NAO Humanoid Robot Set To Hit the Market
KentuckyFC writes "Earlier this year, Paris-based Aldebaran-Robotics picked up $8 million in venture capital funding to help commercialize its NAO humanoid robot. The target market for this device is research labs working on the next generation of robotic hardware and software. Today, the company has posted a detailed spec of NAO on the arXiv saying that it expects the robot to cost about $15,000 each. That's cheap compared to other humanoids. Fuitsu's HOAP humanoids cost $50,000 each and various estimates price Honda's Asimo at $1 million per bot, although they are not for sale. Aldebaran-Robotics says that NAO's cost should come down to about $6,000 as production ramps up."
A hundred years from now, whether the readers are C or Fe, they will get a feeling of nausea reading about the 'retail prices' of 'humanoids.'
You can't talk about Wikipedia's flaws on Wikipedia
I want my robot NAO!
Somewhere in the back of my mind I have this strange feeling that we are slowly heading into Asimov's world. And all the problems (and benefits) that come along with it ...
Help a man when he is in trouble and he will remember you when he is in trouble again.
Yes, it does run Linux.
I don't see the appeal to having a humanoid robot. The robots in Wall*e for example were all designed for a function.
I think of any robot as a machine. They are there to serve a purpose. Even the IVR systems make me angry when they imply "I'm sorry. I didn't get that". No, the computer didn't recognize what I said. And "you" aren't sorry.
Anthropomorphizing robots, cute as they are in Wall*e, is insulting to the beauty of that which is life.
For all the details, hit this PDF
NAOs head is equipped with an x86 AMD GEODE 500 MHz CPU motherboard with 256 Mb SDRAM. An additional 1Gb Flash memory is available. Communication with the robot is possible through WiFi 802.11g protocol and through Ethernet port. The CPU manages audio, video, and WiFi and other advanced modules. One ARM7-60MHz microcontroller located in the torso distributes information to all the actuator module microcontrollers (Microchip 16 bit dsPICS) through a RS485 bus (throughput of 460[Kbits=s]). There are two RS485 buses, one that connects the ARM7 microcontroller to the dsPICS modules of the upper part of the body, and the other that connects the ARM7 to the dsPICS modules of the lower part of the body. This bus partition permits to increase the data throughput.
The ARM-7 microcontroller communicates with the CPU board through a USB-2 bus with a theoretical throughput of 11[Mbits=s]. It can be used to control the robots stabilityusing the inertial unit. The operating system is based on Linux, but the whole system can be modified.
Sensors:
30 FPS CMOS videocamera 1
Gyrometer 2
Accelerometer 3
Magnetic rotary encoder (MRE) 34
FSR 8
Infrared sensor (emitter/receiver) 2
Ultrasonic sensor 2
Loudspeaker 2
Microphone 4
If it can't reach the beer in the fridge, then who really cares.
FTA: "Initially, delivered with basic behaviors, the robot will be, at its market introduction, the ideal introduction to robots. Eventually, with many improved behaviors, it will become an autonomous family companion. Finally, with more sophisticated functions, it will adopt a new role, assisting with daily tasks (monitoring, etc.)"
Will, it, have, full, comma, functionality?
http://www.youtube.com/watch?v=W1czBcnX1Ww
Why can't someone make a bipedal robot as impressive as bigdog?
The RoboCup 2008 world competition just finished in Suzhou, China -- new this year was a league where all the teams must use the Nao robots. The top two teams were from the University of Newcastle (Australia) and a combined Carnegie Mellon/Georgia Tech team. The final game was scoreless and decided by penalty kicks. Full results are here:
http://www.tzi.de/4legged/bin/view/Website/NaoResults2008
I wasn't at the competition but it's clear due to the scores that the league is still in its infancy, with scores being few and far between. As with any humanoid robot, falling over is a huge problem. I'm sure there will be some videos of the competition online once all the teams get home and have time to edit and upload them.
Here's a video of the robot walking, from the 2008 RoboCup US Open (where there was no competition but a couple small demos for the public.)
http://youtube.com/watch?v=N7USdkA0My8