Technology

A robotgot to know its limitations. But that doesn&t mean it has to accept them. This one in particular uses tools to expand its capabilities, commandeering nearby items to construct ramps and bridges. Itsatisfying to watch but, of course, also a little worrying.

This research, from Cornell and the University of Pennsylvania, is essentially about making a robot take stock of its surroundings and recognize something it can use to accomplish a task that it knows it can&t do on its own. Itactually more like a team of robots, since the parts can detach from one another and accomplish things on their own. But you didn&t come here to debate the multiplicity or unity of modular robotic systems! Thatfor the folks at the IEEE International Conference on Robotics and Automation, where this paper was presented (and Spectrum got the first look).

SMORES-EP is the robot in play here, and the researchers have given it a specific breadth of knowledge. It knows how to navigate its environment, but also how to inspect it with its little mast-cam and from that inspection derive meaningful data like whether an object can be rolled over, or a gap can be crossed.

It also knows how to interact with certain objects, and what they do; for instance, it can use its built-in magnets to pull open a drawer, and it knows that a ramp can be used to roll up to an object of a given height or lower.

A high-level planning system directs the robots/robot-parts based on knowledge that isn&t critical for any single part to know. For example, given the instruction to find out whatin a drawer, the planner understands that to accomplish that, the drawer needs to be open; for it to be open, a magnet-bot will have to attach to it from this or that angle, and so on. And if something else is necessary, for example a ramp, it will direct that to be placed as well.

The experiment shown in this video has the robot system demonstrating how this could work in a situation where the robot must accomplish a high-level task using this limited but surprisingly complex body of knowledge.

In the video, the robot is told to check the drawers for certain objects. In the first drawer, the target objects aren&t present, so it must inspect the next one up. But ittoo high — so it needs to get on top of the first drawer, which luckily for the robot is full of books and constitutes a ledge. The planner sees that a ramp block is nearby and orders it to be put in place, and then part of the robot detaches to climb up and open the drawer, while the other part maneuvers into place to check the contents. Target found!

In the next task, it must cross a gap between two desks. Fortunately, someone left the parts of a bridge just lying around. The robot puts the bridge together, places it in position after checking the scene, and sends its forward half rolling towards the goal.

These cases may seem rather staged, but this isn&t about the robot itself and its ability to tell what would make a good bridge. That comes later. The idea is to create systems that logically approach real-world situations based on real-world data and solve them using real-world objects. Being able to construct a bridge from scratch is nice, but unless you know what a bridge is for, when and how it should be applied, where it should be carried and how to get over it, and so on, itjust a part in search of a whole.

Likewise, many a robot with a perfectly good drawer-pulling hand will have no idea that you need to open a drawer before you can tell whatin it, or that maybe you should check other drawers if the first doesn&t have what you&re looking for!

Such basic problem-solving is something we take for granted, but nothing can be taken for granted when it comes to robot brains. Even in the experiment described above, the robot failed multiple times for multiple reasons while attempting to accomplish its goals. Thatokay — we all have a little room to improve.

Once a month or so, I&m reminded that my phone has a front-facing camera when I accidentally hit the toggle button, only to be greeted with a closeup image of my own, dumb face.

Honestly, I can&t remember the last time I used the thing — not intentionally, at least. I tried scrolling through my camera roll to locate the precise moment in which I felt compelled to take a selfie, but ultimately ended up getting tired of the exercise, giving up some time around May of last year.

I have no use for the front-facing camera. I don&t know, maybe I&m in the minority on this one, but I&m pretty sure I&m not alone. Every time I see another phone with another notch or hear stories about companies frantically pushing for some workaround, I quietly wonder what it would be like to live in a world where that wasn&t an issue, because there was no camera getting in the way of that precious screen real estate.

I realize for most mainstream manufacturers, this is probably just a pipe dream. Too many companies have invested too much in the technology to make it appear unnecessary. In recent years, the device has taken on an importance beyond the selfie, including, most notably, the big push by Apple, Samsung and countless Android manufacturers to add face unlock.

There are the proprietary apps like FaceTime and Animoji and a powerful lobby of third-party social media companies that rely on the inclusion of as many cameras as humanly possible on a mobile device. I suppose I fall out of that target demographic. I don&t Snapchat or FaceTime, and when the Google app changed from Hangouts to Meet and I suddenly saw video of myself staring back, again, total freak-out.

Perhaps itbest left to some smaller manufacturer looking to distinguish themselves from a million other Android manufacturers. Someone out there could be the first to go truly full screen, without a silly gimmick like the Vivopop-up, or whatever eight million patents Essential has filed over the past couple of years. Full screen, without the inherent vanity of that unblinking eye staring back at you.

I&m not saying its enough for one company to get me to switch over, but it2018 and 90 percent of smartphones look virtually identical. Why not at least give the consumer the ability to opt out, at least until phone manufacturers solve the notch

CancerAid, a self-reporting and symptom monitoring tool for cancer patients, has scored its first major coup in the U.S. healthcare market with its integration into Epic Systems electronic health records at Cedars Sinai in Los Angeles and an integration with AppleHealthKit.

Cedars, an investor in the company through an accelerator program it ran in conjunction with Techstars, marks the first U.S. hospital system to incorporate CancerAidself-reporting information into a dashboard system for doctors.

Itbeen a long road for company co-foundersRaghav Murali-Ganesh and Nikhil Pooviah, who first met eight years ago at the Chris O&Brien Lifehouse,a Sydney, Australia cancer treatment center.

Pooviah was a resident working with Murali-Ganesh in radiation oncology, positions the two men occupied for several years before venturing off on their own to launch the service that would become CancerAid.

The companyinitial inspiration came from years spent checking out the tools that were already in the market for cancer patients — tools like Chemo Calendar that helped with things like scheduling and monitoring appointments.

Instead of studying for some particularly tricky upcoming exams, Pooviah was spending time developing a patient-facing self-reporting symptom tracker and a community portal for cancer patients to discuss, share and monitor their own symptoms.

CancerAid co-founders Drs. Nikhil Pooviah and Raghav Murali-Ganesh and Martin Seneviratne

It was that first tool that won the company acceptance into the Cedars Sinai accelerator and a competitive position in TechCrunchinaugural Startup Battlefield competition in Sydney, Australia.

From its initial development, CancerAid now has four primary functions. On the patient side, therepersonalized cancer information for patients after their initial diagnosis. The company also provides a personal journal and symptom journal for patients to report on how they&re feeling, both emotionally and physically, as they progress through their treatment.

A feature the company calls &Champions& was added so that family and friends could keep up with patients and encourage them. And finally, the company added a social networking feature so patients could connect with a broader community of patients and survivors.

Now, the company has added &ClinicianLink,& a clinician-facing dashboard that sits in Epic and integrates with the existing workflows of nurses, oncologists, radiologists and the rest of the hospital administration and operational staff that touches patients as they undergo treatment.

The company expects to lock in six-figure licensing deals for hospital systems to access the entire toolkit and offer it to patients.

For hospitals, theresome research that suggests simply by reporting their symptoms patients can improve their own outcomes, because doctors have a better sense on more regular intervals of the potential problems their patients face, the company said.

&Patients will be able to use the patient-facing app at home, with a feedback loop back to their care team (physicians, nurses) in the hospital in real-time,& wrote Pooviah in an email. &This feedback loop helps reduce [emergency room] visits and 30 day readmissions (saving $19,000 per patient per year).&

Beyond the Epic integration, CancerAid is also integrating with HealthKit — so that Apple wearables will be able to have the CancerAid functionality, the company said.

The company has 20,000 patients on the app already, and is being used in 80 of the 200 largest U.S. health systems, according to Pooviah.

Backed by $1.9 million in funding from strategic and financial investors, including Cedars-Sinai Health System, Techstars, AustraliaShark Tank, Slingshot Ventures and Artesian Capital, the company is looking to expand in the U.S. through a dedicated subsidiary as it concentrates on one of the worldlargest healthcare markets.