Task models representations and algorithms for human robot collaboration.

A set of tools and experimental scripts used to achieve multimodal learning with nonnegative matrix factorization (NMF).

Intended to ease the design of human-robot collaboration experiments, it focuses on scenarios like the collaborative assembly of furniture and consists of miniature pieces of furniture composed of a combination of standard hardware components and 3D printed custom designs. The parts have been chosen and designed for the purpose of robotics experiments with an additional care on modularity. The model has been thought to be easy to extend and distribute.

This dataset is made of choreography motions captured through a kinect device. The choreography motions have a particular combinatorial structure: choreographies are designed as simultaneous execution of some primitive motions from a given set of primitive dance motions.

This dataset is made of single gestures captured through a kinect device.

The Caregiver dataset was recorder by the Acorns project. It is available online thanks to Christina Bergman's work. See also Modelling the Noise-Robustness of Infants’ Word Representations: The Impact of Previous Experience for details on permissions to use the dataset. I also provide features to use directly in the multimodal experiments (see the code for more details).