Per Sjöborg has a series of audio interviews with leading researchers and thinkers in the field self-reconfiguring modular robotics.
On his website Flexibility Envelope he describes the field of self-reconfiguring modular robotics as the joining two elements:
The first part is Modular robotics. This is a branch of robotics that aims to build complex systems with simple components. A bit like Lego,simple pieces are,by cooperating,capable of building complex objects.
The Second part is Self-reorganization to make the units able to move among each other on their own accord and thus reconfigure themselves from one task to another without human intervention. This also allows the system created to be active and dynamic.
His audio interviews can be found on here and are a great listen.
Birgus Latro has posted a write up and several videos looking at the Cubelets KT01 Construction Kit from Modular Robotics. This is the first production run of the Cublets and was limited to just 100 kits.
Cublets are a modular robotics kit that consists of 20 magnetic blocks that can be snapped together to make an endless variety of robots with no programming and no wires. Each cubelet in the kit has different equipment on board and a different default behavior. There are Sense Blocks that act like our eyes and ears; they can sense light, temperature, and how far they are away from other objects.
IEEE Spectrum has an article by Dr Massimiliano Versace about a memristor-based approach to AI that consists of a chip that mimics how neurons process information.
Researchers have suspected for decades that real artificial intelligence can't be done on traditional hardware, with its rigid adherence to Boolean logic and vast separation between memory and processing. But that knowledge was of little use until about two years ago, when HP built a new class of electronic device called a memristor. Before the memristor, it would have been impossible to create something with the form factor of a brain, the low power requirements, and the instantaneous internal communications. Turns out that those three things are key to making anything that resembles the brain and thus can be trained and coaxed to behave like a brain. In this case, form is function, or more accurately, function is hopeless without form.
Basically, memristors are small enough, cheap enough, and efficient enough to fill the bill. Perhaps most important, they have key characteristics that resemble those of synapses. That's why they will be a crucial enabler of an artificial intelligence worthy of the term.
Kinect RGBDemo and the Nestk Library by Nicolas Burrus aim at providing a simple toolkit to start playing with Kinect data and develop standalone computer vision programs without the hassle of integrating existing libraries.
The 0.6 release includes two new demos, an interactive program to calibrate multiple RGBD cameras, and a one shot 3D model acquisition of objects lying on a table based on PCL table top detector.
Current features include:
- Grab kinect images and visualize / replay them
- Support for libfreenect and OpenNI/Nite backends
- Extract skeleton data / hand point position (Nite backend)
- Integration with OpenCV and PCL
- Multiple Kinect support and calibration
- Calibrate the camera to get point clouds in metric space (libfreenect)
- Export to meshlab/blender using .ply files
- Demo of 3D scene reconstruction using a freehand Kinect
- Demo of people detection and localization
- Demo of gesture recognition and skeleton tracking using Nite
- Demo of 3D model estimation of objects lying on a table (based on PCL table top object detector)
- Demo of multiple kinect calibration
- Linux, MacOSX and Windows support
The robotic inspector looks like nothing more than a small metallic cannonball. There are no propellers or rudders, or any obvious mechanism on its surface to power the robot through an underwater environment. A robot outfitted with external thrusters or propellers would easily lodge in a reactor’s intricate structures, including sensor probes, networks of pipes and joints.
As the robot navigates a pipe system, the onboard camera takes images along the pipe’s interior. The original plan was to retrieve the robot and examine the images afterward. But now the MIT project director and his students are working to equip the robot with wireless underwater communications, using laser optics to transmit images in real time across distances of up to 100 meters.
MAKE Magazine has a selection of ten of the most interesting robotic limbs from the archives. Including a robot sorts over 400 pancakes per minute.
- an iRobot Create
- a Kinect (modified to run off of a battery)
- a computer running all the nessecary open source software
- a small robot arm that uses geared motors, and can lift objects weighting up to 3 lbs
- and all the mounting hardware, , wiring and electronics needed to put it all together.
Gregory Epps uses standard industrial robots to build complex and accurate forms out of sheet metal. The forming is achieved by folding sheet metal along curved crease lines.
Using the Grasshopper generative CAD software alongside Kangaroo, physics simulation software, Gregory is able to build objects not possible with other methods of sheet metal manipulation.
The Robofold webpage is here and Gregory also has another site that discusses topics related to CAD and generative design.
You can also watch a video of the robots assembling the chair pictured here.
The project has ended and the results of the project are available here or on their YouTube channel here.
Records 481 to 495 of 504