Deeply-learnt damped least-squares (DL-DLS) method for inverse kinematics of snake-like robots

Olatunji Mumini Omisore; Shipeng Han; Lingxue Ren; Ahmed Elazab; Li Hui; Talaat Abdelhamid; Nureni Ayofe Azeez; Lei Wang

doi:10.1016/j.neunet.2018.06.018

Deeply-learnt damped least-squares (DL-DLS) method for inverse kinematics of snake-like robots

Neural Netw. 2018 Nov:107:34-47. doi: 10.1016/j.neunet.2018.06.018. Epub 2018 Aug 23.

Authors

Olatunji Mumini Omisore¹, Shipeng Han², Lingxue Ren³, Ahmed Elazab⁴, Li Hui⁵, Talaat Abdelhamid⁶, Nureni Ayofe Azeez⁷, Lei Wang⁸

Affiliations

¹ Research Centre for Medical Robotics and Minimally Invasive Surgical Devices, Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, 1068 Xueyuan Avenue, Shenzhen 518055, China; Shenzhen College of Advanced Technology, University of Chinese Academy of Sciences, Shenzhen 518055, China; CAS Key Laboratory for Health Informatics, Shenzhen Institutes of Advanced Technology, Shenzhen 518055, China. Electronic address: omisore@siat.ac.cn.
² Research Centre for Medical Robotics and Minimally Invasive Surgical Devices, Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, 1068 Xueyuan Avenue, Shenzhen 518055, China. Electronic address: sp.han@siat.ac.cn.
³ Research Centre for Medical Robotics and Minimally Invasive Surgical Devices, Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, 1068 Xueyuan Avenue, Shenzhen 518055, China. Electronic address: lx.ren@siat.ac.cn.
⁴ Computer Science Department, Misr Higher Institute for Commerce and Computers, Mansoura City, Egypt; School of Biomedical Engineering, Health Science Center, Shenzhen University, Shenzhen 518060, China. Electronic address: ahmedelazab@szu.edu.cn.
⁵ Research Centre for Medical Robotics and Minimally Invasive Surgical Devices, Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, 1068 Xueyuan Avenue, Shenzhen 518055, China. Electronic address: hui.li1@siat.ac.cn.
⁶ Physics and Mathematical Engineering Department, Faculty of Electronic Engineering, Menoufiya University, Menouf 32952, Egypt. Electronic address: talaat@siat.ac.cn.
⁷ School of Computer Science and Information, North-West University, Vaal Triangle Campus, South Africa; Department of Computer Sciences, University of Lagos, Akoka, Lagos State, Nigeria. Electronic address: 30041708@nwu.ac.za.
⁸ Research Centre for Medical Robotics and Minimally Invasive Surgical Devices, Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, 1068 Xueyuan Avenue, Shenzhen 518055, China; CAS Key Laboratory for Health Informatics, Shenzhen Institutes of Advanced Technology, Shenzhen 518055, China. Electronic address: wang.lei@siat.ac.cn.

PMID: 30241968
DOI: 10.1016/j.neunet.2018.06.018

Abstract

Recently, snake-like robots are proposed to assist experts during medical procedures on internal organs via natural orifices. Despite their well-spelt advantages, applications in radiosurgery is still hindered by absence of suitable designs required for spatial navigations within clustered and confined parts of human body, and inexistence of precise and fast inverse kinematics (IK) models. In this study, a deeply-learnt damped least squares method is proposed for solving IK of spatial snake-like robot. The robot's model consists of several modules, and each module has a pair of serial-links connected with orthogonal twists. For precise control of the robot's end-effector, damped least-squares approach is used to minimize error magnitude in a function modeled over analytical Jacobian of the robot. This is iteratively done until an apt joint vector needed to converge the robot to desired positions is obtained. For fast control and singularity avoidance, a deep network is built for prediction of unique damping factor required for each target point in the robot's workspace. The deep network consists of 11 x 15 array of neurons at the hidden layer, and deeply-learnt with a huge dataset of 877,500 data points generated from workspace of the snake robot. Implementation results for both simulated and actual prototype of an eight-link model of the robot show the effectiveness of the proposed IK method. With error tolerance of 0.01 mm, the proposed method has a very high reachability measure of 91.59% and faster mean execution time of 9.20 (±16.92) ms for convergence. In addition, the method requires an average of 33.02 (±39.60) iterations to solve the IK problem. Hence, approximately 3.6 iterations can be executed in 1 ms. Evaluation against popularly used IK methods shows that the proposed method has very good performance in terms of accuracy and speed, simultaneously.

Keywords: DLS methods; Deep neural network; Inverse kinematics; Jacobian matrix; Radiosurgical robots; Snake-like robots.

MeSH terms

Biomechanical Phenomena
Deep Learning*
Robotics / methods*
Stereotaxic Techniques / instrumentation*