Using Interaction-Based Learning to Construct an Adaptive and Fault-Tolerant Multi-Link Floating Robot

  • Wenwei Yu
  • Ishioka Takuya
  • Daisuke Iijima
  • Hiroshi Yokoi
  • Yukinori Kakazu
Conference paper


How to build distributed autonomous systems that can adaptively behave through learning in the real world is still an open problem in the research field. In order to tackle this problem, we constructed a distributed autonomous floating robot that consisted of mechanically linked multiple identical units and proposed a new control framework, adaptive oscillator method, to deal with units’ temporal and spatial interaction with their environment. A single model reinforcement learning system was first employed to realize the framework, and a multiple-model reinforcement learning system was proposed further and employed to cope with environmental changes caused by adding obstacles. In order to confirm adaptive behavior acquisition and fault-tolerance in a real environment, we did experiments on target approaching task by using the real floating robot.


Reinforcement Learn Obstacle Avoidance Back Propagation Neural Network Action Rule Control Framework 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Fukuda, T., Ueyama, T., Kawauchi, Y., and Arai, F. (1992). Concept of Cellular Robotic System (CEBOT) and Basic Strategies for its Realization, Computers Elect. Eng 18(1): 11–39, Pergamon Press.CrossRefGoogle Scholar
  2. 2.
    Yim, M. (1993). A Reconfigurable Modular Robot with Many Modes of Locomotion, Proc. of the JSME Int. Conf. on Advanced Mechatronics, 283–288.Google Scholar
  3. 3.
    Kokaji, S., Murata, S., and Kurokawa, H. (1994). Self Organization of a Mechanical System, Distributed Autonomous Robotic Systems, 237–242.Google Scholar
  4. 4.
    Grillner, S. (1985). Neurobiological Bases of Rhythmic Motor Acts in Vertebrates, Science 228:143–149.CrossRefGoogle Scholar
  5. 5.
    Hirose, S. (1993). Biologically Inspired Robots (Snake-Like Locomotors and Manipulators), Oxford Univ. Press.Google Scholar
  6. 6.
    Ijspeert, A.J., Hallam, J., and Willshaw, D. (1999). Evolving Swimming Controllers for a Simulated Lamprey with Inspiration from Neurobiology, Adaptive Behavior 7(2) 151–172.CrossRefGoogle Scholar
  7. 7.
    Iijima, D., Yu, W., Yokoi, H., and Kakazu, Y. (1998). Autonomous Acquisition of Adaptive Behavior for a Distributed Floating Robot Based on the AHC Method, Intelligent Engineering Systems through Artificial Neural Networks 8:537–542.Google Scholar
  8. 8.
    Iijima, D., Yu, W., Yokoi, H., and Kakazu, Y. (1999). Autonomous Acquisition of Target Approaching Behavior for Distributed Controlled Swimming Robot (The Case of Presetting Oscillation Action Patterns), Trans. of the JSME 65(637):208–215.Google Scholar
  9. 9.
    Watkins, C.J.C.H., Dayan, P. (1993). Technical Note: Q-Learning, Sutton, Reinforcement Learning, 55–68.Google Scholar
  10. 10.
    Lin, L.J. (1993). Scaling Up Reinforcement Learning for Robot Control, Proc. of the 10th Int. Conf. on Machine Learning, 182–196.Google Scholar
  11. 11.
    Tani, J., and Nolfi, S. (1998). Learning to Perceive the World as Articulated: An Approach for Hierarchical Learning in Sensory-Motor Systems, From Animals To Animais 5, 270–279.Google Scholar
  12. 12.
    Taga, G. (1995). A Model of the Neuro-Musculo-Skeletal System for Human Locomotion II. Real-Time Adaptability under Various Constraints, Biol. Cybern. 73:113–121.MATHCrossRefGoogle Scholar

Copyright information

© Springer-Verlag Tokyo 2002

Authors and Affiliations

  • Wenwei Yu
    • 1
  • Ishioka Takuya
    • 1
  • Daisuke Iijima
    • 2
  • Hiroshi Yokoi
    • 1
  • Yukinori Kakazu
    • 1
  1. 1.Hokkaido UniversitySapporoJapan
  2. 2.Nango CorporationTokyoJapan

Personalised recommendations