HOME / ACCUEIL
View My Blog
Send me a message
devenir annonceur / advertise
Sport and digital creation: when athletes and artists share the same playground
Reaching for the sky: artists conquering space
When digital artists take up the challenge of new stakes in artificial intelligence
Augmented reality and artistic experience(s)
The European Digital Art and Science Network supports new CREATION processes for artists
Signal 2016 : festival of lights in Prague
International Digital Art Festival Patchlab in Krakow
Virtual Reality Revisited with ArtFutura festival 2016
Japan Media Arts Festival 20th Anniversary Exhibition - Power to Change
Sounds, visuals and lights: the multidisciplinary experience of Atonal 2016
More blog entries
Art-bot artists such as Bill Vorn or Morgan Rauscher can maybe take into account for their next works the new robot arm developed by Lausanne-based Learning Algorithms and Systems Laboratory (LASA) at EPFL (Ecole Polytechnique Fédérale de Lausanne).
The 1.5m long robotic arm is effectively capable of reacting on the spot and grasping objects with complex shapes and trajectories in less than five hundredths of a second! The experiences made with a ball, an empty bottle, a half full bottle, a hammer and a tennis racket – objects offering a varied range of situations - is actually very close to a genuine learning programme, copying the way humans learn themselves, by imitation, trial and error.
Aude Billard, head of LASA, explains the way it works. "Today’s machines are often pre-programmed and cannot quickly assimilate data changes. Consequently, their only choice is to recalculate the trajectories, which requires too much time from them in situations in which every fraction of a second can be decisive."
On an opposite way, the technique used here was called Programming by Demonstration. Without giving specific directions to the robot, it shows instead examples of possible trajectories to it, through a series of cameras located all around the robot. The robot then creates a model for the objects’ kinetics based on their trajectories, speeds and rotational movement, a model that the machine refines and corrects by repeating the exercise several times.
Aude Billard Bill Vorn dm_feature dm_innovation dm_news EPFL INNOVATION innovation LASA machine robot by
Digitalarti media: Digitalarti media is published by Digitalarti. For digital creations services, please check the Digitalarti services site and contact us.