Diffusion-Based Path Planning
After the topology preserving map of a given input manifold M has been established, we want to generate a path from any initial position to a given target, e.g., to guide an end effector of a robot manipulator in the presence of obstacles within the workspace. We propose to use for this purpose a diffusion-based path finding algorithm on the discrete network lattice in which the target neuron is the source of a diffusing substance. The goal is to find a linked chain on the graph leading from the current position to the target position. Details of our diffusion-based path planning algorithm can be found in the related publications.
A detailed account of this work can be found in the following publications:
Vision-based motion planning of a pneumatic robot using a topology representing neural network. Michael Zeller, Rajeev Sharma, and Klaus Schulten. In Proceedings of 1996 IEEE Int. Symposium on Intelligent Control, pp. 7-12, 1996.
Learning the perceptual control manifold for sensor-based robot path planning. Michael Zeller, Rajeev Sharma, and Klaus Schulten. In Proceedings of the 1997 IEEE International Symposium on Computational Intelligence in Robotics and Automation (CIRA'97), pp. 48-53. IEEE Computer Society Press, 1997.