Learning-Based End-to-End Navigation for Planetary Rovers Considering Non-Geometric Hazards

Autonomous navigation plays an increasingly crucial role in rover-based planetary missions. End-to-end navigation approaches developed upon deep reinforcement learning have enabled great adaptability in complex environments. However, most existing works focus on geometric obstacle avoidance thus have limited capability to cope with ubiquitous non-geometric hazards, such as sinkage and slippage. Autonomous navigation in unstructured harsh environments remains a great challenge requiring further in-depth study. In this letter, a DRL-based navigation method is proposed to autonomously guide a planetary rover towards goals via hazard-free paths with low wheel slip ratios. We introduce an end-to-end network architecture, in which the visual perception and the wheel-terrain interaction are fused to learn the representation of terrain mechanical properties implicitly and further facilitate policy learning for non-geometric hazard avoidance. Our approach outperforms baseline methods in simulation evaluation with superior avoidance capabilities against geometric obstacles and non-geometric hazards. Experiments conducted at a Mars emulation site suggest the successful deployment of our approach on a planetary rover prototype and the capacity of dealing with locomotion risks in real-world navigation tasks.