Neural networks for manipulator path planning

  • Margit Sturm
Part of the Lecture Notes in Computer Science book series (LNCS, volume 1337)


In order to manipulate objects, robot arms need to approach objects, and therefore need to move to certain positions in a certain orientation. The question solved by path planning is how to approach the goals, i.e., how to move the manipulator's joint angles without colliding with any of the surrounding objects. This article gives an overview of manipulator path planning methods, and shows the benefit of combining neural networks with graph-based techniques. This combination results in an adaptive modeling of free space, together with the connectivity of free space regions being captured in a graph.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. [1]
    Brychcy, T., Kinder, M.: A neural network inspired architecture for robot motion planning. In Bulsari, A., Kallio, S. (Hrsg.), Engineering Applications of Artificial Neural Networks: Proceedings of the International Conference EANN '95, 21–23 August 1995, Otaniemi/Helsinki, Finland. Finnish Artificial Intelligence Society, 1995, S. 103–110.Google Scholar
  2. [2]
    Dijkstra, E.: A note on two problems in connection with graphs. Numerische Mathematik, Bd. 1 [1959], S. 269–271.MATHMathSciNetCrossRefGoogle Scholar
  3. [3]
    Eldracher, M.: Planung kinematischer Trajektorien für Manipulatoren mit Hilfe von Subzielen und neuronalen Netzen. Dissertation, Technische Universität München, München 1995.Google Scholar
  4. [4]
    Kavraki, L., Latombe, J.-C: Randomized preprocessing of configuration space for fast path planning. In 1994 IEEE International Conference on Robotics and Automation, San Diego, 1994, S. 2138–2145.Google Scholar
  5. [5]
    Kinder, M.: Pfadplanung für Manipulatoren in komplexen Umgebungen mittels generalisierender Pfadspeicherung in Ellipsoidkarten. Reihe 8: Mes-, Steuerungs-und Regelungstechnik, Nr. 580, VDI Verlag, Düsseldorf 1996. in German.Google Scholar
  6. [6]
    Kohonen, T.: Self-Organization and Associative Memory. 2. Auflage. Springer, Berlin, Heidelberg, New York, London, Paris, Tokyo 1988.Google Scholar
  7. [7]
    Latombe, J.-C.: Robot Motion Planning. 3. Auflage. Kluwer Academic Press, Boston 1991.Google Scholar
  8. [8]
    Moore, A. W.: The partigame algorithm for variable resolution reinforcement learning in multidimensional statespaces. In Neural Information Processing Systems 6. Morgan Kaufmann, 1994, S. 711–718.Google Scholar
  9. [9]
    Poggio, T., Girosi, F.: Networks for Approximation and Learning. In Proceedings of the IEEE, Bd. 78, 1990, S. 1481–1497.CrossRefGoogle Scholar
  10. [10]
    Powell, M.: Radial basis functions for multivariable interpolation: A review. In IMA conference on “Algorithms for the Approximation of Functions and Data”. RMCS Shrivenham, 1985.Google Scholar
  11. [11]
    Stutz, C.: Pfadplanung für Manipulatoren durch Aufbau eines Graphen aus Ellipsoiden mit Hilfe von Explorationsmethoden. Diplomarbeit, Institut für Informatik, Technische Universität München 1995.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1997

Authors and Affiliations

  • Margit Sturm
    • 1
  1. 1.Siemens AG, Corporate TechnologyDepartment Information and CommunicationMunich

Personalised recommendations