A Semi-Supervised Reservoir Computing System Based on Tapered Whisker for Mobile Robot Terrain Identification and Roughness Estimation

Identifying terrain type is important for safely operating robots exploration in unstructured environments. In this letter, we firstly proposed a novel tapered whisker-based semi-supervised reservoir computing (TWSSRC) system improving classification and property estimation traversability assessment with low cost. Three Hall sensors are used to capture the vibration at different locations of whisker. It could provide morphological computation power achieve frequency separation time domain simultaneously without any data procession only help an additional simple linear regression, signals can be classified. The movement robot on types will result behaviors whiskers whiskered learn from prior physical experiences through cost-efficient self-supervised auto-labeling new classification. Experimental results demonstrate that method good performance when encounters accurately estimate unknown surface speeds.