eduzhai > Applied Sciences > Engineering >

Mastering the working sequence in human-robot collaborative assembly based on reinforcement learning

  • king
  • (0) Download
  • 20210505
  • Save

... pages left unread,continue reading

Document pages: 11 pages

Abstract: A long-standing goal of the Human-Robot Collaboration (HRC) in manufacturingsystems is to increase the collaborative working efficiency. In line with thetrend of Industry 4.0 to build up the smart manufacturing system, the Co-robotin the HRC system deserves better designing to be more self-organized and tofind the superhuman proficiency by self-learning. Inspired by the impressivemachine learning algorithms developed by Google Deep Mind like Alphago Zero, inthis paper, the human-robot collaborative assembly working process is formattedinto a chessboard and the selection of moves in the chessboard is used toanalogize the decision making by both human and robot in the HRC assemblyworking process. To obtain the optimal policy of working sequence to maximizethe working efficiency, the robot is trained with a self-play algorithm basedon reinforcement learning, without guidance or domain knowledge beyond gamerules. A neural network is also trained to predict the distribution of thepriority of move selections and whether a working sequence is the one resultingin the maximum of the HRC efficiency. An adjustable desk assembly is used todemonstrate the proposed HRC assembly algorithm and its efficiency.

Please select stars to rate!


0 comments Sign in to leave a comment.

    Data loading, please wait...