Paper: (ICMLA) Terrain Classification

My paper on classifying terrain using the sensors on a quadrupedal robot, got accepted to the ICMLA conference.

Posted by 317070 on December 4, 2013

Using data retrieved from the Puppy II robot at the University of Zurich (UZH), we show that machine learning techniques with non-linearities and fading memory are effective for terrain classification, both supervised and unsupervised, even with a limited selection of input sensors. The results indicate that most information for terrain classification is found in the combination of tactile sensors and proprioceptive joint angle sensors. The classification error is small enough to have a robot adapt the gait to the terrain and hence move more robustly.

The paper can be found here