EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

AMSDS: Adaptive Cloud-Edge Visual Navigation via DNN Partitioning and Semantic Compression

Yuntao Hao, Nan Ding, Wenbin Sun, Li Xu

ACM Transactions on Embedded Computing Systems · 30.11.2026 · 25 (6) · 1-30

DOI: 10.1145/3860325 ↗

Kurz gefasst

Fachartikel in der Zeitschrift ACM Transactions on Embedded Computing Systems, online erschienen am 16.11.2026. Verfasst von Yuntao Hao und 3 weiteren Autor:innen. Die Arbeit nennt 29 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Visual navigation has become a fundamental capability for embodied intelligent agents, but deploying such systems on resource-constrained embedded edge devices remains difficult due to the substantial computation and communication overhead of high-level decision models. This article proposes the Adaptive Model Partitioning and Deployment System (AMSDS), an edge–cloud collaborative framework for reducing end-to-end inference latency in target-driven visual navigation. AMSDS adaptively determines the collaborative inference mode according to the topology of the high-level decision model, model complexity, workload state, and runtime network condition. For models with acceptable partitioning overhead, AMSDS applies offline DAG simplification and efficient cut inference to obtain low-latency partition strategies. For models with overly complex models, or heavy-workload states, AMSDS switches to a semantic-compression path based on a Semantic Map Convolutional Autoencoder (SM-CAE), which reduces transmission overhead while preserving navigation performance. Experimental results show that AMSDS consistently outperforms baseline methods in inference latency, latency speedup, and throughput. Moreover, evaluations under dynamic bandwidth/load traces and time-varying task-arrival conditions demonstrate that AMSDS remains effective under realistic runtime variations.

Förderung

  • National Natural Science Foundation of China

Zitieren

APA

Hao, Y., Ding, N., Sun, W., & Xu, L. (2026). AMSDS: Adaptive Cloud-Edge Visual Navigation via DNN Partitioning and Semantic Compression. ACM Transactions on Embedded Computing Systems, 25(6), 1-30. https://doi.org/10.1145/3860325

Vancouver

Hao Y, Ding N, Sun W, Xu L. AMSDS: Adaptive Cloud-Edge Visual Navigation via DNN Partitioning and Semantic Compression. ACM Transactions on Embedded Computing Systems. 2026;25(6):1-30. doi:10.1145/3860325

BibTeX
@article{Hao2026,
  author = {Hao, Yuntao and Ding, Nan and Sun, Wenbin and Xu, Li},
  title = {AMSDS: Adaptive Cloud-Edge Visual Navigation via DNN Partitioning and Semantic Compression},
  journal = {ACM Transactions on Embedded Computing Systems},
  year = {2026},
  volume = {25},
  number = {6},
  pages = {1--30},
  doi = {10.1145/3860325}
}
Kostenlos starten →