A Review of Off-Road Datasets, Sensor Technologies and Terrain Traversability Analysis

Autonomous ground navigation has advanced significantly in urban and structured environments, supported by the availability of comprehensive datasets. However, navigating complex and off-road terrains remains challenging due to limited datasets, diverse terrain types, adverse environmental conditions, and sensor limitations affecting vehicle perception. This study presents a comprehensive review of off-road datasets, integrating their applications with sensor technologies and terrain traversability analysis methods. It identifies critical gaps, including class imbalances, sensor performance under adverse conditions, and limitations in existing traversability estimation approaches. Key contributions include a novel classification of off-road datasets based on annotation methods, providing insights into scalability and applicability across diverse terrains. The study also evaluates sensor technologies under adverse conditions and proposes strategies for incorporating event-based and hyperspectral cameras to enhance perception systems. Additionally, we address the lack of unified evaluation metrics by introducing performance qualifiers for assessing perception, planning, and control systems. Finally, a comparison of geometry-based, learning-based, and probabilistic methods for terrain navigability prediction highlights the importance of multi-sensor data integration for improved decision-making. These actionable recommendations aim to guide the development of adaptive and robust autonomous navigation systems, advancing real-world applications in complex off-road environments.