|
Whoa. Just Whoa.
I won’t even pretend that I understand all that is going on in the walking gait here, but this is darn near human-like in every aspect. And being able to walk like that is one thing, being able to recover from a sideways push is an entirely different accomplishment all together. Absolutely brilliant.
The complexity shown in LittleDog’s adaptive gait and terrain navigation seriously makes my head hurt. If you consider yourself a geek you are of course familiar with BigDog; the 4 legged robot that robot dreams are made of. LittleDog is similar in concept but at a much smaller scale, and MIT has been using it as a research platform for a number of years. Evan Eckerman from Botjunkie sums it up quite well:
Researchers at places like MIT have been using Boston Dynamics‘ LittleDog robot for years now as a testbed to teach legged robots to learn how to traverse variable terrain on their own. This video shows some highlights of a “dynamic double-support gait,” which means (as near as I can tell) that LittleDog is supporting itself, at times, on only two of its four legs. This is a substantially more efficient way of negotiating terrain than we first saw two years ago. LittleDog also demonstrates some markedly biological ways of negotiating obstacles (with the possible exception of the belly flop on the Jersey barrier)… I especially liked how it pranced in place slightly before tackling each stair. All this stuff is obviously a lot of work for a little bot, since poor LittleDog completely collapses at the end of every test.
LittleDog, remember, is teaching itself the most efficient way to negotiate these surfaces. Overhead cameras examine the terrain and plan out LittleDog’s route by computing a ‘cost’ for each step, which takes into account the distance moved towards the goal as well as the potential for a fall. After a lot of trial and error, LittleDog figures out how to best compromise between progress and stability, and the lessons it learns could be propagated up to other, larger quadruped robots.
This video is from Phase 2 of DARPA’s Learning Locomotion program… MIT’s LittleDog team was awarded funding for Phase 3 of this program back in 2008, so we’ll keep you updated.
Ok, we’ve seen some pretty incredible advancements in robotics these last couple of years, but this tops the cake! The articulation from this arm is amazing. It looks like something straight out of the Cyberdyne lab in the Terminator series.
via (BoingBoing)
GM has unveiled an entry into the Defense Advanced Research Projects Agency (DARPA) Grand Challenge competition on November 3, 2007. For those that have been living in a cave and haven’t heard of the DARPA challenge yet, from the Grand Challenge website, “The Urban Challenge features autonomous ground vehicles maneuvering in a mock city environment, executing simulated military supply missions while merging into moving traffic, navigating traffic circles, negotiating busy intersections, and avoiding obstacles”.
Neither of the past DARPA competitions (2004, 2005) attracted much interest from the automotive industry, mostly because creating an autonomous vehicle to travel across the types of roads and other conditions that past competitors were exposed to simply didn’t fit into their business model.
It’s sad but at the same time exciting to hear that corporations are starting to participate in this autonomous vehicle competition. I’d much rather see the past methods continue of corporate sponsorship of teams rather than the actual corporation itself participating, but hey; If this is what has to happen in order for us to see these robotic vehicles on the road and taking ourselves to and from work everyday without us having to touch the wheel then so be it. I’d love to see the day when my car drives itself and I can catch up on things that I need to do while I’m on my way to/from work.
Named “Boss” for Charles “Boss” Kettering, this Tahoe has over 25 external sensors, the computing power of ten Compaq Intel Core 2 Duo laptops, and many other electric and electronic devices all powered by an auxiliary 8-kW generator under the hood.
via (Robot Stock News, Motor Trend)
“Although a fair amount of entrants into DARPA’s Urban Challenge flank their vehicles with hordes of less-than-attractive sensors, we’ve been quick to forgive such atrociousness due to the complexities involved in cruising around sans a driver. Ibeo-led Team LUX, however, is looking to add a dash of style to this year’s (now lucrative) competition, as its Volkswagen Passat TDI wagon touts a clean exterior, three “laser scanners” for complete 360-degree perception, and amazingly, not much else. Apparently, the trio of uber-capable modules are all that’s needed to keep the car under control, and while we’d typically doubt such bold claims, the 11-member team has quite an impressive resume in the autonomous vehicle department. Still, the minimalist approach will probably face some stiff competition, and although we’re certainly not experts on design, we still think the Wolfpack’s Lotus packs a bit more sexy.”
via (Engadget)
A view of the “brains” of “Junior,” a modified 2006 Volkswagen Passat wagon being developed by Stanford University’s Racing Team to compete in DARPA’s Urban Challenge in November. The competition among driverless cars will take place on city streets, among other cars.
via Digg post
Thought-controlled robotic limbs were only the beginning.
hand.jpgScientists have had a string of remarkable successes lately, taking signals from the brains of monkeys and men, and using them to move mechanical arms.
Darpa, the Pentagon’s blue-sky research division, now wants to ratchet that work up about ten notches, by developing a “neurally controlled artificial limb that will restore full motor and sensory capability to upper extremity amputee patients. This revolutionary prosthesis will be controlled, feel, look and perform like the native limb.”
via Digg
Thanks to the hard work of 20 developers, there is an open source vision library, freely available to the public, named OpenCV.
This library is mainly aimed at real time computer vision. Some example areas would be Human-Computer Interaction (HCI); Object Identification, Segmentation and Recognition; Face Recognition; Gesture Recognition; Motion Tracking, Ego Motion, Motion Understanding; Structure From Motion (SFM); and Mobile Robotics.
Wondering about some credentials and how well this software works? OpenCV was used as the vision system of “Stanley”, the winning entry to the $2M DARPA Grand Challenge race of 2005.
Wondering what kind of a support community is out there for a vision library of such a caliber? There is a Yahoo Tech Group currently with 23,804 members who are contributing to this library’s success. If your interested in being a part of this community, join this group and find more out about this library and what you need to do to get started with implementing it in your own projects.
Convinced? I thought so. The library can be downloaded at the OpenCV Sourceforge Page, where more information can be found about the library as well.
via Intel
If you happen to have missed the NOVA hour long documentary on the DARPA grand challenge you can now watch it from their website. This is why we love the internet.
THIS IS NOT A TOY: Micro Air Vehicle Weighs Less, Flies Longer
About as long as a No. 2 pencil and as heavy as a cellphone, the Wasp may look like a toy, but this tiny Micro Air Vehicle (MAV) has broken records with a flight time of 1.5 hours and can fly like a helicopter — just don’t point it at your sister or the family pet.
Mini Helicopter Thinks for Itself — On the Fly — to React to Dangerous Situations — Now Transitioning to Military
Unmanned aerial vehicles (UAVs) are one step closer to someday matching — and possibly surpassing — their human-piloted counterparts, thanks to the completion of a project successfully tested by Georgia Tech and sponsored by the Defense Advanced Research Projects Agency (DARPA) and the U.S. Air Force Research Laboratory. The project was supported by DARPA’s Information Exploitation Office with Dr. John Bay serving as the program manager.
