An online optimization escape entrapment strategy for planetary rovers based on Bayesian optimization

Abstract

Planetary rovers may become stuck due to the soft terrain on Mars and other planetary surface. The escape entrapment control strategy is of great significance for planetary rover traversing loosely consolidated granular terrain. After analyzing the performance of the published quadrupedal rotary sequence gait, a “sweeping-spinning” gait was proposed to improve escape entrapment capability. And the forward distance of planetary rovers with “sweeping-spinning” gait was modeled as a function of six control parameters. An online optimization escape entrapment strategy for planetary rover was proposed based on the Bayesian Optimization algorithm. Single-factor experiments were conducted to investigate the effect of each control parameter on forward distance, and determine the parameter ranges. The average forward distance with randomly selected control parameters is 89.64 cm, while that is 136.93 cm with Bayesian optimized control parameters, which verifies the effectiveness of the escape entrapment strategy. Moreover, compared with the trajectory of a planetary rover prototype with the published quadrupedal rotary sequence gait, the trajectory of a planetary rover prototype with “sweeping-spinning” gait is more accurate. Furthermore, the online estimated equivalent terrain mechanical parameters can be used to determine the running state of the planetary rover prototype, which was verified using experiments.