EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

DASH-ACT: Demonstration-Adaptive Step-Horizon Action Chunking for Manipulation

Yibo Cao, Zijun Yin, Jiahong Huang

Sensors · 17.11.2026 · 26 (22) · 7239

DOI: 10.3390/s26227239 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 17.11.2026. Verfasst von Yibo Cao und 2 weiteren Autor:innen. Die Arbeit nennt 26 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Key Technology Research (Second Batch) Program of Ningbo, South China Normal University.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Action Chunking Transformer (ACT) policies predict future action sequences, but their execution rules determine how quickly new observations can influence control. We present DASH-ACT, a supervised ACT extension combining motion-derived heuristic horizon labels, multihorizon prefix reconstruction, and a learned commitment selector. The policy predicts 20 actions and commits 5, 10, or 20 before replanning. On three LIBERO-10 tasks, mean success rates across three training seeds increase from 70.7% to 78.0%, 46.0% to 67.3%, and 68.0% to 91.3% relative to the evaluated fixed-20-step ACT baseline. These differences are descriptive and do not reach training-seed-level significance after correction across tasks. Separate execution controls reuse the trained DASH-ACT predictor with fixed horizons. Their post-hoc best per-task settings have slightly higher mean success than adaptive selection, leaving the benefit of the learned selector unresolved. In an independently trained physical eraser pick-and-place evaluation with lateral human perturbations, DASH-ACT succeeds in 44 of 50 trials, compared with 17 of 50 for ACT. The results identify queue commitment as a useful design variable within ACT and motivate direct label validation and component attribution.

Förderung

  • Key Technology Research (Second Batch) Program of Ningbo
  • South China Normal University

Zitieren

APA

Cao, Y., Yin, Z., & Huang, J. (2026). DASH-ACT: Demonstration-Adaptive Step-Horizon Action Chunking for Manipulation. Sensors, 26(22), 7239. https://doi.org/10.3390/s26227239

Vancouver

Cao Y, Yin Z, Huang J. DASH-ACT: Demonstration-Adaptive Step-Horizon Action Chunking for Manipulation. Sensors. 2026;26(22):7239. doi:10.3390/s26227239

BibTeX
@article{Cao2026,
  author = {Cao, Yibo and Yin, Zijun and Huang, Jiahong},
  title = {DASH-ACT: Demonstration-Adaptive Step-Horizon Action Chunking for Manipulation},
  journal = {Sensors},
  year = {2026},
  volume = {26},
  number = {22},
  pages = {7239},
  doi = {10.3390/s26227239}
}
Kostenlos starten →