Metraipolis › archive › dc_4471ead1e202

Self-Supervised Anchoring of Fingertip Sensing to Proprioception and Proactive Actions for Robot Imitation Learning — arXiv:2609.29822

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.29822
License (as archived)
CC0-1.0
Archived
2026-10-08T07:17:03.525Z
SHA-256 of the archived text
e821888510845a3e645167122a28f3ee328a570bce27da5ffa8f9583019adf4d
Stable URL of this page
https://metraipolis.com/documento/dc_4471ead1e202

How to cite

Self-Supervised Anchoring of Fingertip Sensing to Proprioception and Proactive Actions for Robot Imitation Learning — arXiv:2609.29822 — arXiv (en), https://arxiv.org/abs/2609.29822 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_4471ead1e202 (Metraipolis archive dc_4471ead1e202, sha256 e821888510845a3e645167122a28f3ee328a570bce27da5ffa8f9583019adf4d)
BibTeX
@misc{dc4471ead1e202,
  title = {Self-Supervised Anchoring of Fingertip Sensing to Proprioception and Proactive Actions for Robot Imitation Learning — arXiv:2609.29822},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.29822},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_4471ead1e202; sha256 e821888510845a3e645167122a28f3ee328a570bce27da5ffa8f9583019adf4d},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.29822. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Robotic imitation learning often relies on external cameras, yet local interaction cues such as object proximity, contact onset, and grasp state are difficult to observe near the fingertips because of occlusion and limited temporal resolution. We study how to effectively incorporate complementary fingertip sensing into imitation learning using pressure-sensitive tactile and reflective proximity sensors, along with pretrained sensor encoders. The two modalities provide information at different manipulation phases: proximity sensing is informative before contact, whereas tactile sensing becomes informative after contact. However, naively adding these signals to a policy does not consistently improve performance and can even underperform vision-only policies, suggesting that sparse, phase-dependent sensor signals are difficult to exploit from limited demonstrations. We therefore propose a proprioception-anchored pretraining method, PROprioceptive-and-PRoactive Anchoring (PROPRA), which independently aligns each fingertip sensor history with proprioceptive and action segments. This provides a continuously available sensorimotor reference, allowing each sensor to be aligned independently during its informative phases. Experiments on real-world manipulation tasks show that our pretraining method improves average success rates over vision-only policies and image-anchored pretraining baselines. Representation analysis further shows that it preserves richer information about pre-contact states, enabling more effective use of complementary fingertip sensing. Please refer to our project page: this https URL

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-25 in cs.RO).
Categorie arXiv: Robotics (cs.RO).
Pagina del lavoro: https://arxiv.org/abs/2609.29822 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-08T06:38:53.825Z dalla pagina https://arxiv.org/catchup/cs.RO/2026-09-25?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).