Path planning strategy for a space relocatable robotic manipulator based on improved GBNN algorithm

Abstract

For the purpose of assisting astronauts in performing specific operations on orbital space stations, the space relocatable robotic manipulator has been studied and applied by many countries. In practical application scenarios, achieving optimal mobility and resource efficiency are the primary technical requirements for this manipulator. Therefore, we have developed an improved path-planning strategy based on the Glasius Bio-inspired Neural Network algorithm. This approach reduces computational resource consumption, dynamically avoids obstacles, and accounts for physical constraints. To simplify the complex process of 3D map rasterization, our method directly abstracts and constructs a topologically connected graph for the grasping points. Furthermore, the improved algorithm enhances the energy efficiency of path planning by incorporating a function that integrates global information. It also employs a diffusive updating method, enabling the rapid propagation of neuron activity values to target points within a single iteration. To further advance the practical application of the algorithm, we have considered the kinematic properties and physical constraints of the manipulator. Finally, we developed a dual-layer planning strategy that enables the manipulator to move efficiently across the surface of a non-regular space station. The effectiveness and advantages of the improved algorithm have been thoroughly evaluated through comprehensive comparisons with existing algorithms.