EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

A Spectral-Linear Trajectory Representation for Guided Diffusion-Based Manipulator Motion Planning in Constrained Environments

Zongjian Chen, Zichao Zou, Rongqian Yang, Shizhong Jiang

Machines · 13.07.2026 · 14 (7) · 782

DOI: 10.3390/machines14070782 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Machines, online erschienen am 13.07.2026. Verfasst von Zongjian Chen und 3 weiteren Autor:innen. Die Arbeit nennt 43 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Municipal Key Research and Development Project of Guangzhou, Natural Science Foundation of Guangdong Province, China, Key Project of the National Key Research Program.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Guided diffusion planners for robot manipulators often fail in bottleneck scenes. The reason is that local collision corrections must be coordinated through a limited latent parameterization. This study examines the issue at the level of trajectory representation. Spectral-linear representation is introduced as a compact joint-space representation that combines an endpoint-conditioned linear reference path with a small set of globally supported eigenmodes derived from a conditioned temporal kernel. Using a shared training corpus, conditioning scheme, guidance rule, and dense-evaluation protocol, spectral-linear representation is compared with five representative alternatives across six representation families and dimensionality sweeps from 14 to 448 dimensions. With 14 latent dimensions, spectral-linear representation attains the highest structured-scene success rates among the tested families, reaching 74.2% on narrow-passage scenes and 84.5% on rack-like scenes. Expert-only controls, per-family guidance tuning, and a Transformer-backbone rerun are consistent with the same broad ranking pattern. These results indicate that, under limited guidance budgets and within the tested protocol, the representation structure is more predictive of bottleneck success than latent width alone.

Förderung

  • Municipal Key Research and Development Project of Guangzhou
  • Natural Science Foundation of Guangdong Province, China
  • Key Project of the National Key Research Program

Zitieren

APA

Chen, Z., Zou, Z., Yang, R., & Jiang, S. (2026). A Spectral-Linear Trajectory Representation for Guided Diffusion-Based Manipulator Motion Planning in Constrained Environments. Machines, 14(7), 782. https://doi.org/10.3390/machines14070782

Vancouver

Chen Z, Zou Z, Yang R, Jiang S. A Spectral-Linear Trajectory Representation for Guided Diffusion-Based Manipulator Motion Planning in Constrained Environments. Machines. 2026;14(7):782. doi:10.3390/machines14070782

BibTeX
@article{Chen2026,
  author = {Chen, Zongjian and Zou, Zichao and Yang, Rongqian and Jiang, Shizhong},
  title = {A Spectral-Linear Trajectory Representation for Guided Diffusion-Based Manipulator Motion Planning in Constrained Environments},
  journal = {Machines},
  year = {2026},
  volume = {14},
  number = {7},
  pages = {782},
  doi = {10.3390/machines14070782}
}
Kostenlos starten →