Metraipolis › archive › dc_89fbdce60a20

A Multimodal Label Forecasting Method for Aperiodic Visuo-Motor Time Series — arXiv:2609.07930

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.07930
License (as archived)
CC0-1.0
Archived
2026-10-16T15:31:13.715Z
SHA-256 of the archived text
239b61ba6aabc26eaf7e3e4bcd20eac0718c109960c7e6d1a24399ab6f1e6716
Stable URL of this page
https://metraipolis.com/documento/dc_89fbdce60a20

How to cite

A Multimodal Label Forecasting Method for Aperiodic Visuo-Motor Time Series — arXiv:2609.07930 — arXiv (en), https://arxiv.org/abs/2609.07930 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_89fbdce60a20 (Metraipolis archive dc_89fbdce60a20, sha256 239b61ba6aabc26eaf7e3e4bcd20eac0718c109960c7e6d1a24399ab6f1e6716)
BibTeX
@misc{dc89fbdce60a20,
  title = {A Multimodal Label Forecasting Method for Aperiodic Visuo-Motor Time Series — arXiv:2609.07930},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.07930},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_89fbdce60a20; sha256 239b61ba6aabc26eaf7e3e4bcd20eac0718c109960c7e6d1a24399ab6f1e6716},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.07930. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Deep learning models have been increasingly applied to Time Series Forecasting (TSF) in recent years. Transformer-based and MLP-based models have both been used effectively on many real-world TSF regression benchmarks, and there is ongoing debate as to which family of methods is best. While these benchmarks have drawn much attention, it is also worth noting that many current datasets and methods assume approximate periodicity in the time series. In this work, we focus on a new TSF task without periodicity: anticipating falls during humanoid locomotion, on the basis of egocentric vision and proprioception. When the locomotion trajectories are sufficiently diverse, periodicity is violated. We contribute two new benchmark datasets (one from simulation, one from real hardware), showing that periodicity is violated and recent deep TSF methods struggle on these benchmarks. We also propose a novel deep learning architecture that exploits both endogenous and exogenous variables and a training process that rigorously enforces i.i.d sampling of training examples. Our results show statistically significant improvement over prior art in multiple experimental conditions, by 12.73% or more on the real data and 10.40% or more on the simulation data. Code and datasets will be available upon acceptance.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-09 in cs.RO).
Categorie arXiv: Robotics (cs.RO).
Pagina del lavoro: https://arxiv.org/abs/2609.07930 — 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 2026-10-16T15:11:47.611Z dalla pagina https://arxiv.org/catchup/cs.RO/2026-09-09?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).