Probabilistic, Real-Time, Reactive Planner for Aggressive 3D Aircraft Maneuvers

The ultimate goal is to build a Path Planner (PP) that can rapidly plan collision-free routes for a variety of aircraft in highly dynamic environments with large numbers of threats. Our Phase II includes Advanced Rotorcraft Technology (ART) and their highly successful FlightLab product with accompanying high fidelity aircraft models. It also includes Stanford University''s Professor Jean-Claude Latombe, a pioneer in autonomous path planning, at the forefront of rapid path planning with moving obstacles and complex environments, and creator of the Probabilistic Roadmap approach proposed here. In Phase II, we will develop the full-scale, operational PRM PP, apply the PRM PP to at least two different aircraft, a manned helicopter and an fixed wing UAV, develop maneuver library building software to allow pilots to easily and quickly build up libraries of maneuvers, and build additional testing infrastructure around FlightLab to make defining of testing scenarios and testing, evaluation, and visualization as efficient as possible. We will also thoroughly test the PRM PP with the chosen aircraft models in FlightLab and compare its capabilities to those of human pilots. As shown in the proposal, our approach can be readily adapted to different types of aircraft and different types of planning constraints.