Skip to main content
Springer Nature Link
Log in

Omnidirectional walking using central pattern generator

  • Original Article
  • Published:
International Journal of Machine Learning and Cybernetics Aims and scope Submit manuscript

Abstract

The effective and accurate walking is the biggest challenge for humanoid robot locomotion. In dynamic environments, such as RoboCup competition, not only must the speed of actions be high, but action switching must also be done almost immediately. This paper concentrates on two major behavior actions of humanoid soccer robot; straight walking and turning actions. Matsuoka central pattern generator model is used to generate trajectory actions. Both actions have their own parameters, which are obtained by comprehensive learning particle swarm optimization. By using these two actions and proper switching between them, robot can reach every point in the environment within a reasonable time. This paper tries to highlight the importance of action switching in movement maneuverability and proposes an effective solution for it. As transition from one action to another cannot be done in every posture of robot, the switching is done when robot is in double support phase. In this situation, membrane potential of each neuron has its minimum value and switching does not create big torque. The maximum time required for change action in this model is less than one step of robot. This method has been successfully implemented in rcssserver3d simulation server on NAO humanoid robot.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Subscribe and save

Springer+ Basic
$34.99 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10
Fig. 11

Similar content being viewed by others

Explore related subjects

Discover the latest articles, news and stories from top researchers in related subjects.

References

  1. Taormina R, Chau KW, Sethi R (2012) Artificial neural network simulation of hourly groundwater levels in a coastal aquifer system of the Venice lagoon. Eng Appl Artif Intell 25(8):1670–1676. doi:10.1016/j.engappai.2012.02.009

    Article  Google Scholar 

  2. Muttil N, Chau KW (2006) Neural network and genetic programming for modelling coastal algal blooms. Int J Environ Pollut 28:223–238. doi:10.1504/IJEP.2006.011208

    Article  Google Scholar 

  3. Wu CL, Chau KW, Li YS (2009) Predicting monthly streamflow using data-driven models coupled with data-preprocessing techniques. Water Resour Res 45:W08432. doi:10.1029/2007WR006737

    Article  Google Scholar 

  4. Cheng CT, Chau KW, Sun Y, Lin J (2005) Long-term prediction of discharges in Manwan reservoir using artificial neural network models. Lect Notes Comput Sci 3498:1040–1045. doi:10.1007/11427469_165

    Article  MATH  Google Scholar 

  5. Liu J, Veloso M (2008) Online ZMP sampling search for biped walking planning. In: International conference on intelligent robots and systems. pp 185–190. doi:10.1109/IROS.2008.4651017

  6. Ijspeert AJ (2008) Central pattern generators for locomotion control in animals and robots: a review. Neural Netw 21(4):642–653. doi:10.1016/j.neunet.2008.03.014

    Article  Google Scholar 

  7. Grélot L, Milano S, Portillo F, Miller D (1993) Respiratory interneurons of the lower cervical (C4–C5) cord: membrane potential changes during fictive coughing, vomiting, and swallowing in the decerebrate cat. Pflügers Archiv Eur J Physiol 425(3):313–320. doi:10.1007/BF00374181

    Article  Google Scholar 

  8. Delcomyn F (1980) Neural basis of rhythmic behavior in animals. Science 210(4469):492–498. doi:10.1126/science.7423199

    Article  Google Scholar 

  9. Ijspeert AJ, Crespi A (2007) Online trajectory generation in an amphibious snake robot using a lamprey-like central pattern generator model. In: International conference on robotics and automation. IEEE, pp 262–268. doi:10.1109/ROBOT.2007.363797

  10. Wolff K, Pettersson J, Heralic A, Wahde M (2006) Structural evolution of central pattern generators for bipedal walking in 3D simulation. In: International conference on systems, man and cybernetics. IEEE, pp 227–234. doi:10.1109/ICSMC.2006.384387

  11. Liu GL, Habib MK, Watanabe K, Izumi K (2008) Central pattern generators based on Matsuoka oscillators for the locomotion of biped robots. Artif Life Robot 12(1):264–269. doi:10.1007/s10015-007-0479-z

    Article  Google Scholar 

  12. Kim JJ, Lee JW, Lee JJ (2009) Central pattern generator parameter search for a biped walking robot using nonparametric estimation based particle swarm optimization. Int J Control Autom Syst 7(3):447–457. doi:10.1007/s12555-009-0314-5

    Article  Google Scholar 

  13. Endo G, Nakanishi J, Morimoto J, Cheng G (2005) Experimental studies of a neural oscillator for biped locomotion with QRIO. In: International conference on robotics and automation. IEEE, pp 596–602. doi:10.1109/ROBOT.2005.1570183

  14. Endo G, Morimoto J, Nakanishi J, Cheng G (2004) An empirical exploration of a neural oscillator for biped locomotion control. In: International conference on robotics and automation. IEEE, pp 3036–3042. doi:10.1109/ROBOT.2004.1307523

  15. Zehr EP, Carroll TJ, Chua R, Collins DF, Frigon A, Haridas C, Hundza SR, Thompson AK (2004) Possible contributions of CPG activity to the control of rhythmic human arm movement. Can J Physiol Pharmacol 82(8–9):556–568. doi:10.1139/y04-056

    Article  Google Scholar 

  16. Inada H, Ishii K (2004) A bipedal walk using central pattern generator. Int Congr Ser 1269:185–188. doi:10.1016/j.ics.2004.05.129

  17. Eberhart R, Shi Y (2004) Comparison between genetic algorithms and particle swarm optimization. Lect Notes Comput Sci 1447:611–616. doi:10.1007/BFb0040812

    Article  Google Scholar 

  18. Liang JJ, Qin AK, Suganthan PN, Baskar S (2004) Evaluation of comprehensive learning particle swarm optimizer. Lect Notes Comput Sci 3316:230–235. doi:10.1007/978-3-540-30499-9_34

    Article  Google Scholar 

  19. Aoi S, Tsuchiya K (2005) Locomotion control of a biped robot using nonlinear oscillators. Auton Robots 19(3):219–232. doi:10.1007/s10514-005-4051-1

    Article  Google Scholar 

  20. Aoi S, Tsuchiya K (2007) Adaptive behavior in turning of an oscillator-driven biped robot. Auton Robots 23(1):37–57. doi:10.1007/s10514-007-9029-8

    Article  MathSciNet  Google Scholar 

  21. Nakanishi J, Morimoto J, Endo G, Cheng G, Schaal S, Kawato M (2004) Learning from demonstration and adaptation of biped locomotion. Robot Auton Syst 47(2–3):79–91. doi:10.1016/j.robot.2004.03.003

    Article  Google Scholar 

  22. Yang L, Chew CM, Poo AN, Zielinska T (2006) Adjustable bipedal gait generation using genetic algorithm optimized Fourier series formulation. In: International conference on intelligent robots and systems. IEEE, pp 4435–4440. doi:10.1109/IROS.2006.282077

  23. Chew CM, Pratt GA (2002) Dynamic bipedal walking assisted by learning. Robotica 20(5):477–491. doi:10.1017/S0263574702004290

    Article  Google Scholar 

  24. Wu QD, Liu C, Zhang J, Chen QJ (2009) Survey of locomotion control of legged robots inspired by biological concept. Sci China Ser F Inf Sci 52(10):1715–1729. doi:10.1007/s11432-009-0169-7

    Article  MATH  Google Scholar 

  25. Matsuoka K (2011) Analysis of a neural oscillator. Biol Cybern 104(4–5):1–8. doi:10.1007/s00422-011-0432-z

    MathSciNet  MATH  Google Scholar 

  26. Zaier R (2012) Design of oscillatory neural network for locomotion control of humanoid robots. The future of humanoid robots—research and applications. InTech:41–60. doi:10.5772/25470

  27. Matsuoka K (1987) Mechanisms of frequency and pattern control in the neural rhythm generators. Biol Cybern 56:345–353. doi:10.1007/BF00319514

    Article  Google Scholar 

  28. Hairer E, Wanner G (1996) Implementation of Implicit Runge-Kutta Methods. Springer Ser Comput Math 14:118–130. doi:10.1007/978-3-642-05221-7_8

    Article  MathSciNet  Google Scholar 

  29. Gouaillier D, Hugel V, Blazevic P, Kilner C, Monceaux J, Lafourcade P, Marnier B, Serre J, Maisonnier B (2008) The NAO humanoid: a combination of performance and affordability. CoRR abs/0807.3223

  30. Obst O, Rollmann M (2004) Spark-A generic simulator for physical multi-agent simulations. Lect Notes Comput Sci 3187:243–257. doi:10.1007/978-3-540-30082-3_18

    Article  Google Scholar 

  31. Smith R Home page of open dynamics engine project. http://www.ode.org/ode.html

  32. Vorst P (2006) Readylog agents for the robocup 3d soccer simulation league. RWTH Aachen University Thesis

  33. Tian N, Lai CH (2014) Parallel quantum-behaved particle swarm optimization. Int J Mach Learn Cybern 5(2):309–318. doi:10.1007/s13042-013-0168-2

    Article  MathSciNet  Google Scholar 

  34. Ma W, Wang M, Zhu X (2014) Improved particle swarm optimization based approach for bilevel programming problem-an application on supply chain model. Int J Mach Learn Cybern 5(2):281–292. doi:10.1007/s13042-013-0167-3

    Article  Google Scholar 

  35. Rana S, Jasola S, Kumar R (2013) A boundary restricted adaptive particle swarm optimization for data clustering. Int J Mach Learn Cybern 4(4):391–400. doi:10.1007/s13042-012-0103-y

    Article  Google Scholar 

  36. Wang XZ, He YL, Dong LC, Zhao HY (2011) Particle Swarm Optimization for Determining Fuzzy Measures from Data. Inf Sci 181(19):4230–4252. doi:10.1016/j.ins.2011.06.002

    Article  MATH  Google Scholar 

  37. Zhang J, Chau KW (2009) Multilayer Ensemble Pruning via Novel Multi-sub-swarm Particle Swarm Optimization. J Univers Comput Sci 15(4):840–858. doi:10.3217/jucs-015-04-0840

    Google Scholar 

  38. Chau KW (2007) Application of a PSO-based neural network in analysis of outcomes of construction claims. Autom Constr 16(5):642–646. doi:10.1016/j.autcon.2006.11.008

    Article  MathSciNet  Google Scholar 

  39. Kennedy J, Eberhart R (1995) Particle swarm optimization. In: International conference on neural networks. IEEE, pp 1942–1948. doi:10.1109/ICNN.1995.488968

Download references

Author information

Authors and Affiliations

  1. Computer Engineering and Information Technology Department, Amirkabir University of Technology, Tehran, Iran

    Karim Moradi & Saeed Shiry Ghidary

  2. Department of Computer Engineering and Information Technology, Hamedan University of Technology, Hamedan, Iran

    Mohsen Fathian

Authors
  1. Karim Moradi
    View author publications

    You can also search for this author inPubMed Google Scholar

  2. Mohsen Fathian
    View author publications

    You can also search for this author inPubMed Google Scholar

  3. Saeed Shiry Ghidary
    View author publications

    You can also search for this author inPubMed Google Scholar

Corresponding author

Correspondence to Mohsen Fathian.

Appendix A: some properties of NAO dynamics

Appendix A: some properties of NAO dynamics

NAO is one the most humanoid robot built in 2004 by the Aldebaran Robotics company for the purpose of research and education. It has been used in RoboCup Standard Platform since 2007. Beside usability and efficiency this robot has some weak point which makes the stability control become hard.

Here, we give some properties of NAO robot which makes stability control difficult while walking and turning:

  1. 1.

    The center of mass (COM) of NAO is placed on the upper part of the robot body. The COM is the weighted average of the robot’s parts. The projection of its point on the ground can be used to estimate the robot stability. If COM is in the support area, the robot is in stable posture. Generally, the COM in all humanoid robots located in torso and upper part of robot.

  2. 2.

    The NAO robot does not have any joints in its foot tip and have a big foot in proportion to its height, so if the robot wants to walk, it has to lift its foot in the beginning of each walking cycle.

  3. 3.

    It has massive legs in contrast to the other parts of the body. This property causes a big moment when robot moves in the support phase.

  4. 4.

    The abdomen of robot is very small and robot’s heavy components, such as its power supply and on-board computer, are situated higher than the middle of the robot; so the robot stability is not good and it falls down when it tilts to each side.

  5. 5.

    Weight of the robot is not distributed equally between body parts; for example the weight of its head is about 400 g, which is almost 10 % of the total weight of its body. This results in a center of gravity near to the head of NAO.

  6. 6.

    NAO’s legs cannot rotate around the z axis with respect the body. Aside from that, robot has only transverse Hip-Yaw-Pitch joint which bent outside of robot.

  7. 7.

    Robot does not have any compensate joint. Compensate joints often use for maintain stability.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Moradi, K., Fathian, M. & Shiry Ghidary, S. Omnidirectional walking using central pattern generator. Int. J. Mach. Learn. & Cyber. 7, 1023–1033 (2016). https://doi.org/10.1007/s13042-014-0307-4

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s13042-014-0307-4

Keywords