Integration of Soft Computing Towards Autonomous Legged Robots

  • Anthony Wong
  • Marcelo H. AngJr.
Part of the Studies in Fuzziness and Soft Computing book series (STUDFUZZ, volume 116)


Mobile robots are extensively used in various terrains to handle situations inaccessible to man. Legged robots in particular are tasked to move in uneven terrain. Hence the primary problem of these robots is locomotion in an autonomous fashion. Autonomy is important as the tasks are plagued with many uncertainties. Some of these tasks include leg movement and coordination, navigation, localisation, and stability during movement, all operating in dynamic and unexplored territories.

Classical control and traditional programming methods provide stable and simple solutions in a known environment. The environment that legged robots work in is dynamic and unstructured, and such control methods are not always able to cope with. It is difficult to model the environment to provide the controller with the relevant data and program actions for all possible situations. Hence controllers with abilities to learn and to adapt are needed to solve this problem. Soft computing provides an attractive avenue to deal with these situations.

Soft computing methods are based on biological systems and they provide the following features: generalisation, adaptation and learning. As more is realised about the use and properties of soft computing methods, the development of controller is shifting towards using soft computing. They have properties that can be used to improve the stability, adaptability, and generalisation of the controllers. Some of the more popular methods used are fuzzy logic, artificial neural networks, reinforcement learning and genetic algorithms. They are commonly integrated with classical methods to enhance the features of classical controllers and vice versa. Each soft computing method serves a different purpose, with its advantages and disadvantages, and the methods are often used together to complement each other.

This chapter provides a survey on the different uses of soft computing methods in the different aspects of legged robotics. We see how soft computing methods and classical techniques compliment each other. Two areas of legged robotics are dealt with - control architecture and the problem of navigation. The Central Pattern Generator (CPG) controller and the behaviour-based controller are two architectures presented in this chapter. Various soft computing techniques are used to implement and improve these two controllers.


Fuzzy Logic Mobile Robot Fuzzy Controller Soft Computing Central Pattern Generator 
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.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Kaynak, O. and Rudas, I. (1995): Soft computing methodologies and their fusion in mechatronic products. Computing and Control Engineering Journal, 6(2):68–72.CrossRefGoogle Scholar
  2. 2.
    Cervantes, F., Olivares, R., Weitzenfeld, A., Arkin, R. and Corbacho, F. (1998): A neural schema architecture for autonomous robots. Proc. of 1998 International Symposium on Robotics and Automation, pages 245–252. Saltillo, Mexico.Google Scholar
  3. 3.
    Kolushev, F.A., Timofeev, A.V. and Bogdanov, A.A. (1999): Hybrid algorithms of multi-agent control of mobile robots. International Joint Conference on Neural Networks, 6:4115–4118.Google Scholar
  4. 4.
    Pasparakis, G., Luk, B.L., Galt, S., Kalyvas, T. and Virk, G.S. (1996): A.I. solutions for semi-autonomous legged robots. IEE Colloquium on Information Technology for Climbing and Walking Robots, 1996/167:9/1–9/4.Google Scholar
  5. 5.
    Benediktsson, H., Benediktsson, J.A., and Amason, K. (2000): Absolute neurofuzzy classification of remote sensing data. Geoscience and Remote Sensing Symposium Proceedings. IEEE 2000 International., 3:969–971.Google Scholar
  6. 6.
    Brooks, R.A. (1985) : A robust layered control system for a mobile robot. Massachusetts Institute of Technology Artificial Intelligence Laboratory.Google Scholar
  7. 7.
    Cymbalyuk, G., Dean, J., Cruse, H., Bartling, C.H., and Dreifert, M. (1994): A neural net controller for six-legged walking system. From Perception to Action Conference IEEE Computer Society Press, pages 55–65. Edited by P. Gaussier, J.-D. Nicoud. Los Alamitos, California.Google Scholar
  8. 8.
    Beer, R.D., Chiel, H.J. (1989): A lesion study of a heterogeneous artificial neural network for hexapod locomotion. International Joint Conference on Neural Networks, 1:407–414.Google Scholar
  9. 9.
    Saffiotti, A., Buschka, P., and Wasik, Z. (2000): Fuzzy landmark-based localization for a legged robot. IEEE/RSJ International Conference on Intelligent Robots and Systems, pages 1205–1210. Takamatsu, Japan.Google Scholar
  10. 10.
    Saffiiotti, A. (1997) : The use of fuzzy logic for autonomous robot navigation. Soft Computing, 1(4):180–197.CrossRefGoogle Scholar
  11. 11.
    Sanz, A. (1997): The uses of fuzzy logic in autonomous robot navigation. 6th IEEE International Conference on Fuzzy Systems, 2:1089–1093. Barcelona, Spain.Google Scholar
  12. 12.
    Boone, G., Ram, A., Arkin, R. and Pearce, M. (1994): Using genetic algorithms to learn reactive control parameters for autonomous robotic navigation. Adaptive Behavior, 2:277–304.CrossRefGoogle Scholar
  13. 13.
    Bruce, J., Lenser, S., and Veloso, M. (2002): A modular hierarchical behaviorbased architecture. In Birk, A., Coradeschi, S. and Tadokoro, S., editors, RoboCup-2001: The Fifth RoboCup Competitions and Conferences. Springer Verlag, Berlin, 2002, forthcoming.Google Scholar
  14. 14.
    Atienza, R.O. (1998): An AI-Enhanced Control System for a Four-legged Robot. National University of Singapore.Google Scholar
  15. 15.
    Muscato, G. (1998): Soft computing techniques for the control of walking robots. Computing and Control Engineering Journal, 9(4):193–200, August 1998.CrossRefGoogle Scholar
  16. 16.
    Bonissone, P.P. (1997): Soft computing: The convergence of emerging reasoning technologies. Soft Computing, 1:6–18. CrossRefGoogle Scholar
  17. 17.
    Haykin, S. (1999) : Neural Networks - A Comprehensive Foundation. McMaster University, Prentice-Hall Inc., 2nd edition.MATHGoogle Scholar
  18. 18.
    Tomas, L.M., Zamora, M.A., Toledo, F.J., Luis, J.D., and Martinez, H. (2000): Map building with ultrasonic sensors of indoor environments using neural networks. IEEE International Conference on Systems, Man, and Cybernetics, 2:3334–3339.Google Scholar
  19. 19.
    Whitley, D. (1994): A genetic algorithm tutorial. Statistics and Computing, 4:65–85.CrossRefGoogle Scholar
  20. 20.
    Sutton, R.S. and Barto, A.G. (1998): Reinforcement learning : An introduction, rich/book/the-book.html.Google Scholar
  21. 21.
    Hennig, D., Burgard, W., Fox, D. and Schmidt, T. (1996) : Position tracking with position probability grids. Proceedings of the First Euromicro Workshop on Advanced Mobile Robot, pages 2–9.Google Scholar
  22. 22.
    Al-Jumaily, A.A.S. and Amin, S.H.M. (1999): Fuzzy logic based behaviors blending for intelligent reactive navigation of walking robot. Proceedings of the Fifth International Symposium on Signal Processing and Its Applications, 1:155–158.Google Scholar
  23. 23.
    Oh, S.Y. and Han, S.J. (2001) : Evolutionary algorithm based neural network controller with selective sensor usage for autonomous mobile robot navigation, INNS-IEEE International Joint Conference on Neural Networks, 3:2194–2199, Washington. DC, USA, July 2001.Google Scholar
  24. 24.
    Kirchner, F. (1997) : Q-learning of complex behaviours on a six-legged walking machine. Proceedings of the second Euromicro Workshop on Advanced Mobile Robots IEEE, pages 51–59. Brescia, Italy.Google Scholar
  25. 25.
    Randell, M.J. and Pipe, A.G. (2000): A novel soft computing architecture for the control of autonomous walking robots. Soft Computing, 4:165–185.CrossRefGoogle Scholar
  26. 26.
    Micci-Barreca, D., Ogmen, H. (1994): A central pattern generator for insect gait production. From Perception to Action Conference, IEEE, pages 348–351.Google Scholar
  27. 27.
    Felipe, M.G., Yang, F. and Yang, Z. (2000): Building artificial CPGs with asymmetric hopfield networks. of the IEEE-INNS-ENNS International Joint Conference on Neural Networks, 4:290–295.Google Scholar
  28. 28.
    Quinn, R.D., Espenschied, K.S., Chiel, H.J., Beer, R.D. (1992): Robustness of a distributed neural network controller for locomotion in a hexapod. IEEE Transactions on Robotics and Automation, 8(3):293–303.CrossRefGoogle Scholar
  29. 29.
    Singh, S.P. (1992) : Transfer of training by composing solutions for elemental sequential tasks. Machine Learning, 8(3/4):323–339.MATHGoogle Scholar
  30. 30.
    Gander, R.E., Srinivasan, S. and Wood, H.C. (1992): A movement pattern generator model using artificial neural networks. IEEE Transactions on Biomedical Engineering, 39(7):716–722.CrossRefGoogle Scholar
  31. 31.
    Hoff, J. and Bekey, G.A. (1997) : A cerebellar approach to adaptive locomotion for legged robots. IEEE International Symposium on Computational Intelligence in Robotics and Automation, pages 94–100. Monterey, California.Google Scholar
  32. 32.
    Muller, U., Cruse, H., Dean, J. and Schmitz, J. (1991): The stick insect as a walking robot. Proceedings of the Fifth International Conference on Advanced Robotics IEEE, 2:936–940.Google Scholar
  33. 33.
    Cruse, H., Kindermann, T. and Dean, J. (1998) : A biologically motivated controller for a six-legged walking system. Proceedings of the 24th Annual Conference of the IEEE Industrial Electronics Society, 4:2168–2173.Google Scholar
  34. 34.
    Ijspeert, A.J. (2001): A connectionist central pattern generator for the aquatic and terrestrial gaits of a simulated salamander. Biological Cybernetics, 84:331–348.CrossRefGoogle Scholar
  35. 35.
    Ijspeert, A.J. and Kodjabachian, J. (1999): Evolution and development of a central pattern generator for the swimming of a lamprey. Artificial Life, 5:247–269.CrossRefGoogle Scholar
  36. 36.
    Yang, J. (1993): Adaptive control for a biped locomotion system. Proceedings of the 36th Midwest Symposium on Circuits and Systems, 1:657–660.CrossRefGoogle Scholar
  37. 37.
    Cao, M. and Kawaniura, A. (1998) : A design method of neural oscillatory networks for generation of humanoid biped walking patterns. Proceedings of IEEE International Conference on Robotics and Automation, pages 2357–2362.Google Scholar
  38. 38.
    Zheng, Y.F. (1990) : A neural synthesizer for autonomous biped robots. Proceedings of IEEE International, pages 657–660.Google Scholar
  39. 39.
    Hu, J. and Pratt, G. (1999) : Self-organising cmac neural networks and adaptive dynamic control. Proceedings of IEEE International Symposium on Intelligent Control/Intelligent Systems and Semiotics, pages 259–265.Google Scholar
  40. 40.
    Michaud, F. and Matarić, M.J. (1998): A history-based approach for adaptive robot behaviour in dynamic environments. Proceedings, Autonomous Agents, pages 422–429.Google Scholar
  41. 41.
    Bekey, G.A., Fagg, A.H. and Lotspeich, D. (1994): A reinforcement-learning approach to reactive control policy design for autonomous robots. Proceedings of the 1994 IEEE International Conference on Robotics and Automation, pages 39–44.Google Scholar
  42. 42.
    Matarić, M.J. (1998): Behavior-based robotics as a tool for synthesis of artificial behavior and analysis of natural behavior. Trends in Cognitive Science, 2(3) :82–87.CrossRefGoogle Scholar
  43. 43.
    Zhou, C. and Jagannathan, K. (1996): Adaptive network based fuzzy control of a dynamic biped walking robot. Proceedings of the IEEE International Joint Symposia on Intelligence and Systems, pages 109–116.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2003

Authors and Affiliations

  • Anthony Wong
    • 1
  • Marcelo H. AngJr.
    • 1
  1. 1.Department of Mechanical and Production EngineeringNational University of SingaporeSingapore

Personalised recommendations