. Hosted last night at a public awards ceremony in Los Angeles, the awards were presented to 10 laureates – including five young laureates – that included such wide-ranging topics as opthamology and agritech.   Cont'd...

Care-O-bot 4 celebrates its premiere as a shopping assistant

By Fraunhofer IPA via RoboHub:  In January 2015, Fraunhofer IPA presented a prototype of the “Care-O-bot 4” service robot. The charming helper is now proving its worth in the real world. “Paul” the robot has been greeting customers in Saturn-Markt Ingolstadt since the end of October 2016 and directing them towards their desired products. Care-O-bot 4, alias Paul, approaches Saturn customers and welcomes them to the store. If they ask him about a certain product, he accompanies the customer to the department and points them in the direction of the relevant shelf. As he indulges in small talk about the weather, or another subject, Paul turns out to be a most charming contact partner. However, he prefers to leave actual customer service to his human colleagues. Paul is able to call another member of staff for support via “Voice over IP”. Before Paul bids a fond farewell and returns to the store entrance, he still has time to ask for feedback. In this way, he discovers whether customers appreciated the interaction or not. Martin Wild, Chief Digital Officer at Media-Saturn-Holding: “With Paul, we are offering our customers the opportunity to get to know one of the most advanced robots in the world.”   Cont'd...

Relay Is a Robot Butler Coming to a Hotel Near You

Nathaniel Mott for Inverse:  Ordering room service can be a lesson in embarrassment. It could arrive right after you’ve taken off your clothes, while you’re indisposed, or while you’re in the middle of other hotel-related behavior.  Thankfully, a robot butler named Relay is here to take that embarrassment (and other inconveniences) out of hotel deliveries. Relay is basically an autonomous locker on wheels. Guests ask for an item, a hotel worker puts the object inside Relay’s compartment, and then the robot scoots over to the guest’s room with its cargo. It then calls the guests to let them know their item is ready before heading back down to the lobby so it can recharge before its next assignment.   Cont'd...

ASU Robot learns to shoot hoops

ASU Interactive Robotics Lab:  The video shows a bi-manual robot that learns to throw a ball into the hoop using reinforcement learning. A novel reinforcement learning algorithm "Sparse Latent Space Policy Search" allows the robot to learn the task within only about 2 hours. The robot repeatedly throws the ball and receives a reward based on the distance of the ball to the center of the hoop. Algorithmic details about the method can be found here: 

New US Robotics Roadmap calls for increased regulations, education and research

From Phys.org:  A new U.S. Robotics Roadmap released Oct. 31 calls for better policy frameworks to safely integrate new technologies, such as self-driving cars and commercial drones, into everyday life. The document also advocates for increased research efforts in the field of human-robot interaction to develop intelligent machines that will empower people to stay in their homes as they age. It calls for increased education efforts in the STEM fields from elementary school to adult learners The roadmap's authors, more than 150 researchers from around the nation, also call for research to create more flexible robotics systems to accommodate the need for increased customization in manufacturing, for everything from cars to consumer electronics The goal of the U.S. Robotics Roadmap is to determine how researchers can make a difference and solve societal problems in the United States. The document provides an overview of robotics in a wide range of areas, from manufacturing to consumer services, healthcare, autonomous vehicles and defense. The roadmap's authors make recommendation to ensure that the United States will continue to lead in the field of robotics, both in terms of research innovation, technology and policies.   Cont'd...

Swarm of Origami Robots Can Self Assemble Out of a Single Sheet

Evan Ackerman for IEEE Spectrum:  One of the biggest challenges with swarms of robots is manufacturing and deploying the swarm itself. Even if the robots are relatively small and relatively simple, you’re still dealing with a whole bunch of them, and every step in building the robots or letting them loose is multiplied over the entire number of bots in the swarm. If you’ve got more than a few robots to handle, it starts to get all kinds of tedious. The dream for swarm robotics is to be able to do away with all of that, and just push a button and have your swarm somehow magically appear. We’re not there yet, but we’re getting close: At IROS this month, researchers from the Wyss Institute for Biologically Inspired Engineering at Harvard presented a paper demonstrating an autonomous collective robotic swarm that can be manufactured in a single flat composite sheet. On command, they’ll rip themselves apart from each other, fold themselves up into origami structures, and head off on a mission en masse.   Cont'd...

Virtual Immortality: Reanimating characters from TV shows

From James Charles, Derek Magee, David Hogg: The objective of this work is to build virtual talking avatars of characters fully automatically from TV shows. From this unconstrained data, we show how to capture a character’s style of speech, visual appearance and language in an effort to construct an interactive avatar of the person and effectively immortalize them in a computational model. We make three contributions (i) a complete framework for producing a generative model of the audiovisual and language of characters from TV shows; (ii) a novel method for aligning transcripts to video using the audio; and (iii) a fast audio segmentation system for silencing nonspoken audio from TV shows. Our framework is demonstrated using all 236 episodes from the TV series Friends (≈ 97hrs of video) and shown to generate novel sentences as well as character specific speech and video... (full paper)  

As China Invests in Robotics, iRobot and Other Companies Eye Deals

Jeff Engel for Xconomy:  China emerged as a manufacturing powerhouse over the past few decades, thanks in large part to a deep pool of cheap labor. Now, the country is investing heavily in factory automation, and Boston-area robotics companies and their allies smell opportunity. Executives from 11 New England robotics firms will travel to several cities in China later this month on a trade mission aimed at sparking business deals and more technology collaboration between the U.S. and China. The trip is being organized by InTeahouse, along with local nonprofit robotics support group MassRobotics.    Cont'd... Full Press Release:

This Robot Can Do More Push-Ups Because It Sweats

Evan Ackerman for IEEE Spectrum:  When we use our muscles, they produce heat as a byproduct. When we use them a lot, we need to actively cool them, which is why we sweat. By sweating, we pump water out of our bodies, and as that water evaporates, it cools us down. Robots, especially dynamic robots like humanoids that place near-constant high torque demands on their motors, generate enough heat that it regularly becomes a major constraint on their performance. One of the reasons that SCHAFT did so well at the DRC Trials, for example, was their fancy liquid-cooled motors that could put out lots of torque over an extended period of time without overheating. Engineers solve this heat-generating problem in most mechanical systems by using fans, heat sinks, and radiators, which means that you’ve got all of this dedicated cooling infrastructure that takes up space and adds mass. At the IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) this week, Japanese researchers presented a novel idea of how to cool humanoid robots in a much more efficient way: Design them to be able to sweat water straight out of their bones.   Cont'd...

What Leading AI, Machine Learning And Robotics Scientists Say About The Future

Jason Lim for Forbes:  Every year there is a new hot topic in tech. Today, it’s all about artificial intelligence, machine learning, virtual reality and autonomous vehicles. The difference between now and the past is that everything is becoming interconnected at a faster rate. We are entering an extremely critical time in history where society will change dramatically – how we work, live and play. Science fiction is morphing into reality. Flying cars exist, cars that drive themselves are on the road, and artificial intelligence that automates our lives is here. To make all of this amazing science and technology happen, it takes some extremely intelligent and curious people. In many ways, scientists are still at the helm of discovering breakthroughs through research.    Cont'd...

Omnidirectional Mobile Robot Has Just Two Moving Parts

Byron Spice for Carnegie Mellon University:  More than a decade ago, Ralph Hollisinvented the ballbot, an elegantly simple robot whose tall, thin body glides atop a sphere slightly smaller than a bowling ball. The latest version, called SIMbot, has an equally elegant motor with just one moving part: the ball. The only other active moving part of the robot is the body itself.        The spherical induction motor (SIM) invented by Hollis, a research professor in Carnegie Mellon University's Robotics Institute, and Masaaki Kumagai, a professor of engineering at Tohoku Gakuin University in Tagajo, Japan, eliminates the mechanical drive systems that each used on previous ballbots. Because of this extreme mechanical simplicity, SIMbot requires less routine maintenance and is less likely to suffer mechanical failures.    Cont'd...

Reviving Japan's Dairy Industry, One Milking Robot at a Time

Aya Takada for Bloomberg:  Jin Kawaguchiya gave up a career in finance to help revive Japan’s ailing dairy industry -- one robot at a time. In a country that relies increasingly on imported foods like cheese and butter, Japan’s milk output tumbled over two decades, touching a 30-year low in 2014. Costs rose faster than prices as the economy stagnated, eroding profit, and aging farmers quit the business because they couldn’t find enough young people willing to take on the hard labor of tending to cows every day. But technology is altering that dynamic. On the northern island of Hokkaido, Japan’s top dairy-producing region, Kawaguchiya transformed the 20-cow farm he inherited from his father-in-law 16 years ago into Asia’s largest automated milking factory. Robots extract the white fluid from 360 cows three times a day and make sure the animals are fed and healthy. The machines even gather up poop and deposits it in a furnace that generates electricity.   Cont'd...

Could the future of pizza be in the hands of robots?

CARTER EVANS for CBS:   In this emerging age of drone deliveries, anddriverless cars​, technology now brings us -- robo-pizza.  Silicon Valley is at the forefront of reinventing the pie. The kitchen at Zume Pizza is where technology and culinary arts collide. Humans and robots work side-by-side at Zume Pizza in Mountain View, California. Veteran restaurateur Julia Collins founded the delivery-only pizza company with Alex Garden, the former president of online gaming company, Zynga. “I saw an opportunity to go after the $40 billion domestic delivery pizza market,” Garden said.   Cont'd...

Deep-Diving Robots Zap, Kill Invasive Lionfish

Mindy Weisberger for Live Science:  The robotics company iRobot, known for creating the autonomous and endearing Roomba vacuums, is taking steps to make a clean sweep of lionfish in the coastal waters of the Atlantic Ocean, with a robot designed to target and dispatch the invasive fish. A diving robot will enable individuals on the ocean surface to remotely zap and kill lionfish with electrical charges. The effort is meant to help curb the fast-growing populations of these voracious predators, which are recognized by environmental officials as a serious threat to marine ecosystems in the western Atlantic. The initiative to launch the lionfish-targeting robot is called Robots in Service of the Environment (RISE) and represents an iRobot partnership with organizations and volunteer experts in the fields of robotics, engineering and conservation.   Cont'd...

Records 211 to 225 of 364

First | Previous | Next | Last

Featured Product

Stäubli TX2-60 Industrial Robot

Stäubli TX2-60 Industrial Robot

TX2 robots: redefining performance by offering collaborative safety and high performance in a single machine. These pioneering robots can be used in all areas, including sensitive and restrictive environments, thanks to their unique features. Safety functions are easy and inexpensive to implement. They allow a higher level of interactions between robots and human operators, while still guaranteeing protection of your people, production and investment.