California produces about 90% of the nation’s strawberries, but severe drought and worker shortages are threatening the fruit. One company is hoping to change that with the power of robots.
Eric Adamson’s company is behind a strawberry robotic revolution. He said they’re programmed to think on their own, with cameras that sense texture and color.
“People think robots have been around forever, but they’re actually very, very new, especially robots that make decisions and are autonomous,” Adamson said.
Over the last several decades, obesity has rapidly grown to affect more than 2 billion people, making it one of the biggest contributors to poor health globally. Many individuals still have trouble losing weight despite decades of study on diet and exercise regimens. Researchers from Baylor College of Medicine and affiliated institutions now believe they understand why, and they argue that the emphasis should be shifted from treating obesity to preventing it.
The research team reports in the journal Science Advances that early-life molecular processes of brain development are likely a major determinant of obesity risk. Previous large human studies have shown that the genes most strongly associated with obesity are expressed in the developing brain. This most recent study in mice focused on epigenetic development. Epigenetics is a molecular bookmarking system that regulates whether genes are utilized or not in certain cell types.
“Decades of research in humans and animal models have shown that environmental influences during critical periods of development have a major long-term impact on health and disease,” said corresponding author Dr. Robert Waterland, professor of pediatrics-nutrition and a member of the USDA Children’s Nutrition Research Center at Baylor. “Body weight regulation is very sensitive to such ‘developmental programming,’ but exactly how this works remains unknown.”
If you’ve ever played the claw game at an arcade, you know how hard it is to grab and hold onto objects using robotics grippers. Imagine how much more nerve-wracking that game would be if, instead of plush stuffed animals, you were trying to grab a fragile piece of endangered coral or a priceless artifact from a sunken ship.
Most of today’s robotic grippers rely on embedded sensors, complex feedback loops, or advanced machine learning algorithms, combined with the skill of the operator, to grasp fragile or irregularly shaped objects. But researchers from the Harvard John A. Paulson School of Engineering and Applied Sciences (SEAS) have demonstrated an easier way.
Taking inspiration from nature, they designed a new type of soft, robotic gripper that uses a collection of thin tentacles to entangle and ensnare objects, similar to how jellyfish collect stunned prey. Alone, individual tentacles, or filaments, are weak. But together, the collection of filaments can grasp and securely hold heavy and oddly shaped objects. The gripper relies on simple inflation to wrap around objects and doesn’t require sensing, planning, or feedback control.
Register now for your free virtual pass to the Low-Code/No-Code Summit this November 9. Hear from executives from Service Now, Credit Karma, Stitch Fix, Appian, and more. Learn more.
Retail AI is everywhere this holiday season — even if you don’t realize it.
Say you’re a fashion retailer. You’ve always had to try to predict trends — but now with a slowed supply chain, you have to look 12 months out instead of six.
Aside from the open-sourced nature of the project, the possible widespread applications of the technology also makes it noteworthy. It could be a plausible alternative to mechanical traps, as well as chemicals that often damage the environment and target non-pest insect species. Not to mention, it’s cheaper (the paper notes that all devices cost not more than $250) and more compact than other current pest-controlling technologies.
That being said, although the prototype is suitable for academic research, there’s a lot more to be done before it can be deployed on a larger scale. For example, the paper notes that a smaller laser point would be more effective at killing the roaches but is difficult to implement experimentally. The ability to precisely control which parts of the cockroach’s bodies were hit would also be helpful, the paper says.
“We got a thousand times improvement [in training performance per chip] over the last 10 years, and a lot of it has been due to number representation,” Bill Dally, chief scientist and senior vice president of research at Nvidia said at the recent IEEE Symposium on Computer Arithmetic.
Originally published on Towards AI the World’s Leading AI and Technology News and Media Company. If you are building an AI-related product or service, we invite you to consider becoming an AI sponsor. At Towards AI, we help scale AI and technology startups. Let us help you unleash your technology to the masses.
