Alert button
Picture for Juan Barragan Noguera

Juan Barragan Noguera

Alert button

DESK: A Robotic Activity Dataset for Dexterous Surgical Skills Transfer to Medical Robots

Mar 03, 2019
Naveen Madapana, Md Masudur Rahman, Natalia Sanchez-Tamayo, Mythra V. Balakuntala, Glebys Gonzalez, Jyothsna Padmakumar Bindu, L. N. Vishnunandan Venkatesh, Xingguang Zhang, Juan Barragan Noguera, Thomas Low, Richard Voyles, Yexiang Xue, Juan Wachs

Figure 1 for DESK: A Robotic Activity Dataset for Dexterous Surgical Skills Transfer to Medical Robots
Figure 2 for DESK: A Robotic Activity Dataset for Dexterous Surgical Skills Transfer to Medical Robots
Figure 3 for DESK: A Robotic Activity Dataset for Dexterous Surgical Skills Transfer to Medical Robots
Figure 4 for DESK: A Robotic Activity Dataset for Dexterous Surgical Skills Transfer to Medical Robots

Datasets are an essential component for training effective machine learning models. In particular, surgical robotic datasets have been key to many advances in semi-autonomous surgeries, skill assessment, and training. Simulated surgical environments can enhance the data collection process by making it faster, simpler and cheaper than real systems. In addition, combining data from multiple robotic domains can provide rich and diverse training data for transfer learning algorithms. In this paper, we present the DESK (Dexterous Surgical Skill) dataset. It comprises a set of surgical robotic skills collected during a surgical training task using three robotic platforms: the Taurus II robot, Taurus II simulated robot, and the YuMi robot. This dataset was used to test the idea of transferring knowledge across different domains (e.g. from Taurus to YuMi robot) for a surgical gesture classification task with seven gestures. We explored three different scenarios: 1) No transfer, 2) Transfer from simulated Taurus to real Taurus and 3) Transfer from Simulated Taurus to the YuMi robot. We conducted extensive experiments with three supervised learning models and provided baselines in each of these scenarios. Results show that using simulation data during training enhances the performance on the real robot where limited real data is available. In particular, we obtained an accuracy of 55% on the real Taurus data using a model that is trained only on the simulator data. Furthermore, we achieved an accuracy improvement of 34% when 3% of the real data is added into the training process.

* 8 pages, 5 figures, 4 tables, submitted to IROS 2019 conference 
Viaarxiv icon