Robotic Motion Planning
George Konidaris and Daniel Sorin of Duke University have developed a new technology that cuts robotic motion planning times by 10,000 while consuming a small fraction of the power compared to current options. Watch one of their robotic arms in action as they explain how their innovative solution works.
Artificial Intelligence Produces Realistic Sounds That Fool Humans
From MIT News: Video-trained system from MIT’s Computer Science and Artificial Intelligence Lab could help robots understand how objects interact with the world. Researchers from MIT’s Computer Science and Artificial Intelligence Laboratory (CSAIL) have demonstrated an algorithm that has effectively learned how to predict sound: When shown a silent video clip of an object being hit, the algorithm can produce a sound for the hit that is realistic enough to fool human viewers.
This “Turing Test for sound” represents much more than just a clever computer trick: Researchers envision future versions of similar algorithms being used to automatically produce sound effects for movies and TV shows, as well as to help robots better understand objects’ properties... (full article)(full paper)
Teaching robots the physics of sliding and pushing objects
Jiaji Zhou for RoboHub: The Manipulation Lab at the CMU Robotics Institute proposes a computational model that relates an applied robot action to the resultant object motion. Their research won the Best Conference Paper Award atICRA 2016.
Understanding the mechanics of manipulation is essential for robots to autonomously interact with the physical world. One of the common manipulation scenarios involves pushing objects in a plane subject to dry friction. We propose a planar friction (force-motion) model that relates an applied robot action to the resultant object motion. Cont'd...
Amazon's $775 million deal for robotics company Kiva is starting to look really smart
Eugene Kim for Business Insider: It wasn't until 2014 that Amazon really started to use the machines made by Kiva, the robotics company it bought for $775 million in 2012. Kiva makes robots that automate the picking and packing process at large warehouses.
But in the short two years they've been deployed across Amazon's warehouses, Kiva's robots have been a real cost saver, according to a new note published by Deutsche Bank on Wednesday.
The note says Kiva robots have cut operating expenses by about 20%, quoting Amazon exec Dave Clark, adding that it would translate to roughly $22 million in cost savings for each fulfillment center.
Additionally, Deutsche Bank estimates Amazon could cut another $800 million in one-time cost savings once it deploys more Kiva robots across the 110 fulfillment centers that don't have them yet. Amazon uses Kiva robots in only 13 of its fulfillment centers currently. Cont'd...
Japan is all set to welcome first ever Robot Development and Application Expo (RoboDeX)
The Expo is covering topics from development technology of robots to application of robots.
Wal-Mart Experimenting With Robotic Shopping Cart for Stores
Spencer Soper & Shannon Pettypiece for Bloomberg: Wal-Mart Stores Inc. is working with a robotics company to develop a shopping cart that helps customers find items on their lists and saves them from pushing a heavy cart through a sprawling store and parking lot, according to a person familiar with the matter.
Such carts are an emerging opportunity for robotics companies as brick-and-mortar stores look for innovative ways to match the convenience of Amazon.com Inc. and other online retailers, said Wendy Roberts, founder and chief executive officer of Five Elements Robotics.
Roberts, who spoke Tuesday on a robotics panel at the Bloomberg Technology Conference 2016, said her company was working with the "worlds largest retailer" on such a shopping cart.
That retailer is Wal-Mart, which is evaluating a prototype in its lab and giving feedback to the New Jersey robotics company, a person familiar said. Wal-Mart spokesman Ravi Jariwala said he couldnt immediately comment on the robotic shopping cart. Cont'd...
Google's developing its own version of the Laws of Robotics
Graham Templeton for ExtremeTech: Google’s artificial intelligence researchers are starting to have to code around their own code, writing patches that limit a robot’s abilities so that it continues to develop down the path desired by the researchers — not by the robot itself. It’s the beginning of a long-term trend in robotics and AI in general: once we’ve put in all this work to increase the insight of an artificial intelligence, how can we make sure that insight will only be applied in the ways we would like?
That’s why researchers from Google’s DeepMind and the Future of Humanity Institute have published a paper outlining a software “killswitch” they claim can stop those instances of learning that could make an AI less useful — or, in the future, less safe. It’s really less a killswitch than a blind spot, removing from the AI the ability to learn the wrong lessons. Cont'd...
Vyo Is a Fascinating and Unique Take on Social Domestic Robots
Evan Ackerman for IEEE Spectrum: A group of researchers including Michal Luria, Guy Hoffman, Benny Megidish, Oren Zuckerman, Roberto Aimi, and Sung Park from IDC Herzliya, Cornell, and SK Telecom have developed a prototype social robot called Vyo. Vyo is “a personal assistant serving as a centralized interface for smart home devices.” Nothing new there, but what sets Vyo apart is how you interact with it: it combines non-anthropomorphic design with anthropomorphic expressiveness and a tactile object-based control system into a social robot that’s totally, adorably different. But is it practical? Full Article:
Sushi Robots and Vending-Machine Pizza Will Reinvent the Automat
Leslie Patton for Bloomberg: Decades from now, historians may look back on 2016 as the year Earthlings ate pizza from vending machines, bought burritos from a box in New York’s Grand Central Terminal and devoured sushi rolled by robots.
“Automation is coming whether we want it to come or not,” said Andy Puzder, chief executive officer of CKE Restaurants Inc., which owns the Hardee’s and Carl’s Jr. fast-food chains. “It’s everywhere. It’s in everything.”
At a time when more consumers are embracing hand-made artisanal foods, 24/7 Pizza Box, Burritobox and Sushi Station are headed in the other direction. Vending-machine pizza will start popping up in Florida later this year and chipotle-chicken burritos, accompanied by guacamole and salsa, can now be ordered from an automated box. Sushi-making robots from Japan are already operating in U.S. restaurants and university cafeterias. Cont'd...
New Muscle-Inspired Actuators Hold Potential to Build Safer, Soft-Bodied Robots
Robots should be safer and softer in order to make them more cooperative and execute tasks in close contact with humans. George Whitesides, Ph.D., a Core Faculty member at Harvard’s Wyss Institute for Biologically Inspired Engineering and the Woodford L. and Ann A. Flowers University Professor of Chemistry and Chemical Biology in Harvard University’s Faculty of Arts and Sciences (FAS), along with his team, has created a new actuator that moves like human skeletal muscles by using vacuum power for automating soft, rubber beams.
These actuators are soft and shock absorbing similar to real muscles, and do not pose any danger to their surroundings or the human beings working along with them or the future robots containing them. This study was published in the June 1 issue of the Advanced Materials Technologies journal. Cont'd...
Robot wars: Boston Dynamics fell out with Google over humanoid Atlas
Mary-Ann Russon for International Business Times: When former Boston Dynamics employees released video of humanoid robot Atlas – walking unassisted over difficult terrain, such as rocks and snow – Google was reportedly displeased; despite the research receiving high praise from roboticists while wowing the public.
And the real reason Google is selling off Boston Dynamics is, by and large, due to insiders telling Tech Insider that the robotics firm was unwilling to fall in line with the internet giant's vision of a consumer robot for the home.
Google reportedly envisioned the firm as one of nine in a division called Replicant. Initially, under the guidance of Android co-founder Andy Rubin, the firms would continue with existing research and Google would see what ideas and innovations they came up with. Cont'd...
Chrysalix partners with Dutch RoboValley on €100 million robotics fund
Terry Dawes for Cantech Letter: Vancouver-based Chrysalix Venture Capital has announced a €100 million fund aimed at driving the global robotics revolution, in partnership withRoboValley, a centre for robotics commercialization based at the Delft University of Technology in the Netherlands.
The RoboValley Fund is Chrysalix’s first robotics fund, and will concentrate on disbursing seed and Series A rounds of funding to early-stage companies developing component technology, intelligent software, and other breakthrough robotics technologies.
“Robotics is predicted to be the next big step in the digital revolution having an unprecedented impact on the way that we live, and provides an answer to some of the grand challenges of the 21st Century,” said RoboValley managing director Arie van den Ende. “Together with Chrysalix long-standing expertise in commercializing early stage industrial innovations, the RoboValley Fund will bring much needed capital and accelerated paths to market for our most promising next generation robotics technologies.” Cont'd...
OpenAI Gym Beta
From the OpenAI team:
We're releasing the public beta of OpenAI Gym, a toolkit for developing and comparing reinforcement learning(RL) algorithms. It consists of a growing suite ofenvironments (from simulated robots to Atari games), and a site for comparing and reproducing results.
OpenAI Gym is compatible with algorithms written in any framework, such asTensorflow and Theano. The environments are written in Python, but we'll soon make them easy to use from any language. We originally built OpenAI Gym as a tool to accelerate our own RL research. We hope it will be just as useful for the broader community. Getting started: If you'd like to dive in right away, you can work through our tutorial... (full intro post)
Tether free actuator hailed as soft robotics breakthrough
Jon Excell for The Engineer: Designed by a team at the Max Planck Institute for Intelligent Systems in Stuttgart, the new device is claimed to have considerable advantages over existing pneumatically-powered soft actuators as it doesn’t require a tether.
The device consists of a dielectric elastomer actuator (DEA): a membrane made of hyperelastic material like a latex balloon, with flexible (or ‘compliant’) electrodes attached to each side.
The stretching of the membrane is regulated by means of an electric field between the electrodes, as the electrodes attract each other and squeeze the membrane when voltage is applied. By attaching multiple such membranes, the place of deformation can be shifted controllably in the system. Air is displaced between two chambers.
The membrane material has two stable states. In other words, it can have two different volume configurations at a given pressure without the need to minimize the larger volume. Thanks to this bi-stable state, the researchers are able to move air between a more highly inflated chamber and a less inflated one. They do this by applying an electric current to the membrane of the smaller chamber which responds by stretching and sucking air out of the other bubble. Cont'd...
Real-time behaviour synthesis for dynamic Hand-Manipulation
From Vikash Kumar at University of Washington:
Dexterous hand manipulation is one of the most complex types of biological movement, and has proven very difficult to replicate in robots. The usual approaches to robotic control - following pre-defined trajectories or planning online with reduced models - are both inapplicable. Dexterous manipulation is so sensitive to small variations in contact force and object location that it seems to require online planning without any simplifications. Here we demonstrate for the first time online planning (or model-predictive control) with a full physics model of a humanoid hand, with 28 degrees of freedom and 48 pneumatic actuators. We augment the actuation space with motor synergies which speed up optimization without removing flexibility. Most of our results are in simulation, showing nonprehensile object manipulation as well as typing. In both cases the input to the system is a high level task description, while all details of the hand movement emerge online from fully automated numerical optimization. We also show preliminary results on a hardware platform we have developed "ADROIT" - a ShadowHand skeleton equipped with faster and more compliant actuation... (website)
Records 1291 to 1305 of 1499
First | Previous | Next | Last
Mobile Robots - Featured Product
ElectroCraft's Motion Control for Mobile Robots
ElectroCraft is showcasing its award-winning mobile robot technology including their powerful and compact wheel drives, high-torque-density brushless DC motors, precision linear actuators as well as servo motor drive technology at a variety of conferences and tradeshows including the Boston Robotics Summit. Robotics Summit is the premier symposium for the sharing of ideas, technology, and market developments for robotic technologies across industries. Beyond a showcase and pitch of product, ElectroCraft is eager to participate in the collaborative discussion of challenges and opportunities that will shape the near and long-term robotic marketplace.
Robotics and Automation - Featured Company
Basler
Basler AG is an international leader and experienced expert in computer vision. The company offers a broad coordinated portfolio of vision hardware and software. In addition, it enables customers to solve their vision application issues by developing customer-specific products or solutions. Founded in 1988, the Basler Group employs around 850 people at its headquarters in Ahrensburg, Germany, as well as other sales and development locations throughout Europe, Asia, and North America.
