Tutorial, HRI conference 2025
This tutorial aims to equip researchers with the knowledge and skills to leverage multimodal data in human-robot interaction (HRI) studies. It covers the HRI study cycle, from sensor selection to data analysis, introducing commonly used sensors, pre-processing data, feature extraction techniques, fusion techniques and analysis techniques: both frequentist and Bayesian. Hands-on exercises using public datasets are designed to provide practical experience. The concluding panel discussion on bias and fairness in HRI data is focused on fostering broader ethical considerations of HRI studies
Registration (8.30 am - 9.00 am)
Morning Session 1 (9.00 am - 10.30 am): Welcome, Overview of HRI experimental study life cycle and Introduction to Sensors
Hands on: HRI Methodology Guideline - Life Cycle Design Tool
Coffee Break I (10.30 am - 11.00 am)
Morning Session 2 (11.00 am - 12.30 pm): Sensors and feature extraction
Physiological and behavioural features
Sensors suited for different contexts
Preprocessing and synchronisation
Feature extraction and user modelling
Hands on: Analysis and extraction of features from 2 datasets
Lunch Break (12.30pm - 1.30pm)
Afternoon Session 1 (1.30 pm - 3.00 pm): Data Fusion and Analysis
Overview of fusion techniques
Frequentist approach for data analysis
Bayesian approach for data analysis
Hands on: Fusion and analysis with a dataset
Coffee Break II (3.00 pm - 3.30 pm)
Afternoon Session 2 (3.30 pm - 4.00 pm): XAR Demonstration
Afternoon Session 2 (4.00 pm - 5.00 pm): Panel Discussion (see below)
Ethics of Robotics Research and Biases in Data
Panel Discussion
Afternoon Session 2