Efficient Waste Collection via Edge Perception and Optimized Mobile Routing

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

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

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.

Original languageEnglish
Title of host publicationProceedings - 2025 International Conference on Metaverse Computing, Networking and Applications, MetaCom 2025
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages123-124
Number of pages2
ISBN (Electronic)9798331522551
DOIs
StatePublished - 2025
Event3rd IEEE International Conference on Metaverse Computing, Networking and Applications, MetaCom 2025 - Seoul, Korea, Republic of
Duration: 27 Aug 202529 Aug 2025

Publication series

NameProceedings - 2025 International Conference on Metaverse Computing, Networking and Applications, MetaCom 2025

Conference

Conference3rd IEEE International Conference on Metaverse Computing, Networking and Applications, MetaCom 2025
Country/TerritoryKorea, Republic of
CitySeoul
Period27/08/2529/08/25

Keywords

  • depth aware pose refinement
  • edge camera localization
  • hierarchical perception planning architecture
  • mobile robot routing efficiency
  • multi layer perceptron residual correction
  • multi objective tsp path planning
  • robotic waste collection

Fingerprint

Dive into the research topics of 'Efficient Waste Collection via Edge Perception and Optimized Mobile Routing'. Together they form a unique fingerprint.

Cite this