Research on Path Planning Optimization for Patrol Robot based on Sparse Subspace Clustering Algorithm

Abstract

The rationality of path control for transmission line inspection robots is crucial for ensuring that these robots can autonomously, accurately, and efficiently complete their inspection tasks. As computer-based technologies advance rapidly, the support for path planning in increasingly complex environments has seen substantial improvements. This paper introduces an innovative path optimization method that merges the Sparse Subspace Clustering (SSC) algorithm with traditional path planning strategies to address these complexities. By leveraging clustering technology, the complex and high-dimensional road information is effectively decomposed and analyzed within a low-dimensional subspace, allowing for more precise interpretation and decision-making. This integration aims to overcome prevalent challenges, such as insufficient path planning accuracy, suboptimal energy efficiency, and the difficulties posed by navigating through intricate environments. The proposed SSC-based path planning and optimization strategy is particularly effective in identifying and segmenting transmission line pixels from hyperspectral remote sensing images, which plays a key role in optimizing the inspection path. By minimizing redundant information and enhancing the overall performance of path planning, this method not only improves the precision of path control but also ensures energy-efficient operations. Experimental results confirm that this approach significantly enhances path planning accuracy, offering a robust and reliable solution for the automated path control of transmission line inspection robots.