Autonomous Excavation of Rocks Using a Gaussian Process Model and Unscented Kalman Filter

Abstract

In large-scale open-pit mining and construction works, excavators must deal with large rocks mixed with gravel and granular soil. Capturing and moving large rocks with the bucket of an excavator requires a high level of skill that only experienced human operators possess. In an attempt to develop autonomous rock excavators, this letter presents a control method that predicts the rock movement in response to bucket operation and computes an optimal bucket movement to capture the rock. The process is highly nonlinear and stochastic. A Gaussian process model, which is nonlinear, nonparametric, and stochastic, is used for describing rock behaviors interacting with the bucket and surrounding soil. Experimental data is used directly for identifying the model. An Unscented Kalman Filter (UKF) is then integrated with the Gaussian process model for predicting the rock movements and estimating the length of the rock. A feedback controller that optimizes a cost function is designed based on the rock motion prediction and implemented on a robotic excavator prototype. Experiments demonstrate encouraging results towards autonomous mining and rock excavation.