Walking Motion Generation and Neuro-Fuzzy Control with Push Recovery for Humanoid Robot

Authors

  • Paul Erick Mendez Monroy Universidad Nacional Autonoma de Mexico

Keywords:

push recovery, neuro-fuzzy systems, reinforcement learning, biped walking

Abstract

Push recovery is an essential requirement for a humanoid robot with the objective of safely performing tasks within a real dynamic environment. In this environment, the robot is susceptible to external disturbance that in some cases is inevitable, requiring push recovery strategies to avoid possible falls, damage in humans and the environment. In this paper, a novel push recovery approach to counteract disturbance from any direction and any walking phase is developed. It presents a pattern generator with the ability to be modified according to the push recovery strategy. The result is a humanoid robot that can maintain its balance in the presence of strong disturbance taking into account its magnitude and determining the best push recovery strategy. Push recovery experiments with different disturbance directions have been performed using a 20 DOF Darwin-OP robot. The adaptability and low computational cost of the whole scheme allows is incorporation into an embedded system.

Author Biography

Paul Erick Mendez Monroy, Universidad Nacional Autonoma de Mexico

Dr. Paul Erick Méndez Monroy is an associate researcher at Applied Mathematics and Systems Research Institute at the National Autonomous University of Mexico. He received his Ph.D. degree in electrical engineering from National Autonomous University of Mexico. His current research interests include development of network control systems, distributed and embedded systems, using fuzzy logic techniques, neural networks, and machine learning in general. With applications in robotics, control and pattern recognition.

References

Adiwahono A.H., Chew C.M., Liu B. (2013); Push recovery through walking phase modification for bipedal locomotion, International Journal of Humanoid Robotics, DOI: http://dx.doi.org/10.1142/S0219843613500229, 10(3), 1350022, 2013. https://doi.org/10.1142/S0219843613500229

Allgeuer P., Behnke S.(2014); Fused angles for body orientation representation, Proceedings of 9th Workshop on Humanoid Soccer Robots of the IEEE-RAS Int. Conf. on Humanoid Robots (Humanoids), DOI: 10.1109/IROS.2015.7353399, 366-373, 2014. https://doi.org/10.1109/IROS.2015.7353399

Faber F., Behnke S. (2007); Stochastic optimization of bipedal walking using gyro feedback and phase resetting, 7th IEEE-RAS International Conference on Humanoid Robots, 203-209, doi: 10.1109/ICHR.2007.4813869, 2007. https://doi.org/10.1109/ICHR.2007.4813869

Fuller R. (2013); Introduction to neuro-fuzzy systems, Vol. 2, Springer Science and Business Media, 2013.

Hyon S.H., Osu R., Otaka Y. (2009); Integration of multi-level postural balancing on humanoid robots, IEEE Int. Conf. Robotics and Automation (ICRA), doi: 10.1109/ROBOT.2009.5152434, 1549-1556, 2009. https://doi.org/10.1109/ROBOT.2009.5152434

Komura T., Leung H., Kudoh S., Kuffner J. (2005); A feedback controller for biped humanoids that can counteract large perturbations during gait, IEEE Int. Conf. Robotics and Automation (ICRA), Barcelona, Spain, 1989-1995, 2005.

Koolen T., de Boer T., Rebula J.R., Goswami A., Pratt J.E. (2012): Capturability-based analysis and control of legged locomotion: Theory and application to three simple gait models - Part 1, Int. J. of Robotics Research, 31(9), 1094-1113, 2012. https://doi.org/10.1177/0278364912452673

Missura M., Behnke S. (2015); Gradient-Driven Online Learning of Bipedal Push Recovery, IEEE/RSJ, Int. Conf. on Intelligent Robots and Systems (IROS), Hamburg, Germany, doi: 10.1109/IROS.2015.7353402, 387-392, 2015. https://doi.org/10.1109/IROS.2015.7353402

Missura M., Behnke S. (2013); Omnidirectional Capture Steps for Bipedal Walking, The IEEE-RAS Int. Conf. on Humanoid Robots (Humanoids), 14-20, doi: 10.1109/HUMANOIDS. 2013.7029949, 2013.

Park J.-W., Kim J.-Y., Oh J.-H. (2008); Online Walking Pattern Generation and Its Application to a Biped Humanoid Robot - KHR-3 (HUBO), Advanced Robotics, 22(2), 159-190, 2008.

Pratt J., Carff J., Drakunov S., Goswami A. (2006); Capture point: A step toward humanoid push recovery, IEEE-RAS Int. Conf. Humanoid Robots, Genova, Italy, 200-207, 2006.

Pratt J.E., Koolen T., de Boer T., Rebula J.R., Cotton S., Carffer J., Johnson M., Neuhaus P.D. (2012); Capturability-based analysis and control of legged locomotion: Application to M2V2, a lower-body humanoid - Part 2, Int. J. of Robotics Research, 31(10), 1117-1133, 2012. https://doi.org/10.1177/0278364912452762

Ranganathan A. (2004), The Levenberg-Marquardt Algorithm, Tutorial on LM algorithm, 2004.

Rebula J., Pratt J., Canas F., Goswami A. (2007); Learning capture point for improved humanoid push recovery, IEEE-RAS Int. Conf. Humanoid Robots, Pittsburgh, PA, doi: 10.1109/ICHR.2007.4813850, 65-72, 2007. https://doi.org/10.1109/ICHR.2007.4813850

Semwal V.B., Chakraborty P., Nandi G.C. (2015); Less computationally intensive fuzzy logic

Si J., Wang Y.T. (2001); On-line Learning Control by Association and Reinforcement, IEEE Trans. on Neural Networks, doi: 10.1109/72.914523, 12(2), 264-276, 2001. https://doi.org/10.1109/72.914523

Stephens B. (2007); Humanoid push recovery, IEEE-RAS Int. Conf. Humanoid Robots, IEEE Press, Pittsburgh, PA, 589-595, 2007. https://doi.org/10.1109/ichr.2007.4813931

Tedrake R. (2004); Stochastic policy gradient reinforcement learning on a simple 3d biped, Proc. of the 10th Int. Conf. on Intelligent Robots and Systems, 2849-2854, 2004. https://doi.org/10.1109/iros.2004.1389841

Wieber P.B. (2006); Trajectory free linear model predictive control for stable walking in the presence of strong perturbations, IEEE-RAS Int. Conf. Humanoid Robots, IEEE Press, Nashville, doi: 10.1109/ICHR.2006.321375, 137-142, 2006. https://doi.org/10.1109/ICHR.2006.321375

Published

2017-04-23

Most read articles by the same author(s)

Obs.: This plugin requires at least one statistics/report plugin to be enabled. If your statistics plugins provide more than one metric then please also select a main metric on the admin's site settings page and/or on the journal manager's settings pages.