Hostname: page-component-76fb5796d-skm99 Total loading time: 0 Render date: 2024-04-28T07:50:42.114Z Has data issue: false hasContentIssue false
  • English
  • Français

Kinematics-based end-effector path control of a mobile manipulator system on an uneven terrain using a two-stage Support Vector Machine

Published online by Cambridge University Press:  22 November 2019

Hitesh Jangid ,
Subham Jain ,
Beteley Teka ,
Rekha Raja  and
Ashish Dutta Open the ORCID record for Ashish Dutta [Opens in a new window]
Hitesh Jangid
Affiliation:
Department of Mechanical Engineering, IIT Kanpur, Kanpur208016, India E-mails: hiteshjangid.jangid4@gmail.com, meshubham89@gmail.com, beteley@iitk.ac.in
Subham Jain
Affiliation:
Department of Mechanical Engineering, IIT Kanpur, Kanpur208016, India E-mails: hiteshjangid.jangid4@gmail.com, meshubham89@gmail.com, beteley@iitk.ac.in
Beteley Teka
Affiliation:
Department of Mechanical Engineering, IIT Kanpur, Kanpur208016, India E-mails: hiteshjangid.jangid4@gmail.com, meshubham89@gmail.com, beteley@iitk.ac.in
Rekha Raja
Affiliation:
University of California Davis, CA 95616, USA. E-mail: rekha.cob@gmail.com
Ashish Dutta*
Affiliation:
Department of Mechanical Engineering, IIT Kanpur, Kanpur208016, India E-mails: hiteshjangid.jangid4@gmail.com, meshubham89@gmail.com, beteley@iitk.ac.in
*
*Corresponding author. E-mail: adutta@iitk.ac.in
Get access Rights & Permissions [Opens in a new window]

Summary

A mobile manipulator system (MMS) consists of a robotic arm mounted on a mobile platform that is used in rescue and relief, space exploration, warehouse automation, etc. As the total system has 14 Degrees of Freedom (DOF), it does not have a closed-form inverse kinematics (IK) solution. A learning-based method is proposed, which uses the forward kinematics data to learn the IK relation for motion of an MMS on a rough terrain, using a one-class support vector machine (SVM) framework. Once trained, the model estimates the joint probability distribution of the MMS configuration and end-effector position. This distribution is used to find the MMS configuration for a given desired end-effector path. Past research using a Kohonen Self organizing map (KSOM) neural network-based open-loop control method has shown that the MMS deviates from its desired path while moving on an uneven terrain due to unknown disturbances such as wheel slip, slide, and terrain deformation. Therefore, a new sequential two-stage SVM-based end-effector path-tracking control scheme is proposed to control the end-effector path. In this scheme, the error in the end-effector path is continuously tracked with the help of a Microsoft Kinect 2.0 (Microsoft Regional Sales, Singapore 119968) and is sent as a feedback to the controller. Once the error reaches a threshold value, the error correction step of the controller gets activated to correct the error until the desired accuracy is reached. The effectiveness of the proposed approach is proved through extensive simulations and experiments conducted on 3D terrain in which it is shown that the end effector can follow the desired path with an average experimental error of around 2 cm between the desired and final corrected path.

Keywords

Inverse kinematicsMobile manipulator systemPath followingSupport vector machineNonholonomic constraintRough terrain motion planning
Type
Articles
Information
Robotica , Volume 38 , Issue 8 , August 2020 , pp. 1415 - 1433
Copyright
© Cambridge University Press 2019

Access options

Get access to the full version of this content by using one of the access options below. (Log in options will check for institutional or personal access. Content may require purchase if you do not have access.)

References

Akli, I., Bouzouia, B. and Achour, N., “Motion analysis of a mobile manipulator executing pick-up tasks,” Comput. Electr. Eng. 43, 257–269 (2015).CrossRefGoogle Scholar
Hvilshoj, M. and Bogh, S., “Little helper – An autonomous industrial mobile manipulator concept,” Int. J. Adv. Rob. Syst. 8(2), 80–90 (2011).Google Scholar
Wolovich, K. A. and Elliott, H., “A Computational Technique for Inverse Kinematics,” The 23rd IEEE Conference on Decision and Control, Las Vegas, Nevada, USA, vol. 23, (1984) pp. 1359–1363.Google Scholar
Seraji, H., “An On-line Approach to Coordinated Mobility and Manipulation,” Proceedings of IEEE International Conference on Robotics and Automation, Atlanta, GA, USA (1993) pp. 28–35.Google Scholar
Bayle, B., Fourquet, J.-Y., Lamiraux, F. and Renaud, M., “Kinematics Control of Wheeled Mobile Manipulators,” Proceedings of the International Conference on Intelligent Robots and Systems, Lausanne, Switzerland (2002) pp. 1572–1577.Google Scholar
Hudson, N., Backes, P., DiCicco, M. and Bajracharya, M., “Estimation and Control for Autonomous Coring from a Rover Manipulator,” Proceedings of the IEEE Aerospace Conference, Big Sky, MT, USA (2010) pp. 1–10.Google Scholar
Hamner, B., Koterba, S., Shi, J., Simmons, R. and Singh, S., “An autonomous mobile manipulator for assembly tasks,” Auton. Robots 28, 131–149 (2010).CrossRefGoogle Scholar
Castillo, O., Trujillo, L. and Melin, P., “Multiple objective genetic algorithms for path-planning optimization in autonomous mobile robots,” Soft Comput. 11(8), 269–279 (2007).CrossRefGoogle Scholar
Huang, H.-C. and Hsu, H.-S., “Biologically inspired deoxyribonucleic acid soft computing for inverse kinematics solver of five-DOF robotic manipulators,” Soft Comput. 19(4), 875–881 (2015).CrossRefGoogle Scholar
Biondi, G. O. and Prati, R. C., “Setting parameters for support vector machines using transfer learning,” J. Intell. Rob. Syst. 80(1), 295–311 (2015).CrossRefGoogle Scholar
Bentez-Peña, S., Blanquero, R., Carrizosa, E. and Ramirez-Cobo, P., “Cost-sensitive feature selection for support vector machines,” Comput. Oper. Res. 106, 169–178 (2018).CrossRefGoogle Scholar
Ou, Y., Qian, H. and Xu, Y., “Support vector machine based approach for abstracting human control strategy in controlling dynamically stable robots,” J. Intell. Rob. Syst. 55(1), 39–54 (2009).CrossRefGoogle Scholar
Liu, Z., Wang, L., Zhang, Y. and Chen, C. P., “A SVM controller for the stable walking of biped robots based on small sample sizes,” Appl. Soft Comput. 38, 738–753 (2016).CrossRefGoogle Scholar
Charalampous, K., Kostavelis, I. and Gasteratos, A., “Thorough robot navigation based on SVM local planning,” Rob. Auton. Syst. 70, 166–180 (2016).CrossRefGoogle Scholar
Wang, X., Huang, F. and Cheng, Y., “Computational performance optimization of support vector machine based on support vectors,” Neurocomputing 211, 66–71 (2016).CrossRefGoogle Scholar
Huang, K. and Zhang, X.-Y., “Field support vector machines,” IEEE Trans. Emerging. Top. Comput. Intell. 1(6), 454–463 (2017).CrossRefGoogle Scholar
Köker, R., “A genetic algorithm approach to a neural-network-based inverse kinematics solution of robotic manipulators based on error minimization,” Inf. Sci. 222, 528–543 (2013).CrossRefGoogle Scholar
Toshani, H. and Farrokhi, M., “Real-time inverse kinematics of redundant manipulators using neural networks and quadratic programming: a Lyapunov-based approach,” Rob. Auton. Syst. 62(6), 766–781 (2014).CrossRefGoogle Scholar
Almusawi, A. R. J., Dülger, L. C., and Kapucu, S., “A new artificial neural network approach in solving inverse kinematics of robotic arm,” Comput Intell Neurosci., 1–10 (2016).CrossRefGoogle Scholar
Chen, J. and Lau, H. Y. K., “Inverse Kinematics Learning for Redundant Robot Manipulators with Blending of Support Vector Regression Machines,” Proceedings of the IEEE International Workshop on Advanced Robotics and its Social Impacts (ARSO), Shanghai (2016) pp. 267–272.Google Scholar
Ahanda, J. J.-B. M., Mbede, J. B., Melingui, A., Zobo, B. E., Lakhal, O. and Merzouki, R., “Robust control for robot manipulators: Support vector regression based command filtered adaptive backstepping approach,” IFAC PapersOnLine 50(1), 8208–8213 (2017).CrossRefGoogle Scholar
Vijay, M. and Jena, D., “Backstepping terminal sliding mode control of robot manipulator using radial basis functional neural networks,” Comput. Electr. Eng. 67, 690–707 (2018).CrossRefGoogle Scholar
Raja, R., Dutta, A. and Dasgupta, B., “KSOM Based Learning for Cooperative Motion of a Redundant Rover-manipulator on an Uneven Terrain,” 13th International Conference on Control, Automation, Robotics & Vision, Marina Bay Sands, Singapore (2014).CrossRefGoogle Scholar
Xu, H., Liu, X., Fu, H., Putra, B. B. and He, L., “Visual contact angle estimation and traction control for mobile robot in rough-terrain,” J. Intell. Rob. Syst. 74(4), 985–997 (2014).CrossRefGoogle Scholar
Spong, M. W. and Vidyasagar, M., Robot Dynamics and Control (John Wiley & Sons, Chichester, UK, 2004).Google Scholar
Nocedal, J. and Wright, S. J., Numerical Optimization (Springer, New York, 2006).Google Scholar
Scholkopf, B. and Smola, A. J., Learning with Kernels: Support Vector Machines, Regularization, Optimization, and Beyond (MIT Press, Cambridge, MA, USA, 2001).Google Scholar
Chang, C.-C. and Lin, C.-J., “LIBSVM: A Library for Support Vector Machines,” Available: http://www.csie.ntu.edu.tw/~cjlin/papers/libsvm.pdf (2001).Google Scholar
Nelder, J. A. and Mead, R., “A simplex method for function minimization,” Comput. J. 7(4), 308–313 (1965).CrossRefGoogle Scholar
Yoshikawa, T., Foundations of Robotics: Analysis and Control (PHI Publications, India, 2001).Google Scholar
Pagliari, D. and Pinto, L., “Calibration of Kinect for Xbox one and comparison between the two generations of Microsoft sensors,” Sensors 15, 27569–27589 (2015).CrossRefGoogle ScholarPubMed
Wikipedia, “Kalman Filter,” [Online]. Available: https://en.m.wikipedia.org/wiki/Kalman_filter.Google Scholar