Sparsed potential-PCNN for real time path planning and indoor navigation scheme for mobile robots

Abstract

One of the main problems associated with mobile intelligent agents is path planning. Numerous approaches have been presented for path planning of mobile robots. One of the most efficient methods is Pulse Coupled Neural Network (PCNN). This paper presents a novel approach we call the Sparsed Potential PCNN method for real time path planning for mobile robots. In the proposed method a Potential Field approach is used to limit the propagation of the autowave only in the direction of the destination rather than propagating in all directions. This increases the efficiency of the PCNN algorithm. Furthermore a sparsing technique is applied to make the algorithm even more time efficient. The algorithm has proven to be a robust and time efficient path planning scheme. The Sparsed Potential-PCNN plans the shortest path in the shortest possible time. The algorithm is also capable of avoiding obstacles in its path. Simulation results in Player/Stage for Pioneer 3 AT mobile robot navigating among obstacles in an indoor environment are also presented to demonstrate the effectiveness of the proposed algorithm.