Robotics expert: Self-driving cars not ready for deployment
Joan Lowy for PHYS.org: Self-driving cars are "absolutely not" ready for widespread deployment despite a rush to put them on the road, a robotics expert warned Tuesday.
The cars aren't yet able to handle bad weather, including standing water, drizzling rain, sudden downpours and snow, Missy Cummings, director of Duke University's robotics program, told the Senate commerce committee. And they certainly aren't equipped to follow the directions of a police officer, she said.
While enthusiastic about research into self-driving cars, "I am decidedly less optimistic about what I perceive to be a rush to field systems that are absolutely not ready for widespread deployment, and certainly not ready for humans to be completely taken out of the driver's seat," Cummings said.
It's relatively easy for hackers to take control of the GPS navigation systems of self-driving cars, Cummings said.
"It is feasible that people could commandeer self-driving vehicles ... to do their bidding, which could be malicious or simply just for the thrill of it," she said, adding that privacy of personal data is another concern. Cont'd...
Image Processing 101
Sher Minn Chong wrote a good introductory to image processing in Python:
In this article, I will go through some basic building blocks of image processing, and share some code and approaches to basic how-tos. All code written is in Python and uses OpenCV , a powerful image processing and computer vision library...
... When we’re trying to gather information about an image, we’ll first need to break it up into the features we are interested in. This is called segmentation. Image segmentation is the process representing an image in segments to make it more meaningful for easier to analyze3.
Thresholding
One of the simplest ways of segmenting an image isthresholding. The basic idea of thresholding is to replace each pixel in an image with a white pixel if a channel value of that pixel exceeds a certain threshold... ( full tutorial ) ( iPython Notebook )
18 months since the toolkit's release, soft robotics is flying
Gordon Hunt for SiliconRepublic: Pioneered in Ireland by the likes of Dr Dónal Holland, with a plethora of departments in Harvard University in the US involved, the Soft Robotics Toolkit has gone on to foster significant interest in an area exploding into the mainstream.
More than 76,000 people have engaged with the service since it was created, represented across 150 different countries, with the toolkit identified as having made one of the most significant contributions to the development of the nascent industry to date.
While robotics engineering used to focus much more attention on creating the rigid, hard-bodied prototypes like Bender from Futurama, for example, lately there has been a push towards soft, malleable structures that take their inspiration from nature. Cont'd...
Carnegie Mellon robotics selected for research projects totaling more than $11 million
Carnegie Mellon University's National Robotics Engineering Center (NREC) has been selected as a prime contractor or subcontractor on four major new federal research projects totaling more than $11 million over the next three years. The projects range from research on a wheel that can transform into a track to automated stress testing for critical software.
Herman Herman, NREC director, said the center has hired 10 new technical staff members in the past six months and anticipates hiring another five-to-10 staff members in the coming months to augment its existing staff of about 100.
"For the past 20 years, NREC has been an important national resource, combining unique technical skills and testing capabilities to solve problems that other groups can't," said Martial Hebert, director of CMU's Robotics Institute, which includes the NREC. "These new projects are a reminder that NREC continues to advance the art and science of robotics and that it remains a vital part of Carnegie Mellon's Robotics Institute." Full Press Release:
Artificial Skin That Glows, Stretches Could Change Robotics?
By Brendan Byrne for ValueWalk: Researchers at Cornell University have developed an electronic artificial skin that doesn’t mind being stretched to 500% its original size (cell phone), glows in the dark and can move a bit like a worm.
In a paper published yesterday in the journal Science, a team of researchers showed off glowing electric skin that could be put to use in future wearables. While artificial skin that responds to commands has been done before, electronics embedded in the skin have generally broken when stretched. However, the team seems to have leaped over this hurdle by using hyperelastic, light-emitting capacitor (HLEC) technology.
“It’s actually much, much, much more stretchable than human skin or octopus skin,” says Chris Larson, a doctoral candidate and researcher in Cornell’s Organic Robotics Lab. “In terms of texture, it’s actually more like a rubber band or a balloon.”
While Larson freely admits that he doesn’t know much about cephalopods, the team was inspired by biology, specifically, the octopus beak with its ability to both move and stretch.
“The researchers created a three-chamber robot from the material, with the newly developed ‘skin’ layers on top, and inflatable layers below that allow movement,” according to a release from the American Association for the Advancement of Science. “As the chambers expand linearly, the robot moves forward with a worm-like wiggle.” Cont'd.. .
Postdoc's Trump Twitterbot Uses AI To Train Itself On Transcripts From Trump Speeches
From MIT:
This week a postdoc at MIT’s Computer Science and Artificial Intelligence Lab (CSAIL) developed a Trump Twitterbot that Tweets out remarkably Trump-like statements, such as “I’m what ISIS doesn’t need.” The bot is based on an artificial-intelligence algorithm that is trained on just a few hours of transcripts of Trump’s victory speeches and debate performances...
... ( MIT article ) ( twitter feed )
How This New Drone Can Track Your Every Move
Lisa Eadicicco for Time: Drones can already follow professional snowboarders as they speed down a slope or keep up with mountain bikers racing through rocky terrain. But drone-equipped athletes are usually required to keep their phone nearby, since the aerial devices often rely on handheld devices’ GPS signal to track a person’s location.
DJI’s newest drone, the Phantom 4, claims to eliminate that hassle. The company says the Phantom 4’s new ActiveTrack feature uses the drone’s front-facing sensors to see and track a target.
“Being able to learn about the object, as it squats, as it rotates, as it turns, is really complicated,” says Michael Perry, DJI’s director of strategic partnerships. “When you’re flying toward something, you have to make a decision to fly around it, fly above it, or stop. And to train the system to learn those different functions is also a big challenge.” Cont'd...
Would you buy meat from a robot butcher?
Greg Nichols for The Kernel: In an era when hunks of cow and pig are packaged and distributed like Amazon Prime parcels, butchering has retained a surprising degree of its old-world craftsmanship. Workers armed with knives and hooks anachronistically slice flesh from bone the same way they have for hundreds of years. That’s because cutting meat—be it on an assembly line or in a niche shop in Santa Monica, California, or Brooklyn, New York—is a skill that requires exceptional dexterity, a good eye, and a honed tactile sense for texture and firmness. Industrial robots may be perfectly suited to welding chassis and painting cars, but they don’t have the touch to cut a succulent T-bone steak.
That’s likely to change. JBS, one of the country’s largest meat processors, recently acquired a controlling share of Scott Technology, a New Zealand-based robotics firm. Now JBS is looking at ways to automate its facilities. Robots don’t sleep, don’t collect overtime, and don’t suffer the horrific repetitive stress injuries that plague meat workers. Meat is already packed using machines, and if engineers can figure out how to make automated systems that approximate the deft hands of a butcher, there’s little question giants like JBS, Cargill, and Tyson will replace many of their line workers with robots. In the next decade, adroit robots that can see, feel, and move like humans may finally kill off the butcher. Cont'd...
Mercedes Boots Robots From the Production Line:
By Elisabeth Behrmann & Christoph Rauwald for Bloomberg Business: “Robots can’t deal with the degree of individualization and the many variants that we have today,” Markus Schaefer, the German automaker’s head of production, said at its factory in Sindelfingen, the anchor of the Daimler AG unit’s global manufacturing network. “We’re saving money and safeguarding our future by employing more people.”
Mercedes’s Sindelfingen plant, the manufacturer’s biggest, is an unlikely place to question the benefits of automation. While the factory makes elite models such as the GT sports car and the ultra-luxury S-Class Maybach sedan, the 101-year-old site is far from a boutique assembly shop. The complex processes 1,500 tons of steel a day and churns out more than 400,000 vehicles a year.
That makes efficient, streamlined production as important at Sindelfingen as at any other automotive plant. But the age of individualization is forcing changes to the manufacturing methods that made cars and other goods accessible to the masses. The impetus for the shift is versatility. While robots are good at reliably and repeatedly performing defined tasks, they’re not good at adapting. That’s increasingly in demand amid a broader offering of models, each with more and more features. Cont'd...
Atlas, The Next Generation
From Boston Dynamics: A new version of Atlas, designed to operate outdoors and inside buildings. It is specialized for mobile manipulation. It is electrically powered and hydraulically actuated. It uses sensors in its body and legs to balance and LIDAR and stereo sensors in its head to avoid obstacles, assess the terrain, help with navigation and manipulate objects. This version of Atlas is about 5' 9" tall (about a head shorter than the DRC Atlas) and weighs 180 lbs.
Roving robot 'ground drones' take to streets for deliveries
MARK BLUNDEN for Evening Standard: A delivery robot tested among the crowds of central London is set to start being deployed in the capital.
The self-driving, battery-powered box on wheels is poised to undertake local delivery trials in Greenwich following 3,000 hours of testing.
The robots by Starship Technologies have been described as “ground drones” and were created by former Skype co-founders Ahti Heinla and Janus Friis.
Their invention is expected to be popular at smaller local businesses, such as bakeries and corner shops, that could send out the robot containing goods in its tub body costing only a pound or two. Cont'd...
Republican-Leaning Cities Are At Greater Risk Of Job Automation
By Jed Kolko for Five Thirty Eight: More and more work activities and even entire jobs are at risk of beingautomated by algorithms, computers and robots, raising concerns that more and more humans will be put out of work. The fear of automation is widespread — President Obama cited it as the No. 1 reason Americans feel anxious about the economy in his State of the Union address last month — but its effects are not equally distributed, creating challenges for workers and policymakers. An analysis of where jobs are most likely to face automation shows that areas that voted Republican in the last presidential election are more at risk, suggesting that automation could become a partisan issue.
So-called “routine” jobs — those that “can be accomplished by following explicit rules” — are most at risk of automation. These include both “manual” routine occupations, such as metalworkers and truck drivers, and “cognitive” routine occupations, such as cashiers and customer service reps.1 Whereas many routine jobs tend to be middle-wage, non-routine jobs include both higher-wage managerial and professional occupations and lower-wage service jobs. Cont'd...
Japanese Firm To Open World's First Robot-run Farm
Spread , a vegetable producer, said industrial robots would carry out all but one of the tasks needed to grow the tens of thousands of lettuces it produces each day at its vast indoor farm in Kameoka, Kyoto prefecture, starting from mid-2017.
The robots will do everything from re-planting young seedlings to watering, trimming and harvesting crops.
The innovation will boost production from 21,000 lettuces a day to 50,000 a day, the firm said, adding that it planned to raise that figure to half a million lettuces daily within five years.
“The seeds will still be planted by humans, but every other step, from the transplanting of young seedlings to larger spaces as they grow to harvesting the lettuces, will be done automatically,” said JJ Price, Spread’s global marketing manager.
The new farm – an extension of its existing Kameoka farm – will improve efficiency and reduce labour costs by about half. The use of LED lighting means energy costs will be slashed by almost a third, and about 98% of the water needed to grow the crops will be recycled.
The farm, measuring about 4,400 sq metres, will have floor-to-ceiling shelves where the produce is grown... ( cont'd )
DARPA - FLA Program Takes Flight
They may not have zoomed flawlessly around obstacles like the Millennium Falcon did as it careened through the hull of a crashed Star Destroyer in Star Wars VII. But the sensor-loaded quadcopters that recently got tested in a cluttered hangar in Massachusetts did manage to edge their way around obstacles and achieve their target speeds of 20 meters per second. Moreover, the quadcopters were unmanned … and real. Thus was the initial phase of data collection for DARPA's Fast Lightweight Autonomy (FLA) program recently deemed an encouraging success.
DARPA’s FLA program aims to develop and test algorithms that could reduce the amount of processing power, communications, and human intervention needed for unmanned aerial vehicles (UAVs) to accomplish low-level tasks, such as navigation around obstacles in a cluttered environment. If successful, FLA would reduce operator workload and stress and allow humans to focus on higher-level supervision of multiple formations of manned and unmanned platforms as part of a single system. Cont'd...
Humanoid robots in tomorrow's aircraft manufacturing
From Phys.Org: Developing humanoid robotic technology to perform difficult tasks in aircraft manufacturing facilities is the goal of a four-year joint research project, which is being conducted by the Joint Robotics Laboratory (CNRS/AIST) and Airbus Group. It will officially be launched on 12 February 2016 at the French Embassy in Tokyo. The introduction of humanoids on aircraft assembly lines will make it possible to relieve human operators of the most laborious and dangerous tasks, thus allowing them to concentrate on higher value-added ones. The primary difficulty for these robots will be to work in a confined environment and move without colliding with the numerous surrounding objects. This is the first issue researchers will have to solve by developing new algorithms for the planning and control of precise movements. Cont'd...
Records 1036 to 1050 of 1550
First | Previous | Next | Last
Featured Product
igus® - Free heavy-duty plastic bearings sample box
The iglide® heavy-duty sample box provides a selection of five unique iglide bearings, each suitable for use in heavy-duty equipment due to their self-lubricating, dirt-resistant properties. Each bearing material boasts unique benefits and is best suited for different application conditions, though each can withstand surface pressures of at least 11,603 psi at 68°F.
