A little over a year ago, we reported on the status of the Robonaut 2 on the International Space Station. Things had not gone all that well for R2 ever since an attempt had been made to install a pair of legs back in 2014, leading to an intermittent power problem that was very hard to diagnose. NASA brought Robonaut back to Earth last year for repairs, and a few weeks ago, we stopped by NASA's Johnson Space Center (JSC) in Houston, Texas, to visit the Robonaut lab and get an update on what's been happening with R2. The Robonaut lab is in Building 9 at JSC, attached to the space vehicle mockup facility. JSC's Valkyrie lives in this massive high bay, and was busy practicing a bomb disposal task (!) when we peeked in.

Today, Zipline is officially opening the first of four distribution centers in Ghana, inaugurating a drone-delivery network that will eventually serve 2,000 hospitals and clinics covering 12 million people. Here's what Zipline says in a press release about the new operation: The revolutionary new service will use drones to make on-demand, emergency deliveries of 148 different vaccines, blood products, and life-saving medications. The service will operate 24 hours a day, seven days a week, from 4 distribution centers--each equipped with 30 drones--and deliver to 2,000 health facilities serving 12 million people across the country. Together, all four distribution centers will make up to 600 on-demand delivery flights a day on behalf of the Government of Ghana. Each Zipline distribution center has the capacity to make up to 500 flights per day. Zipline's contract with the government of Ghana is worth US $12.5 million, but there has been significant criticism over the deal from the minority party in the Ghanaian government (backed by the Ghana Medical Association) arguing that funding was urgently needed for basic services rather than for medical drone delivery.

The history of AI is often told as the story of machines getting smarter over time. What's lost is the human element in the narrative, how intelligent machines are designed, trained, and powered by human minds and bodies. In this six-part series, we explore that human history of AI--how innovators, thinkers, workers, and sometimes hucksters have created algorithms that can replicate human thought and behavior (or at least appear to). While it can be exciting to be swept up by the idea of super-intelligent computers that have no need for human input, the true history of smart machines shows that our AI is only as good as we are. At the turn of millennium, Amazon began expanding its services beyond book selling.

The Paris Fire Brigade has seen its share of logistical challenges, but the massive conflagration that consumed parts of the Notre Dame cathedral on the night of 15 April required a fight of epic proportions. The cathedral is 856 years old and built in a style that makes it almost structurally impossible to contain a fire. The site doubles as both a wildly popular tourist attraction and a holy site for Christians. Defending this symbol of French heritage would require all the tactical and physical power the Brigade had at its disposal--human and otherwise. Soon after firefighters arrived at the scene, the cathedral's giant spire began to show signs of collapsing into the building.

Video Friday is your weekly selection of awesome robotics videos, collected by your Automaton bloggers. We'll also be posting a weekly calendar of upcoming robotics events for the next few months; here's what we have so far (send us your events!): Let us know if you have suggestions for next week, and enjoy today's videos. It only takes 10 Spotpower (SP) to haul a truck across the Boston Dynamics parking lot ( 1 degree uphill, truck in neutral). These Spot robots are coming off the production line now and will be available for a range of applications soon.

Robots offer an opportunity to enable people to live safely and comfortably in their homes as they grow older. In the near future (we're all hoping), robots will be able to help us by cooking, cleaning, doing chores, and generally taking care of us, but they're not yet at the point where they can do those sorts of things autonomously. Putting a human in the loop can help robots be useful more quickly, which is especially important for the people who would benefit the most from this technology--specifically, folks with disabilities that make them more reliant on care. Ideally, the people who need things done would be the people in the loop telling the robot what to do, but that can be particularly challenging for those with disabilities that limit how mobile they are. If you can't move your arms or hands, for example, how are you going to control a robot?

It's been a little over two years since we were first introduced to Astrobee, an autonomous robotic cube designed to fly around the International Space Station. Tomorrow, a pair of Astrobee robots (named Honey and Bumble) will launch to the ISS aboard a Cygnus cargo flight. There's already a nice comfy dock waiting for them in the Japanese Experiment Module (JEM), and the plan is to put them to work as soon as possible. After a bit of astronaut-assisted setup, the robots will buzz around autonomously, doing experiments and taking video, even operating without direct human supervision on occasion. NASA has big plans for these little robots, and before they head off to space, we checked in with folks from the Intelligent Robotics Group at NASA's Ames Research Center in Moffett Field, Calif., to learn about what we have to look forward to.

A prized attribute among law enforcement specialists, the expert ability to visually identify human faces can inform forensic investigations and help maintain safe border crossings, airports, and public spaces around the world. The field of forensic facial recognition depends on highly refined traits such as visual acuity, cognitive discrimination, memory recall, and elimination of bias. Humans, as well as computers running machine learning (ML) algorithms, possess these abilities. And it is the combination of the two--a human facial recognition expert teamed with a computer running ML analyses of facial image data--that provides the most accurate facial identification, according to a recent 2018 study in which Rama Chellappa, Distinguished University Professor and Minta Martin Professor of Engineering, and his team collaborated with researchers at the National Institute of Standards and Technology and the University of Texas at Dallas. Chellappa, who holds appointments in UMD's Departments of Electrical and Computer Engineering and Computer Science and Institute for Advanced Computer Studies, is not surprised by the study results.

The history of AI is often told as the story of machines getting smarter over time. What's lost is the human element in the narrative, how intelligent machines are designed, trained, and powered by human minds and bodies. In this six-part series, we explore that human history of AI--how innovators, thinkers, workers, and sometimes hucksters have created algorithms that can replicate human thought and behavior (or at least appear to). While it can be exciting to be swept up by the idea of super-intelligent computers that have no need for human input, the true history of smart machines shows that our AI is only as good as we are. In the 1970s, Dr. Geoffrey Franglen of St. George's Hospital Medical School in London began writing an algorithm to screen student applications for admission.

We don't see a lot of inflatable robots, which is really too bad, because they're weirdly excellent at being exactly the sort of robot that everybody seems to want: They're cheap, being made of mostly fabric and rubber, and they're very easy to fix. Relative to most other robots, they're extraordinarily lightweight, and they pack down to a small fraction of their size once deflated. Despite their squishiness, they can be strong and unexpectedly fast, since they're essentially hydraulic in nature. And perhaps most importantly, in most cases they're passively safe, since they don't have much in the way of rigid components or the inertia that comes with them. The downside of inflatable robots is that in general they're not very good at precise, repeatable control, precisely because they're so floppy.