Explore projects

Minimal running example of the Python script used to calculate "Time spent together", "Number of different clusters" and "Number of cluster switches" from the scores provided in the Excel file.

The python script and YAML database to generate CNCS website pages automatically, fetching also people's pictures.

Addressee Estimation is the ability to understand to whom a person is directing an utterance. This ability is crucial for social robot engaging in multi-party interaction to understand the basic dynamics of social communication. In this project, we deploy a DL model on an iCub robot to estimate the placement of the addressee from the robot's first person perspective by taking as input visual information of the speaker. Specifically, we extract two visual features: body pose vectors and face images of the speaker from the camera stream of the iCub and use them to feed our model. The model classify the addressee's placement as 'robot', 'left', or 'right, meaning respectfully that the addressee is the robot, or is at the robot's left or right.

This project is meant to implement a model to provide the iCub robot with addressee estimation skill through a classifier based on hybrid deep learning neural network.

A controller for the cartesian velocity of iCub

Autoencoder that recovers details in images obtained by perspective transformation

This is the project for a demo to let iCub guess which letter/word the user writes on its skin.

The project contains the HW , FW and SW needed to built and operate stand-alone magnetically docking devices for Tattoo Electrode interface. All material is available as open source.

Paco is a tool to build solvers and optimize quality functions on graphs for community detection.