A UNIVERSAL TRAJECTORY TRACKING CONTROLLER FOR MOBILE ROBOTS VIA MODEL-FREE ONLINE REINFORCEMENT LEARNING

Farbod Fahimi and Susheel Praneeth

References

  1. [1] Z. Yu and A. Dexter, Online tuning of a supervisory fuzzycontroller for low-energy building system using reinforcementlearning, Control Engineering Practice, 18(5), 2010, 532–539.
  2. [2] Z. Shen, C. Guo, and N. Zhang, A general fuzzified CMACbased reinforcement learning control for ship steering usingrecursive least-squares algorithm, Neurocomputing, 73(4–6),2010, 700–706.
  3. [3] C.-K. Lin, H∞ reinforcement learning control of robot manip-ulators using fuzzy wavelet networks, Fuzzy Sets and Systems,160(12), 2009, 1765–1786.
  4. [4] D.M. Katic, A.D. Rodic, and M.K. Vukobratovic, Hybriddynamic control algorithm for humanoid robots based onreinforcement learning, Journal of Intelligent and RoboticSystems: Theory and Applications, 51(1), 2008, 3–30.
  5. [5] J. Zhou, L. Yu, S. Mabu, K. Hirasawa, J. Hu, and S. Markon, El-evator group supervisory control system using genetic networkprogramming with macro nodes and reinforcement learning,IEEJ Transactions on Electronics, Information and Systems,127(8), 2007, 1234–1242+15.
  6. [6] J. Hong and V.V. Prabhu, Distributed reinforcement learningcontrol for batch sequencing and sizing in just-in-time manu-facturing systems, Applied Intelligence, 20(1), 2004, 71–87.
  7. [7] I. Bucak, M. Zohdy, and M. Shillor, Motion control of a non-linear spring by reinforcement learning, Control and IntelligentSystems, 36(1), 2008, 27–36.
  8. [8] J.d.R. Millan, Reinforcement learning of goal-directed obstacle-avoiding reaction strategies in an autonomous mobile robot,Robotics and Autonomous Systems, 15(4), 1995, 275–299.
  9. [9] X. Ma, Y. Xu, G.-Q. Sun, L.-X. Deng, and Y.-B. Li, State-chainsequential feedback reinforcement learning for path planningof autonomous mobile robots, Journal of Zhejiang University:Science C (Computers & Electronics), 14(3), 2013, 167–178.
  10. [10] X.-D. Zhuang, Q.-C. Meng, T.-B. Wei, X.-Z. Wang, R. Tan,and X.-J. Li, Robot path planning in dynamic environmentbased on reinforcement learning, Journal of Harbin Instituteof Technology (New Series), 8(3), 2001, 253–255.
  11. [11] Y. Cai, S. X. Yang, and X. Xu, A hierarchical reinforcementlearning-based approach to multi-robot cooperation for targetsearching in unknown environments, Control and IntelligentSystems, 41(4), 2013, 218–230.
  12. [12] L. Zuo, X. Xu, C. Liu, and Z. Huang, A hierarchical reinforce-ment learning approach for optimal path tracking of wheeledmobile robots, Neural Computing and Applications, 23(7–8),2013, 1873–1883.
  13. [13] J.-M. Choi, S.-J. Lee, and M. Won, Self-learning navigationalgorithm for vision-based mobile robots using machine learningalgorithms, Journal of Mechanical Science and Technology,25(1), 2011, 247–254.63
  14. [14] J.-H. Ye, D. Li, and F. Ye, Dual reinforcement learning adaptivefuzzy control of wheeled mobile robot, Jilin Daxue Xuebao(Gongxueban)/Journal of Jilin University (Engineering andTechnology Edition), 44(3), 2014, 742–749.
  15. [15] I. Vincent and Q. Sun, A combined reactive and reinforcementlearning controller for an autonomous tracked vehicle, Roboticsand Autonomous Systems, 60(4), 2012, 599–608.
  16. [16] X. Xu, C. Liu, S. X. Yang, and D. Hu, Hierarchical approximatepolicy iteration with binary-tree state space decomposition,IEEE Transactions on Neural Networks, 22(12 Part 1), 2011,1863–1877.
  17. [17] F.L. Lewis, A. Yesildirak, and S. Jagannathan, Neural networkcontrol of robot manipulators and nonlinear systems (Philadel-phia, PA: Taylor & Francis, Inc., 1998).
  18. [18] Q. Yang and S. Jagannathan, Reinforcement learning controllerdesign for affine nonlinear discrete-time systems using onlineapproximators, IEEE Transactions on Systems, Man, andCybernetics, Part B: Cybernetics, 42(2), 2012, 377–390.
  19. [19] S. Blazic, A novel trajectory-tracking control law for wheeledmobile robots, Robotics and Autonomous Systems, 59(11),2011, 1001–1007.
  20. [20] Q. Yang, J. B. Vance, and S. Jagannathan, Control of nonaffinenonlinear discrete-time systems using reinforcement-learning-based linearly parameterized neural networks, IEEE Transac-tions on Systems, Man, and Cybernetics, Part B: Cybernetics,38(4), 2008, 994–1001.

Important Links:

Go Back