Processing requirement of a complex autonomous robotic vehicle demands high efficiency in algorithmic and software execution. Today’s advanced computer hardware technology provides processing capabilities that were not available a decade ago. There are still major space and time limitations on these technologies for autonomous robotic applications. Increasingly, small to miniature mobile robots are required for reconnaissance, surveillance, and hazardous material detections for military and industrial applications. The small sized autonomous mobile robotic applications have limited power capacity as well as memory and processing resources.

A number of algorithms exist for producing optimal traverses given changing arc costs. One algorithm stands out as the most used algorithm in simple path finding applications such as games, named the A* algorithm. This paper investigated the hypothesis that cognitive based adaptive path planning algorithms are efficient. This assumption is based on the observed capability of biological systems, which ignore irrelevant information and quickly process non-optimum but efficient paths. Path planning function for all organisms from insects to humans is a critical function of survival, and living organisms perform it with graceful accuracy and efficiency. This hypothesis was tested by developing a Cognitive Based Adaptive Path Planning Algorithm (CBAPPA) and a limited simulation program to test the theory of the algorithm, and comparing the result with other known approaches.

This paper presents a new cognitive based approach in solving the path planning problems for autonomous robotic applications. This paper illustrated that the CBAPPA’s path-finding efficiency exceeds the efficiency of some popular analytical and heuristic approaches. This research paper concluded that the hypothesis was verified and cognitive based path planning algorithm is efficient and is a viable approach for autonomous robotic applications.