Marty the robot rolls into this U.S. grocery chain
From Popular Mechanics:
Giant Food Stores, supermarkets that are common sights in Pennsylvania, Maryland, Virginia, and West Virginia, are getting some robotic assistance. Within six months, each of these 172 supermarkets will be working with robots called Marty. Giant’s parent company, Ahold Delhaize USA, which is based out of the Netherlands, also owns Martin’s and Stop & Shop locations. They’ll also be getting robots, bringing the total number of stores getting Martys to 500.
The robots aren’t quite replacing the humans in these supermarkets. Built by Brain Corp., which has also built robotic janitors for Walmart, Martys will be alerting humans to problems that need their attention. They’ll move through the Giants and when they notice spills or other trip hazards, they’ll alert customers verbally and reach out to employees through the store’s public announcement system.
“Bringing robotics and A.I. from a research lab to the sales floor has been a very exciting journey, and we were thrilled by the customer response in our pilot stores,” says Nicholas Bertram, president of Giant, in a press release. “Our associates have worked hard to bring this innovation to life with amazing partners.”
“Marty does not replace our associates — instead, he allows members of our team to spend more time engaging with and assisting customers,” says Ashley Flower, spokeswoman.
Machine learning detects fake honey
From Fast Company:
Honey is one of the world’s most adulterated or mislabeled foods. Last year, Capilano, Australia’s largest honey producer was accused of selling honey that was a mix of cheaper ingredients like cane sugar, corn and rice syrups. Occasionally fake honey is even unsafe to eat. In 2011, an investigation found that American grocery store shelves were selling honey laced with animal antibiotics, lead and other heavy metals.
Enter machine learning, which excels at classifying things that humans have a hard time telling apart. The current process of Melissopalynology, or the authentication of honey from its botanical sources, is often expensive and time-consuming, conducted in laboratories by specialists who require special equipment.
A new, computer vision-powered method that would be much more affordable is laid out in “Honey Authentication with Machine Learning Augmented Bright-Field Microscopy.” The paper was accepted at the “AI for Social Good” workshop at last year’s Neural Information Processing Systems (NeurIPS), a prestigious AI conference.
The team developed the honey authentication tool using a $130 microscope that they found was easy enough for an 11-year-old to use. “We thus reckon that it would, in practice, prove scalable as a decentralized system where producers/consumers/beekeeping associations are able to test honey easily and help weed out fraudsters,” said Peter He, one of the authors of the paper and a student at Imperial College London.
A driverless vehicle that can project its intended direction
Car makers have explored a number of ways to have self-driving vehicles signal where they’re going, but they tend to rely on blinking lights or other codes that might not be easy to interpret in a hurry. Jaguar Land Rover might have something more intuitive: it has developed a system that projects an autonomous vehicle’s direction of travel on the road ahead.
The system casts a series of bars on the road to indicate when it’s turning, setting off or stopping. The gap between the bars can expand or shrink to indicate changes in speed. You’ll know if it’s safe to cross the road without having to carefully watch a car’s actions.
The company has been testing the projections on self-driving pods from Aurrigo, which also helped it test “virtual eyes” reflecting a driverless car’s intent. There are hurdles to overcome before a system like this is useful. How well would it work in daylight or inclement weather? There’s also the question of getting other brands to embrace the concept so that there’s a common framework.