
Terramechanics and Machine Learning for the Characterization of Terrain
Abstract
An instrumented rover wheel can collect vast amounts of data about a planetary surface. Planetary surfaces are changed by complex geological processes which can be better understood with an abundance of surface data and the use of terramechanics. Identifying terrain parameters such as cohesion and angle of friction hold importance for both the rover driver and the planetary scientist. Knowledge of terrain characteristics can warn of unsafe terrain and flag potential interesting scientific sites. The instrumented wheel in this research utilizes a pressure pad to sense load and sinkage, a string potentiometer to measure slip, and records motor current draw. This thesis demonstrates the utilization of the instrumented wheel's data to estimate cohesion, angle of friction and grain size and demonstrates a machine learning solution for classifying terrain types with the same data. Mars simulants available at NASA-JPL were used for the collection of the data. Two machine learning classifiers were explored: Random Forest and Support Vector Machine. Binary and multi-class classification were both demonstrated and it is proposed that the classification model can identify terrain types based on the instrumented wheel data. The Random Forest model performed best in all classification types.