Publikation
Investigating Active Sampling for Hardness Classification with Vision-Based Tactile Sensors
Junyi Chen; Alap Kshirsagar; Frederik Heller; Mario Gomez Andreu; Boris Belousov; Tim Schneider; Lisa Pui Yee Lin; Katja Doerschner; Knut Drewing; Jan Peters
In: Computing Research Repository eprint Journal (CoRR), Vol. abs/2505.13231, Pages 1-7, arXiv, 2025.
Zusammenfassung
One of the most important object properties that
humans and robots perceive through touch is hardness. This
paper investigates information-theoretic active sampling strate-
gies for sample-efficient hardness classification with vision-
based tactile sensors. We evaluate three probabilistic classifier
models and two model-uncertainty-based sampling strategies on
a robotic setup as well as on a previously published dataset of
samples collected by human testers. Our findings indicate that
the active sampling approaches, driven by uncertainty metrics,
surpass a random sampling baseline in terms of accuracy
and stability. Additionally, while in our human study, the
participants achieve an average accuracy of 48.00%, our best
approach achieves an average accuracy of 88.78% on the same
set of objects, demonstrating the effectiveness of vision-based
tactile sensors for object hardness classification.
