Task Constraint-Guided Inverse Reinforcement Learning (TC-IRL) in Human-Robot Collaborative Assembly

Yi Chen, Weitian Wang, Yunyi Jia

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

Abstract

Collaborative robots transit from the traditional robot-in-a-cell scenarios to a human-robot-shared workspace. This demands robots to better understand their human partners and then assist them. Existing robot learning from demonstration work mainly focuses on enabling robots to repeat human demonstrated tasks alone and usually require significant training efforts but have limited scalability to new tasks. This paper proposes a new task constraint-guided inverse reinforcement learning (TC-IRL) approach to learn assembly tasks from human demonstrations with significantly reduced state and action space (leading to less training data requirement) and computational efforts (landing to better real-time performance) than the conventional IRL. The TC-IRL is also extended to new geometric-scaled tasks to generate robot assistance to human in collaborative assembly. The proposed approaches are validated and evaluated through human-robot collaborative assembly experiments.

Original languageEnglish
Title of host publication2024 IEEE International Conference on Advanced Robotics and Its Social Impacts, ARSO 2024
PublisherIEEE Computer Society
Pages253-259
Number of pages7
ISBN (Electronic)9798350344639
DOIs
StatePublished - 2024
Event20th IEEE International Conference on Advanced Robotics and Its Social Impacts, ARSO 2024 - Hong Kong, China
Duration: 20 May 202422 May 2024

Publication series

NameProceedings of IEEE Workshop on Advanced Robotics and its Social Impacts, ARSO
ISSN (Print)2162-7568
ISSN (Electronic)2162-7576

Conference

Conference20th IEEE International Conference on Advanced Robotics and Its Social Impacts, ARSO 2024
Country/TerritoryChina
CityHong Kong
Period20/05/2422/05/24

Fingerprint

Dive into the research topics of 'Task Constraint-Guided Inverse Reinforcement Learning (TC-IRL) in Human-Robot Collaborative Assembly'. Together they form a unique fingerprint.

Cite this