Abstract
The robot’s weak ability to manipulate deformable objects makes robots rarely used in the garment manufacturing industry. Designing a robot skill acquisition frame that can learn to manipulate fabrics helps to improve the intelligence of the garment manufacturing industry. This paper proposes a process learning framework for robot fabric stacking based on a composite reward function. A limited task flow model describes the overall process, and robot skills represent a single task. Based on the robot’s acquisition of operational skills, a priori knowledge of the technological process is embedded into the reward function to form a composite reward function, and then it takes to guide the robot to use the acquired skills to complete the overall process task. Experiments are conducted on the UR5e robot to prove the effectiveness of this method, and results show that the robot guided by the composite reward function can complete the process task of fabric manipulation before garment sewing.
Supported by Shandong Major Science and Technology Innovation Project(No.2019JZZY010430), Shandong Major Science and Technology Innovation Project(No.2019JZZY010429), Shandong Provincial Key Research and Development Program(Grand No.2019TSLH0302).
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsReferences
Nayak, R., Padhye, R.: Introduction to automation in garment manufacturing. In: Nayak, R., Padhye, R. (eds.) Automation in Garment Manufacturing. The Textile Institute Book Series, pp. 1–27. Woodhead Publishing, Sawston (2018). https://doi.org/10.1016/B978-0-08-101211-6.00001-X
Nayak, R., Padhye, R.: Automation in material handling. In: Nayak, R., Padhye, R. (eds.) Automation in Garment Manufacturing. The Textile Institute Book Series, pp. 165–177. Woodhead Publishing, Sawston (2018). https://doi.org/10.1016/B978-0-08-101211-6.00007-0
Delgado, A., Jara, C.A., Torres, F.: Adaptive tactile control for in-hand manipulation tasks of deformable objects. Int. J. Adv. Manuf. Technol. 91(9), 4127–4140 (2017). https://doi.org/10.1007/s00170-017-0046-2
Gale, C.: The robot seamstress. Adv. Res. Text. Eng. 1(1), 1–2 (2016)
Kruse, D., Radke, R.J., Wen, J.T.: Collaborative human-robot manipulation of highly deformable materials. In: 2015 IEEE International Conference on Robotics and Automation (ICRA), pp. 3782–3787 (2015). https://doi.org/10.1109/ICRA.2015.7139725
Li, F., Jiang, Q., Quan, W., Cai, S., Song, R., Li, Y.: Manipulation skill acquisition for robotic assembly based on multi-modal information description. IEEE Access 8, 6282–6294 (2020). https://doi.org/10.1109/ACCESS.2019.2934174
Lillicrap, T.P., et al.: Continuous control with deep reinforcement learning (2019)
Liu, Y., Shamsi, S.M., Fang, L., Chen, C., Napp, N.: Deep Q-learning for dry stacking irregular objects. In: 2018 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), pp. 1569–1576 (2018). https://doi.org/10.1109/IROS.2018.8593619
Matas, J., James, S., Davison, A.J.: Sim-to-real reinforcement learning for deformable object manipulation. In: Billard, A., Dragan, A., Peters, J., Morimoto, J. (eds.) Proceedings of The 2nd Conference on Robot Learning. Proceedings of Machine Learning Research PMLR, vol. 87, pp. 734–743, 29–31 October 2018
Moll, M., Kavraki, L.E.: Path planning for deformable linear objects. IEEE Trans. Rob. 22(4), 625–636 (2006). https://doi.org/10.1109/TRO.2006.878933
Navarro-Alarcon, D., et al.: Automatic 3-d manipulation of soft objects by robotic arms with an adaptive deformation model. IEEE Trans. Rob. 32(2), 429–441 (2016). https://doi.org/10.1109/TRO.2016.2533639
Parker, J.K., Dubey, R., Paul, F.W., Becker, R.J.: Robotic fabric handling for automating garment manufacturing. J. Eng. Ind. 105(1), 21–26 (1983). https://doi.org/10.1115/1.3185859
Wada, T., Hirai, S., Kawamura, S., Kamiji, N.: Robust manipulation of deformable objects by a simple pid feedback. In: Proceedings 2001 ICRA. IEEE International Conference on Robotics and Automation (Cat. No.01CH37164), vol. 1, pp. 85–90 (2001). https://doi.org/10.1109/ROBOT.2001.932534
Zhang, J., Zhang, W., Song, R., Ma, L., Li, Y.: Grasp for stacking via deep reinforcement learning. In: 2020 IEEE International Conference on Robotics and Automation (ICRA), pp. 2543–2549 (2020). https://doi.org/10.1109/ICRA40945.2020.9197508
Zhang, T., Xiao, M., Zou, Y., Xiao, J.: Robotic constant-force grinding control with a press-and-release model and model-based reinforcement learning. Int. J. Adv. Manuf. Technol. 106(1), 589–602 (2020). https://doi.org/10.1007/s00170-019-04614-0
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 Springer Nature Switzerland AG
About this paper
Cite this paper
Fu, T., Li, F., Zheng, Y., Song, R. (2021). Process Learning of Robot Fabric Manipulation Based on Composite Reward Functions. In: Liu, XJ., Nie, Z., Yu, J., Xie, F., Song, R. (eds) Intelligent Robotics and Applications. ICIRA 2021. Lecture Notes in Computer Science(), vol 13014. Springer, Cham. https://doi.org/10.1007/978-3-030-89098-8_16
Download citation
DOI: https://doi.org/10.1007/978-3-030-89098-8_16
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-89097-1
Online ISBN: 978-3-030-89098-8
eBook Packages: Computer ScienceComputer Science (R0)