Automaton iconAutomaton

Is a Cambrian Explosion Coming for Robotics?

This article originally appeared in the Journal of Economic Perspectives, Vol. 29, No. 3 (Summer 2015). We thank the American Economic Association for giving us permission to reproduce it here.

About half a billion years ago, life on earth experienced a short period of very rapid diversification called the “Cambrian Explosion.” Many theories have been proposed for the cause of the Cambrian Explosion, with one of the most provocative being the evolution of vision, which allowed animals to dramatically increase their ability to hunt and find mates (for discussion, see Parker 2003). Today, technological developments on several fronts are fomenting a similar explosion in the diversification and applicability of robotics. Many of the base hardware technologies on which robots depend—particularly computing, data storage, and communications—have been improving at exponential growth rates. Two newly blossoming technologies—“Cloud Robotics” and “Deep Learning”—could leverage these base technologies in a virtuous cycle of explosive growth. In Cloud Robotics—a term coined by James Kuffner (2010)—every robot learns from the experiences of all robots, which leads to rapid growth of robot competence, particularly as the number of robots grows. Deep Learning algorithms are a method for robots to learn and generalize their associations based on very large (and often cloud-based) “training sets” that typically include millions of examples. Interestingly, Li (2014) noted that one of the robotic capabilities recently enabled by these combined technologies is vision—the same capability that may have played a leading role in the Cambrian Explosion.

Read More

Video Friday: Mini Surgical Robot, Precision Drones, and Bioinspired Robotics at Harvard

When you have a brand new robot to show the world, it’s not always easy to come up with a demo that will attract attention, especially if your robot does stuff that’s (and forgive us for saying this) inherently kind of boring. Don’t get me wrong: robots that do boring things are very important, because otherwise humans would be doing those things instead.

PRENAV (which I’m going to call Prenav so that I don’t get a headache) is introducing an aerial robot that can inspect tall structures, and what’s impressive about it is that it can (through the assistance of another robot on the ground) localize itself with centimeter-level accuracy. To demonstrate how well this works, Prenav stuck some lights on its drone and photographed it while it flew around. The timelapsed footage is amazing.

Be amazed, and then watch some other videos, it’s Video Friday.


Read More

Robots With Smooth Moves Are Up to 40% More Efficient

Robot arms (and robots in general) are all about following orders. Your orders, merciless human overlord. You tell them to jump, and they say “I’m an arm, I don’t jump, but I can move around a little bit if you want.” And then they do, as best as they can. As far as the arm is concerned, its entire reason for existing is to move where you tell it to as fast as possible, I guess because it figures (usually quite wrongly) that you have better things to do than sit there and mind it.

These fast, precise movements are one of the reasons that we like robots as much as we do, but as it turns out, they’re not particularly energy efficient. This might not be something that you think about after dropping tens of thousands of dollars (or whatever) on a robot arm, but energy use adds up, especially if you have tens of thousands (or whatever) of arms.

Swedish researchers at Chalmers University of Technology, working as part of the European Union’s AREUS Project (Automation and Robotics for European Sustainable Manufacturing), have taken a crack at robot arm efficiency, and come up with an optimization algorithm that tweaks acceleration and deceleration to reduce energy consumption by up to 40 percent.

Read More

Sony's New Drone: a Modern Take on a Familiar Design

Last month, Sony Mobile announced a partnership with ZMP to build drones. Or rather, “to collaborate on the development and launch of enterprise solutions using autonomous unmanned aerial vehicles for image capture combined with cloud-based data processing.”

Okay then.

To me, this kind of sounds like Sony mostly just not wanting to be left out of this whole drone thing that everybody seems to be so excited about, so they figure they’d better come up with some drones that can, you know, do some… stuff (they mentioned “solutions that meet needs including measuring, surveying, observing, and inspecting”). Having said that, if Sony can develop a reliable and streamlined real-time cloud interface for drones, that would be pretty cool.

The partnership between Sony and ZMP is called Aerosense, and yesterday, they released a flight test video of their new fixed-wing VTOL drone.

Read More

Video Friday: Giant Fighting Robots, Glass 3D Printer, and 10 New Robots from Fetch

Once again, the biggest thing that happened in robotics this week was apparently something about a giant robot duel, despite the fact that we posted some absolutely excellent stuff about robot arms control and simulated evolution in leafcutter ants. But, it’s basically impossible to compete with giant robot duels, so that’s what we’re starting with today.


Read More

Ban or No Ban, Hard Questions Remain on Autonomous Weapons

This is a guest post. The views expressed here are solely those of the authors and do not represent positions of IEEE Spectrum or the IEEE.

Last month, over 1,000 robotics and artificial intelligence researchers signed an open letter calling for a ban on offensive autonomous weapons, putting new energy into an already spirited debate about the role of autonomy in weapons of the future.

These researchers join an ongoing conversation among lawyers, ethicists, academics, activists, and defense professionals on potential future weapons that would select, engage, and destroy targets without a human in the loop. As AI experts, the authors of the letter can help militaries better understand the risks associated with increasingly intelligent and autonomous systems, and we welcome their contribution to the discussion.

By calling for a ban on autonomous weapons, the letter raises a host of complex issues, and it will take continued engagement by scientists to help address them. In this article, we discuss some historical precedents for weapons bans, as well as some of the specific challenges that an effective restriction on lethal autonomous weapons would face.


Read More

Robots Discover How Cooperative Behavior Evolved in Insects

Insects like bees, termites, and ants have somehow figured out a whole repertoire of extraordinarily complex cooperative behaviors, which is all the more remarkable considering that their brains are the size of, uh, something very small. They team up to build structures, forage for food, and move enormous amounts of material relative to their size. All of this cleverness has evolved over time, Darwinian selection-style, but without waiting around for however many millions of years that took, it’s hard to see it in action.

In a paper published this month in PLOS Computational Biology, researchers used identical simulated robots to watch behavioral evolution in action, and remarkably, the robots were able to figure out how to organize themselves into a system of specialized division of labor completely on their own.

Read More

This Robot Submarine Inspects the Worst Pools Ever

I’ve been swimming in a lot of weird places. Some of them have even been a little dangerous. But I would never, ever, ever go swimming inside of the core of a nuclear reactor, operating or otherwise. Neither would anyone else in their right mind, but it is the job of human inspectors to go out on catwalks over reactor vessels and dip long poles with cameras attached into the water to inspect the vessel’s interior to make sure that nothing evil is leaking out.

This is not a particularly safe nor fun activity, but you know who doesn’t care about safety or funness? Robots.

Read More

What Boston Dynamics Is Working on Next

It’s almost impossible to get information out of Boston Dynamics (especially after this happened). Infuriatingly (for us), the way the company does PR is to just upload awesome videos on YouTube, sit back, and let millions of people be amazed by their newest robotic innovation while we desperately try to get a post up that says something more relevant than “go watch this video right now.” We even showed up at Boston Dynamics ourselves once, and mostly all that we learned was that Marc Raibert is an enigmatic guy on a pogo stick.

Raibert, and other people from Boston Dynamics, do speak at conferences sometimes, but usually they don’t talk much about future projects, and they almost always ask that anything new (or any outtakes that they might show, which are unfailingly hilarious) isn’t recorded.

Earlier this month, at the FAB 11 Conference at MIT, Raibert gave a 7-minute presentation as part of a panel on “Making Robots,” which also included Sangbae KimRuss TedrakeRadhika NagpalMick Mountz, and Gil Pratt. Raibert’s presentation featured some video that we’d never seen before as well as tantalizing hints of what Boston Dynamics has been working on.

Read More
Advertisement

Automaton

IEEE Spectrum's award-winning robotics blog, featuring news, articles, and videos on robots, humanoids, automation, artificial intelligence, and more.
Contact us:  e.guizzo@ieee.org

Editor
Erico Guizzo
New York, N.Y.
Senior Writer
Evan Ackerman
Berkeley, Calif.
 
Contributor
Jason Falconer
Canada
Contributor
Angelica Lim
Tokyo, Japan
 

Newsletter Sign Up

Sign up for the Automaton newsletter and get biweekly updates about robotics, automation, and AI, all delivered directly to your inbox.

Advertisement
Load More