The Qbo kit includes a basic chassis and mounting plates, the five open-source hardware controller boards TheCorpora has developers, webcams and the necessary cabling. However, buyers will have to provide everything else: the PC brain, servo motors, batteries, etc. There’s a full list of components here.

The Qbo Lite comes in at €1,699 ($2,220; again, a promotion), and is fitted with an Atom D2700 Mini-ITX board, 2GB of DDR3 memory, an HDD and WiFi b/g/n. It will begin shipping in Q4 2012.

Finally, the Qbo Pro is €2,299 ($3,005; a promo price), and comes with an Intel Core i3-2100T Mini-ITX computer with 2GB of ultra-low-profile memory and a 40GB Intel SSD. There are also various added extras on top of the Lite model, such as mechanical eyelids. It too will ship in Q4.

We’ve been huge fans of Qbo over the months, watching the robot learn how to use 3D cameras for environment mapping, take advantage of crowd-sourcing to recognize objects, and track gestures, among many other things. More details in the timeline below.

TheCorpora say that three versions of the robot will be available. First, the company will offer a kit, which will let brave souls build their own robot from scratch. If you’re not quite feeling up for that, you’ll be able to buy two different pre-assembled kits. The Lite edition will come with an Intel Atom processor inside, while the Pro version will pack a little more juice with a Core i3 CPU.

The Qbo robot has a myriad of powerful features at its disposal that developers will be able to take advantage of. Included in the body are four ultrasonic sensors, two HD webcams to serve as eyes, as well as an ASUS 3D sensor which will scan the surrounding environment and generate a 3D model that can be layered on top of the 2D mapping generated by the other sensors.

Unfortunately there are no pricing details for the Qbo robots yet, although we expect that there will be some info when the official website and pre-orders go live next week.

In total there are five hardware boards that TheCorpora have designed, the specifications of which will be released under open-source licensing for others to play with. They’ll be paired with standard EMG-30 motors, SRF10 ultrasonic sensors, an LCD, storage, a PC motherboard and “many other components” before being hidden by the plastic body panels.

However, although the expectation is that most will probably choose the Qbo base platform to work from, that’s not to say it’s a requirement. As long as there’s sufficient room in your platform of choice, there’s plenty of flexibility; if you’d rather have an intelligent Dalek rather than the altogether cuter Qbo then you can.

Exactly how intelligent that Dalek can be might surprise you. Although Qbo looks toylike, it can use 3D sensors similar to Microsoft’s Kinect for digital terrain mapping and navigation, identify people and objects and recognize them subsequently, and even use crowdsourcing to boost its skills. There’s also an Android remote control app for using Qbo as a telepresence or security system.

Luckily for those who are more hands-off with their tech, TheCorpora will be offering a fully-constructed version of the Qbo so that you can leave your screwdrivers in the toolbox. Pricing and availability are still yet to be confirmed, though the ‘bot is said to be coming “very soon.”

“This sensor emits a 3D point cloud that, along with the robot’s odometry sensor and the incorporated gyroscope, enables Q.bo to build maps, 3D modeling of objects and autonomous localization in real-time” the TheCorpora team says of the modification. ASUS’ sensor is based on the same sort of 3D tracking technology as in Microsoft’s Kinect, but the Xtion Pro Live was picked because it is more compact.

All combined, both 2D and 3D sensors are used for SLAM (Simultaneous Localization And Mapping), allowing Qbo to navigate around a changing environment autonomously. The Xtion sensor builds up a 2D map of the room which is cached and then overlaid with ad-hoc collision prevention data.

Qbo is, TheCorpora says, nearing the stage of commercial readiness, with the robot expected to go on sale sometime later in 2012. No word on pricing yet, however.

Have a peek at the hands-on presentation video in this post to get a better idea of what it could mean for you to be controlling a robot friend from the other side of the world – Qbo does this, or at least it will very soon, and you’ll be able to take advantage of it from any Android device. You’ll be able to move this little guy around, change his expressions, make him say whatever you want via Google’s speech recognition OR directly through your microphone, and, best of all, you can do things like recognize objects and follow them. Weird and awesome!

Here’s a note directly from the Qbo team on the inner workings of this new system:

How the system works?
Internally, Qbo acts as a server, with REST as a communication protocol, sending information in JSON format. You will find an API, very easy to use and very handy. For example, in order to move the head just pack the coordinates into a JSON, and make a HTTP petition to, for example  “http://192.168.4.6:8880/control/qbo_arduqbo/headServos” and Qbo will manage itself, launching the necessary ROS nodes.
The audio connection uses the SIP protocol (Session Initiative Protocol). We wanted to make each Qbo independent from any external SIP server, so each one has the Asterisk SIP server installed to make calls directly to the robot. On top, it has a SIP client to accept incoming calls and send audio back. This enables Qbo to communicate with devices regardless of the platform, since there are applications available in each of these systems (MacOSX, Windows, Linux, Android, IOS…).

Looks like a lot of fun! Can you even wait to try it out? We can’t!

[via Qbo]

The Qbo pays attention to the hands that are nearby using stereoscopic vision. To control the music the user can put their finger s in a “V” and point the V towards the ground to get the bot to turn down the volume. Turing the V towards the sky will turn the volume up. A closed fist will stop the music and play the music.

Pointing left and right with a finger will get the bot to skip forward and backwards in the playlist. Watching the video the robot needs a few seconds at the start to respond to the commands. Later in the video, the robot is responding more quickly to the gestures. Watch the video below to see for yourself.

[via TheCorpora]

In the first part of the demo below, Qbo is shown using first a face-identifying system to spot people nearby, and then a skin color filter to track that person’s movement around the room. The second demo relies on the robot’s stereoscopic vision, with Qbo defaulting to focusing on objects nearest to it.

Interestingly, once Qbo has identified an object, it can subsequently spot it even if there are changes in color, scale, orientation or even if the object is partially blocked from the robot’s sight. Repeated viewing speeds up subsequent identification, and thanks to the cloud system those recurring encounters needn’t be with the same Qbo unit. Specifically, The Corpora has implemented a “bag of words” model (coupled with SURF), breaking the view of an object up into multiple sections.

Qbo flips between the two modes via voice prompts, part of the team’s intent to make controlling the robot something that needn’t be done with a keyboard, mouse and display. Still no exact timescale for when we’ll be able to buy – or build – one of our own, unfortunately.

The demo was designed to show the company eventually responsible for mass-production of Qbo exactly what the robot was capable of, though it actually ended up teaching TheCorpora more about naturalistic interactions. The log file storing the ‘bot’s activity recorded various occasions where bright sunlight distracted its vision, as well as a tendency to position itself further back from taller people than from shorter.

Rather than making a bad impression, however, the glitchy Qbo was perceived as more human in its behaviors. Just as people can be dazzled by bright light, or generally increase inter-personal distance when near taller companions, those tendencies in the robot only made it seem more alive rather than a PC on wheels.

The question TheCorpora is left with is deciding just how many bugs in their “social robot” software to iron out, and how many to leave based on the premise that “flaws” in perfect robot behavior actually contribute more than they confuse. That’s only likely to make the software environment more complex; for this particular demo, only the artificial vision, synthesis and speech recognition, the chatterbot and the modules in charge of sending and receiving data to the two Qbo internal controllers were active, but there’s considerably more in the roadmap.

If you’re not up to speed, Qbo is Francisco Paz’s attempt to bring DIY robotics to a more affordable price point, using a combination of off-the-shelf hardware and custom software. The latter will be released under an open-source license, meaning anybody can build their own ‘bot; we’re presuming that the option to buy an official chassis – and maybe even a completely pre-built Qbo – will also be on the cards.

Head molds for the robot arrived back in January – shown below – though it seems we’re still some way off having our own personal voice-activated butler. Expect stereoscopic vision, WiFi and Bluetooth connectivity, obstacle avoidance and more when Qbo finally reaches release status.

That includes stereoscopic high-def webcam vision in a moveable head, complete with three microphones and even motorized eyelids.  Meanwhile the base section has various ultrasonic and infrared sensors, a status display, stereo speakers and the brains of the Qbo, a Mini-ITX board with Intel Atom CPU and NVIDIA Ion graphics.

Altogether that supports stereoscopic vision, speech recognition and synthesis, and object avoidance, with the ‘bot using WiFi and Bluetooth to communicate.  Being a big robot geek I’m really looking forward to seeing this project grow; who knows, maybe I’ll retrieve my spanner set from Elton and make one myself.

As of right now, Qbo has only a few skills at its disposal. However, those skills are pretty impressive for a robot that doesn’t have any arms, and a big head. Don’t let the no arms thing scare you: Paz intended to keep the arms off the ‘bot, due to the high cost of resources. Right now, the Qbo is apparently constructed of more than 30 plastic parts, making it one of the more intricate robots out there, for sure. Especially its small size. And that small size is meant for a reason: to make sure that the robot can interact with you in a way that seems (almost) natural, and doesn’t necessarily get in the way. Unobtrusive, it seems.

Now, let’s get down into the skills, where the meat and bones of this little robot are. First, it features stereoscopic vision, which includes: webcam calibration for two webcams; depth, face, color, and object recognition; the ability to track faces and objects; and right now there’s even a map generating software being currently tested. Speech recognition is thrown in for good measure, making sure that you can talk to your Qbo, too. Other features include Speech Synthesis systems, a WEB control panel, an Internet connection thanks to a WiFi controller in the head, the ability to avoid obstacles thanks to the ultrasound sensors, and finally the ability to autocharge the battery, which is still being tested. As of right now, there’s still no word on when it will get released, or even finished, but if the schematics are any sign, it’s looking very, very good.

[via The Corpora]

Full specifications of Qbo are unclear – in fact we don’t even have a full photo of the ‘bot – but Paz has fleshed out some of his intentions.  He wants to create the Ford Model T of hobby robots, an affordable platform with controller, memory, ultrasound sensors, webcams, compass, batteries and a physical framework, the Linux-based OS and an attractive casing to clad it in.

The guess is that Qbo will be able to do image processing, speech recognition, speech synthesis and object avoidance, things that would typically require a pretty expensive off-the-shelf robot or an expensive DIY project.  Paz is promising to flesh things out with the full details soon.

[via PlasticPals]