In this letter, we present for the first time the use of tapered whisker-based reservoir computing (TWRC) system mounted on a mobile robot for terrain classification and roughness estimation of unknown terrain.
Hall effect sensors captured the oscillations at different locations along a tapered spring that served as a reservoir to map time-domain vibrations signals caused by the interaction perturbations from the ground to frequency domain features directly.
Three hall sensors are used to measure the whisker reservoir outputs and these temporal signals could be processed efficiently by the proposed TWRC system which can provide morphological computation power for data processing and reduce the model training cost compared to the convolutional neural network (CNN) approaches.
To predict the unknown terrain properties, an extended TWRC method including a novel detector is proposed based on the Mahalanobis distance in the Eigen space, which has been experimentally demonstrated to be feasible and sufficiently accurate.
We achieved a prediction success rate of 94.3\% for six terrain surface classification experiments and 88.7\% for roughness estimation of the unknown terrain surface.