Efficient Waste Collection via Edge Perception and Optimized Mobile Routing

  • Lee, Yunseon
  • Lee, Myeonghyeon
  • Park, Kimun
  • Kwon, Dahun
  • Seok, Moon Gi
Citations

WEB OF SCIENCE

0
Citations

SCOPUS

0

초록

We present a two-stage framework for robotic waste collection that combines global perception and local planning. Fixed edge cameras perform wide-area object detection, and a Multi-Layer Perceptron (MLP) corrects geometric projection errors for improved localization. Mobile robots then refine poses using depth sensing and execute pickup actions along routes optimized by a multi-objective Traveling Salesman Problem (TSP) planner. Experiments in a controlled lab demonstrate that the MLP correction significantly enhances positioning accuracy, while the optimized routing reduces path length and improves collection efficiency. © 2025 Elsevier B.V., All rights reserved.

키워드

depth aware pose refinementedge camera localizationhierarchical perception planning architecturemobile robot routing efficiencymulti layer perceptron residual correctionmulti objective tsp path planningrobotic waste collection
제목
Efficient Waste Collection via Edge Perception and Optimized Mobile Routing
저자
Lee, YunseonLee, MyeonghyeonPark, KimunKwon, DahunSeok, Moon Gi
DOI
10.1109/MetaCom65502.2025.00027
발행일
2025
유형
Proceedings Paper
저널명
2025 International Conference on Metaverse Computing, Networking and Applications (MetaCom)
페이지
123 ~ 124