Learning the Forward and Inverse Kinematics of a 6-DOF Concentric Tube Continuum Robot in SE(3)

Grassmann, Reinhard M.; Modes, Vincent; Burgner-Kahrs, Jessica

doi:10.1109/iros.2018.8594451

Cited by 46 publications

(31 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…MIS procedures involve operations in which there are incisions up to 15mm in diameter at the skin level and surgical tools are inserted in the form of laparoscopes or articulated devices such as robotic manipulation arms. This approach guarantees that patients are As an extrinsic actuation approach, Kahrs et al developed a stiffness controllable flexible manipulator using a tendon driven mechanism that is not only able to change its shape but also it can elongate [9][10]. Other prominent examples of extrinsic actuation approaches include the CardioARM; a highly articulated manipulation system that can provide unlimited and controllable flexibility using a tendon drive mechanism [11]; Hansen Medical Inc. proposed a catheter robot by integrating a multi-axis force/torque sensor at the tip of the multi-backbone structure as well as shape control capability [12]; Webster III et al created a concentric tube robot to reach a specific location of the brain with no damage [13].…”

Section: Introductionmentioning

confidence: 99%

A Contact Force Sensor Based on S-Shaped Beams and Optoelectronic Sensors for Flexible Manipulators for Minimally Invasive Surgery (MIS)

Noh

Han

Gawenda³

et al. 2020

IEEE Sensors J.

View full text Add to dashboard Cite

Flexible, highly articulated robotic tools can greatly facilitate procedures in which the operator needs to access small openings and confined spaces. Particularly, in the context of robotic-assisted minimally invasive surgery (RMIS), the application of such manipulation tools can be significantly beneficial in preventing unnecessary interactions with sensitive body organs by which reducing patient's recovery time when compared with conventional methods. However, these systems usually lack tactile feedback and are not able to perceive and quantify the interactions between themselves and soft body organs. This deficiency may result in damaging the organs due to unwanted excessive force applied. To this end, we introduce a contact force sensor based on three 'dyadic-S-shaped' beams and three optoelectronic sensors. The modular design of a flexible manipulation system described as part of this paper allows ready integration of a series of the proposed sensors within its structure. The sensor uses our novel sensing principle for measuring contact forces. The strategic employment of custom sensor structure and the optoelectronic components fulfill our design objectives which has been focused on the creation of a modular, low-cost, low-noise (electrically) with large voltage variation, without the need for an amplifier, through a simple fabrication process for MIS. Our experimental results, following a very simple calibration processes show the average errors of Fx (+19.37%±0.82,-18.32%±2.06) and Fy (+18.56%±1.69,-17.00%±1.32), and the average RMS errors of Fx (0.12N±0.0067) and Fy (0.11N±0.0032) in the measurement of force values within the range of-4 to 4 N.

show abstract

Section: Introductionmentioning

confidence: 99%

A Contact Force Sensor Based on S-Shaped Beams and Optoelectronic Sensors for Flexible Manipulators for Minimally Invasive Surgery (MIS)

Noh

Han

Gawenda³

et al. 2020

IEEE Sensors J.

View full text Add to dashboard Cite

show abstract

“…All states follow the Markov property and transitions between states are fully defined with an action and reward Fig. 2 3 tube illustration in a single plane adapted from [8].…”

Section: Prior Work and Preliminariesmentioning

confidence: 99%

“…The modelling inconsistencies are manufacturing tolerances, unmodelled tube interactions and unpredictable contacts. Furthermore, unlike neural network approaches that have been proposed [2,8] reinforcement learning can be trained in successively complex environments and eventually to a real environment by combining training parameters [17]. Reinforcement learning is then data efficient, if the cost of collecting real life data is high.…”

Section: Introductionmentioning

confidence: 99%

Investigating exploration for deep reinforcement learning of concentric tube robot control

2020

View full text Add to dashboard Cite

Purpose Concentric tube robots are composed of multiple concentric, pre-curved, super-elastic, telescopic tubes that are compliant and have a small diameter suitable for interventions that must be minimally invasive like fetal surgery. Combinations of rotation and extension of the tubes can alter the robot's shape but the inverse kinematics are complex to model due to the challenge of incorporating friction and other tube interactions or manufacturing imperfections. We propose a model-free reinforcement learning approach to form the inverse kinematics solution and directly obtain a control policy. Method Three exploration strategies are shown for deep deterministic policy gradient with hindsight experience replay for concentric tube robots in simulation environments. The aim is to overcome the joint to Cartesian sampling bias and be scalable with the number of robotic tubes. To compare strategies, evaluation of the trained policy network to selected Cartesian goals and associated errors are analyzed. The learned control policy is demonstrated with trajectory following tasks. Results Separation of extension and rotation joints for Gaussian exploration is required to overcome Cartesian sampling bias. Parameter noise and Ornstein-Uhlenbeck were found to be optimal strategies with less than 1 mm error in all simulation environments. Various trajectories can be followed with the optimal exploration strategy learned policy at high joint extension values. Our inverse kinematics solver in evaluation has 0.44 mm extension and 0.3 • rotation error. ConclusionWe demonstrate the feasibility of effective model-free control for concentric tube robots. Directly using the control policy, arbitrary trajectories can be followed and this is an important step towards overcoming the challenge of concentric tube robot control for clinical use in minimally invasive interventions.

show abstract

“…where K ∈ n×n is the covariance matrix of the GP model, and K ij is the relevance measurement between x i and x j . In (14), the square exponential covariance is employed as the covariance function for the GP model:…”

Section: A Gaussian Process Regressionmentioning

confidence: 99%

“…In [13], three data-driven approaches, Extreme Learning Machine (ELM), Gaussian Mixture Regression (GMR) and K-Nearest Neighbors Regression (KNNR), are employed to learn the inverse kinematic model for a tendon-driven surgical manipulator to compensate its tip error. In [14], the forward and inverse kinematic models are obtained based on FNN technique for a concentric tube continuum robot, which shows good performance on the compensation of the translation and rotation errors. Compared with the analytic kinematic modeling approaches, the above data-based methods can effectively obtain more accurate kinematic models for flexible continuum robots.…”

Section: Introductionmentioning

confidence: 99%

An Accuracy Enhancement Method for a Cable-Driven Continuum Robot With a Flexible Backbone

et al. 2020

View full text Add to dashboard Cite

In this paper, an integrated accuracy enhancement method based on both the kinematic model and the data-driven Gaussian Process Regression (GPR) technique is proposed for a Cable-Driven Continuum Robot (CDCR) with a flexible backbone. Different from the conventional continuum robots driven by pneumatic actuators, a segmented CDCR is developed in this work, which is a modular manipulator composed by a number of consecutive Cable-Driven Segments (CDSs). Based on the unique design of the backbone structure which merely allows 2-DOF bending motions, a two-variable Product-of-Exponential (POE) formula is employed to formulate the kinematic model of the CDCR. However, such an analytic kinematic model is unable to accurately describe the actual deflections of the backbone structure. Therefore, GPR is proposed to compensate the tip error of a CDCR. Compared with other machine learning methods, GPR requires less learning parameters and training data, which makes the learning process computationally efficient. To validate the effectiveness of the proposed integrated accuracy enhancement method, experiments on the actual testbed are conducted. Experimental results show that the CDCR's position and orientation errors are reduced by 68.72% and 51.74%, respectively. INDEX TERMS Cable-driven continuum robot, kinematic modeling, tip error compensation, Gaussian process regression.

show abstract

Learning the Forward and Inverse Kinematics of a 6-DOF Concentric Tube Continuum Robot in SE(3)

Cited by 46 publications

References 16 publications

A Contact Force Sensor Based on S-Shaped Beams and Optoelectronic Sensors for Flexible Manipulators for Minimally Invasive Surgery (MIS)

A Contact Force Sensor Based on S-Shaped Beams and Optoelectronic Sensors for Flexible Manipulators for Minimally Invasive Surgery (MIS)

Investigating exploration for deep reinforcement learning of concentric tube robot control

An Accuracy Enhancement Method for a Cable-Driven Continuum Robot With a Flexible Backbone

Contact Info

Product

Resources

About