Path planning by potential diffusion networks

Wei Shen; Jun Shen; Jean-Paul Lallemand

doi:10.1117/12.143790

4 May 1993 Path planning by potential diffusion networks

Wei Shen, Jun Shen, Jean-Paul Lallemand

Proceedings Volume 1831, Mobile Robots VII; (1993) https://doi.org/10.1117/12.143790
Event: Applications in Optical Science and Engineering, 1992, Boston, MA, United States

Abstract

In presence of obstacles of arbitrary forms, the existent methods for shortest path planning need to analyze all classes of topologically different paths, which is time-consuming. In the present paper, we propose the potential diffusion network for path planning in presence of obstacles of arbitrary forms which avoids different topological paths analysis. The starting and goal points of a mobile robot are considered as diffusion sources separately. For each diffusing source, we calculate the potential field by use of a diffusing network which converges to a stable state representing the potential field. The sum of the two fields corresponding respectively to the sources at starting and goal points gives the composed potential distribution in the space. The optimal path is shown to be the iso-potential line of the field, which begins from the starting point and terminates at the goal point. Scenes in robotics being in general represented by discrete arrays of voxels, additional processing for discrete space case is presented also. Our method is implemented and tested for complicated scenes of obstacles of arbitrary forms to find the optimal path, the experimental results are satisfactory.

Citation Download Citation

Wei Shen, Jun Shen, and Jean-Paul Lallemand "Path planning by potential diffusion networks", Proc. SPIE 1831, Mobile Robots VII, (4 May 1993); https://doi.org/10.1117/12.143790

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available