Machine learning (ML) plays a crucial role in assessing traversability for autonomous rover operations on deformable terrains but suffers from inevitable prediction errors. Especially for heterogeneous terrains where the geological features vary from place to place, erroneous traversability prediction can become more apparent, increasing the risk of unrecoverable rover's wheel slip and immobilization. In this work, we propose a new path planning algorithm that explicitly accounts for such erroneous prediction. The key idea is the probabilistic fusion of distinctive ML models for terrain type classification and slip prediction into a single distribution. This gives us a multimodal slip distribution accounting for heterogeneous terrains and further allows statistical risk assessment to be applied to derive risk-aware traversing costs for path planning. Extensive simulation experiments have demonstrated that the proposed method is able to generate more feasible paths on heterogeneous terrains compared to existing methods.

SUMMARY Wheel slip prediction on rough terrain is crucial for secure, long-term operations of planetary exploration rovers. Although rough, unstructured terrain hampers mobility, prediction by modeling wheel–terrain interactions remains difficult owing to unclear terrain conditions and complexities of terramechanics models. This study proposes a vision-based approach with machine learning for predicting wheel slip risk by estimating the slope from 3D information and classifying terrain types from image information. It considers the slope estimation accuracy for risk prediction under sharp increases in wheel slip due to inclined ground. Experimental results obtained with a rover testbed on several terrain types validate this method.