GSNN: A Neuromorphic Computing Model for the Flexible Path Planning in Various Constraint Environments

Abstract

Spiking Neural Networks (SNNs) represent a new generation of artificial neural networks that draw inspiration from biological systems. However, due to the intricate dynamics they exhibit and the discontinuity inherent in spike signals, SNNs often encounter performance limitations when addressing optimization problems. In this paper, we introduce the Graph-connected Spiking Neural Network model (GSNN), an extension of the SNN framework. The GSNN model holds the potential for integration with various existing path planning methods, rendering it applicable to a wide array of common path planning tasks. We specifically present two fundamental models within the GSNN framework. The first model employs GSNN to extract heuristic information from constrained pixel maps. This extracted data is then amalgamated with a novel sampling method, resulting in enhanced planning efficiency when compared to conventional techniques. The second model leverages GSNN to map a weighted graph, effectively utilizing plasticity methods to ascertain the shortest path within the graph. Moreover, this model facilitates path planning under diverse constraint environments, encompassing dynamic considerations, cost-awareness, and the collision dimensions of moving objects. Recognizing that the size of pixel maps or the number of nodes within weighted graphs might constrain GSNN’s capabilities, we propose a partitioning strategy to address this limitation. Empirical results unequivocally demonstrate the superiority of both GSNN models in resolving static path planning problems. Furthermore, the second GSNN model demonstrates rational performance across various constrained scenarios. <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Note to Practitioners</i> —The primary motivation behind this study is to explore the utilization of neural morphic computation methods in addressing path planning challenges. To accomplish this, we introduce an encompassing model named GSNN. Given the limited coverage of neural morphic computation within this field, we present a comprehensive overview of its potential applications, with the intention of providing a valuable reference for both researchers and practitioners. Moreover, GSNN has the capability to seamlessly integrate with existing advanced optimization methods, thereby leading to enhanced performance and the capacity to tackle even more intricate problems.

Topics & Concepts