Probabilistic Generative Terrain Mapping for Planetary Rovers

The need for autonomy capable of navigating rough terrain is paramount as NASA deploys additional rovers on the moon and Mars.While rovers are adept at navigating barren terrain and identifying and avoiding obstacles that protrude above the ground (“positiveobstacles”), their ability to successfully identify and avoid obstacles below ground level (“negative obstacles”) such as craters, pits,rills, and cliffs remains limited. However, rovers will need to perceive and appropriately respond to the presence of negative obstacleswhen traversing rugged Martian or lunar terrain. This research will develop methodologies for autonomous detection and navigationaround negative obstacles, including craters, from the perspective of a surface rover. Geometric and feature-based approaches, aswell as machine learning approaches, will be studied separately and in conjunction with one another to develop a negative obstacledetection methodology capable of use on a surface rover. Synthetic datasets built from simulations and 3D-printed models of lunarterrain will be used to develop the methodology, while actual lunar surface imagery will be used to evaluate performance. Theresulting methodologies and algorithms will be broadly applicable to NASA rover missions, but especially to planned autonomousmissions to the lunar surface, such as VIPER.

This is early/mid-stage (TRL 2) — the most realistic path in is NASA SBIR/STTR, which funds small businesses and research institutions to develop technology aligned with NASA's needs (equity-free, phased funding). Check whether a current SBIR/STTR solicitation topic overlaps with this project's technology area, or contact the project directly (above) to ask.

None of these are guaranteed paths for this specific project — TechPort itself doesn't have an "apply" button. Reaching out to the contact(s) above with a specific question is usually the fastest way to find out what's actually open.