Collaborative path planning for multi-robot multi-target inspection using the GBNN algorithm

With the development of power grid intelligence, substations as a critical component of the power grid its safety and reliability directly impact the overall security and reliability of the grid’s power supply. In order to maintain substation power supply reliability, and improve inspection robot inspection efficiency. This study presents a Glasius Bio-Inspired Neural Network (GBNN) algorithm for autonomous path planning in collaborative multi-robot systems designed to perform multi-target inspections in smart substations. The approach begins with constructing a standard GBNN model that incorporates the substation’s environmental characteristics. Subsequently, neuron activation values are updated using the GBNN algorithm. Simulations demonstrate the algorithm’s effectiveness in enabling efficient path planning for multi-robot, multi-task inspections in dynamic and uncertain environments.