The Best Robots of 2008

An anonymous reader writes "Robot innovation continued its relentless advances during 2008. SingularityHub has a showcase of the best robot videos of the past year. These robot videos are really amazing, and they show just how far we have come in the field of robotics in recent years." The videos include toy robots, robot musicians (which we've discussed in the past), modular robots that work together to move around, robots doing synchronized martial arts, the BigDog robot that can walk on almost any type of terrain, and robot soccer. We've also recently talked about a couple of robots that will bring you beer.

Comments

Until there is a robot in the kitchen

[rolfwind]

Robots as we imagine them haven't really evolved. I think the number 1 advancement in robotics of 2008 will be the memristor, if it delivers what some say it will to artificial intelligence (will programming languages fundamentally change considering that, new keywords and all?)

The synchronized robots are nice, but besides the lack of muscle (being worked upon), it seems the lack of brain is holding back robotics indefinitely. It seems as if would be like the car industry trying to advance in the late 1800s and early 1900s without a suitable motor to power everything else about the vehicle.

Re:Until there is a robot in the kitchen

[geckipede]

A memristor isn't going to suddenly allow you to make computers that can do more than any other turing-machine-alike. If it did change the game for mobile AIs, we'd be able to simulate the effect on giant static hardware already.

Fembots?

[Ritz_Just_Ritz]

Call me when there's a fembot that will bring pizza and beer (and er....other services) without being summoned to do so. Then I'll be all set to retire and contemplate truly meaningful things like how to more effectively eliminate lint and sweater pills. Oh, and mister designer...don't forget the MUTE button.

No NXT?

[Virtualetters]

The engineering introduction to programming course at my university uses Lego NXT robots as a mainstay. Having played around with them, I am amazed at the flexibility. Someone with a little time and dedication could make a pretty decent version of most of the robots in each of the videos. That said, I've seen some great videos of NXT robots this year and was a little disappointed to see none of them in the list. BTW, the Big Dog video's kick moment is probably the highlight of all. I was expecting a little tap but the kicker really goes all out and I almost feel sorry for him when the robot recovers so easily.

There's been real progress

[Animats]

Very nice. If you haven't been paying attention to Japanese hobbyist robotics, you may not have realized how far things have come. They're way beyond Lego Mindstorms. Humanoid toy-sized robots are going through obstacle courses. The robotic toys in the $100-$200 range are becoming quite good, too. WowWee Toys has a line of advanced robotic toys, including the first production fembot.

At the high end, there's Big Dog, of course. The successor to Big Dog is the Legged Squad Support System, now in the bidding stage at DARPA. LS3 is "Big Dog on steroids". Big Dog was an experimental machine; the LS3 will be a combat-ready prototype. The specs for LS3 call for military temperature requirements, a quieter engine, more payload, faster running, longer range, operation in snow, sandstorms, and rain, and the ability to ford a rushing stream three feet deep. LS3 is intended to haul the heavy weapons of a squad just about anywhere an infantry squad can go.

All the technology is falling into place. The navigation and vision from the DARPA Grand Challenge, the success of the newer algorithms in machine learning, the balance and slip control of Big Dog, and the cost structure of the toy industry are coming together. We have not yet seen the "killer app", but I think that robotics is now where personal computers were in about 1976, after the Apple I but before the Apple II.

Re:There's been real progress

[Animats]

No offense to DARPA, not all of the navigation and vision algorithms in those cars with a whole set of high speed computers are really practical for use on smaller home service robots.

Vision works better on home service robots that it does outdoors. Outdoors, getting a long enough baseline for a stereo pair is hard, except through motion vision. Humans only have stereo out to a few meters, anyway. SLAM (Simultaneous Location and Mapping) for mobile robots is getting quite good. Willow Robotics demoed their system at RoboDevelopment a few months ago, and the latest issue of IEEE Trans. on Robotics, a special issue on SLAM, indicates how good that's become.

But machine learning is facing some strong limitations when compared with the abilities of biological systems in coping with unsupervised learning in uncertain and dynamic environments.

I recently went over to Stanford to see the CS229 project presentations, and it's very impressive what small teams of students are getting done in one quarter. Self-guiding robot helicopters, for example. The field has moved away from neural nets; Bayesian statistics, with real theory underneath, works better.

the balance and slip control of Big Dog, applies to quadrupeds with the similar mechanical characteristics. If you are trying to imply that the results are relevant to humanoids, I suggest you read up on the loads of material on everything from 3d linear inverted pendulum model to spin angular momentum regulation and control for humanoids.

Been there, done that, own the patent on legged slip control. For systems which really use dynamic balance, the number of legs doesn't matter all that much from an algorithm standpoint. In fact, most real progress has been made by first getting the one-legged case to work. Key insights: 1) balance has priority over movement, 2) slip/traction control has priority over balance, 3) legs need three joints, not two, so you can play with the force vector at ground contact independent of foot position, and 4) legs are viewed as assets to be deployed to manage traction, balance, and propulsion. "Gaits" are an emergent behavior, the state into which things settle down when movement is not disrupted.

Error establishing a database connection

[ohnotherobots]

Oh no! They're taking over already!

Please let's not exclude my personal favorite,

[WhatDoIKnow]

the Adrienne Barbeaubot

Industrial Robots

[Dabel]

Don't forget about industrial robots. While not garnering as much media attention as the robots in the link, today's industrial robots can pull off some amazing work.

4 robot coordinated system with 2 robots exchanging holding fixtures and coordinating with 2 more welding robots http://www.youtube.com/watch?v=8EK1ad4-gWM

1 robot system taking human-readable commands from a linux based touchscreen and generating offsets and moves dynamically http://www.youtube.com/watch?v=wFSCm24O7lA

(full disclosure - I work at the company, Automation IG, that designed and built these robot cells)

Can't connect to database?

[windsurfer619]

The server seems to be running on a robot... and the robot has left the building. Impressive.

Re:BigDog is uber creepy

[oever]

You man like this?