TY - GEN
T1 - Task Constraint-Guided Inverse Reinforcement Learning (TC-IRL) in Human-Robot Collaborative Assembly
AU - Chen, Yi
AU - Wang, Weitian
AU - Jia, Yunyi
N1 - Publisher Copyright:
© 2024 IEEE.
PY - 2024
Y1 - 2024
N2 - 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.
AB - 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.
UR - http://www.scopus.com/inward/record.url?scp=85197318264&partnerID=8YFLogxK
U2 - 10.1109/ARSO60199.2024.10557849
DO - 10.1109/ARSO60199.2024.10557849
M3 - Conference contribution
AN - SCOPUS:85197318264
T3 - Proceedings of IEEE Workshop on Advanced Robotics and its Social Impacts, ARSO
SP - 253
EP - 259
BT - 2024 IEEE International Conference on Advanced Robotics and Its Social Impacts, ARSO 2024
PB - IEEE Computer Society
T2 - 20th IEEE International Conference on Advanced Robotics and Its Social Impacts, ARSO 2024
Y2 - 20 May 2024 through 22 May 2024
ER -