Dragonfly Pictures, Inc. (DPI) and UPENN propose to develop a novel real-time trajectory prediction tool called Trajectory Tree Prediction Planner (TTPP). TTPP is based on two ideas. First, since it is impossible to robustly predict a single trajectory of an aircraft if its full state and intent is unknown, we advocate generating a set (tree) of trajectories. Each of the trajectories will be associated with the probability of occurrence, and the cumulative probability of predicted trajectories will be near one. Second, while the prediction of multiple trajectories will be even more computationally expensive than the prediction of a single trajectory, we will generate these trajectories using our previously developed incremental planning algorithms (e.g., D* Lite, Anytime D*, Adaptive A*). These algorithms are specifically designed for solving repeated planning problems in real-time and compute the new paths orders of magnitude faster by re-using their previous planning efforts. These algorithms have been shown to work well on various unmanned ground and air vehicles and will therefore be well-suited to the problem of generating the tree of future trajectories in real-time.
Benefit: The Navys PMA 262, 263, and 266 offices could use the proposed Trajectory Prediction Planner (TPP) as a decision aid in their ground control stations. The Navys PEO(T), PEO(A), PEO(JSF), and others could integrate the decision aid into their pilots next generation pilot assistants. DPI will use the TTPP for its ground controls stations human interface, path planning module, and autonomy architecture of its DP-12 Rhino Tier II/ STUAS candidate. University of Pennsylvanias General Robotics, Autonomy, Sensory, and Perception (GRASP) Lab will use the TTPP to extend its capabilities in path planning in real time with limited information. Industry, standards organizations, FAA, and the Services will be interested in the approachs ability to reduce the cost and improve reliability of sense and avoid and collision avoidance systems. DPIs vision is to sell the autonomy architecture across its entire product line of UAS by using an open, modular, and standard interface.
Keywords: D* Lite, D* Lite, VTOL, autonomous helicopter, Anytime D*, Adaptive A*
