Mapping by Demonstration

A personalisation technique for gestural and sensor-based interfaces in which the system learns the relationship between user input (movement, breath, gaze) and output (sound, visuals, commands) from examples the user provides, rather than from designer-authored rules. The approach, associated with Jules Francoise and others, reduces the need for users to conform to a fixed gesture vocabulary and is particularly relevant for accessibility, where impairment-related variability in movement makes generic recognizers unreliable. Mapping by demonstration treats each user's movement repertoire as the training set rather than as noise to be normalised.