JAIST Repository >
JAIST >
Theses >
Doctor of Philosophy(Information Science) >
R07) (Jun.2025 - Mar.2026 >

Please use this identifier to cite or link to this item: https://hdl.handle.net/10119/20593

Title: 軌道走行型パトロールロボットシステムの速度制御とSim-to-Real展開のための説明可能な深層強化学習フレームワーク
Authors: 李, 鎬先
Authors(alternative): い, ほせん
Keywords: Rail-guided patrol robot
Adaptive speed control
Deep reinforcement learning (DRL)
DDPG-based robot control
Simulation-to-real transfer
CycleGAN-based domain adaptation
Explainable artificial intelligence (XAI)
Grad-CAM visualization
Facility monitoring automation
Disaster assessment
Issue Date: Mar-2026
Description: Supervisor: 丁 洛榮
先端科学技術研究科
博士
Title(English): An Explainable Deep Reinforcement Learning Framework for Patrol Speed Control and Sim-to-Real Deployment of Rail-Guided Robot System
Authors(English): HOSUN, LEE
Language: eng
URI: https://hdl.handle.net/10119/20593
Academic Degrees and number: 甲第1632号
Degree-granting date: 2026-03-25
Degree name: 博士 (情報科学)
Degree-granting institutions: 北陸先端科学技術大学院大学
Appears in Collections:D-IS. 2025年度(R07) (Jun.2025 - Mar.2026)

Files in This Item:

File Description SizeFormat
abstract.pdf要旨50KbAdobe PDFView/Open
paper.pdf本文44309KbAdobe PDFView/Open
summary.pdf内容の要旨及び論文審査の結果の要旨316KbAdobe PDFView/Open

All items in DSpace are protected by copyright, with all rights reserved.

 


Contact : Scholarly Communication Section, JAIST (ir-sys[at]ml.jaist.ac.jp)