Trajectory Tracking of a Spherical Robot Based on an RBF Neural Network

Abstract:

This paper deals with trajectory tracking problem of a spherical mobile robot, BHQ-1. First, a desired velocity is obtained by proposing a PD controller based on the kinematics. Then a PD controller with an RBF (Radial Basis Function) neural network is proposed based on the desired velocity and the inexact dynamics. The weights of the RBF network are designed with an adaptive rule based on the tracking error, and hence the network can compensate the uncertainties of the dynamics more effectively. Stability is presented via Lyapunov Theory and simulation results are provided to illustrate the tracking performance.

• Periodical: Advanced Materials Research (Volumes 383-390)
• Pages: 631-637
• DOI: https://doi.org/10.4028/www.scientific.net/AMR.383-390.631
• Online since: November 2011
• Authors: Ming Hui Zheng, Qiang Zhan, Jin Kun Liu, Yao Cai
• Keywords: Dynamic, Kinematics, RBF, Spherical Robot, Trajectory Tracking

References

[1] Aarne Halme, Torsten Schönberg, Yan Wang, Motion control of a spherical mobile robot, IEEE International International Workshop on Advanced Motion Control, 1996: 100-106.

DOI: 10.1109/amc.1996.509415

[2] Shourov Bhattacharya, Sunil K. Agrawal, Design, Experiments and Motion Planning of a Spherical Rolling Robot, IEEE International Conference on Robotics and Automation, 2000: 1027-1012.

DOI: 10.1109/robot.2000.844763

[3] Carlo Camicia, Fahio Conticelli, Antonio Bicchi, Nonholonomic Kinematics and Dynamics of the Sphericle, IEEE/RSJ International Conference on Intelligent Robots and Systems, 2000: 806-810.

DOI: 10.1109/iros.2000.894703

[4] Alessia Marigo, Antonio Bicchi, A local-local planning algorithm for rolling objects, IEEE International Conference on Robotics and Automation, 2002: 1759-1764.

DOI: 10.1109/robot.2002.1014796

[5] Mukherjee Ranjan, Tuhin Das, Feedback Stabilization of a Spherical Mobile Robot, IEEE International Conference on Intelligent Robots and Systems, 2002: 2154-2162.

DOI: 10.1109/irds.2002.1041586

[6] Tuhin Kumar Das, Feedback stabilization of the rolling sphere: An intractable nonholonomic system, PhD thesis, Michigan State University. Dept. of Mechanical Engineering, 2002(9).

[7] Vrunda A. Joshi, Ravi N. Banavar, Rohit Hippalgaonkar, Design and analysis of a spherical mobile robot, Mechanism and Machine Theory 2010, 45(2): 130–136.

DOI: 10.1016/j.mechmachtheory.2009.04.003

[8] Qiang Zhan, Yao Cai, Zengbo Liu, Near-Optimal Trajectory Plan-ning of a Spherical Mobile Robot for Environment Exploration, IEEE Conference on Robotics, Automation and Mechatronics, 2008: 84-89.

DOI: 10.1109/ramech.2008.4681380

[9] Qiang Zhan, Tingzhi Zhou, Ming Chen, Sanlong Cai, Dynamic Trajectory Planning of a Spherical Mobile Robot, IEEE Conference on Robotics, Automation and Mechatronics, 2006: 714-719.

DOI: 10.1109/ramech.2006.252705

[10] Zhan Qiang, Liu Zengbo, Cai Yao, A back-stepping Based Traj-ectory Tracking Control for a Non-chained Nonholonomic Spherical Robot, Chinese Journal of Aeronautics, 2008, 21(5): 472-480.

DOI: 10.1016/s1000-9361(08)60061-8

[11] Zheng Minghui, Zhan Qiang, Liu Jinkun, Cai Yao, Control of a Spherical Robot Path Following: Based on Nonholonomic Kinematics and Dynamics, , unpublished.

[12] D.S. Broomhead and D. Lowe, Multivariable functional interpolation and adaptive networks, Complex Systems 1988, 2: 321-355.

[13] Gang Feng, A compensating scheme for robot tracking based on neural networks, Robotics and Autonomous Systems, 1995, 15(3): 199-206.

DOI: 10.1016/0921-8890(95)00023-9

[14] Jorge I. Arciniegas, Adel H. Eltimsahy, Krzysztof J. Cios, Neural-networks-based adaptive control of flexible robotic arms, Neurocomputing, 1997, 17(3-4): 141-157.

DOI: 10.1016/s0925-2312(97)00037-4

[15] S.K. Tso, Y.H. Fung, N.L. Lin, Analysis and real-time implement-ation of a radial-basis-function neural-network compensator for high-performance robot manipulators, Mechatronics, 2000, 10(1-2): 265-287.

DOI: 10.1016/s0957-4158(99)00058-6

[16] V. David S' anchez A, Searching for a solution to the automatic RBF network design problem, Neurocomputing, 2002, 42(1-4): 147–170.

DOI: 10.1016/s0925-2312(01)00600-2

[17] Huang Sunan, Tan Kok Kiong and Lee Tong Heng, Adaptive neural network algorithm for control design of rigid-link electrically driven robots, Neurocomputing , 2008, 71(4-6): 885–894.

DOI: 10.1016/j.neucom.2007.02.012