Data-Efficient Visual Perception under Edge-Computing Constraints: Application to Autonomous Localization and Humanoid Robot Soccer
學年 115
學期 1
出版（發表）日期 2026-10-11
作品名稱 Data-Efficient Visual Perception under Edge-Computing Constraints: Application to Autonomous Localization and Humanoid Robot Soccer
作品名稱（其他語言）
著者 Jaesik Jeong; Guilherme Henrique Galelli Christmann; Jeehyun Yang; Chao-Hsiang Hsiao; Yin-Tien Wang
單位
出版者
著錄名稱、卷期、頁數 Electronics 15(20) , p. 4638
摘要 For small robots, annotation can outlast computation as a bottleneck: hardware is bought once, labels at every deployment. We study label efficiency for landmark detection on a humanoid soccer robot. Against soft-argmax and pooled coordinate-regression baselines on 10–100% of 1193 labeled images under one protocol and two held-out sessions, the heatmap configuration is the more label-efficient: with hyperparameters fixed on the full pool, 298 training images (509 annotated) give 0.436 PCK@10 px, which neither baseline reaches with all 1193. The heatmap and soft-argmax arms differ in target, loss and readout, so the interval compares configurations, not representations; at equal held-out false-detection rates the heatmap stays ahead at both tolerances. A validation-to-held-out gap widens from 0.245 to 0.350 PCK@10 with more labels, similarly on both sessions. Int8 conversion, on the host CPU for two checkpoints, changes PCK@10 by at most 0.003. Two Edge TPU accelerators run the detectors in 5.18 and 19.71 ms, timed alone; reduced host bandwidth slows them by 2.8 and 8.2 for the landmark network despite near-complete parameter caching. A Monte Carlo filter is accurate to centimeters in simulation; one field demonstration agrees with hand-annotated positions only to decimeters, with an unresolved frame offset. Loop latency is unmeasured.
關鍵字 label efficiency; keypoint heatmaps; cross-session generalization; landmark localization; edge inference; humanoid robot soccer; teleoperation
語言 en
ISSN 2079-9292
期刊性質 國外
收錄於 SCI
產學合作
通訊作者 Yin-Tien Wang
審稿制度 是
國別 CHE
公開徵稿
出版型式 ,電子版
相關連結

機構典藏連結 ( http://tkuir.lib.tku.edu.tw:8080/dspace/handle/987654321/129984 )