Motion Planning in Unknown Environments

The objective of the proposed research is to develop new theoretical and algorithmic frameworks that enable mobile robots to safely and efficiently navigate unknown environments. Traditionally, robot motion planning has been considered in the context of a known state of the world, such as an environment map that is already known. However, we must address the problem of what to do when that map is evolving, incomplete or even unavailable to the robot. In particular, one major part of this work will consider methods of intelligently reasoning about the unobserved environment beyond the robot's perception horizon using machine learning techniques. Another significant component of this work will involve using this reasoning to plan safe and efficient trajectories through these environments. Given that the surfaces of planets and other celestial bodies are inherently unknown, this work would allow for more effective exploration of these environments by enabling the use of more agile vehicles, not limited by human operation capabilities or constraining communication delays from an earthbound groundstation.

Given that the surfaces of planets and other celestial bodies are inherently unknown, this work would allow for more effective exploration of these environments by enabling the use of more agile vehicles, not limited by human operation capabilities or constraining communication delays from an earthbound groundstation.

This is early/mid-stage (TRL 3) — 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.