Slip Estimation Model for Planetary Rover Using Gaussian Process Regression

Monitoring the rover slip is important; however, a certain level of estimation uncertainty inevitable. In this paper, we establish models for China’s Mars rover, Zhurong, using Gaussian process regression (GPR). The model was able to predict not only average value longitudinal (slip_x) and lateral (slip_y), but also maximum possible that slip_x slip_y could reach. training data were collected on two simulated soils, TYII-2 JLU Mars-2, GA-BP algorithm applied as comparison. analysis results demonstrated soil type dataset source had direct impact applicability conditions. properties Martian near Zhurong landing site closer Mars-2 soil. proposed GPR high accuracy potential in value, 95% confidence interval reach during motion. This work part research effort aimed at ensuring safety Zhurong. may be used subsequent path tracking research, will help guide planning.