The iCub humanoid robot: an open platform for research in embodied cognition

437 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Is Deep Learning Safe for Robot Vision? Adversarial Examples Against the iCub Humanoid (2017, background): “Our case study focuses on the iCub humanoid, as it provides a cognitive humanoid robotic platform well suited to our task [18, 21].”
DeepMind Lab (2016, background): “One option is to directly study embodied intelligence in the real world itself using robots (e.g. Brooks, 1990; Metta et al., 2008).”
Bootstrapping humanoid robot skills by extracting semantic representations of human-like activities from virtual reality (2014, methodology): “Therefore, as a final step, we validate our framework on a humanoid robot, the iCub a 53 degrees of freedom humanoid robot [24].”
First-person tele-operation of a humanoid robot (2015, background): “It consists of a high resolution display, split vertically (one half for each eye) and a gyroscope to accurately track the head movement with a frequency of 1 kHz which is needed to avoid motion sickness.”
Tactile sensing in dexterous robot hands - Review (2015, methodology): “[99] is used to control iCub humanoid robot [100]; the controlling operating system dSPACE from dSPACE Co.”
Teaching iCub to recognize objects using deep Convolutional Neural Networks (2015, background): “Appearing in Proceedings of the 4 th Workshop on Ma- chine Learning for Interactive Systems (MLIS) 2015, Lille, France.”