DARPA is constantly working on projects to make robots and drones smarter. Its Fast Lightweight Autonomy (FLA) program recently completed Phase 2 flight tests, demonstrating how advanced algorithms can be used to turn small air & ground robots into a team that could perform tasks dangerous to humans autonomously.
Using these algorithms, small drones can fly between multi-story buildings and through narrow openings to create 3D maps of the interior before existing. As J.C. Ledé, DARPA program manager, explains:
FLA honed algorithms that in the not too distant future could transform lightweight, commercial-off-the-shelf air or ground unmanned vehicles into capable operational systems requiring no human input once you’ve provided a general heading, distance to travel, and specific items to search
Such algorithms are useful on the battlefield too. They can add autonomous scouting capabilities to small drones and robots.