Adaptive and Neural Learning for Biped Robot Actuator Control

  • Pavan K. Vempaty
  • Ka C. Cheok
  • Robert N. K. Loh
  • Micho Radovnikovich
Chapter
Part of the Lecture Notes in Electrical Engineering book series (LNEE, volume 68)

Abstract

Many robotics problems do not take the dynamics of the actuators into account in the formulation of the control solutions. The fallacy is in assuming that forces/torques can be instantaneously and accurately generated. In practice, actuator dynamics may be unknown. This paper presents a Model Reference Adaptive Controller (MRAC) for the actuators of a biped robot that mimics a human walking motion. The MRAC self-adjusts so that the actuators produce the desired torques. Lyapunov stability criterion and a rate of convergence analysis is provided. The control scheme for the biped robot is simulated on a sagittal plane to verify the MRAC scheme for the actuators. Next, the paper shows how a neural network (NN) can learn to generate its own walking gaits using successful runs from the adaptive control scheme. In this case, the NN learns to estimate and anticipate the reference commands for the gaits.

Keywords

Biped Robot Model Reference Adaptive Control Biped Walking Actuator Torque Neural Network Estimation 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

References

  1. 1.
    E. Bobasu, D. Popescu, Adaptive nonlinear control algorithms of robotic manipulators. Proceedings of the 7th WSEAS International Conference on Automation & Information, 2006, pp. 83–88Google Scholar
  2. 2.
    R. Chalodnan, D.B. Grimes, R.P.N. Rao, Learning to walk through imitation. Proceedings of the 20th International Joint Conference on Artificial Intelligence, 2007, pp. 2084–2090Google Scholar
  3. 3.
    S. Ha, Y. Han, H. Hahn, Adaptive gait pattern generation of biped robot based on humans gait pattern analysis. Proc. Int. J. Mech. Sys. Sci. Engr. 1(2), 80–85 (2008)Google Scholar
  4. 4.
    O. Haavisto, H. Hyotyniemi, Simulation tool of biped walking robot model. Master’s thesis, Helsinki University of Technology, Espoo, Finland, 2004Google Scholar
  5. 5.
    J. Hu, J. Pratt, C.-M. Chew, H. Herr, G. Pratt, Adaptive virtual model control of a bipedal walking robot. Int. J. Artif. Intel. Tools 8(3), 337–348(1999)CrossRefGoogle Scholar
  6. 6.
    S. Kajita, F. Kanehiro, K. Kaneko, K. Fijiwara, K. Yokoi, H. Hirukawa, A realtime pattern generator for biped walking. Proceedings of the IEEE International Conference on Robotics & Automation, vol. 1, 2002, pp. 31–37Google Scholar
  7. 7.
    S. Kajita, F. Kanehiro, K. Kaneko, K. Fujiwara, K. Harada, K. Yokoi, H. Hirukawa, Biped walking pattern generation by using preview control of zero-moment point. Proceedings of the IEEE International Conference on Robotics & Automation, vol. 2, 2003, pp. 1620–1626Google Scholar
  8. 8.
    P. Manoonpong, T. Geng, T. Kulvicius, B. Porr, F. Worgotter, Adaptive, fast walking in a biped robot under neuronal control and learning. PLos Computat. Biol. 3(7), 1305–1320(2007)Google Scholar
  9. 9.
    J. Morimoto, G. Cheng, C.-G. Atkeson,G. Zeglen, A simple reinforcement learning algorithm for biped walking. Proceedings of the IEEE Conference on Robotics and Automation, vol. 3, 2004, pp. 3030–3035Google Scholar
  10. 10.
    J. Nakanishi, J. Morimoto, G. Endo, G. Cheng, S. Schaal, M. Kawato, Learning from demonstration and adaptation of biped locomotion with dynamical movement primitives. Proceedings of the 4th IEEE/RAS International Conference on Humanoid Robotics, vol. 2, 2004, pp. 925–940Google Scholar
  11. 11.
    J. Pratt, C.-M. Chew, A. Torres, P. Dilworth, G. Pratt, Virtual model control: an intuitive approach for bipedal locomotion. Int. J. Robot. Res. 20(2), 129–143 (2001)CrossRefGoogle Scholar
  12. 12.
    A. Takanobu, S. Jun, K. Shigenobu, Reinforcement learning for biped walking using human demonstration towards the human like walking of biped robot. Chino Shisutemu Shinpojiumu Shiryo, 32, 393–398 (2005)Google Scholar
  13. 13.
    P.K. Vempaty, K.C. Cheok, R.N.K. Loh, Model reference adaptive control for actuators of a biped robot locomotion. Proceedings of the World Congress on Engineering and Computer Science, San Francisco, USA, vol. 2, 2009, pp. 983–988Google Scholar
  14. 14.
    K. Wolff, P. Nordin, Evolutionary learning from first principles of biped walking on a simulated humanoid robot. Proceedings of the Business and Industry Symposium of the Simulation Technologies Conference, 2003, pp. 31–36Google Scholar
  15. 15.
    C. Zhou, Q. Meng, Dynamic balance of a biped robot using fuzzy reinforcement learning agents. Fuzzy Sets Syst. Arch. 134, 169–187 (2003)MathSciNetMATHCrossRefGoogle Scholar

Copyright information

© Springer Science+Business Media B.V. 2010

Authors and Affiliations

  • Pavan K. Vempaty
    • 1
  • Ka C. Cheok
  • Robert N. K. Loh
  • Micho Radovnikovich
  1. 1.Department of Electrical and Computer EngineeringOakland UniversityRochesterUSA

Personalised recommendations