Slashdot Mirror

No, not at all.

From the DARPA page at http://www.theroboticschallenge.org/about

"development of robots featuring task-level autonomy that can operate in the hazardous, degraded conditions "

and

"Task-level autonomy is the opposite of tele-operation"

The tele-operation was something like "open door", no team used game controllers for tele-operations.

The competition is in December 2013, and this team may not be ready by then. Here are the other robots being entered.

The simulated challenge back in June revealed that the entrants' movement control software isn't very good yet. The winning team's simulated robot fell down 12 times. DARPA has posted only heavily censored videos of the results, possibly because they're so embarrassingly bad.

Some of the blame attaches to the simulator used. The Gazebo simulator's physics engine, which is borrowed from video games, is not good enough for the job. Video game simulators use tricks that look OK, but aren't physically realistic. That's no good when you're using them to match a real robot, or even if you're doing control based on reported forces from the simulator. This should be fixed in early 2014 when they get an honest physics engine from Mike Sherman, who knows what he's doing. (If you need a accurate humanoid robot simulator right now, try OpenHRP3, from AIST in Japan.)

I suspect that the December 2013 event, which will be public, will be rather disappointing. But the planned 2014 event may be very impressive.

That's how it went with 2004 DARPA Grand Challenge for automatic driving, which was so pathetic it was covered by the Comedy Channel. Then in 2005, all the robot vehicles at the event could drive autonomously without running into anything and several finished the whole course with good times. The second day of the 2005 Grand Challenge was the moment when automatic driving became real to the world.

The competition is in December 2013, and this team may not be ready by then. Here are the other robots being entered.

The simulated challenge back in June revealed that the entrants' movement control software isn't very good yet. The winning team's simulated robot fell down 12 times. DARPA has posted only heavily censored videos of the results, possibly because they're so embarrassingly bad.

Some of the blame attaches to the simulator used. The Gazebo simulator's physics engine, which is borrowed from video games, is not good enough for the job. Video game simulators use tricks that look OK, but aren't physically realistic. That's no good when you're using them to match a real robot, or even if you're doing control based on reported forces from the simulator. This should be fixed in early 2014 when they get an honest physics engine from Mike Sherman, who knows what he's doing. (If you need a accurate humanoid robot simulator right now, try OpenHRP3, from AIST in Japan.)

I suspect that the December 2013 event, which will be public, will be rather disappointing. But the planned 2014 event may be very impressive.

That's how it went with 2004 DARPA Grand Challenge for automatic driving, which was so pathetic it was covered by the Comedy Channel. Then in 2005, all the robot vehicles at the event could drive autonomously without running into anything and several finished the whole course with good times. The second day of the 2005 Grand Challenge was the moment when automatic driving became real to the world.

The competition is in December 2013, and this team may not be ready by then. Here are the other robots being entered.

The simulated challenge back in June revealed that the entrants' movement control software isn't very good yet. The winning team's simulated robot fell down 12 times. DARPA has posted only heavily censored videos of the results, possibly because they're so embarrassingly bad.

Some of the blame attaches to the simulator used. The Gazebo simulator's physics engine, which is borrowed from video games, is not good enough for the job. Video game simulators use tricks that look OK, but aren't physically realistic. That's no good when you're using them to match a real robot, or even if you're doing control based on reported forces from the simulator. This should be fixed in early 2014 when they get an honest physics engine from Mike Sherman, who knows what he's doing. (If you need a accurate humanoid robot simulator right now, try OpenHRP3, from AIST in Japan.)

I suspect that the December 2013 event, which will be public, will be rather disappointing. But the planned 2014 event may be very impressive.

That's how it went with 2004 DARPA Grand Challenge for automatic driving, which was so pathetic it was covered by the Comedy Channel. Then in 2005, all the robot vehicles at the event could drive autonomously without running into anything and several finished the whole course with good times. The second day of the 2005 Grand Challenge was the moment when automatic driving became real to the world.

You are really narrow-sighted about the concept of cloud simulation. Yes, it's a tool to host the VRC. It also has many other benefits for education at the highschool and college level, and hosting other educational competitions. With a little spit and polish it could be a be a mechanism to crowd-source robot design, and environment building. I haven't even touch upon the concept of running many simulation simultaneously as a prediction tool for physical robots.

I would love a cloud based simulation solution for development purposes. Please, spare me from the tedium of install and maintaining software. All I want to do is get work done.

Just because it can run on Amazon AWS doesn't mean it's free. Each job running in simulation ties up three large AWS machines and one small one. You'd have to rent machine time from Amazon and load up your own instances. There's no free world simulator to connect to. This thing takes a lot of engine behind it.