Real-world planning problems often involve hundreds or even thousands of objects, straining the limits modern planners. In this work, we address challenge by learning to predict a small set objects that, taken together, would be sufficient for finding plan. We propose graph neural network architecture predicting object importance in single inference pass, thus incurring little overhead while gr...

Low-altitude urban flight planning for small unmanned aircraft systems (UASs) accurate vehicle kinodynamics, environment maps, and risk models to assure that plans consider the landscape as well airspace constraints. This paper presents a suite of motion metrics designed UAS defines map-based path-based holistically characterize plan quality. Proposed are examined in context representative geom...

When controlling an autonomous system, it is inefficient or sometimes impossible for the human operator to specify detailed commands. Instead, the field of AI autonomy has developed goal-directed systems, in which human operators specify a series of goals to be accomplished. Increasingly, the control of autonomous systems involves performing a mix of discrete and continuous actions. For example...

Some of the current best conformant probabilistic planners focus on finding a fixed length plan with maximal probability. While these approaches can find optimal solutions, they often do not scale for large problems or plan lengths. As has been shown in classical planning, heuristic search outperforms bounded length search (especially when an appropriate plan length is not given a priori). The ...

Automatic generation of distribution system diagrams is an important aid for the distribution system planner and operator alike for easy visualization of the system. Since a Radial distribution system has a tree structure, what we need to develop is essentially a tree drawing algorithm. In addition,we aim to generate a distribution system graph that is aesthetically pleasing. We define a new se...