Metraipolis › archive › dc_689a95a3bec8

Lightweight and Resource-Efficient Perception for Robotic Guide Dogs — arXiv:2610.03187

Source
arXiv
Original
https://arxiv.org/abs/2610.03187
License (as archived)
CC0-1.0
Archived
2026-10-05T22:52:57.493Z
SHA-256 of the archived text
76de505a663c95dc673d8fb3bc81a4962f24a13b928dbb404ae7c59d80119142
Stable URL of this page
https://metraipolis.com/documento/dc_689a95a3bec8

How to cite

Lightweight and Resource-Efficient Perception for Robotic Guide Dogs — arXiv:2610.03187 — arXiv, https://arxiv.org/abs/2610.03187 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_689a95a3bec8 (Metraipolis archive dc_689a95a3bec8, sha256 76de505a663c95dc673d8fb3bc81a4962f24a13b928dbb404ae7c59d80119142)
BibTeX
@misc{dc689a95a3bec8,
  title = {Lightweight and Resource-Efficient Perception for Robotic Guide Dogs — arXiv:2610.03187},
  howpublished = {arXiv},
  url = {https://arxiv.org/abs/2610.03187},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_689a95a3bec8; sha256 76de505a663c95dc673d8fb3bc81a4962f24a13b928dbb404ae7c59d80119142},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv, https://arxiv.org/abs/2610.03187. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Multi-camera streaming perception is increasingly deployed on heterogeneous edge platforms shared with co-resident workloads, yet accelerator placement is often evaluated using isolated single-stream experiments and mean streaming average precision (sAP). Using two end-to-end pipelines on a single GPU--NPU platform, we show that isolated evaluation can mis-rank deployment-time placement. Although the GPU pipeline is preferred in isolation, GPU-localized contention introduces deadline misses that make detections stale and can reverse the preferred placement before full GPU saturation. The NPU pipeline is less accurate than the GPU pipeline on small and medium objects in isolation, but nearly matches it on large objects. The largest absolute sAP losses in our latency and contention experiments occur for large objects. In our four-stream experiments, the preferred placement depends on which path becomes stale, and increasing GPU-side contention shifts the best placement from All-GPU to All-NPU. Under a GPU-saturating vision--language co-tenant, All-NPU achieves $5.2\times$ the worst-stream sAP of All-GPU. Because mean sAP can hide severe single-stream degradation, evaluation should report contention sweeps, deadline-miss rates on both paths, and worst-stream sAP alongside mean sAP.

Tema degli esploratori: calcolo e infrastrutture (elenco arXiv cs.DC, nuovi lavori del giorno).
Categorie arXiv: Distributed, Parallel, and Cluster Computing (cs.DC) ; Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2610.03187 — 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 2026-10-05T22:46:25.534Z dalla pagina https://arxiv.org/list/cs.DC/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).