Proton 2: Increasing the sensitivity and portability of a visuo-haptic surface interaction recorder

Robust Surface Recognition With the Maximum Mean Discrepancy: Degrading Haptic-Auditory Signals Through Bandwidth and Noise

“…1(a)) with an instrumented tool, as such data have previously been shown to reflect the friction, hardness, and texture of the surface being touched [25]. We prefer humanoperated rather than automatic haptic data collection because the hardware costs less and can be made portable for field use [3]. We carefully selected a set of C = 10 surface textures (Fig.…”

“…We carefully selected a set of C = 10 surface textures (Fig. 1(b)) from the Penn Haptic Texture Toolkit [26] drawn from material categories that are also representative of other surface datasets [2], [3]; similar pairs of materials (e.g., wood and laminate) were purposefully included to make recognition more challenging.…”