Metraipolis › archive › dc_e55eef78c824
PredTac: Learning Contact-Rich Manipulation with Predicted Touch — arXiv:2609.15198
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.15198
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-16T02:14:45.364Z
- SHA-256 of the archived text
0fd980b1cf020c66d2eeba4a6c39bcd87edc6d4a75676b99a48aae2c22537732- Stable URL of this page
https://metraipolis.com/documento/dc_e55eef78c824
How to cite
PredTac: Learning Contact-Rich Manipulation with Predicted Touch — arXiv:2609.15198 — arXiv (en), https://arxiv.org/abs/2609.15198 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_e55eef78c824 (Metraipolis archive dc_e55eef78c824, sha256 0fd980b1cf020c66d2eeba4a6c39bcd87edc6d4a75676b99a48aae2c22537732)
BibTeX
@misc{dce55eef78c824,
title = {PredTac: Learning Contact-Rich Manipulation with Predicted Touch — arXiv:2609.15198},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.15198},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_e55eef78c824; sha256 0fd980b1cf020c66d2eeba4a6c39bcd87edc6d4a75676b99a48aae2c22537732},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.15198. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Contact-rich manipulation benefits from tactile feedback, yet physical tactile sensors introduce hardware, calibration, synchronization, and maintenance costs that complicate policy learning and deployment. We formulate predicted touch as an alternative to measured tactile input and present PredTac, a framework that learns to infer tactile states from causal visual observations and robot states and uses the predicted touch as an explicit interface for policy learning and execution. A tactile predictor is first trained with tactile supervision and then used to provide contact information without requiring measured tactile input during downstream policy training or execution. We evaluate PredTac across three contact-rich manipulation tasks in simulation and on a real robot, and further examine how policy performance depends on the predicted contact content. In simulation goal-offset evaluations, predicted-touch policies achieve 27.0%, 52.0%, and 44.7% success on USB, Barbed-spike, and Valve, respectively, improving over the visual baseline by 8.0-13.7 percentage points. On the real robot, predicted-touch ACT achieves 70.0%, 50.0%, and 90.0% success on USB insertion, Barbed extraction, and Valve rotation, respectively, with a three-task mean of 70.0%, approaching measured-touch ACT at 72.2% and substantially outperforming visual ACT at 21.1%. Fixed-policy interventions further show that performance is sensitive to the spatial structure of predicted contact, with spatial rearrangement at fixed value distributions reducing Valve success by 10.7 percentage points. These results demonstrate that predicted touch can provide useful contact information for contact-rich manipulation without requiring tactile sensing as a policy input. Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-15 in cs.RO). Categorie arXiv: Robotics (cs.RO). Pagina del lavoro: https://arxiv.org/abs/2609.15198 — 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 2026-10-16T01:52:32.358Z dalla pagina https://arxiv.org/catchup/cs.RO/2026-09-15?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).