The post Sculptures Robots – A Creative Robot Design by “+BRAUER” appeared first on Robotpark ACADEMY.

The machine watches itself while painting and decides indepentently where to add new strokes. This way paintings are created that are not completely defined by the programmer but are the result of a visual optimization process. (informatik.uni-konstanz.de/en/edavid/news/)

Paintings of e-David Robot

---

Scientific Motivation of e-David

Our hypothesis is that painting – at least the technical part of painting – can be seen as optimization processes in which color is manually distributed on a canvas until the painter is able to recognize the content – regardless if it is a representational painting or not. Optimization happens intuitively during the drawing process and is highly dependent on the medium and its restrictions. Centuries of so-called academic art have been shown to what extent algorithms for spatial division as well as color and content composition can be used for creating art works.

On the other side computer graphics, and especially in so-called non-photorealistic rendering made a lot of progress in imitating painting styles using the computer. By simulating media and stroke composition a lot of painting-like images were produced, typically by computing pixel information that later was printed on a conventional printer. E-David will substitute this by distributing real color on real canvas and thus will enable us to enclose the whole process of drawing production into an optimization framework. This will allow us to investigate human “optimization schemes” and to find out to what extent such schemes can be formulated using algorithms. We will use iterated optimization schemes to produce color distributions on the canvas which are constrained by given styles. Semantic information can be integrated to optimize representational paintings; a tree will be painted in a different way than a face even if the colors are similar. Such semantic information can be obtained from semantic image analysis of the given target image. A number of other questions arise immediately:

When you watch an artist paint, individual brush strokes can seem random. It’s often not until close to the very end that the image the painter is after becomes clear. This is doubly true when you watch e-David, the robot painter, at work. David, which stands for “Drawing Apparatus for Vivid Image Display,” was created by a team of engineers at the University of Konstanz in Germany.

He’s a former welding robot who has been retrofitted to reproduce, brush stroke by brush stroke, existing works of art. The robotic arm has access to five different brushes and 25 colors of paint, and after each dab of paint, it takes a photograph of what it has painted so far- computer software analyzes the photograph and tells David where to place the next brush stroke. The strangeness of the process is especially evident when David signs his name at the end.

As you can see in this video, he begins by making the dot over the “i” and then writes the rest of his name backwards- hardly how you or I would do it, and a clear reminder that- once someone else has given you the idea- there’s more than one way to make the Mona Lisa.

Resources:

Video Link Vimeo – http://vimeo.com/68859229

http://www.boston.com/bostonglobe/ideas/brainiac/2013/08/paint-by-robot.html

http://www.informatik.uni-konstanz.de/en/edavid/

The post e-David Robot Painting 11114 appeared first on Robotpark ACADEMY.

ETH Zurich, 2012.

Autonomous Systems Lab – http://www.asl.ethz.ch
Legged Robotics – http://leggedrobotics.ethz.ch
Ballbot Rezero – http://rezero.ethz.ch
NCCR – http://www.nccr-robotics.ch/
myCopter – http://mycopter.eu
ICARUS – http://www.fp7-icarus.eu

The post A Robotic Christmas Video – 11101 appeared first on Robotpark ACADEMY.

Video Link

Youtube: http://youtu.be/hlx-M53dC7M

The post BMW Museum – Kinetic Sculpture 11074 appeared first on Robotpark ACADEMY.

“adorable little lamp ROBOT that appears in the Disney Pixar Logo”

Luxo Jr, the adorable little lamp that appears in the Disney Pixar logo, illustrates how animators can breathe life into mundane inanimate objects. Now, robotics technology allows us to do the same thing in real life, as shown by a trio from the Victoria University of Wellington, New Zealand. Using a combination of readily available robotics and automated manufacturing technology, mixed with open-source software, they were able to grace a desk lamp with a little personality.

Pinokio, unlike its fairy tale namesake, needs strings to move – strings of code, that is. Its actions are driven primarily by Arduino and image processing software OpenCV, which searches for faces in the images from its web cam. When it finds a face, it attempts to follow it as if trying to maintain eye contact.

Programmer Shanshan Zhou ensured it would change its behavior with preset “moods” – introvert or extrovert – causing the lamp to recoil or stretch outwards, respectively. When switched off, Pinokio responds by flicking its power switch back on – similar to the most useless machine ever– further adding to its character.

Adam Ben-Dror, who worked out the mechanical details, found that it only took six servo motors to actuate the lamp’s hinges. These hinges had to be replaced with ones he designed in CAD, which were then manufactured using a variety of techniques, from 3D printing, laser cutting, water jet cutting, and CNC lathing to good old-fashioned welding. He also had to work out how to fit the halogen bulb (covered with a mechanical iris), a hacked webcam, a microphone, and a pair of servos – including the necessary wiring – into the back of the lamp’s shade.

As you’ll see in the video below, the end result lives up to the concept sketches provided by the team’s designer, Joss Dogget. Pinokio springs to life and engages its audience with seemingly effortless interaction.

External Links

http://www.creativeapplications.net/processing/pinokio-the-animatronic-lamp-that-is-aware-of-its-environment/

The post Creative Project – Adorable Little Lamp Robot – 31014 appeared first on Robotpark ACADEMY.

Client: SATURN
Advertising Agency: Scholz&Friends, Berlin, Germany (www.s-f.com)

Creative Director: Oliver Handlos
Art Director: James Cruickshank, Michael Hess
Copywriter: Felix Fenz, Sebastian Plum, Bastian Engbert

Management Supervisor: Uli Schuppach
Account Supervisor: Sandra Ortmann, Jürgen Fink
TV-Producer: Claudia Knipping, Nina Heyn, Mathis Rekowski

Director: Carl Erik Rinsch
Executive Producer: Lutz Müller
Producer: Tobias Steinhauser
DoP: Javier Aguirresarobe
Postproduction: Alex Grau
Charakter-Design: Jeff Julian, Big Lazy Robot

Sounddesign: Audioforce

The post Robotic Art – Robotic Evolution – 11054 appeared first on Robotpark ACADEMY.