Lifeboat Foundation: Safeguarding Humanity
Toggle light / dark theme

Blog

Category: robotics/AI – Page 2,165

Unexpected Scientific Insights into COVID-19 From AI Machine Learning Tool

A team of materials scientists at Lawrence Berkeley National Laboratory (Berkeley Lab) – scientists who normally spend their time researching things like high-performance materials for thermoelectrics or battery cathodes – have built a text-mining tool in record time to help the global scientific community synthesize the mountain of scientific literature on COVID-19 being generated every day.

The tool, live at covidscholar.org, uses natural language processing techniques to not only quickly scan and search tens of thousands of research papers, but also help draw insights and connections that may otherwise not be apparent. The hope is that the tool could eventually enable “automated science.”

“On Google and other search engines people search for what they think is relevant,” said Berkeley Lab scientist Gerbrand Ceder, one of the project leads. “Our objective is to do information extraction so that people can find nonobvious information and relationships. That’s the whole idea of machine learning and natural language processing that will be applied on these datasets.”

Robotic Exoskeletons, Like This One, Are Getting More Practical

Circa 2019

When you imagine an exoskeleton, chances are it might look a bit like the Guardian XO from Sarcos Robotics. The XO is literally a robot you wear (or maybe, it wears you). The suit’s powered limbs sense your movements and match their position to yours with little latency to give you effortless superstrength and endurance—lifting 200 pounds will feel like 10.

A vision of robots and humankind working together in harmony. Now, isn’t that nice?

Corpse-detecting robots will use AI to recover bodies from the Korean War

South Korea is developing autonomous robots to recover the remains of soldiers killed in the Korean War.

The excavations will take place in Arrowhead Ridge, a former battlefield inside the demilitarized zone (DMZ) that bisects the Korean Peninsula.

The droids will use AI to scan underground for bodies of soldiers still missing from the war, which began in 1950 when North Korean communist forces invaded the capitalist south.

State-of-the-art lasers at the micro level

Many emerging technologies rely on high-quality lasers. Laser-based LiDAR sensors can provide highly accurate scans of three-dimensional spaces, and as such are crucial in applications ranging from autonomous vehicles to geological mapping technologies and emergency response systems. High-quality lasers are also a key part of the high-speed, high-volume data centers that are the backbone of the internet.

When assessing the quality of a , researchers look to the noise in a laser’s frequency, or the number of times the laser’s light wave toggles in each second. Low-quality, “noisy” lasers have more random variations in those toggles, making them useless for systems that are meant to return or convey densely packed information.

At present, lasers with adequately low frequency noise are bulky, expensive and an impractical choice for mass manufacturing. Penn Engineers have set out to solve this problem with a device called a “phase noise filter” that can turn low-cost, compact lasers into those suitable for LiDAR and more.

Navy Confirms Global Strike Hypersonic Weapon Will First Deploy on Virginia Attack Subs

The Navy intends to deploy its conventional prompt strike hypersonic weapon on Virginia-class attack submarines, after previous discussions of putting the weapon on the larger Ohio-class guided-missile submarine (SSGN), according to budget request documents.

In its Fiscal Year 2021 budget overview, the Navy outlines a research and development portfolio with 5 percent more funding than this current year – for a total of $21.5 billion – that is aimed at “providing innovative capabilities in shipbuilding (Columbia class), aviation (F-35), weapons (Maritime Strike Tomahawk), hypersonics (Conventional Prompt Strike), unmanned, family of lasers, digital warfare, applied [artificial intelligence], and [U.S. Marine Corps] expeditionary equipment. These technologies are crucial to maintaining DON’s competitive advantage.”

On the Conventional Prompt Strike, the Navy wants to invest $1 billion for research and development.

Soldier-controlled autonomous robots call for fire in test, attack targets

O,.o!

Armed Army robot vehicles conducted reconnaissance, called for indirect fire and then, when directed by human decision-makers, attacked and destroyed enemy targets in a recent experiment designed to assess the technical maturity and readiness of autonomous ground drones.

“We had four robot vehicles conduct a tactical mission while humans were safe in defilade. We built four robots that are refurbished M113 tracked vehicles and we’ve taken two Bradleys — gutted them — and turned them into two control vehicles with all kinds of sensors on them,” Jeff Langhout, Director, Ground Vehicle Systems Center, told reporters in October at the Association of the United States Army Annual Symposium, Washington, D.C.

Langhout explained that the robots engaged in “direct fire” missions when directed by human decision-makers, per existing doctrine requiring a human to be “in the loop” when it comes to using lethal force for attack.

Mechanisms of viral mutation

Why hasn’t #MachineLearning conquered SARS-CoV-2 that causes COVID-19 (P.S., SARS-CoV-2 is the name of the #virus, while COVID-19 is the name of the disease)? One of the possible answers is that the virus “learns” faster than machines through “mutations”.

That causes us thinking: If mutation is such an efficient weapon (for virus), can we learn something from it and then apply our understanding to #DeepLearning to create “fast-mutating” #DeepLearning models capable of helping us to fight intractable crisis like a #pandemic?

https://bit.ly/3c9GE5s

Virus Mutation https://bit.ly/35xVvUQ

#COVID19 #AI #technology #innovation #NeuralNetworks

The remarkable capacity of some viruses to adapt to new hosts and environments is highly dependent on their ability to generate de novo diversity in a short period of time. Rates of spontaneous mutation vary amply among viruses. RNA viruses mutate faster than DNA viruses, single-stranded viruses mutate faster than double-strand virus, and genome size appears to correlate negatively with mutation rate. Viral mutation rates are modulated at different levels, including polymerase fidelity, sequence context, template secondary structure, cellular microenvironment, replication mechanisms, proofreading, and access to post-replicative repair. Additionally, massive numbers of mutations can be introduced by some virus-encoded diversity-generating elements, as well as by host-encoded cytidine/adenine deaminases. Our current knowledge of viral mutation rates indicates that viral genetic diversity is determined by multiple virus- and host-dependent processes, and that viral mutation rates can evolve in response to specific selective pressures.

Continue reading “Mechanisms of viral mutation” | >

/* */