Reinforcement learning in real-time geometry assurance

被引：5

作者：

Jorge, Emilio ^{[1
]}

Brynte, Lucas ^{[1
]}

Cronrath, Constantin ^{[2
]}

Wigstrom, Oskar ^{[2
]}

Bengtsson, Kristofer ^{[2
]}

Gustaysson, Emil ^{[1
]}

Lennartson, Bengt ^{[2
]}

Jirstrand, Mats ^{[1
]}

机构：

[1] Fraunhofer Chalmers Ctr Ind Math, SE-41288 Gothenburg, Sweden

[2] Chalmers Univ Technol, Dept Elect Engn, SE-41296 Gothenburg, Sweden

来源：

51ST CIRP CONFERENCE ON MANUFACTURING SYSTEMS | 2018年 / 72卷

关键词：

geometry assurance; reinforcement learning; expert advice;

D O I：

10.1016/j.procir.2018.03.168

中图分类号：

T [工业技术];

学科分类号：

08 ;

摘要：

To improve the assembly quality during production, expert systems are often used. These experts typically use a system model as a basis for identifying improvements. However, since a model uses approximate dynamics or imperfect parameters, the expert advice is bound to be biased. This paper presents a reinforcement learning agent that can identify and limit systematic errors of an expert systems used for geometry assurance. By observing the resulting assembly quality over time, and understanding how different decisions affect the quality, the agent learns when and how to override the biased advice from the expert software. (C) 2018 The Authors. Published by Elsevier B.V. Peer-review under responsibility of the scientific committee of the 51st CIRP Conference on Manufacturing Systems.

引用

页码：1073 / 1078

页数：6

共 50 条

[31] Comparing Reinforcement Learning Methods for Real-Time Optimization of a Chemical Process
Quah, Titus
Machalek, Derek
Powell, Kody M.
PROCESSES, 2020, 8 (11) : 1 - 19
[32] Reinforcement Learning for Real-Time Multi-Access Edge Computing
Rajashekar, Kolichala
PROCEEDINGS OF THE 24TH INTERNATIONAL CONFERENCE ON DISTRIBUTED COMPUTING AND NETWORKING, ICDCN 2023, 2023, : 296 - 297
[33] Real-Time Adaptive Control of a Flexible Manipulator Using Reinforcement Learning
Pradhan, Santanu Kumar
Subudhi, Bidyadhar
IEEE TRANSACTIONS ON AUTOMATION SCIENCE AND ENGINEERING, 2012, 9 (02) : 237 - 249
[34] Hybrid DVFS Scheduling for Real-Time Systems Based on Reinforcement Learning
Muhammad, Fakhruddin
ul Islam, Mahbub
Lin, Man
IEEE SYSTEMS JOURNAL, 2017, 11 (02): : 931 - 940
[35] TEXPLORE: real-time sample-efficient reinforcement learning for robots
Hester, Todd
Stone, Peter
MACHINE LEARNING, 2013, 90 (03) : 385 - 429
[36] Tabular Reinforcement Learning in Real-Time Strategy Games via Options
Tavares, Anderson R.
Chaimowicz, Luiz
PROCEEDINGS OF THE 2018 IEEE CONFERENCE ON COMPUTATIONAL INTELLIGENCE AND GAMES (CIG'18), 2018, : 229 - 236
[37] REAL-TIME BATCHING IN JOB SHOPS BASED ON SIMULATION AND REINFORCEMENT LEARNING
Zhang, Tao
Xie, Shufang
Rose, Oliver
2018 WINTER SIMULATION CONFERENCE (WSC), 2018, : 3331 - 3339
[38] Hierarchical Reinforcement-Learning for Real-Time Scheduling of Agile Satellites
Ren, Lili
Ning, Xin
Li, Jiayin
IEEE ACCESS, 2020, 8 (08): : 220523 - 220532
[39] Real-Time Defensive Strategy Selection via Deep Reinforcement Learning
Charpentier, Axel
Neal, Christopher
Boulahia-Cuppens, Nora
Cuppens, Frederic
Yaich, Reda
18TH INTERNATIONAL CONFERENCE ON AVAILABILITY, RELIABILITY & SECURITY, ARES 2023, 2023,
[40] Deep Reinforcement Learning for Real-Time Energy Management in Smart Home
Wei, Guixi
Chi, Ming
Liu, Zhi-Wei
Ge, Mingfeng
Li, Chaojie
Liu, Xianggang
IEEE SYSTEMS JOURNAL, 2023, 17 (02): : 2489 - 2499

← 1 2 3 4 5 →