Combining current existing RRT path-generating methods to optimize simulated UAV flight

Abstract

Rapidly-exploring Random Tree (RRT) path-planning algorithms are widely used in the field of drones and other unmanned aerial vehicles (UAVs). RRT is a sampling-based algorithm that incrementally builds a tree through a state space by randomly selecting points and extending the tree toward them. However, as the state space is sampled randomly, the resulting paths are often inefficient and non-optimal, particularly in large or complex environments.

The purpose of this project was to improve upon existing RRT path-planning algorithms by combining multiple additional functionalities together in order to generate more optimized and feasible paths in 3D space within the same amount of time or less.