Vibration and Image Texture Data Fusion-Based Terrain Classification Using WKNN for Tracked Robots

For terrain recognition needs during vehicle driving, this paper carries out classification research based on vibration and image information. Twenty time-domain features eight frequency-domain of signals that are highly correlated with selected, principal component analysis (PCA) is used to reduce the dimensionality retain main Meanwhile, texture images extracted using gray-level co-occurrence matrix (GLCM) technique, feature information fused in layer. Then, improved weighted K-nearest neighbor (WKNN) algorithm achieve travel process tracked robots. Finally, experimental results verify proposed method improves accuracy robot provides a basis for improving stable autonomous driving vehicles.