A Surrogate Model Based Gait Learning for Biped Robot

Abstract:

Gait learning is usually under a so-called simulation based framework, where a simulation platform is firstly setup, and then based on which the gait pattern is learned via some learning algorithm. For the reason that there exist big differences between simulation platform and real circumstances, an additional adapting procedure is always required when learned gait pattern is applied to a real robot. This case turns out to be more critical for a biped robot, because its control appears more difficult than others, such as a quadruped robot. This leads the new scheme that the gait is directly learned on real robot to be attractive. However, under this real robot based learning scheme, most of those learning algorithms that commonly used under simulation based framework appear to be trivial, since they always needs too many learning trials which may wear out the robot hardware. Faced to this situation, in this paper, a surrogate model based gait learning approach for biped robot is proposed. And the experimental results on a real humanoid robot PKU-HR3 show the effectiveness of the proposed approach.

• Periodical: Applied Mechanics and Materials (Volumes 433-435)
• Pages: 138-145
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.433-435.138
• Online since: October 2013
• Authors: Ding Sheng Luo, Yi Wang, Xi Hong Wu
• Keywords: Gait Learning, Humanoid Robot, Surrogate Model

References

[1] M. Vukobratovic and D. Juricic, Contribution to the synthesis of biped gait, IEEE Transaction on Biomedical Engineering, vol. 16, no. 1, pp.1-6, (1969).

DOI: 10.1109/tbme.1969.4502596

[2] H. Hemami, F. Weimer, and S. Koozekanani, Some aspects of the inverted pendulum problem for modeling of locomotion systems, IEEE Transactions on Automatic Control, vol. 18, no. 6, pp.658-661, (1973).

DOI: 10.1109/tac.1973.1100432

[3] G. Taga, Y. Yamaguchi and H Shimizu, Self-organized control of bipedal locomotion by neural oscillators in unpredictable environment, Biological Cybernetics, vol. 65, no. 3, pp.147-159, (1991).

DOI: 10.1007/bf00198086

[4] J. Pratt, P. Dilworth, and G. Pratt, Virtual model control of a bipedal walking robot, IEEE International Conference on Robotics and Automation, vol. 1, pp.193-198, (1997).

DOI: 10.1109/robot.1997.620037

[5] B. Hengst, D. Ibbotson, S. B. Pham and C. Sammut, Omnidirectional locomotion for quadruped robots, RoboCup 2001: Robot Soccer World Cup V. Springer, p.368–373, (2002).

DOI: 10.1007/3-540-45603-1_45

[6] M. S. Kim and W. Uther, Automzaic gait optimization for quadruped robots, Australasian Conference on Robotics and Automation, pp.1-9, (2003).

[7] M. Hebbel, W. Nistico and D. Fisseler, Learning in a high dimensional space: fast omnidirectional quadrupedal locomotion, Lecture Notes in Computer Science, vol. 4434, pp.314-321, (2007).

DOI: 10.1007/978-3-540-74024-7_28

[8] M. J. Quinland, S. K. Chalup and R. H. Middleton, Techniques for improving vision and locomotion on the sony aibo robot, 2003 Australasian Conference on Robotics and Automation, (2003).

[9] N. Kohl and P. Stone, Policy gradient reinforcement learning for fast quadrupedal locomotion, IEEE International Conference on Robotics and Automation, pp.2619-2624, (2004).

DOI: 10.1109/robot.2004.1307456

[10] C. Niehaus, T. Röfer and T. Laue, Gait-optimization on a humanoid robot using particle swarm optimization, The 2nd Workshop on Humanoid Soccer Robots at the IEEE-RAS International Conference on Humanoid Robots, (2007).

DOI: 10.1109/ichr.2007.4813927

[11] N. Kohl and P. Stone. Machine learning for fast quadrupedal locomotion, The Nineteenth National Conference on Artificial Intelligence, pp.611-616, (2004).

[12] D. Lizotte, T. Wang, M. Bowling and D. Schuurmans, Automatic gait optimization with gaussian process regression, International Joint Conference on Artificial Intelligence, pp.944-949, (2007).

[13] T. Hemker, M. Stelzer, O. von Stryk and H. Sakamoto, Efficient walking speed optimization of a humanoid robot, International Journal of Robotics Research, vol. 28, no. 2, p.303–314, (2009).

DOI: 10.1177/0278364908095171

[14] H. Wang, S. P. Wang and M. M. Tomovic, Modified sequential Kriging optimization for multidisciplinary complex product simulation, Chinese Journal of Aeronautics, vol. 23, no. 5, pp.616-622, (2010).

DOI: 10.1016/s1000-9361(09)60262-4

[15] P. Gill, W. Murray and M. Saunders, User's guide for SNOPT 7. 1: a fortran package for large-scale nonlinear programming, Report NA 05-2, Department of Mathematics, University of California at San Diego, (2006).

[16] L. G. Fonseca, H. J. C. Barbosa and A. C. C. Lemonge, A similaritybased surrogate model for expensive evolutionary optimization with fixed budget of simulations, The 11th Congress on Evolutionary Computation, p.867–874, (2009).

DOI: 10.1109/cec.2009.4983036

[17] A.F. Hernandez and M.G. Gallivan, An exploratory study of discrete time state-space models using kriging, American Control Conference, pp.3993-3998, (2008).

DOI: 10.1109/acc.2008.4587117