A reinforcement learning method for human-robot collaboration in assembly tasks

Zhang, Rong; Lv, Qibing; Li, Jie; Bao, Jinsong; Liu, Tianyuan; Liu, Shimin

doi:10.1016/j.rcim.2021.102227

Cited by 109 publications

(33 citation statements)

References 39 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…More recent studies opted for K-NN, clustering and ANN-based robot trajectory estimation and obstacle detection for safe, collision-free HRI work-spaces [80] , FFT–PCA–SVM–VR based DT for human–robot interactive welding and welder behaviour analysis [81] , reinforcement learning for developing life-cycle framework and optimizing pick and place robots for virtual product development [82] , deep learning based robot development that could self-learn assembly processes [83] , DT-aided CNN based human action recognition [84] , [85] , R-CNN based data augmentation for VR assisted tele-manipulation [35] , deep learning based eye-gaze and head gesture recognition and data processing for gesture control in robot tele-manipulation [71] , reinforcement learning based autonomy of complex assembly workspaces to reduce operator fatigue [86] , and many others.…”

Section: Recent Trends In Dt Incorporated Roboticsmentioning

confidence: 99%

Towards next generation digital twin in robotics: Trends, scopes, challenges, and future

Mazumder¹,

Sahed²,

Tasneem³

et al. 2023

Heliyon

View full text Add to dashboard Cite

Section: Recent Trends In Dt Incorporated Roboticsmentioning

confidence: 99%

Towards next generation digital twin in robotics: Trends, scopes, challenges, and future

Mazumder¹,

Sahed²,

Tasneem³

et al. 2023

Heliyon

View full text Add to dashboard Cite

“…After years of exploration, many papers have been published in the field of disassembly lines [27]. These papers cover a wide range of decision-making, control, and optimization problems in disassembly systems, mainly including disassembly sequences, disassembly line balance, disassembly line layout, product transportation, etc.…”

Section: Problem Descriptionmentioning

confidence: 99%

Reinforcement Learning for Disassembly System Optimization Problems: A Survey

Guo

Bi²,

Wang³

et al. 2023

IJNDI

View full text Add to dashboard Cite

Survey/review study Reinforcement Learning for Disassembly System Optimization Problems: A Survey Xiwang Guo 1,2,*, Zhiliang Bi 2, Jiacun Wang 1, Shujin Qin 3, Shixin Liu 4, and Liang Qi 5 1 Department of Computer Science and Software Engineering, Monmouth University, New Jersey 07710, USA 2 Department of Information Control, Liaoning Petrochemical University, Fushun 113005, China 3 Department of Economic Management, Shangqiu Normal University, Shangqiu 476000, China 4 Department of Information Science and Engineering, Northeast University, Shenyang 110819, China 5 Department of Computer Intelligence Science and Technology, Shandong University of Science and Technology, Qingdao 266590, China * Correspondence: x.w.guo@163.com Received: 16 October 2022 Accepted: 28 November 2022 Published: Abstract: The disassembly complexity of end-of-life products increases continuously. Traditional methods are facing difficulties in solving the decision-making and control problems of disassembly operations. On the other hand, the latest development in reinforcement learning makes it more feasible to solve such kind of complex problems. Inspired by behaviorism psychology, reinforcement learning is considered as one of the most promising directions to achieve universal artificial intelligence (AI). In this context, we first review the basic ideas, mathematical models, and various algorithms of reinforcement learning. Then, we introduce the research progress and application subjects in the field of disassembly and recycling, such as disassembly sequencing, disassembly line balancing, product transportation, disassembly layout, etc. In addition, the prospects, challenges and applications of reinforcement learning based disassembly and recycling are also comprehensively analyzed and discussed.

show abstract

“…In 2021, Ref. [ 29 ] used reinforcement learning on dynamic task partitioning in assembly tasks with good results. Reference [ 30 ] presented an adaptive training method based on a deep Q-learning approach.…”

Section: Related Workmentioning

confidence: 99%

A Framework and Algorithm for Human-Robot Collaboration Based on Multimodal Reinforcement Learning

Cai

Feng

Zhou

et al. 2022

Computational Intelligence and Neuroscience

View full text Add to dashboard Cite

Despite the emergence of various human-robot collaboration frameworks, most are not sufficiently flexible to adapt to users with different habits. In this article, a Multimodal Reinforcement Learning Human-Robot Collaboration (MRLC) framework is proposed. It integrates reinforcement learning into human-robot collaboration and continuously adapts to the user's habits in the process of collaboration with the user to achieve the effect of human-robot cointegration. With the user's multimodal features as states, the MRLC framework collects the user's speech through natural language processing and employs it to determine the reward of the actions made by the robot. Our experiments demonstrate that the MRLC framework can adapt to the user's habits after repeated learning and better understand the user's intention compared to traditional solutions.

show abstract

A reinforcement learning method for human-robot collaboration in assembly tasks

Cited by 109 publications

References 39 publications

Towards next generation digital twin in robotics: Trends, scopes, challenges, and future

Towards next generation digital twin in robotics: Trends, scopes, challenges, and future

Reinforcement Learning for Disassembly System Optimization Problems: A Survey

A Framework and Algorithm for Human-Robot Collaboration Based on Multimodal Reinforcement Learning

Contact Info

Product

Resources

About