Gaussian Process Regression for Sensorless Grip Force Estimation of Cable-Driven Elongated Surgical Instruments

Haptic feedback is a critical but a clinically missing component in robotic minimally invasive surgeries. This paper proposes a Gaussian process regression (GPR) based scheme to address the gripping force estimation problem for clinically commonly used elongated cable-driven surgical instruments. Based on the cable-driven mechanism property studies, and surgical robotic system properties, four different GPR filters were designed and analyzed, including one GPR filter with two-dimensional inputs, one GPR filter with three-dimensional inputs, one GPR unscented Kalman filter (UKF) with two-dimensional inputs, and one GPR UKF with three-dimensional inputs. The four proposed methods were compared with the dynamic model based UKF filter on a 10 mm gripper on the Raven II surgical robot platform. The experimental results demonstrated that the four proposed methods outperformed the dynamic model based method on precision and reliability without parameter tuning. And surprisingly, among the four methods, the simplest GPR Filter with two-dimensional inputs has the best performance.

[1]  Blake Hannaford,et al.  Dynamic modeling of cable driven elongated surgical instruments for sensorless grip force estimation , 2016, 2016 IEEE International Conference on Robotics and Automation (ICRA).

[2]  Ian R. Manchester,et al.  Output-feedback control of nonlinear systems using control contraction metrics and convex optimization , 2014, 2014 4th Australian Control Conference (AUCC).

[3]  Baoliang Zhao,et al.  Estimating Tool-Tissue Forces Using a 3-Degree-of-Freedom Robotic Surgical Tool. , 2016, Journal of mechanisms and robotics.

[4]  Rajnikant V. Patel,et al.  Quasi-static modeling of the da Vinci instrument , 2014, 2014 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[5]  L.D. Seneviratne,et al.  State-of-the-Art in Force and Tactile Sensing for Minimally Invasive Surgery , 2008, IEEE Sensors Journal.

[6]  Rudolph van der Merwe,et al.  The unscented Kalman filter for nonlinear estimation , 2000, Proceedings of the IEEE 2000 Adaptive Systems for Signal Processing, Communications, and Control Symposium (Cat. No.00EX373).

[7]  Carl E. Rasmussen,et al.  Gaussian processes for machine learning , 2005, Adaptive computation and machine learning.

[8]  Lei Cheng,et al.  Computation and Measurement of Force and Tissue Damage for the Grasper-tissue Interface in Robot-assisted Minimal Invasive Surgery , 2015 .

[9]  Rajnikant V. Patel,et al.  Modeling and Estimation of Tip Contact Force for Steerable Ablation Catheters , 2015, IEEE Transactions on Biomedical Engineering.

[10]  Yuichi Matsumoto,et al.  Modeling of force sensing and validation of disturbance observer for force control , 2003, IECON'03. 29th Annual Conference of the IEEE Industrial Electronics Society (IEEE Cat. No.03CH37468).

[11]  William Towsend,et al.  The Effect of Transmission Design on Force-Controlled Manipulator Performance. , 1988 .

[12]  B. Ripley,et al.  Pattern Recognition , 1968, Nature.

[13]  Edward J. Berger,et al.  Friction modeling for dynamic system simulation , 2002 .

[14]  Carl E. Rasmussen,et al.  Gaussian Processes for Data-Efficient Learning in Robotics and Control , 2015, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[15]  Paula Gomes,et al.  Surgical robotics: Reviewing the past, analysing the present, imagining the future , 2011 .

[16]  Blake Hannaford,et al.  Unscented Kalman Filter and 3D vision to improve cable driven surgical robot joint angle estimation , 2016, 2016 IEEE International Conference on Robotics and Automation (ICRA).

[17]  Blake Hannaford,et al.  Raven-II: An Open Platform for Surgical Robotics Research , 2013, IEEE Transactions on Biomedical Engineering.

[18]  Blake Hannaford,et al.  Hysteresis model of longitudinally loaded cable for cable driven robots and identification of the parameters , 2016, 2016 IEEE International Conference on Robotics and Automation (ICRA).

[19]  E. Engeberg,et al.  Force and slip detection with direct-write compliant tactile sensors using multi-walled carbon nanotube/polymer composites , 2013 .

[20]  Blake Hannaford,et al.  Measurement of the cable-pulley Coulomb and viscous friction for a cable-driven surgical robotic system , 2015, 2015 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS).

[21]  Russell H. Taylor,et al.  A Modular 2-DOF Force-Sensing Instrument For Laparoscopic Surgery , 2003, MICCAI.

[22]  M. Mack,et al.  Minimally invasive and robotic surgery. , 2001, JAMA.

[23]  Edwin Olson,et al.  Extracting general-purpose features from LIDAR data , 2010, 2010 IEEE International Conference on Robotics and Automation.

[24]  Dieter Fox,et al.  GP-UKF: Unscented kalman filters with Gaussian process prediction and observation models , 2007, 2007 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[25]  Jaydev P. Desai,et al.  Design, Development, and Testing of an Automated Laparoscopic Grasper with 3-D Force Measurement Capability , 2004, ISMS.

[26]  Rebecca K. Kramer,et al.  Soft Tactile Sensor Arrays for Force Feedback in Micromanipulation , 2014, IEEE Sensors Journal.