Unsupervised Trajectory Segmentation and Promoting of Multi-Modal Surgical Demonstrations

To improve the efficiency of surgical trajectory segmentation for robot learning in robot-assisted minimally invasive surgery, this paper presents a fast unsupervised method using video and kinematic data, followed by a promoting procedure to address the over-segmentation issue. Unsupervised deep learning network, stacking convolutional auto-encoder, is employed to extract more discriminative features from videos in an effective way. To further improve the accuracy of segmentation, on one hand, wavelet transform is used to filter out the noises existed in the features from video and kinematic data. On the other hand, the segmentation result is promoted by identifying the adjacent segments with no state transition based on the predefined similarity measurements. Extensive experiments on a public dataset JIGSAWS show that our method achieves much higher accuracy of segmentation than state-of-the-art methods in the shorter time.

[1]  Gregory D. Hager,et al.  Surgical Gesture Segmentation and Recognition , 2013, MICCAI.

[2]  Gregory D. Hager,et al.  Automatic Detection and Segmentation of Robot-Assisted Surgical Motions , 2005, MICCAI.

[3]  Jürgen Schmidhuber,et al.  Stacked Convolutional Auto-Encoders for Hierarchical Feature Extraction , 2011, ICANN.

[4]  Gregory D. Hager,et al.  Transition State Clustering: Unsupervised Surgical Trajectory Segmentation for Robot Learning , 2017, ISRR.

[5]  Gregory D. Hager,et al.  String Motif-Based Description of Tool Motion for Detecting Skill and Gestures in Robotic Surgery , 2013, MICCAI.

[6]  Gregory D. Hager,et al.  Automatic Recognition of Surgical Motions Using Statistical Modeling for Capturing Variability , 2008, MMVR.

[7]  Allison M. Okamura,et al.  A paced shared-control teleoperated architecture for supervised automation of multilateral surgical tasks , 2015, 2015 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS).

[8]  Sang Hyoung Lee,et al.  Autonomous framework for segmenting robot trajectories of manipulation task , 2015, Auton. Robots.

[9]  Silvio Savarese,et al.  Watch-n-patch: Unsupervised understanding of actions and relations , 2015, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[10]  Donald J. Berndt,et al.  Finding Patterns in Time Series: A Dynamic Programming Approach , 1996, Advances in Knowledge Discovery and Data Mining.

[11]  W. Krzanowski Between-Groups Comparison of Principal Components , 1979 .

[12]  Yiannis Aloimonos,et al.  Minimalist plans for interpreting manipulation actions , 2013, 2013 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[13]  Trevor Darrell,et al.  TSC-DL: Unsupervised trajectory segmentation of multi-modal surgical demonstrations with Deep Learning , 2016, 2016 IEEE International Conference on Robotics and Automation (ICRA).

[14]  Henry C. Lin,et al.  JHU-ISI Gesture and Skill Assessment Working Set ( JIGSAWS ) : A Surgical Activity Dataset for Human Motion Modeling , 2014 .

[15]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.