Robots vs. Ebola: What Makes Sense, and What Doesn't

Results from the Safety Robotics for Ebola Workers workshop suggest ways in which robots may be able to help with medical disasters

Photo: WPI
Roboticists at Worcester Polytechnic Institute outfitted a Husky ground robot with an arm and spray system to demonstrate how a remotely controlled vehicle could assist in decontamination tasks.

Last month, we previewed a workshop on Safety Robotics for Ebola Workers that was being held by the Center for Robot-Assisted Search and Rescue (CRASAR) at Texas A&M University in partnership with the White House Office of Science and Technology. The goal was to try to figure out how (or if) robots might be able to help out in the current Ebola crisis, and how we might prepare for robots to be useful in future medical situations. The workshop was held early this month, and yesterday, CRASAR director Dr. Robin Murphy posted her assessment of how things went.

According to Dr. Murphy, “the major takeaway was that robots do exist that could be immediately repurposed now to protect Ebola health workers but how robots fit into the medical response enterprise is as important as what the robots can actually do.”

What this means is that there are systems available now that fulfill some of those roles that we talked about in our previous article, but that actually getting robots to be useful, and used, in these roles requires thinking about all kinds of complicated stuff that people who develop and use robots right now might not have considered.

Let’s take a look at some examples that Dr. Murphy uses to illustrate how a robot might not be entirely appropriate to use in a context where it might otherwise be valuable:

Does the robot work within the cultural context in which it will be deployed? It seems like telepresence would be a great way to allow doctors to safely interact with patients, but as Dr. Murphy points out, this could easily “overwhelm a non-Western family who has never seen a computer.” A better solution might be to use something less, you know, robotic, like a tablet with a camera in it.

Does the robot fit in with existing workflow and practices? Healthcare workers are extraordinarily busy, and they’ve got a system of strict and established protocols for doing what they do. How likely is it that they’re going to want to spend the free time that they don’t have trying to adjust what they’re doing to deal with some kind of robotic system that they’d been getting along without? Dr. Murphy suggests that “small changes that produce at least a tenfold benefit can make a difference,” and might therefore be worth trying to implement.

Can the robot realistically function reliably within the environment? This is much more of a practical question. Robots will need to be able to deal with lots of dirt, canvas floors, narrow doorways, and electrical power and wireless that may not be reliable at all. Also, the robots will need to be decontaminated, and nobody is going to want to have to deal with some sort of special, gentle, robot-friendly decontamination procedure. Your robot had better be cool with getting doused in bleach.

Is the robot easy to maintain and use? Robots in the field likely won’t have access to a lot of batteries, not to mention spare parts, and even if they do, healthcare workers in protective gear are definitely not going to want to spend their time trying to fix a broken robot that they have no idea how to fix. Similarly, the robot can’t have a steep learning curve, or it just won’t be worth the time for health workers and responders to figure out.

With all of this stuff in mind, Dr. Murphy says that the biggest issue right now is “not the lack of capable robots but rather the lack of requirements that would allow industry to invest in repurposing robots and enable agencies to test and evaluate the robots and develop training.” In other words, the hardware exists, but nobody is quite sure yet how to effectively get the robots that can do the job into situations in which they’d be helpful.

Having said that, the workshop participants did come up with some near-term ways in which robots may be able to help with medical disasters. These seem to be the most realistic:

Remote interaction with family members: Medical interpreters could use telepresence devices to work with family members, performing relatively simple tasks like helping them fill out forms that might otherwise require a human to be present.

Materials handling: Robots could minimize the amount of time humans spend in risky situations by moving litters, transporting contaminated waste, or transitioning materials into or out of “hot” areas.

Decontamination: One of the most obvious uses, robots [like the one pictured above, a prototype developed by Taskin Padir’s group at at Worcester Polytechnic Institute] could sterilize rooms, equipment, or themselves.

Delivery and resupply: Some villages are inaccessible during the rainy season, and unmanned boats or UAVs may be able to deliver small amounts of critical supplies. However, even something as simple as this has important cultural considerations, as Dr. Murphy describes: “for example it is better for a medium sized UAV to drop off a large payload of supplies and let the village equivalent of the American Red Cross representative go fetch it and deliver it to different households as part of their daily routine or should a smaller UAV do a precision drop to individuals?”

In some ways, the things that this workshop is dealing with are considerations that the entire field of robotics needs to try to understand: just because robots can help, doesn’t mean that they should help, and especially doesn’t mean that the people that they would be helping even want them to help, all things considered.

Part of the focus of the workshop was identifying two things: what are the most critical problems in the current situation, and is the value proposition of using a robot to mitigate or solve these problems high enough to make it worthwhile? More specifically, can implementing a robot mean a small change in procedure that leads to a tenfold (at least) benefit?

In a few of the cases that Dr. Murphy discusses, the answer may be yes, although there’s still a lot of work to do in making that actually happen. And with that in mind, CRASAR will host a second workshop to discuss specific use cases for robots in early January of 2015.

Dr. Murphy goes into much more detail on the CRASAR blog, which you can read at the link below.

Via [ CRASAR ]

Robotics News

Biweekly newsletter on advances and news in robotics, automation, control systems, interviews with leading roboticists, and more.

About the Automaton blog

IEEE Spectrum’s award-winning robotics blog, featuring news, articles, and videos on robots, humanoids, automation, artificial intelligence, and more.