Vision Based Topological State Recognition for Deformable Linear Object Untangling Conducted in Unknown Background

In this paper, we propose a deep learning based method to recognize the topological state of a deformable linear object (DLO). The utilization of deep learning can ensure that topological state recognition is robust to background change. This feature is useful if applications of DLO manipulation in real environment. And this feature has never be realized. In addition, the proposed scheme is also applied to the situation when multiple DLOs exist. This situation has never been considered. By integrating the proposed topological state recognition method and DLO untangling strategy, rope untangling experiments are conducted for both the situations of containing a single DLO and double DLOs.

[1]  Atsushi Konno,et al.  Robotized assembly of a wire harness in car production line , 2010, 2010 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[2]  James F. O'Brien,et al.  Modeling and perception of deformable one-dimensional objects , 2011, 2011 IEEE International Conference on Robotics and Automation.

[3]  Takamitsu Matsubara,et al.  Probabilistic Pose Estimation of Deformable Linear Objects , 2018, 2018 IEEE 14th International Conference on Automation Science and Engineering (CASE).

[4]  Huazhu Fu,et al.  Retinal vessel segmentation via deep learning network and fully-connected conditional random fields , 2016, 2016 IEEE 13th International Symposium on Biomedical Imaging (ISBI).

[5]  Hidefumi Wakamatsu,et al.  Manipulation planning for unraveling linear objects , 2006, Proceedings 2006 IEEE International Conference on Robotics and Automation, 2006. ICRA 2006..

[6]  John F. Canny,et al.  A Computational Approach to Edge Detection , 1986, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[7]  Masayoshi Tomizuka,et al.  State estimation for deformable objects by point registration and dynamic simulation , 2017, 2017 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS).

[8]  Guang-Zhong Yang,et al.  Multi-Stage Suture Detection for Robot Assisted Anastomosis Based on Deep Learning , 2018, 2018 IEEE International Conference on Robotics and Automation (ICRA).

[9]  Takamitsu Matsubara,et al.  Model-based reinforcement learning approach for deformable linear object manipulation , 2017, 2017 13th IEEE Conference on Automation Science and Engineering (CASE).